Merge drm/drm-next into drm-intel-next

Sync to v6.16-rc1, among other things to get the fixed size GENMASK_U*() and BIT_U*() macros. Signed-off-by: Jani Nikula <jani.nikula@intel.com>
author: Jani Nikula <jani.nikula@intel.com> 2025-06-09 12:40:46 +0300
committer: Jani Nikula <jani.nikula@intel.com> 2025-06-09 12:40:46 +0300
commit: 34c55367af96f62e89221444f04487440ebc6487 (patch)
tree: fdb36ba67d7dea09455b55037e26043b7e051ef9 /tools/perf
parent: 7247efca0dcbc8ac6147db9200ed1549c0662465 (diff)
parent: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 (diff)
317 files changed, 22109 insertions, 11888 deletions
diff --git a/tools/perf/Documentation/perf-amd-ibs.txt b/tools/perf/Documentation/perf-amd-ibs.txt
index 2fd31d9d7b71..55f80beae037 100644
--- a/tools/perf/Documentation/perf-amd-ibs.txt
+++ b/tools/perf/Documentation/perf-amd-ibs.txt
@@ -85,6 +85,15 @@ System-wide profile, uOps event, sampling period: 100000, L3MissOnly (Zen4 onwar
 
 	# perf record -e ibs_op/cnt_ctl=1,l3missonly=1/ -c 100000 -a
 
+System-wide profile, cycles event, sampling period: 100000, LdLat filtering (Zen5
+onward)
+
+	# perf record -e ibs_op/ldlat=128/ -c 100000 -a
+
+	Supported load latency threshold values are 128 to 2048 (both inclusive).
+	Latency value which is a multiple of 128 incurs a little less profiling
+	overhead compared to other values.
+
 Per process(upstream v6.2 onward), uOps event, sampling period: 100000
 
 	# perf record -e ibs_op/cnt_ctl=1/ -c 100000 -p 1234
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 856f0dfb8e5a..f4af2dd6ab31 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -54,8 +54,15 @@ RECORD OPTIONS
 
 -l::
 --ldlat::
-	Configure mem-loads latency. Supported on Intel and Arm64 processors
-	only. Ignored on other archs.
+	Configure mem-loads latency. Supported on Intel, Arm64 and some AMD
+	processors. Ignored on other archs.
+
+	On supported AMD processors:
+	- /sys/bus/event_source/devices/ibs_op/caps/ldlat file contains '1'.
+	- Supported latency values are 128 to 2048 (both inclusive).
+	- Latency value which is a multiple of 128 incurs a little less profiling
+	  overhead compared to other values.
+	- Load latency filtering is disabled by default.
 
 -k::
 --all-kernel::
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 36ebebc875ea..c6f335659667 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -708,6 +708,10 @@ intel-pt.*::
 		the maximum is exceeded there will be a "Never-ending loop"
 		error. The default is 100000.
 
+	intel-pt.all-switch-events::
+		If the user has permission to do so, always record all context
+		switch events on all CPUs.
+
 auxtrace.*::
 
 	auxtrace.dumpdir::
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 8914f12d2b85..ce0735021473 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -289,6 +289,15 @@ Sums up the event counts for all hardware threads in a core, e.g.:
 
   perf stat -e cpu/event=0,umask=0x3,percore=1/
 
+cpu:
+
+Specifies the CPU to open the event upon. The value may be repeated to
+specify opening the event on multiple CPUs:
+
+
+  perf stat -e instructions/cpu=0,cpu=2/,cycles/cpu=1,cpu=2/ -a sleep 1
+  perf stat -e data_read/cpu=0/,data_write/cpu=1/ -a sleep 1
+
 
 EVENT GROUPS
 ------------
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index 859dc11a7372..c17b3e318169 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -216,6 +216,21 @@ CONTENTION OPTIONS
 --cgroup-filter=<value>::
 	Show lock contention only in the given cgroups (comma separated list).
 
+-J::
+--inject-delay=<time@function>::
+	Add delays to the given lock.  It's added to the contention-end part so
+	that the (new) owner of the lock will be delayed.  But by slowing down
+	the owner, the waiters will also be delayed as well.  This is working
+	only with -b/--use-bpf.
+
+	The 'time' is specified in nsec but it can have a unit suffix.  Available
+	units are "ms", "us" and "ns".  Currently it accepts up to 10ms of delays
+	for safety reasons.
+
+	Note that it will busy-wait after it gets the lock. Delaying locks can
+	have significant consequences including potential kernel crashes.  Please
+	use it at your own risk.
+
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 8a1bd9ff0f86..965e73d37772 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -28,6 +28,8 @@ and kernel support is required. See linkperf:perf-arm-spe[1] for a setup guide.
 Due to the statistical nature of SPE sampling, not every memory operation will
 be sampled.
 
+On AMD this use IBS Op PMU to sample load-store operations.
+
 COMMON OPTIONS
 --------------
 -f::
@@ -67,8 +69,15 @@ RECORD OPTIONS
 	Configure all used events to run in user space.
 
 --ldlat <n>::
-	Specify desired latency for loads event. Supported on Intel and Arm64
-	processors only. Ignored on other archs.
+	Specify desired latency for loads event. Supported on Intel, Arm64 and
+	some AMD processors. Ignored on other archs.
+
+	On supported AMD processors:
+	- /sys/bus/event_source/devices/ibs_op/caps/ldlat file contains '1'.
+	- Supported latency values are 128 to 2048 (both inclusive).
+	- Latency value which is a multiple of 128 incurs a little less profiling
+	  overhead compared to other values.
+	- Load latency filtering is disabled by default.
 
 REPORT OPTIONS
 --------------
@@ -128,6 +137,25 @@ REPORT OPTIONS
 In addition, for report all perf report options are valid, and for record
 all perf record options.
 
+OVERHEAD CALCULATION
+--------------------
+Unlike linkperf:perf-report[1], which calculates overhead from the actual
+sample period, perf-mem overhead is calculated using sample weight. E.g.
+there are two samples in perf.data file, both with the same sample period,
+but one sample with weight 180 and the other with weight 20:
+
+  $ perf script -F period,data_src,weight,ip,sym
+  100000    629080842 |OP LOAD|LVL L3 hit|...     20       7e69b93ca524 strcmp
+  100000   1a29081042 |OP LOAD|LVL RAM hit|...   180   ffffffff82429168 memcpy
+
+  $ perf report -F overhead,symbol
+  50%   [.] strcmp
+  50%   [k] memcpy
+
+  $ perf mem report -F overhead,symbol
+  90%   [k] memcpy
+  10%   [.] strcmp
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-arm-spe[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index c7fc1ba265e2..612612fa2d80 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -340,7 +340,7 @@ OPTIONS
 
 -d::
 --data::
-	Record the sample virtual addresses.
+	Record the sample virtual addresses.  Implies --sample-mem-info.
 
 --phys-data::
 	Record the sample physical addresses.
@@ -368,6 +368,11 @@ OPTIONS
 	the sample_type member of the struct perf_event_attr argument to the
 	perf_event_open system call.
 
+--sample-mem-info::
+	Record the sample data source information for memory operations.
+	It requires hardware supports and may work on specific events only.
+	Please consider using 'perf mem record' instead if you're not sure.
+
 -n::
 --no-samples::
 	Don't sample.
@@ -837,6 +842,15 @@ filtered through the mask provided by -C option.
 	only, as of now.  So the applications built without the frame
 	pointer might see bogus addresses.
 
+	off-cpu profiling consists two types of samples: direct samples, which
+	share the same behavior as regular samples, and the accumulated
+	samples, stored in BPF stack trace map, presented after all the regular
+	samples.
+
+--off-cpu-thresh::
+	Once a task's off-cpu time reaches this threshold (in milliseconds), it
+	generates a direct off-cpu sample. The default is 500ms.
+
 --setup-filter=<action>::
 	Prepare BPF filter to be used by regular users.  The action should be
 	either "pin" or "unpin".  The filter can be used after it's pinned.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 3376c4710575..acef3ff4178e 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -94,6 +94,7 @@ OPTIONS
 
 	- comm: command (name) of the task which can be read via /proc/<pid>/comm
 	- pid: command and tid of the task
+	- tgid: command and tgid of the task
 	- dso: name of library or module executed at the time of sample
 	- dso_size: size of library or module executed at the time of sample
 	- symbol: name of function executed at the time of sample
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 2bc063672486..61d091670dee 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -506,6 +506,13 @@ this option is not set. The TPEBS hardware feature starts from Intel Granite
 Rapids microarchitecture. This option only exists in X86_64 and is meaningful on
 Intel platforms with TPEBS feature.
 
+--tpebs-mode=[mean|min|max|last]::
+Set how retirement latency events have their sample times
+combined. The default "mean" gives the average of retirement
+latency. "min" or "max" give the smallest or largest retirment latency
+times respectively. "last" uses the last retirment latency sample's
+time.
+
 --td-level::
 Print the top-down statistics that equal the input level. It allows
 users to print the interested top-down metrics level instead of the
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 887dc37773d0..c1fb6056a0d3 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -152,7 +152,8 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 
 --summary-mode=mode::
 	To be used with -s or -S, to select how to show summary.  By default it'll
-	show the syscall summary by thread.  Possible values are: thread, total.
+	show the syscall summary by thread.  Possible values are: thread, total,
+	cgroup.
 
 --tool_stats::
 	Show tool stats such as number of times fd->pathname was discovered thru
@@ -251,6 +252,12 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	pretty-printing serves as a fallback to hand-crafted pretty printers, as the latter can
 	better pretty-print integer flags and struct pointers.
 
+--bpf-summary::
+	Collect system call statistics in BPF.  This is only for live mode and
+	works well with -s/--summary option where no argument information is
+	required.
+
+
 PAGEFAULTS
 ----------
 
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index 010a4edcd384..cd95ba09f727 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -370,7 +370,7 @@ struct {
 	u32	mmap_len;
 };
 
-Indicates that trace contains records of PERF_RECORD_COMPRESSED type
+Indicates that trace contains records of PERF_RECORD_COMPRESSED2 type
 that have perf_events records in compressed form.
 
 	HEADER_CPU_PMU_CAPS = 28,
@@ -602,7 +602,14 @@ struct auxtrace_error_event {
 Describes a header feature. These are records used in pipe-mode that
 contain information that otherwise would be in perf.data file's header.
 
-	PERF_RECORD_COMPRESSED 			= 81,
+	PERF_RECORD_COMPRESSED 			= 81, /* deprecated */
+
+The header is followed by compressed data frame that can be decompressed
+into array of perf trace records. The size of the entire compressed event
+record including the header is limited by the max value of header.size.
+
+It is deprecated and new files should use PERF_RECORD_COMPRESSED2 to gurantee
+8-byte alignment.
 
 struct compressed_event {
 	struct perf_event_header	header;
@@ -618,10 +625,17 @@ This is used, for instance, to 'perf inject' events after init and before
 regular events, those emitted by the kernel, to support combining guest and
 host records.
 
+	PERF_RECORD_COMPRESSED2			= 83,
 
-The header is followed by compressed data frame that can be decompressed
-into array of perf trace records. The size of the entire compressed event
-record including the header is limited by the max value of header.size.
+8-byte aligned version of `PERF_RECORD_COMPRESSED`. `header.size` indicates the
+total record size, including padding for 8-byte alignment, and `data_size`
+specifies the actual size of the compressed data.
+
+struct perf_record_compressed2 {
+	struct perf_event_header	header;
+	__u64				data_size;
+	char				data[];
+};
 
 Event types
 
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 364b55b00b48..34af57b8ec2a 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,8 +1,10 @@
 COPYING
 LICENSES/preferred/GPL-2.0
 arch/arm64/tools/gen-sysreg.awk
+arch/arm64/tools/syscall_64.tbl
 arch/arm64/tools/sysreg
 arch/*/include/uapi/asm/bpf_perf_event.h
+include/uapi/asm-generic/Kbuild
 tools/perf
 tools/arch
 tools/scripts
@@ -25,6 +27,10 @@ tools/lib/str_error_r.c
 tools/lib/vsprintf.c
 tools/lib/zalloc.c
 scripts/bpf_doc.py
+scripts/Kbuild.include
+scripts/Makefile.asm-headers
+scripts/syscall.tbl
+scripts/syscallhdr.sh
 tools/bpf/bpftool
 kernel/bpf/disasm.c
 kernel/bpf/disasm.h
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b7769a22fe1a..d1ea7bf44964 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -560,6 +560,8 @@ ifndef NO_LIBELF
     ifeq ($(feature-libdebuginfod), 1)
       CFLAGS += -DHAVE_DEBUGINFOD_SUPPORT
       EXTLIBS += -ldebuginfod
+    else
+      $(warning No elfutils/debuginfod.h found, no debuginfo server support, please install libdebuginfod-dev/elfutils-debuginfod-client-devel or equivalent)
     endif
   endif
 
@@ -625,6 +627,8 @@ endif
 ifndef NO_LIBUNWIND
   have_libunwind :=
 
+  $(call feature_check,libunwind)
+
   $(call feature_check,libunwind-x86)
   ifeq ($(feature-libunwind-x86), 1)
     $(call detected,CONFIG_LIBUNWIND_X86)
@@ -649,7 +653,7 @@ ifndef NO_LIBUNWIND
   endif
 
   ifneq ($(feature-libunwind), 1)
-    $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR)
+    $(warning No libunwind found. Please install libunwind-dev[el] >= 1.1 and/or set LIBUNWIND_DIR and set LIBUNWIND=1 in the make command line as it is opt-in now)
     NO_LOCAL_LIBUNWIND := 1
   else
     have_libunwind := 1
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 979d4691221a..d4c7031b01a7 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1147,7 +1147,8 @@ install-tests: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_probe'; \
 		$(INSTALL) tests/shell/base_probe/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_probe'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
-		$(INSTALL) tests/shell/base_probe/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
+		$(INSTALL) tests/shell/base_report/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
+		$(INSTALL) tests/shell/base_report/*.txt '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/base_report'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/coresight' ; \
 		$(INSTALL) tests/shell/coresight/*.sh '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/shell/coresight'
 	$(Q)$(MAKE) -C tests/shell/coresight install-tests
@@ -1175,7 +1176,7 @@ SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h
 SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
 SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h
 SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h
-SKELETONS += $(SKEL_OUT)/kwork_top.skel.h
+SKELETONS += $(SKEL_OUT)/kwork_top.skel.h $(SKEL_OUT)/syscall_summary.skel.h
 SKELETONS += $(SKEL_OUT)/bench_uprobe.skel.h
 SKELETONS += $(SKEL_OUT)/augmented_raw_syscalls.skel.h
 
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index c0421a26b875..4fd425157d7d 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -14,6 +14,7 @@ int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest);
 int test__bp_modify(struct test_suite *test, int subtest);
 int test__x86_sample_parsing(struct test_suite *test, int subtest);
 int test__amd_ibs_via_core_pmu(struct test_suite *test, int subtest);
+int test__amd_ibs_period(struct test_suite *test, int subtest);
 int test__hybrid(struct test_suite *test, int subtest);
 
 extern struct test_suite *arch_tests[];
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index 86262c720857..5e00cbfd2d56 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -10,6 +10,7 @@ perf-test-$(CONFIG_AUXTRACE) += insn-x86.o
 endif
 perf-test-$(CONFIG_X86_64) += bp-modify.o
 perf-test-y += amd-ibs-via-core-pmu.o
+perf-test-y += amd-ibs-period.o
 
 ifdef SHELLCHECK
   SHELL_TESTS := gen-insn-x86-dat.sh
diff --git a/tools/perf/arch/x86/tests/amd-ibs-period.c b/tools/perf/arch/x86/tests/amd-ibs-period.c
new file mode 100644
index 000000000000..223e059e04de
--- /dev/null
+++ b/tools/perf/arch/x86/tests/amd-ibs-period.c
@@ -0,0 +1,1032 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sched.h>
+#include <sys/syscall.h>
+#include <sys/mman.h>
+#include <sys/ioctl.h>
+#include <sys/utsname.h>
+#include <string.h>
+
+#include "arch-tests.h"
+#include "linux/perf_event.h"
+#include "linux/zalloc.h"
+#include "tests/tests.h"
+#include "../perf-sys.h"
+#include "pmu.h"
+#include "pmus.h"
+#include "debug.h"
+#include "util.h"
+#include "strbuf.h"
+#include "../util/env.h"
+
+static int page_size;
+
+#define PERF_MMAP_DATA_PAGES    32L
+#define PERF_MMAP_DATA_SIZE     (PERF_MMAP_DATA_PAGES * page_size)
+#define PERF_MMAP_DATA_MASK     (PERF_MMAP_DATA_SIZE - 1)
+#define PERF_MMAP_TOTAL_PAGES   (PERF_MMAP_DATA_PAGES + 1)
+#define PERF_MMAP_TOTAL_SIZE    (PERF_MMAP_TOTAL_PAGES * page_size)
+
+#define rmb()                   asm volatile("lfence":::"memory")
+
+enum {
+	FD_ERROR,
+	FD_SUCCESS,
+};
+
+enum {
+	IBS_FETCH,
+	IBS_OP,
+};
+
+struct perf_pmu *fetch_pmu;
+struct perf_pmu *op_pmu;
+unsigned int perf_event_max_sample_rate;
+
+/* Dummy workload to generate IBS samples. */
+static int dummy_workload_1(unsigned long count)
+{
+	int (*func)(void);
+	int ret = 0;
+	char *p;
+	char insn1[] = {
+		0xb8, 0x01, 0x00, 0x00, 0x00, /* mov 1,%eax */
+		0xc3, /* ret */
+		0xcc, /* int 3 */
+	};
+
+	char insn2[] = {
+		0xb8, 0x02, 0x00, 0x00, 0x00, /* mov 2,%eax */
+		0xc3, /* ret */
+		0xcc, /* int 3 */
+	};
+
+	p = zalloc(2 * page_size);
+	if (!p) {
+		printf("malloc() failed. %m");
+		return 1;
+	}
+
+	func = (void *)((unsigned long)(p + page_size - 1) & ~(page_size - 1));
+
+	ret = mprotect(func, page_size, PROT_READ | PROT_WRITE | PROT_EXEC);
+	if (ret) {
+		printf("mprotect() failed. %m");
+		goto out;
+	}
+
+	if (count < 100000)
+		count = 100000;
+	else if (count > 10000000)
+		count = 10000000;
+	while (count--) {
+		memcpy((void *)func, insn1, sizeof(insn1));
+		if (func() != 1) {
+			pr_debug("ERROR insn1\n");
+			ret = -1;
+			goto out;
+		}
+		memcpy((void *)func, insn2, sizeof(insn2));
+		if (func() != 2) {
+			pr_debug("ERROR insn2\n");
+			ret = -1;
+			goto out;
+		}
+	}
+
+out:
+	free(p);
+	return ret;
+}
+
+/* Another dummy workload to generate IBS samples. */
+static void dummy_workload_2(char *perf)
+{
+	char bench[] = " bench sched messaging -g 10 -l 5000 > /dev/null 2>&1";
+	char taskset[] = "taskset -c 0 ";
+	int ret __maybe_unused;
+	struct strbuf sb;
+	char *cmd;
+
+	strbuf_init(&sb, 0);
+	strbuf_add(&sb, taskset, strlen(taskset));
+	strbuf_add(&sb, perf, strlen(perf));
+	strbuf_add(&sb, bench, strlen(bench));
+	cmd = strbuf_detach(&sb, NULL);
+	ret = system(cmd);
+	free(cmd);
+}
+
+static int sched_affine(int cpu)
+{
+	cpu_set_t set;
+
+	CPU_ZERO(&set);
+	CPU_SET(cpu, &set);
+	if (sched_setaffinity(getpid(), sizeof(set), &set) == -1) {
+		pr_debug("sched_setaffinity() failed. [%m]");
+		return -1;
+	}
+	return 0;
+}
+
+static void
+copy_sample_data(void *src, unsigned long offset, void *dest, size_t size)
+{
+	size_t chunk1_size, chunk2_size;
+
+	if ((offset + size) < (size_t)PERF_MMAP_DATA_SIZE) {
+		memcpy(dest, src + offset, size);
+	} else {
+		chunk1_size = PERF_MMAP_DATA_SIZE - offset;
+		chunk2_size = size - chunk1_size;
+
+		memcpy(dest, src + offset, chunk1_size);
+		memcpy(dest + chunk1_size, src, chunk2_size);
+	}
+}
+
+static int rb_read(struct perf_event_mmap_page *rb, void *dest, size_t size)
+{
+	void *base;
+	unsigned long data_tail, data_head;
+
+	/* Casting to (void *) is needed. */
+	base = (void *)rb + page_size;
+
+	data_head = rb->data_head;
+	rmb();
+	data_tail = rb->data_tail;
+
+	if ((data_head - data_tail) < size)
+		return -1;
+
+	data_tail &= PERF_MMAP_DATA_MASK;
+	copy_sample_data(base, data_tail, dest, size);
+	rb->data_tail += size;
+	return 0;
+}
+
+static void rb_skip(struct perf_event_mmap_page *rb, size_t size)
+{
+	size_t data_head = rb->data_head;
+
+	rmb();
+
+	if ((rb->data_tail + size) > data_head)
+		rb->data_tail = data_head;
+	else
+		rb->data_tail += size;
+}
+
+/* Sample period value taken from perf sample must match with expected value. */
+static int period_equal(unsigned long exp_period, unsigned long act_period)
+{
+	return exp_period == act_period ? 0 : -1;
+}
+
+/*
+ * Sample period value taken from perf sample must be >= minimum sample period
+ * supported by IBS HW.
+ */
+static int period_higher(unsigned long min_period, unsigned long act_period)
+{
+	return min_period <= act_period ? 0 : -1;
+}
+
+static int rb_drain_samples(struct perf_event_mmap_page *rb,
+			    unsigned long exp_period,
+			    int *nr_samples,
+			    int (*callback)(unsigned long, unsigned long))
+{
+	struct perf_event_header hdr;
+	unsigned long period;
+	int ret = 0;
+
+	/*
+	 * PERF_RECORD_SAMPLE:
+	 * struct {
+	 *	struct perf_event_header hdr;
+	 *	{ u64			 period;     } && PERF_SAMPLE_PERIOD
+	 * };
+	 */
+	while (1) {
+		if (rb_read(rb, &hdr, sizeof(hdr)))
+			return ret;
+
+		if (hdr.type == PERF_RECORD_SAMPLE) {
+			(*nr_samples)++;
+			period = 0;
+			if (rb_read(rb, &period, sizeof(period)))
+				pr_debug("rb_read(period) error. [%m]");
+			ret |= callback(exp_period, period);
+		} else {
+			rb_skip(rb, hdr.size - sizeof(hdr));
+		}
+	}
+	return ret;
+}
+
+static long perf_event_open(struct perf_event_attr *attr, pid_t pid,
+			    int cpu, int group_fd, unsigned long flags)
+{
+	return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+}
+
+static void fetch_prepare_attr(struct perf_event_attr *attr,
+			       unsigned long long config, int freq,
+			       unsigned long sample_period)
+{
+	memset(attr, 0, sizeof(struct perf_event_attr));
+
+	attr->type = fetch_pmu->type;
+	attr->size = sizeof(struct perf_event_attr);
+	attr->config = config;
+	attr->disabled = 1;
+	attr->sample_type = PERF_SAMPLE_PERIOD;
+	attr->freq = freq;
+	attr->sample_period = sample_period; /* = ->sample_freq */
+}
+
+static void op_prepare_attr(struct perf_event_attr *attr,
+			    unsigned long config, int freq,
+			    unsigned long sample_period)
+{
+	memset(attr, 0, sizeof(struct perf_event_attr));
+
+	attr->type = op_pmu->type;
+	attr->size = sizeof(struct perf_event_attr);
+	attr->config = config;
+	attr->disabled = 1;
+	attr->sample_type = PERF_SAMPLE_PERIOD;
+	attr->freq = freq;
+	attr->sample_period = sample_period; /* = ->sample_freq */
+}
+
+struct ibs_configs {
+	/* Input */
+	unsigned long config;
+
+	/* Expected output */
+	unsigned long period;
+	int fd;
+};
+
+/*
+ * Somehow first Fetch event with sample period = 0x10 causes 0
+ * samples. So start with large period and decrease it gradually.
+ */
+struct ibs_configs fetch_configs[] = {
+	{ .config =  0xffff, .period = 0xffff0, .fd = FD_SUCCESS },
+	{ .config =  0x1000, .period = 0x10000, .fd = FD_SUCCESS },
+	{ .config =    0xff, .period =   0xff0, .fd = FD_SUCCESS },
+	{ .config =     0x1, .period =    0x10, .fd = FD_SUCCESS },
+	{ .config =     0x0, .period =      -1, .fd = FD_ERROR   },
+	{ .config = 0x10000, .period =      -1, .fd = FD_ERROR   },
+};
+
+struct ibs_configs op_configs[] = {
+	{ .config =        0x0, .period =        -1, .fd = FD_ERROR   },
+	{ .config =        0x1, .period =        -1, .fd = FD_ERROR   },
+	{ .config =        0x8, .period =        -1, .fd = FD_ERROR   },
+	{ .config =        0x9, .period =      0x90, .fd = FD_SUCCESS },
+	{ .config =        0xf, .period =      0xf0, .fd = FD_SUCCESS },
+	{ .config =     0x1000, .period =   0x10000, .fd = FD_SUCCESS },
+	{ .config =     0xffff, .period =   0xffff0, .fd = FD_SUCCESS },
+	{ .config =    0x10000, .period =        -1, .fd = FD_ERROR   },
+	{ .config =   0x100000, .period =  0x100000, .fd = FD_SUCCESS },
+	{ .config =   0xf00000, .period =  0xf00000, .fd = FD_SUCCESS },
+	{ .config =   0xf0ffff, .period =  0xfffff0, .fd = FD_SUCCESS },
+	{ .config =  0x1f0ffff, .period = 0x1fffff0, .fd = FD_SUCCESS },
+	{ .config =  0x7f0ffff, .period = 0x7fffff0, .fd = FD_SUCCESS },
+	{ .config =  0x8f0ffff, .period =        -1, .fd = FD_ERROR   },
+	{ .config = 0x17f0ffff, .period =        -1, .fd = FD_ERROR   },
+};
+
+static int __ibs_config_test(int ibs_type, struct ibs_configs *config, int *nr_samples)
+{
+	struct perf_event_attr attr;
+	int fd, i;
+	void *rb;
+	int ret = 0;
+
+	if (ibs_type == IBS_FETCH)
+		fetch_prepare_attr(&attr, config->config, 0, 0);
+	else
+		op_prepare_attr(&attr, config->config, 0, 0);
+
+	/* CPU0, All processes */
+	fd = perf_event_open(&attr, -1, 0, -1, 0);
+	if (config->fd == FD_ERROR) {
+		if (fd != -1) {
+			close(fd);
+			return -1;
+		}
+		return 0;
+	}
+	if (fd <= -1)
+		return -1;
+
+	rb = mmap(NULL, PERF_MMAP_TOTAL_SIZE, PROT_READ | PROT_WRITE,
+		  MAP_SHARED, fd, 0);
+	if (rb == MAP_FAILED) {
+		pr_debug("mmap() failed. [%m]\n");
+		return -1;
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+
+	i = 5;
+	while (i--) {
+		dummy_workload_1(1000000);
+
+		ret = rb_drain_samples(rb, config->period, nr_samples,
+				       period_equal);
+		if (ret)
+			break;
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+	munmap(rb, PERF_MMAP_TOTAL_SIZE);
+	close(fd);
+	return ret;
+}
+
+static int ibs_config_test(void)
+{
+	int nr_samples = 0;
+	unsigned long i;
+	int ret = 0;
+	int r;
+
+	pr_debug("\nIBS config tests:\n");
+	pr_debug("-----------------\n");
+
+	pr_debug("Fetch PMU tests:\n");
+	for (i = 0; i < ARRAY_SIZE(fetch_configs); i++) {
+		nr_samples = 0;
+		r = __ibs_config_test(IBS_FETCH, &(fetch_configs[i]), &nr_samples);
+
+		if (fetch_configs[i].fd == FD_ERROR) {
+			pr_debug("0x%-16lx: %-4s\n", fetch_configs[i].config,
+				 !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("0x%-16lx: %-4s (nr samples: %d)\n", fetch_configs[i].config,
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+
+		ret |= r;
+	}
+
+	pr_debug("Op PMU tests:\n");
+	for (i = 0; i < ARRAY_SIZE(op_configs); i++) {
+		nr_samples = 0;
+		r = __ibs_config_test(IBS_OP, &(op_configs[i]), &nr_samples);
+
+		if (op_configs[i].fd == FD_ERROR) {
+			pr_debug("0x%-16lx: %-4s\n", op_configs[i].config,
+				 !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("0x%-16lx: %-4s (nr samples: %d)\n", op_configs[i].config,
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+
+		ret |= r;
+	}
+
+	return ret;
+}
+
+struct ibs_period {
+	/* Input */
+	int freq;
+	unsigned long sample_freq;
+
+	/* Output */
+	int ret;
+	unsigned long period;
+};
+
+struct ibs_period fetch_period[] = {
+	{ .freq = 0, .sample_freq =         0, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =         1, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =       0xf, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =      0x10, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 0, .sample_freq =      0x11, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 0, .sample_freq =      0x8f, .ret = FD_SUCCESS, .period =      0x80 },
+	{ .freq = 0, .sample_freq =      0x90, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 0, .sample_freq =      0x91, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 0, .sample_freq =     0x4d2, .ret = FD_SUCCESS, .period =     0x4d0 },
+	{ .freq = 0, .sample_freq =    0x1007, .ret = FD_SUCCESS, .period =    0x1000 },
+	{ .freq = 0, .sample_freq =    0xfff0, .ret = FD_SUCCESS, .period =    0xfff0 },
+	{ .freq = 0, .sample_freq =    0xffff, .ret = FD_SUCCESS, .period =    0xfff0 },
+	{ .freq = 0, .sample_freq =   0x10010, .ret = FD_SUCCESS, .period =   0x10010 },
+	{ .freq = 0, .sample_freq =  0x7fffff, .ret = FD_SUCCESS, .period =  0x7ffff0 },
+	{ .freq = 0, .sample_freq = 0xfffffff, .ret = FD_SUCCESS, .period = 0xffffff0 },
+	{ .freq = 1, .sample_freq =         0, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 1, .sample_freq =         1, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =       0xf, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =      0x10, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =      0x11, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =      0x8f, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =      0x90, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =      0x91, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =     0x4d2, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =    0x1007, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =    0xfff0, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =    0xffff, .ret = FD_SUCCESS, .period =      0x10 },
+	{ .freq = 1, .sample_freq =   0x10010, .ret = FD_SUCCESS, .period =      0x10 },
+	/* ret=FD_ERROR because freq > default perf_event_max_sample_rate (100000) */
+	{ .freq = 1, .sample_freq =  0x7fffff, .ret = FD_ERROR,   .period =        -1 },
+};
+
+struct ibs_period op_period[] = {
+	{ .freq = 0, .sample_freq =         0, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =         1, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =       0xf, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =      0x10, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =      0x11, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =      0x8f, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 0, .sample_freq =      0x90, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 0, .sample_freq =      0x91, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 0, .sample_freq =     0x4d2, .ret = FD_SUCCESS, .period =     0x4d0 },
+	{ .freq = 0, .sample_freq =    0x1007, .ret = FD_SUCCESS, .period =    0x1000 },
+	{ .freq = 0, .sample_freq =    0xfff0, .ret = FD_SUCCESS, .period =    0xfff0 },
+	{ .freq = 0, .sample_freq =    0xffff, .ret = FD_SUCCESS, .period =    0xfff0 },
+	{ .freq = 0, .sample_freq =   0x10010, .ret = FD_SUCCESS, .period =   0x10010 },
+	{ .freq = 0, .sample_freq =  0x7fffff, .ret = FD_SUCCESS, .period =  0x7ffff0 },
+	{ .freq = 0, .sample_freq = 0xfffffff, .ret = FD_SUCCESS, .period = 0xffffff0 },
+	{ .freq = 1, .sample_freq =         0, .ret = FD_ERROR,   .period =        -1 },
+	{ .freq = 1, .sample_freq =         1, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =       0xf, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =      0x10, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =      0x11, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =      0x8f, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =      0x90, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =      0x91, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =     0x4d2, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =    0x1007, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =    0xfff0, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =    0xffff, .ret = FD_SUCCESS, .period =      0x90 },
+	{ .freq = 1, .sample_freq =   0x10010, .ret = FD_SUCCESS, .period =      0x90 },
+	/* ret=FD_ERROR because freq > default perf_event_max_sample_rate (100000) */
+	{ .freq = 1, .sample_freq =  0x7fffff, .ret = FD_ERROR,   .period =        -1 },
+};
+
+static int __ibs_period_constraint_test(int ibs_type, struct ibs_period *period,
+					int *nr_samples)
+{
+	struct perf_event_attr attr;
+	int ret = 0;
+	void *rb;
+	int fd;
+
+	if (period->freq && period->sample_freq > perf_event_max_sample_rate)
+		period->ret = FD_ERROR;
+
+	if (ibs_type == IBS_FETCH)
+		fetch_prepare_attr(&attr, 0, period->freq, period->sample_freq);
+	else
+		op_prepare_attr(&attr, 0, period->freq, period->sample_freq);
+
+	/* CPU0, All processes */
+	fd = perf_event_open(&attr, -1, 0, -1, 0);
+	if (period->ret == FD_ERROR) {
+		if (fd != -1) {
+			close(fd);
+			return -1;
+		}
+		return 0;
+	}
+	if (fd <= -1)
+		return -1;
+
+	rb = mmap(NULL, PERF_MMAP_TOTAL_SIZE, PROT_READ | PROT_WRITE,
+		  MAP_SHARED, fd, 0);
+	if (rb == MAP_FAILED) {
+		pr_debug("mmap() failed. [%m]\n");
+		close(fd);
+		return -1;
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+
+	if (period->freq) {
+		dummy_workload_1(100000);
+		ret = rb_drain_samples(rb, period->period, nr_samples,
+				       period_higher);
+	} else {
+		dummy_workload_1(period->sample_freq * 10);
+		ret = rb_drain_samples(rb, period->period, nr_samples,
+				       period_equal);
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+	munmap(rb, PERF_MMAP_TOTAL_SIZE);
+	close(fd);
+	return ret;
+}
+
+static int ibs_period_constraint_test(void)
+{
+	unsigned long i;
+	int nr_samples;
+	int ret = 0;
+	int r;
+
+	pr_debug("\nIBS sample period constraint tests:\n");
+	pr_debug("-----------------------------------\n");
+
+	pr_debug("Fetch PMU test:\n");
+	for (i = 0; i < ARRAY_SIZE(fetch_period); i++) {
+		nr_samples = 0;
+		r = __ibs_period_constraint_test(IBS_FETCH, &fetch_period[i],
+						 &nr_samples);
+
+		if (fetch_period[i].ret == FD_ERROR) {
+			pr_debug("freq %d, sample_freq %9ld: %-4s\n",
+				 fetch_period[i].freq, fetch_period[i].sample_freq,
+				 !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("freq %d, sample_freq %9ld: %-4s (nr samples: %d)\n",
+				 fetch_period[i].freq, fetch_period[i].sample_freq,
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+		ret |= r;
+	}
+
+	pr_debug("Op PMU test:\n");
+	for (i = 0; i < ARRAY_SIZE(op_period); i++) {
+		nr_samples = 0;
+		r = __ibs_period_constraint_test(IBS_OP, &op_period[i],
+						 &nr_samples);
+
+		if (op_period[i].ret == FD_ERROR) {
+			pr_debug("freq %d, sample_freq %9ld: %-4s\n",
+				 op_period[i].freq, op_period[i].sample_freq,
+				 !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("freq %d, sample_freq %9ld: %-4s (nr samples: %d)\n",
+				 op_period[i].freq, op_period[i].sample_freq,
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+		ret |= r;
+	}
+
+	return ret;
+}
+
+struct ibs_ioctl {
+	/* Input */
+	int freq;
+	unsigned long period;
+
+	/* Expected output */
+	int ret;
+};
+
+struct ibs_ioctl fetch_ioctl[] = {
+	{ .freq = 0, .period =     0x0, .ret = FD_ERROR   },
+	{ .freq = 0, .period =     0x1, .ret = FD_ERROR   },
+	{ .freq = 0, .period =     0xf, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x10, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =    0x11, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x1f, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x20, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =    0x80, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =    0x8f, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x90, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =    0x91, .ret = FD_ERROR   },
+	{ .freq = 0, .period =   0x100, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =  0xfff0, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =  0xffff, .ret = FD_ERROR   },
+	{ .freq = 0, .period = 0x10000, .ret = FD_SUCCESS },
+	{ .freq = 0, .period = 0x1fff0, .ret = FD_SUCCESS },
+	{ .freq = 0, .period = 0x1fff5, .ret = FD_ERROR   },
+	{ .freq = 1, .period =     0x0, .ret = FD_ERROR   },
+	{ .freq = 1, .period =     0x1, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =     0xf, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x10, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x11, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x1f, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x20, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x80, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x8f, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x90, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x91, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =   0x100, .ret = FD_SUCCESS },
+};
+
+struct ibs_ioctl op_ioctl[] = {
+	{ .freq = 0, .period =     0x0, .ret = FD_ERROR   },
+	{ .freq = 0, .period =     0x1, .ret = FD_ERROR   },
+	{ .freq = 0, .period =     0xf, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x10, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x11, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x1f, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x20, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x80, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x8f, .ret = FD_ERROR   },
+	{ .freq = 0, .period =    0x90, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =    0x91, .ret = FD_ERROR   },
+	{ .freq = 0, .period =   0x100, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =  0xfff0, .ret = FD_SUCCESS },
+	{ .freq = 0, .period =  0xffff, .ret = FD_ERROR   },
+	{ .freq = 0, .period = 0x10000, .ret = FD_SUCCESS },
+	{ .freq = 0, .period = 0x1fff0, .ret = FD_SUCCESS },
+	{ .freq = 0, .period = 0x1fff5, .ret = FD_ERROR   },
+	{ .freq = 1, .period =     0x0, .ret = FD_ERROR   },
+	{ .freq = 1, .period =     0x1, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =     0xf, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x10, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x11, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x1f, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x20, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x80, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x8f, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x90, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =    0x91, .ret = FD_SUCCESS },
+	{ .freq = 1, .period =   0x100, .ret = FD_SUCCESS },
+};
+
+static int __ibs_ioctl_test(int ibs_type, struct ibs_ioctl *ibs_ioctl)
+{
+	struct perf_event_attr attr;
+	int ret = 0;
+	int fd;
+	int r;
+
+	if (ibs_type == IBS_FETCH)
+		fetch_prepare_attr(&attr, 0, ibs_ioctl->freq, 1000);
+	else
+		op_prepare_attr(&attr, 0, ibs_ioctl->freq, 1000);
+
+	/* CPU0, All processes */
+	fd = perf_event_open(&attr, -1, 0, -1, 0);
+	if (fd <= -1) {
+		pr_debug("event_open() Failed\n");
+		return -1;
+	}
+
+	r = ioctl(fd, PERF_EVENT_IOC_PERIOD, &ibs_ioctl->period);
+	if ((ibs_ioctl->ret == FD_SUCCESS && r <= -1) ||
+	    (ibs_ioctl->ret == FD_ERROR && r >= 0)) {
+		ret = -1;
+	}
+
+	close(fd);
+	return ret;
+}
+
+static int ibs_ioctl_test(void)
+{
+	unsigned long i;
+	int ret = 0;
+	int r;
+
+	pr_debug("\nIBS ioctl() tests:\n");
+	pr_debug("------------------\n");
+
+	pr_debug("Fetch PMU tests\n");
+	for (i = 0; i < ARRAY_SIZE(fetch_ioctl); i++) {
+		r = __ibs_ioctl_test(IBS_FETCH, &fetch_ioctl[i]);
+
+		pr_debug("ioctl(%s = 0x%-7lx): %s\n",
+			 fetch_ioctl[i].freq ? "freq  " : "period",
+			 fetch_ioctl[i].period, r ? "Fail" : "Ok");
+		ret |= r;
+	}
+
+	pr_debug("Op PMU tests\n");
+	for (i = 0; i < ARRAY_SIZE(op_ioctl); i++) {
+		r = __ibs_ioctl_test(IBS_OP, &op_ioctl[i]);
+
+		pr_debug("ioctl(%s = 0x%-7lx): %s\n",
+			 op_ioctl[i].freq ? "freq  " : "period",
+			 op_ioctl[i].period, r ? "Fail" : "Ok");
+		ret |= r;
+	}
+
+	return ret;
+}
+
+static int ibs_freq_neg_test(void)
+{
+	struct perf_event_attr attr;
+	int fd;
+
+	pr_debug("\nIBS freq (negative) tests:\n");
+	pr_debug("--------------------------\n");
+
+	/*
+	 * Assuming perf_event_max_sample_rate <= 100000,
+	 * config: 0x300D40 ==> MaxCnt: 200000
+	 */
+	op_prepare_attr(&attr, 0x300D40, 1, 0);
+
+	/* CPU0, All processes */
+	fd = perf_event_open(&attr, -1, 0, -1, 0);
+	if (fd != -1) {
+		pr_debug("freq 1, sample_freq 200000: Fail\n");
+		close(fd);
+		return -1;
+	}
+
+	pr_debug("freq 1, sample_freq 200000: Ok\n");
+
+	return 0;
+}
+
+struct ibs_l3missonly {
+	/* Input */
+	int freq;
+	unsigned long sample_freq;
+
+	/* Expected output */
+	int ret;
+	unsigned long min_period;
+};
+
+struct ibs_l3missonly fetch_l3missonly = {
+	.freq = 1,
+	.sample_freq = 10000,
+	.ret = FD_SUCCESS,
+	.min_period = 0x10,
+};
+
+struct ibs_l3missonly op_l3missonly = {
+	.freq = 1,
+	.sample_freq = 10000,
+	.ret = FD_SUCCESS,
+	.min_period = 0x90,
+};
+
+static int __ibs_l3missonly_test(char *perf, int ibs_type, int *nr_samples,
+				 struct ibs_l3missonly *l3missonly)
+{
+	struct perf_event_attr attr;
+	int ret = 0;
+	void *rb;
+	int fd;
+
+	if (l3missonly->sample_freq > perf_event_max_sample_rate)
+		l3missonly->ret = FD_ERROR;
+
+	if (ibs_type == IBS_FETCH) {
+		fetch_prepare_attr(&attr, 0x800000000000000UL, l3missonly->freq,
+				   l3missonly->sample_freq);
+	} else {
+		op_prepare_attr(&attr, 0x10000, l3missonly->freq,
+				l3missonly->sample_freq);
+	}
+
+	/* CPU0, All processes */
+	fd = perf_event_open(&attr, -1, 0, -1, 0);
+	if (l3missonly->ret == FD_ERROR) {
+		if (fd != -1) {
+			close(fd);
+			return -1;
+		}
+		return 0;
+	}
+	if (fd == -1) {
+		pr_debug("perf_event_open() failed. [%m]\n");
+		return -1;
+	}
+
+	rb = mmap(NULL, PERF_MMAP_TOTAL_SIZE, PROT_READ | PROT_WRITE,
+		  MAP_SHARED, fd, 0);
+	if (rb == MAP_FAILED) {
+		pr_debug("mmap() failed. [%m]\n");
+		close(fd);
+		return -1;
+	}
+
+	ioctl(fd, PERF_EVENT_IOC_RESET, 0);
+	ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
+
+	dummy_workload_2(perf);
+
+	ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+
+	ret = rb_drain_samples(rb, l3missonly->min_period, nr_samples, period_higher);
+
+	munmap(rb, PERF_MMAP_TOTAL_SIZE);
+	close(fd);
+	return ret;
+}
+
+static int ibs_l3missonly_test(char *perf)
+{
+	int nr_samples = 0;
+	int ret = 0;
+	int r = 0;
+
+	pr_debug("\nIBS L3MissOnly test: (takes a while)\n");
+	pr_debug("--------------------\n");
+
+	if (perf_pmu__has_format(fetch_pmu, "l3missonly")) {
+		nr_samples = 0;
+		r = __ibs_l3missonly_test(perf, IBS_FETCH, &nr_samples, &fetch_l3missonly);
+		if (fetch_l3missonly.ret == FD_ERROR) {
+			pr_debug("Fetch L3MissOnly: %-4s\n", !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("Fetch L3MissOnly: %-4s (nr_samples: %d)\n",
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+		ret |= r;
+	}
+
+	if (perf_pmu__has_format(op_pmu, "l3missonly")) {
+		nr_samples = 0;
+		r = __ibs_l3missonly_test(perf, IBS_OP, &nr_samples, &op_l3missonly);
+		if (op_l3missonly.ret == FD_ERROR) {
+			pr_debug("Op L3MissOnly:    %-4s\n", !r ? "Ok" : "Fail");
+		} else {
+			/*
+			 * Although nr_samples == 0 is reported as Fail here,
+			 * the failure status is not cascaded up because, we
+			 * can not decide whether test really failed or not
+			 * without actual samples.
+			 */
+			pr_debug("Op L3MissOnly:    %-4s (nr_samples: %d)\n",
+				 (!r && nr_samples != 0) ? "Ok" : "Fail", nr_samples);
+		}
+		ret |= r;
+	}
+
+	return ret;
+}
+
+static unsigned int get_perf_event_max_sample_rate(void)
+{
+	unsigned int max_sample_rate = 100000;
+	FILE *fp;
+	int ret;
+
+	fp = fopen("/proc/sys/kernel/perf_event_max_sample_rate", "r");
+	if (!fp) {
+		pr_debug("Can't open perf_event_max_sample_rate. Assuming %d\n",
+			 max_sample_rate);
+		goto out;
+	}
+
+	ret = fscanf(fp, "%d", &max_sample_rate);
+	if (ret == EOF) {
+		pr_debug("Can't read perf_event_max_sample_rate. Assuming 100000\n");
+		max_sample_rate = 100000;
+	}
+	fclose(fp);
+
+out:
+	return max_sample_rate;
+}
+
+/*
+ * Bunch of IBS sample period fixes that this test exercise went in v6.15.
+ * Skip the test on older kernels to distinguish between test failure due
+ * to a new bug vs known failure due to older kernel.
+ */
+static bool kernel_v6_15_or_newer(void)
+{
+	struct utsname utsname;
+	char *endptr = NULL;
+	long major, minor;
+
+	if (uname(&utsname) < 0) {
+		pr_debug("uname() failed. [%m]");
+		return false;
+	}
+
+	major = strtol(utsname.release, &endptr, 10);
+	endptr++;
+	minor = strtol(endptr, NULL, 10);
+
+	return major >= 6 && minor >= 15;
+}
+
+int test__amd_ibs_period(struct test_suite *test __maybe_unused,
+			 int subtest __maybe_unused)
+{
+	char perf[PATH_MAX] = {'\0'};
+	int ret = TEST_OK;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	/*
+	 * Reading perf_event_max_sample_rate only once _might_ cause some
+	 * of the test to fail if kernel changes it after reading it here.
+	 */
+	perf_event_max_sample_rate = get_perf_event_max_sample_rate();
+	fetch_pmu = perf_pmus__find("ibs_fetch");
+	op_pmu = perf_pmus__find("ibs_op");
+
+	if (!x86__is_amd_cpu() || !fetch_pmu || !op_pmu)
+		return TEST_SKIP;
+
+	if (!kernel_v6_15_or_newer()) {
+		pr_debug("Need v6.15 or newer kernel. Skipping.\n");
+		return TEST_SKIP;
+	}
+
+	perf_exe(perf, sizeof(perf));
+
+	if (sched_affine(0))
+		return TEST_FAIL;
+
+	/*
+	 * Perf event can be opened in two modes:
+	 * 1 Freq mode
+	 *   perf_event_attr->freq = 1, ->sample_freq = <frequency>
+	 * 2 Sample period mode
+	 *   perf_event_attr->freq = 0, ->sample_period = <period>
+	 *
+	 * Instead of using above interface, IBS event in 'sample period mode'
+	 * can also be opened by passing <period> value directly in a MaxCnt
+	 * bitfields of perf_event_attr->config. Test this IBS specific special
+	 * interface.
+	 */
+	if (ibs_config_test())
+		ret = TEST_FAIL;
+
+	/*
+	 * IBS Fetch and Op PMUs have HW constraints on minimum sample period.
+	 * Also, sample period value must be in multiple of 0x10. Test that IBS
+	 * driver honors HW constraints for various possible values in Freq as
+	 * well as Sample Period mode IBS events.
+	 */
+	if (ibs_period_constraint_test())
+		ret = TEST_FAIL;
+
+	/*
+	 * Test ioctl() with various sample period values for IBS event.
+	 */
+	if (ibs_ioctl_test())
+		ret = TEST_FAIL;
+
+	/*
+	 * Test that opening of freq mode IBS event fails when the freq value
+	 * is passed through ->config, not explicitly in ->sample_freq. Also
+	 * use high freq value (beyond perf_event_max_sample_rate) to test IBS
+	 * driver do not bypass perf_event_max_sample_rate checks.
+	 */
+	if (ibs_freq_neg_test())
+		ret = TEST_FAIL;
+
+	/*
+	 * L3MissOnly is a post-processing filter, i.e. IBS HW checks for L3
+	 * Miss at the completion of the tagged uOp. The sample is discarded
+	 * if the tagged uOp did not cause L3Miss. Also, IBS HW internally
+	 * resets CurCnt to a small pseudo-random value and resumes counting.
+	 * A new uOp is tagged once CurCnt reaches to MaxCnt. But the process
+	 * repeats until the tagged uOp causes an L3 Miss.
+	 *
+	 * With the freq mode event, the next sample period is calculated by
+	 * generic kernel on every sample to achieve desired freq of samples.
+	 *
+	 * Since the number of times HW internally reset CurCnt and the pseudo-
+	 * random value of CurCnt for all those occurrences are not known to SW,
+	 * the sample period adjustment by kernel goes for a toes for freq mode
+	 * IBS events. Kernel will set very small period for the next sample if
+	 * the window between current sample and prev sample is too high due to
+	 * multiple samples being discarded internally by IBS HW.
+	 *
+	 * Test that IBS sample period constraints are honored when L3MissOnly
+	 * is ON.
+	 */
+	if (ibs_l3missonly_test(perf))
+		ret = TEST_FAIL;
+
+	return ret;
+}
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index a216a5d172ed..bfee2432515b 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -25,6 +25,7 @@ DEFINE_SUITE("x86 bp modify", bp_modify);
 #endif
 DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing);
 DEFINE_SUITE("AMD IBS via core pmu", amd_ibs_via_core_pmu);
+DEFINE_SUITE_EXCLUSIVE("AMD IBS sample period", amd_ibs_period);
 static struct test_case hybrid_tests[] = {
 	TEST_CASE_REASON("x86 hybrid event parsing", hybrid, "not hybrid"),
 	{ .name = NULL, }
@@ -50,6 +51,7 @@ struct test_suite *arch_tests[] = {
 #endif
 	&suite__x86_sample_parsing,
 	&suite__amd_ibs_via_core_pmu,
+	&suite__amd_ibs_period,
 	&suite__hybrid,
 	NULL,
 };
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 8f235d8b67b6..add33cb5d1da 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -19,6 +19,7 @@
 #include "../../../util/evlist.h"
 #include "../../../util/evsel.h"
 #include "../../../util/evsel_config.h"
+#include "../../../util/config.h"
 #include "../../../util/cpumap.h"
 #include "../../../util/mmap.h"
 #include <subcmd/parse-options.h>
@@ -52,6 +53,7 @@ struct intel_pt_recording {
 	struct perf_pmu			*intel_pt_pmu;
 	int				have_sched_switch;
 	struct evlist		*evlist;
+	bool				all_switch_events;
 	bool				snapshot_mode;
 	bool				snapshot_init_done;
 	size_t				snapshot_size;
@@ -794,7 +796,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 			bool cpu_wide = !target__none(&opts->target) &&
 					!target__has_task(&opts->target);
 
-			if (!cpu_wide && perf_can_record_cpu_wide()) {
+			if (ptr->all_switch_events && !cpu_wide && perf_can_record_cpu_wide()) {
 				struct evsel *switch_evsel;
 
 				switch_evsel = evlist__add_dummy_on_all_cpus(evlist);
@@ -1178,6 +1180,16 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
 	return rdtsc();
 }
 
+static int intel_pt_perf_config(const char *var, const char *value, void *data)
+{
+	struct intel_pt_recording *ptr = data;
+
+	if (!strcmp(var, "intel-pt.all-switch-events"))
+		ptr->all_switch_events = perf_config_bool(var, value);
+
+	return 0;
+}
+
 struct auxtrace_record *intel_pt_recording_init(int *err)
 {
 	struct perf_pmu *intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME);
@@ -1197,6 +1209,8 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 		return NULL;
 	}
 
+	perf_config(intel_pt_perf_config, ptr);
+
 	ptr->intel_pt_pmu = intel_pt_pmu;
 	ptr->itr.recording_options = intel_pt_recording_options;
 	ptr->itr.info_priv_size = intel_pt_info_priv_size;
diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index 62df03e91c7e..b38f519020ff 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -26,3 +26,9 @@ struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
 	E(NULL,		NULL,		NULL,	false,	0),
 	E("mem-ldst",	"%s//",		NULL,	false,	0),
 };
+
+struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL,	false,	0),
+	E(NULL,		NULL,		NULL,	false,	0),
+	E("mem-ldst",	"%s/ldlat=%u/",	NULL,	true,	0),
+};
diff --git a/tools/perf/arch/x86/util/mem-events.h b/tools/perf/arch/x86/util/mem-events.h
index f55c8d3b7d59..11e09a256f5b 100644
--- a/tools/perf/arch/x86/util/mem-events.h
+++ b/tools/perf/arch/x86/util/mem-events.h
@@ -6,5 +6,6 @@ extern struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX];
 extern struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX];
 
 extern struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX];
+extern struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX];
 
 #endif /* _X86_MEM_EVENTS_H */
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index e0060dac2a9f..58113482654b 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -8,6 +8,8 @@
 #include <linux/perf_event.h>
 #include <linux/zalloc.h>
 #include <api/fs/fs.h>
+#include <api/io_dir.h>
+#include <internal/cpumap.h>
 #include <errno.h>
 
 #include "../../../util/intel-pt.h"
@@ -16,10 +18,261 @@
 #include "../../../util/fncache.h"
 #include "../../../util/pmus.h"
 #include "mem-events.h"
+#include "util/debug.h"
 #include "util/env.h"
+#include "util/header.h"
 
-void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
+static bool x86__is_intel_graniterapids(void)
 {
+	static bool checked_if_graniterapids;
+	static bool is_graniterapids;
+
+	if (!checked_if_graniterapids) {
+		const char *graniterapids_cpuid = "GenuineIntel-6-A[DE]";
+		char *cpuid = get_cpuid_str((struct perf_cpu){0});
+
+		is_graniterapids = cpuid && strcmp_cpuid_str(graniterapids_cpuid, cpuid) == 0;
+		free(cpuid);
+		checked_if_graniterapids = true;
+	}
+	return is_graniterapids;
+}
+
+static struct perf_cpu_map *read_sysfs_cpu_map(const char *sysfs_path)
+{
+	struct perf_cpu_map *cpus;
+	char *buf = NULL;
+	size_t buf_len;
+
+	if (sysfs__read_str(sysfs_path, &buf, &buf_len) < 0)
+		return NULL;
+
+	cpus = perf_cpu_map__new(buf);
+	free(buf);
+	return cpus;
+}
+
+static int snc_nodes_per_l3_cache(void)
+{
+	static bool checked_snc;
+	static int snc_nodes;
+
+	if (!checked_snc) {
+		struct perf_cpu_map *node_cpus =
+			read_sysfs_cpu_map("devices/system/node/node0/cpulist");
+		struct perf_cpu_map *cache_cpus =
+			read_sysfs_cpu_map("devices/system/cpu/cpu0/cache/index3/shared_cpu_list");
+
+		snc_nodes = perf_cpu_map__nr(cache_cpus) / perf_cpu_map__nr(node_cpus);
+		perf_cpu_map__put(cache_cpus);
+		perf_cpu_map__put(node_cpus);
+		checked_snc = true;
+	}
+	return snc_nodes;
+}
+
+static bool starts_with(const char *str, const char *prefix)
+{
+	return !strncmp(prefix, str, strlen(prefix));
+}
+
+static int num_chas(void)
+{
+	static bool checked_chas;
+	static int num_chas;
+
+	if (!checked_chas) {
+		int fd = perf_pmu__event_source_devices_fd();
+		struct io_dir dir;
+		struct io_dirent64 *dent;
+
+		if (fd < 0)
+			return -1;
+
+		io_dir__init(&dir, fd);
+
+		while ((dent = io_dir__readdir(&dir)) != NULL) {
+			/* Note, dent->d_type will be DT_LNK and so isn't a useful filter. */
+			if (starts_with(dent->d_name, "uncore_cha_"))
+				num_chas++;
+		}
+		close(fd);
+		checked_chas = true;
+	}
+	return num_chas;
+}
+
+#define MAX_SNCS 6
+
+static int uncore_cha_snc(struct perf_pmu *pmu)
+{
+	// CHA SNC numbers are ordered correspond to the CHAs number.
+	unsigned int cha_num;
+	int num_cha, chas_per_node, cha_snc;
+	int snc_nodes = snc_nodes_per_l3_cache();
+
+	if (snc_nodes <= 1)
+		return 0;
+
+	num_cha = num_chas();
+	if (num_cha <= 0) {
+		pr_warning("Unexpected: no CHAs found\n");
+		return 0;
+	}
+
+	/* Compute SNC for PMU. */
+	if (sscanf(pmu->name, "uncore_cha_%u", &cha_num) != 1) {
+		pr_warning("Unexpected: unable to compute CHA number '%s'\n", pmu->name);
+		return 0;
+	}
+	chas_per_node = num_cha / snc_nodes;
+	cha_snc = cha_num / chas_per_node;
+
+	/* Range check cha_snc. for unexpected out of bounds. */
+	return cha_snc >= MAX_SNCS ? 0 : cha_snc;
+}
+
+static int uncore_imc_snc(struct perf_pmu *pmu)
+{
+	// Compute the IMC SNC using lookup tables.
+	unsigned int imc_num;
+	int snc_nodes = snc_nodes_per_l3_cache();
+	const u8 snc2_map[] = {1, 1, 0, 0, 1, 1, 0, 0};
+	const u8 snc3_map[] = {1, 1, 0, 0, 2, 2, 1, 1, 0, 0, 2, 2};
+	const u8 *snc_map;
+	size_t snc_map_len;
+
+	switch (snc_nodes) {
+	case 2:
+		snc_map = snc2_map;
+		snc_map_len = ARRAY_SIZE(snc2_map);
+		break;
+	case 3:
+		snc_map = snc3_map;
+		snc_map_len = ARRAY_SIZE(snc3_map);
+		break;
+	default:
+		/* Error or no lookup support for SNC with >3 nodes. */
+		return 0;
+	}
+
+	/* Compute SNC for PMU. */
+	if (sscanf(pmu->name, "uncore_imc_%u", &imc_num) != 1) {
+		pr_warning("Unexpected: unable to compute IMC number '%s'\n", pmu->name);
+		return 0;
+	}
+	if (imc_num >= snc_map_len) {
+		pr_warning("Unexpected IMC %d for SNC%d mapping\n", imc_num, snc_nodes);
+		return 0;
+	}
+	return snc_map[imc_num];
+}
+
+static int uncore_cha_imc_compute_cpu_adjust(int pmu_snc)
+{
+	static bool checked_cpu_adjust[MAX_SNCS];
+	static int cpu_adjust[MAX_SNCS];
+	struct perf_cpu_map *node_cpus;
+	char node_path[] = "devices/system/node/node0/cpulist";
+
+	/* Was adjust already computed? */
+	if (checked_cpu_adjust[pmu_snc])
+		return cpu_adjust[pmu_snc];
+
+	/* SNC0 doesn't need an adjust. */
+	if (pmu_snc == 0) {
+		cpu_adjust[0] = 0;
+		checked_cpu_adjust[0] = true;
+		return 0;
+	}
+
+	/*
+	 * Use NUMA topology to compute first CPU of the NUMA node, we want to
+	 * adjust CPU 0 to be this and similarly for other CPUs if there is >1
+	 * socket.
+	 */
+	assert(pmu_snc >= 0 && pmu_snc <= 9);
+	node_path[24] += pmu_snc; // Shift node0 to be node<pmu_snc>.
+	node_cpus = read_sysfs_cpu_map(node_path);
+	cpu_adjust[pmu_snc] = perf_cpu_map__cpu(node_cpus, 0).cpu;
+	if (cpu_adjust[pmu_snc] < 0) {
+		pr_debug("Failed to read valid CPU list from <sysfs>/%s\n", node_path);
+		cpu_adjust[pmu_snc] = 0;
+	} else {
+		checked_cpu_adjust[pmu_snc] = true;
+	}
+	perf_cpu_map__put(node_cpus);
+	return cpu_adjust[pmu_snc];
+}
+
+static void gnr_uncore_cha_imc_adjust_cpumask_for_snc(struct perf_pmu *pmu, bool cha)
+{
+	// With sub-NUMA clustering (SNC) there is a NUMA node per SNC in the
+	// topology. For example, a two socket graniterapids machine may be set
+	// up with 3-way SNC meaning there are 6 NUMA nodes that should be
+	// displayed with --per-node. The cpumask of the CHA and IMC PMUs
+	// reflects per-socket information meaning, for example, uncore_cha_60
+	// on a two socket graniterapids machine with 120 cores per socket will
+	// have a cpumask of "0,120". This cpumask needs adjusting to "40,160"
+	// to reflect that uncore_cha_60 is used for the 2nd SNC of each
+	// socket. Without the adjustment events on uncore_cha_60 will appear in
+	// node 0 and node 3 (in our example 2 socket 3-way set up), but with
+	// the adjustment they will appear in node 1 and node 4. The number of
+	// CHAs is typically larger than the number of cores. The CHA numbers
+	// are assumed to split evenly and inorder wrt core numbers. There are
+	// fewer memory IMC PMUs than cores and mapping is handled using lookup
+	// tables.
+	static struct perf_cpu_map *cha_adjusted[MAX_SNCS];
+	static struct perf_cpu_map *imc_adjusted[MAX_SNCS];
+	struct perf_cpu_map **adjusted = cha ? cha_adjusted : imc_adjusted;
+	int idx, pmu_snc, cpu_adjust;
+	struct perf_cpu cpu;
+	bool alloc;
+
+	// Cpus from the kernel holds first CPU of each socket. e.g. 0,120.
+	if (perf_cpu_map__cpu(pmu->cpus, 0).cpu != 0) {
+		pr_debug("Ignoring cpumask adjust for %s as unexpected first CPU\n", pmu->name);
+		return;
+	}
+
+	pmu_snc = cha ? uncore_cha_snc(pmu) : uncore_imc_snc(pmu);
+	if (pmu_snc == 0) {
+		// No adjustment necessary for the first SNC.
+		return;
+	}
+
+	alloc = adjusted[pmu_snc] == NULL;
+	if (alloc) {
+		// Hold onto the perf_cpu_map globally to avoid recomputation.
+		cpu_adjust = uncore_cha_imc_compute_cpu_adjust(pmu_snc);
+		adjusted[pmu_snc] = perf_cpu_map__empty_new(perf_cpu_map__nr(pmu->cpus));
+		if (!adjusted[pmu_snc])
+			return;
+	}
+
+	perf_cpu_map__for_each_cpu(cpu, idx, pmu->cpus) {
+		// Compute the new cpu map values or if not allocating, assert
+		// that they match expectations. asserts will be removed to
+		// avoid overhead in NDEBUG builds.
+		if (alloc) {
+			RC_CHK_ACCESS(adjusted[pmu_snc])->map[idx].cpu = cpu.cpu + cpu_adjust;
+		} else if (idx == 0) {
+			cpu_adjust = perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu - cpu.cpu;
+			assert(uncore_cha_imc_compute_cpu_adjust(pmu_snc) == cpu_adjust);
+		} else {
+			assert(perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu ==
+			       cpu.cpu + cpu_adjust);
+		}
+	}
+
+	perf_cpu_map__put(pmu->cpus);
+	pmu->cpus = perf_cpu_map__get(adjusted[pmu_snc]);
+}
+
+void perf_pmu__arch_init(struct perf_pmu *pmu)
+{
+	struct perf_pmu_caps *ldlat_cap;
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) {
 		pmu->auxtrace = true;
@@ -33,12 +286,31 @@ void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
 #endif
 
 	if (x86__is_amd_cpu()) {
-		if (!strcmp(pmu->name, "ibs_op"))
-			pmu->mem_events = perf_mem_events_amd;
-	} else if (pmu->is_core) {
-		if (perf_pmu__have_event(pmu, "mem-loads-aux"))
-			pmu->mem_events = perf_mem_events_intel_aux;
-		else
-			pmu->mem_events = perf_mem_events_intel;
+		if (strcmp(pmu->name, "ibs_op"))
+			return;
+
+		pmu->mem_events = perf_mem_events_amd;
+
+		if (!perf_pmu__caps_parse(pmu))
+			return;
+
+		ldlat_cap = perf_pmu__get_cap(pmu, "ldlat");
+		if (!ldlat_cap || strcmp(ldlat_cap->value, "1"))
+			return;
+
+		perf_mem_events__loads_ldlat = 0;
+		pmu->mem_events = perf_mem_events_amd_ldlat;
+	} else {
+		if (pmu->is_core) {
+			if (perf_pmu__have_event(pmu, "mem-loads-aux"))
+				pmu->mem_events = perf_mem_events_intel_aux;
+			else
+				pmu->mem_events = perf_mem_events_intel;
+		} else if (x86__is_intel_graniterapids()) {
+			if (starts_with(pmu->name, "uncore_cha_"))
+				gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/true);
+			else if (starts_with(pmu->name, "uncore_imc_"))
+				gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/false);
+		}
 	}
 }
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 279ab2ab4abe..b558ab98719f 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -3,6 +3,7 @@ perf-bench-y += sched-pipe.o
 perf-bench-y += sched-seccomp-notify.o
 perf-bench-y += syscall.o
 perf-bench-y += mem-functions.o
+perf-bench-y += futex.o
 perf-bench-y += futex-hash.o
 perf-bench-y += futex-wake.o
 perf-bench-y += futex-wake-parallel.o
diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c
index 5a27691469ed..79cedcf94a39 100644
--- a/tools/perf/bench/evlist-open-close.c
+++ b/tools/perf/bench/evlist-open-close.c
@@ -46,25 +46,6 @@ static struct record_opts opts = {
 	.ctl_fd_ack          = -1,
 };
 
-static const struct option options[] = {
-	OPT_STRING('e', "event", &event_string, "event", "event selector. use 'perf list' to list available events"),
-	OPT_INTEGER('n', "nr-events", &nr_events,
-		     "number of dummy events to create (default 1). If used with -e, it clones those events n times (1 = no change)"),
-	OPT_INTEGER('i', "iterations", &iterations, "Number of iterations used to compute average (default=100)"),
-	OPT_BOOLEAN('a', "all-cpus", &opts.target.system_wide, "system-wide collection from all CPUs"),
-	OPT_STRING('C', "cpu", &opts.target.cpu_list, "cpu", "list of cpus where to open events"),
-	OPT_STRING('p', "pid", &opts.target.pid, "pid", "record events on existing process id"),
-	OPT_STRING('t', "tid", &opts.target.tid, "tid", "record events on existing thread id"),
-	OPT_STRING('u', "uid", &opts.target.uid_str, "user", "user to profile"),
-	OPT_BOOLEAN(0, "per-thread", &opts.target.per_thread, "use per-thread mmaps"),
-	OPT_END()
-};
-
-static const char *const bench_usage[] = {
-	"perf bench internals evlist-open-close <options>",
-	NULL
-};
-
 static int evlist__count_evsel_fds(struct evlist *evlist)
 {
 	struct evsel *evsel;
@@ -225,6 +206,29 @@ out_error:
 
 int bench_evlist_open_close(int argc, const char **argv)
 {
+	const struct option options[] = {
+		OPT_STRING('e', "event", &event_string, "event",
+			   "event selector. use 'perf list' to list available events"),
+		OPT_INTEGER('n', "nr-events", &nr_events,
+			    "number of dummy events to create (default 1). If used with -e, it clones those events n times (1 = no change)"),
+		OPT_INTEGER('i', "iterations", &iterations,
+			    "Number of iterations used to compute average (default=100)"),
+		OPT_BOOLEAN('a', "all-cpus", &opts.target.system_wide,
+			    "system-wide collection from all CPUs"),
+		OPT_STRING('C', "cpu", &opts.target.cpu_list, "cpu",
+			   "list of cpus where to open events"),
+		OPT_STRING('p', "pid", &opts.target.pid, "pid",
+			   "record events on existing process id"),
+		OPT_STRING('t', "tid", &opts.target.tid, "tid",
+			   "record events on existing thread id"),
+		OPT_STRING('u', "uid", &opts.target.uid_str, "user", "user to profile"),
+		OPT_BOOLEAN(0, "per-thread", &opts.target.per_thread, "use per-thread mmaps"),
+		OPT_END()
+	};
+	const char *const bench_usage[] = {
+		"perf bench internals evlist-open-close <options>",
+		NULL
+	};
 	char *evstr, errbuf[BUFSIZ];
 	int err;
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index b472eded521b..fdf133c9520f 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -18,9 +18,11 @@
 #include <stdlib.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/prctl.h>
 #include <linux/zalloc.h>
 #include <sys/time.h>
 #include <sys/mman.h>
+#include <sys/prctl.h>
 #include <perf/cpumap.h>
 
 #include "../util/mutex.h"
@@ -50,9 +52,12 @@ struct worker {
 static struct bench_futex_parameters params = {
 	.nfutexes = 1024,
 	.runtime  = 10,
+	.nbuckets = -1,
 };
 
 static const struct option options[] = {
+	OPT_INTEGER( 'b', "buckets", &params.nbuckets, "Specify amount of hash buckets"),
+	OPT_BOOLEAN( 'I', "immutable", &params.buckets_immutable, "Make the hash buckets immutable"),
 	OPT_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('r', "runtime", &params.runtime, "Specify runtime (in seconds)"),
 	OPT_UINTEGER('f', "futexes", &params.nfutexes, "Specify amount of futexes per threads"),
@@ -118,6 +123,7 @@ static void print_summary(void)
 	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
 	       !params.silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
 	       (int)bench__runtime.tv_sec);
+	futex_print_nbuckets(&params);
 }
 
 int bench_futex_hash(int argc, const char **argv)
@@ -161,6 +167,7 @@ int bench_futex_hash(int argc, const char **argv)
 
 	if (!params.fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
+	futex_set_nbuckets_param(&params);
 
 	printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n",
 	       getpid(), params.nthreads, params.nfutexes, params.fshared ? "shared":"private", params.runtime);
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 0416120c091b..5144a158512c 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -41,10 +41,13 @@ static struct stats throughput_stats;
 static struct cond thread_parent, thread_worker;
 
 static struct bench_futex_parameters params = {
+	.nbuckets = -1,
 	.runtime  = 10,
 };
 
 static const struct option options[] = {
+	OPT_INTEGER( 'b', "buckets", &params.nbuckets, "Specify amount of hash buckets"),
+	OPT_BOOLEAN( 'I', "immutable", &params.buckets_immutable, "Make the hash buckets immutable"),
 	OPT_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('r', "runtime", &params.runtime, "Specify runtime (in seconds)"),
 	OPT_BOOLEAN( 'M', "multi",   &params.multi, "Use multiple futexes"),
@@ -67,6 +70,7 @@ static void print_summary(void)
 	printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
 	       !params.silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
 	       (int)bench__runtime.tv_sec);
+	futex_print_nbuckets(&params);
 }
 
 static void toggle_done(int sig __maybe_unused,
@@ -203,6 +207,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	mutex_init(&thread_lock);
 	cond_init(&thread_parent);
 	cond_init(&thread_worker);
+	futex_set_nbuckets_param(&params);
 
 	threads_starting = params.nthreads;
 	gettimeofday(&bench__start, NULL);
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index aad5bfc4fe18..a2f91ee1950b 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -42,6 +42,7 @@ static unsigned int threads_starting;
 static int futex_flag = 0;
 
 static struct bench_futex_parameters params = {
+	.nbuckets = -1,
 	/*
 	 * How many tasks to requeue at a time.
 	 * Default to 1 in order to make the kernel work more.
@@ -50,6 +51,8 @@ static struct bench_futex_parameters params = {
 };
 
 static const struct option options[] = {
+	OPT_INTEGER( 'b', "buckets", &params.nbuckets, "Specify amount of hash buckets"),
+	OPT_BOOLEAN( 'I', "immutable", &params.buckets_immutable, "Make the hash buckets immutable"),
 	OPT_UINTEGER('t', "threads",  &params.nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('q', "nrequeue", &params.nrequeue, "Specify amount of threads to requeue at once"),
 	OPT_BOOLEAN( 's', "silent",   &params.silent, "Silent mode: do not display data/details"),
@@ -77,6 +80,7 @@ static void print_summary(void)
 	       params.nthreads,
 	       requeuetime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
+	futex_print_nbuckets(&params);
 }
 
 static void *workerfn(void *arg __maybe_unused)
@@ -204,6 +208,8 @@ int bench_futex_requeue(int argc, const char **argv)
 	if (params.broadcast)
 		params.nrequeue = params.nthreads;
 
+	futex_set_nbuckets_param(&params);
+
 	printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %s%p), "
 	       "%d at a time.\n\n",  getpid(), params.nthreads,
 	       params.fshared ? "shared":"private", &futex1,
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 4352e318631e..ee66482c29fd 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -57,9 +57,13 @@ static struct stats waketime_stats, wakeup_stats;
 static unsigned int threads_starting;
 static int futex_flag = 0;
 
-static struct bench_futex_parameters params;
+static struct bench_futex_parameters params = {
+	.nbuckets = -1,
+};
 
 static const struct option options[] = {
+	OPT_INTEGER( 'b', "buckets", &params.nbuckets, "Specify amount of hash buckets"),
+	OPT_BOOLEAN( 'I', "immutable", &params.buckets_immutable, "Make the hash buckets immutable"),
 	OPT_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('w', "nwakers", &params.nwakes, "Specify amount of waking threads"),
 	OPT_BOOLEAN( 's', "silent",  &params.silent, "Silent mode: do not display data/details"),
@@ -218,6 +222,7 @@ static void print_summary(void)
 	       params.nthreads,
 	       waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
+	futex_print_nbuckets(&params);
 }
 
 
@@ -291,6 +296,8 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	if (!params.fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
+	futex_set_nbuckets_param(&params);
+
 	printf("Run summary [PID %d]: blocking on %d threads (at [%s] "
 	       "futex %p), %d threads waking up %d at a time.\n\n",
 	       getpid(), params.nthreads, params.fshared ? "shared":"private",
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 49b3c89b0b35..8d6107f7cd94 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -42,6 +42,7 @@ static unsigned int threads_starting;
 static int futex_flag = 0;
 
 static struct bench_futex_parameters params = {
+	.nbuckets = -1,
 	/*
 	 * How many wakeups to do at a time.
 	 * Default to 1 in order to make the kernel work more.
@@ -50,6 +51,8 @@ static struct bench_futex_parameters params = {
 };
 
 static const struct option options[] = {
+	OPT_INTEGER( 'b', "buckets", &params.nbuckets, "Specify amount of hash buckets"),
+	OPT_BOOLEAN( 'I', "immutable", &params.buckets_immutable, "Make the hash buckets immutable"),
 	OPT_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('w', "nwakes",  &params.nwakes, "Specify amount of threads to wake at once"),
 	OPT_BOOLEAN( 's', "silent",  &params.silent, "Silent mode: do not display data/details"),
@@ -93,6 +96,7 @@ static void print_summary(void)
 	       params.nthreads,
 	       waketime_avg / USEC_PER_MSEC,
 	       rel_stddev_stats(waketime_stddev, waketime_avg));
+	futex_print_nbuckets(&params);
 }
 
 static void block_threads(pthread_t *w, struct perf_cpu_map *cpu)
diff --git a/tools/perf/bench/futex.c b/tools/perf/bench/futex.c
new file mode 100644
index 000000000000..26382e4d8d4c
--- /dev/null
+++ b/tools/perf/bench/futex.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <err.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/prctl.h>
+#include <sys/prctl.h>
+
+#include "futex.h"
+
+void futex_set_nbuckets_param(struct bench_futex_parameters *params)
+{
+	unsigned long flags;
+	int ret;
+
+	if (params->nbuckets < 0)
+		return;
+
+	flags = params->buckets_immutable ? FH_FLAG_IMMUTABLE : 0;
+	ret = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_SET_SLOTS, params->nbuckets, flags);
+	if (ret) {
+		printf("Requesting %d hash buckets failed: %d/%m\n",
+		       params->nbuckets, ret);
+		err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)");
+	}
+}
+
+void futex_print_nbuckets(struct bench_futex_parameters *params)
+{
+	char *futex_hash_mode;
+	int ret;
+
+	ret = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_SLOTS);
+	if (params->nbuckets >= 0) {
+		if (ret != params->nbuckets) {
+			if (ret < 0) {
+				printf("Can't query number of buckets: %m\n");
+				err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)");
+			}
+			printf("Requested number of hash buckets does not currently used.\n");
+			printf("Requested: %d in usage: %d\n", params->nbuckets, ret);
+			err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)");
+		}
+		if (params->nbuckets == 0) {
+			ret = asprintf(&futex_hash_mode, "Futex hashing: global hash");
+		} else {
+			ret = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_IMMUTABLE);
+			if (ret < 0) {
+				printf("Can't check if the hash is immutable: %m\n");
+				err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)");
+			}
+			ret = asprintf(&futex_hash_mode, "Futex hashing: %d hash buckets %s",
+				       params->nbuckets,
+				       ret == 1 ? "(immutable)" : "");
+		}
+	} else {
+		if (ret <= 0) {
+			ret = asprintf(&futex_hash_mode, "Futex hashing: global hash");
+		} else {
+			ret = asprintf(&futex_hash_mode, "Futex hashing: auto resized to %d buckets",
+				       ret);
+		}
+	}
+	if (ret < 0)
+		err(EXIT_FAILURE, "ENOMEM, futex_hash_mode");
+	printf("%s\n", futex_hash_mode);
+	free(futex_hash_mode);
+}
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index ebdc2b032afc..9c9a73f9d865 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -25,6 +25,8 @@ struct bench_futex_parameters {
 	unsigned int nfutexes;
 	unsigned int nwakes;
 	unsigned int nrequeue;
+	int nbuckets;
+	bool buckets_immutable;
 };
 
 /**
@@ -143,4 +145,7 @@ futex_cmp_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2,
 					val, opflags);
 }
 
+void futex_set_nbuckets_param(struct bench_futex_parameters *params);
+void futex_print_nbuckets(struct bench_futex_parameters *params);
+
 #endif /* _FUTEX_H */
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 5d5bb0f32334..e2e257bcc461 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -1969,10 +1969,11 @@ static struct c2c_fmt *get_format(const char *name)
 static int c2c_hists__init_output(struct perf_hpp_list *hpp_list, char *name)
 {
 	struct c2c_fmt *c2c_fmt = get_format(name);
+	int level = 0;
 
 	if (!c2c_fmt) {
 		reset_dimensions();
-		return output_field_add(hpp_list, name);
+		return output_field_add(hpp_list, name, &level);
 	}
 
 	perf_hpp_list__column_register(hpp_list, &c2c_fmt->fmt);
diff --git a/tools/perf/builtin-check.c b/tools/perf/builtin-check.c
index 61a11a9b4e75..9a509cb3bb9a 100644
--- a/tools/perf/builtin-check.c
+++ b/tools/perf/builtin-check.c
@@ -22,6 +22,17 @@ static const char *check_feature_usage[] = {
 	NULL
 };
 
+#define FEATURE_STATUS(name_, macro_) {    \
+	.name = name_,                     \
+	.macro = #macro_,                  \
+	.is_builtin = IS_BUILTIN(macro_) }
+
+#define FEATURE_STATUS_TIP(name_, macro_, tip_) { \
+	.name = name_,				  \
+	.macro = #macro_,			  \
+	.tip = tip_,				  \
+	.is_builtin = IS_BUILTIN(macro_) }
+
 struct feature_status supported_features[] = {
 	FEATURE_STATUS("aio", HAVE_AIO_SUPPORT),
 	FEATURE_STATUS("bpf", HAVE_LIBBPF_SUPPORT),
@@ -31,7 +42,7 @@ struct feature_status supported_features[] = {
 	FEATURE_STATUS("dwarf_getlocations", HAVE_LIBDW_SUPPORT),
 	FEATURE_STATUS("dwarf-unwind", HAVE_DWARF_UNWIND_SUPPORT),
 	FEATURE_STATUS("auxtrace", HAVE_AUXTRACE_SUPPORT),
-	FEATURE_STATUS("libbfd", HAVE_LIBBFD_SUPPORT),
+	FEATURE_STATUS_TIP("libbfd", HAVE_LIBBFD_SUPPORT, "Deprecated, license incompatibility, use BUILD_NONDISTRO=1 and install binutils-dev[el]"),
 	FEATURE_STATUS("libcapstone", HAVE_LIBCAPSTONE_SUPPORT),
 	FEATURE_STATUS("libcrypto", HAVE_LIBCRYPTO_SUPPORT),
 	FEATURE_STATUS("libdw-dwarf-unwind", HAVE_LIBDW_SUPPORT),
@@ -43,7 +54,7 @@ struct feature_status supported_features[] = {
 	FEATURE_STATUS("libpython", HAVE_LIBPYTHON_SUPPORT),
 	FEATURE_STATUS("libslang", HAVE_SLANG_SUPPORT),
 	FEATURE_STATUS("libtraceevent", HAVE_LIBTRACEEVENT),
-	FEATURE_STATUS("libunwind", HAVE_LIBUNWIND_SUPPORT),
+	FEATURE_STATUS_TIP("libunwind", HAVE_LIBUNWIND_SUPPORT, "Deprecated, use LIBUNWIND=1 and install libunwind-dev[el] to build with it"),
 	FEATURE_STATUS("lzma", HAVE_LZMA_SUPPORT),
 	FEATURE_STATUS("numa_num_possible_cpus", HAVE_LIBNUMA_SUPPORT),
 	FEATURE_STATUS("zlib", HAVE_ZLIB_SUPPORT),
@@ -66,21 +77,20 @@ static void on_off_print(const char *status)
 }
 
 /* Helper function to print status of a feature along with name/macro */
-static void status_print(const char *name, const char *macro,
-			 const char *status)
+void feature_status__printf(const struct feature_status *feature)
 {
+	const char *name = feature->name, *macro = feature->macro,
+		   *status = feature->is_builtin ? "on" : "OFF";
+
 	printf("%22s: ", name);
 	on_off_print(status);
-	printf("  # %s\n", macro);
-}
+	printf("  # %s", macro);
+
+	if (!feature->is_builtin && feature->tip)
+		printf(" ( tip: %s )", feature->tip);
 
-#define STATUS(feature)                                           \
-do {                                                              \
-	if (feature.is_builtin)                                   \
-		status_print(feature.name, feature.macro, "on");  \
-	else                                                      \
-		status_print(feature.name, feature.macro, "OFF"); \
-} while (0)
+	putchar('\n');
+}
 
 /**
  * check whether "feature" is built-in with perf
@@ -95,7 +105,7 @@ static int has_support(const char *feature)
 		if ((strcasecmp(feature, supported_features[i].name) == 0) ||
 		    (strcasecmp(feature, supported_features[i].macro) == 0)) {
 			if (!quiet)
-				STATUS(supported_features[i]);
+				feature_status__printf(&supported_features[i]);
 			return supported_features[i].is_builtin;
 		}
 	}
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 7caa18d5ffc3..bba36ebc2aa7 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -19,6 +19,7 @@
 #include <ctype.h>
 #include <linux/capability.h>
 #include <linux/string.h>
+#include <sys/stat.h>
 
 #include "debug.h"
 #include <subcmd/pager.h>
@@ -45,6 +46,8 @@ static volatile sig_atomic_t done;
 
 static struct stats latency_stats;  /* for tracepoints */
 
+static char tracing_instance[PATH_MAX];	/* Trace instance directory */
+
 static void sig_handler(int sig __maybe_unused)
 {
 	done = true;
@@ -100,6 +103,34 @@ static bool is_ftrace_supported(void)
 	return supported;
 }
 
+/*
+ * Wrapper to test if a file in directory .../tracing/instances/XXX
+ * exists. If so return the .../tracing/instances/XXX file for use.
+ * Otherwise the file exists only in directory .../tracing and
+ * is applicable to all instances, for example file available_filter_functions.
+ * Return that file name in this case.
+ *
+ * This functions works similar to get_tracing_file() and expects its caller
+ * to free the returned file name.
+ *
+ * The global variable tracing_instance is set in init_tracing_instance()
+ * called at the  beginning to a process specific tracing subdirectory.
+ */
+static char *get_tracing_instance_file(const char *name)
+{
+	char *file;
+
+	if (asprintf(&file, "%s/%s", tracing_instance, name) < 0)
+		return NULL;
+
+	if (!access(file, F_OK))
+		return file;
+
+	free(file);
+	file = get_tracing_file(name);
+	return file;
+}
+
 static int __write_tracing_file(const char *name, const char *val, bool append)
 {
 	char *file;
@@ -109,7 +140,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append)
 	char errbuf[512];
 	char *val_copy;
 
-	file = get_tracing_file(name);
+	file = get_tracing_instance_file(name);
 	if (!file) {
 		pr_debug("cannot get tracing file: %s\n", name);
 		return -1;
@@ -167,7 +198,7 @@ static int read_tracing_file_to_stdout(const char *name)
 	int fd;
 	int ret = -1;
 
-	file = get_tracing_file(name);
+	file = get_tracing_instance_file(name);
 	if (!file) {
 		pr_debug("cannot get tracing file: %s\n", name);
 		return -1;
@@ -209,7 +240,7 @@ static int read_tracing_file_by_line(const char *name,
 	char *file;
 	FILE *fp;
 
-	file = get_tracing_file(name);
+	file = get_tracing_instance_file(name);
 	if (!file) {
 		pr_debug("cannot get tracing file: %s\n", name);
 		return -1;
@@ -299,6 +330,39 @@ static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
 	return 0;
 }
 
+/* Remove .../tracing/instances/XXX subdirectory created with
+ * init_tracing_instance().
+ */
+static void exit_tracing_instance(void)
+{
+	if (rmdir(tracing_instance))
+		pr_err("failed to delete tracing/instances directory\n");
+}
+
+/* Create subdirectory within .../tracing/instances/XXX to have session
+ * or process specific setup. To delete this setup, simply remove the
+ * subdirectory.
+ */
+static int init_tracing_instance(void)
+{
+	char dirname[] = "instances/perf-ftrace-XXXXXX";
+	char *path;
+
+	path = get_tracing_file(dirname);
+	if (!path)
+		goto error;
+	strncpy(tracing_instance, path, sizeof(tracing_instance) - 1);
+	put_tracing_file(path);
+	path = mkdtemp(tracing_instance);
+	if (!path)
+		goto error;
+	return 0;
+
+error:
+	pr_err("failed to create tracing/instances directory\n");
+	return -1;
+}
+
 static int set_tracing_pid(struct perf_ftrace *ftrace)
 {
 	int i;
@@ -629,14 +693,17 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace)
 
 	select_tracer(ftrace);
 
+	if (init_tracing_instance() < 0)
+		goto out;
+
 	if (reset_tracing_files(ftrace) < 0) {
 		pr_err("failed to reset ftrace\n");
-		goto out;
+		goto out_reset;
 	}
 
 	/* reset ftrace buffer */
 	if (write_tracing_file("trace", "0") < 0)
-		goto out;
+		goto out_reset;
 
 	if (set_tracing_options(ftrace) < 0)
 		goto out_reset;
@@ -648,7 +715,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace)
 
 	setup_pager();
 
-	trace_file = get_tracing_file("trace_pipe");
+	trace_file = get_tracing_instance_file("trace_pipe");
 	if (!trace_file) {
 		pr_err("failed to open trace_pipe\n");
 		goto out_reset;
@@ -723,7 +790,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace)
 out_close_fd:
 	close(trace_fd);
 out_reset:
-	reset_tracing_files(ftrace);
+	exit_tracing_instance();
 out:
 	return (done && !workload_exec_errno) ? 0 : -1;
 }
@@ -924,6 +991,9 @@ static int prepare_func_latency(struct perf_ftrace *ftrace)
 	if (ftrace->target.use_bpf)
 		return perf_ftrace__latency_prepare_bpf(ftrace);
 
+	if (init_tracing_instance() < 0)
+		return -1;
+
 	if (reset_tracing_files(ftrace) < 0) {
 		pr_err("failed to reset ftrace\n");
 		return -1;
@@ -942,7 +1012,7 @@ static int prepare_func_latency(struct perf_ftrace *ftrace)
 		return -1;
 	}
 
-	trace_file = get_tracing_file("trace_pipe");
+	trace_file = get_tracing_instance_file("trace_pipe");
 	if (!trace_file) {
 		pr_err("failed to open trace_pipe\n");
 		return -1;
@@ -993,7 +1063,7 @@ static int cleanup_func_latency(struct perf_ftrace *ftrace)
 	if (ftrace->target.use_bpf)
 		return perf_ftrace__latency_cleanup_bpf(ftrace);
 
-	reset_tracing_files(ftrace);
+	exit_tracing_instance();
 	return 0;
 }
 
@@ -1304,17 +1374,20 @@ static int __cmd_profile(struct perf_ftrace *ftrace)
 		goto out;
 	}
 
+	if (init_tracing_instance() < 0)
+		goto out;
+
 	if (reset_tracing_files(ftrace) < 0) {
 		pr_err("failed to reset ftrace\n");
-		goto out;
+		goto out_reset;
 	}
 
 	/* reset ftrace buffer */
 	if (write_tracing_file("trace", "0") < 0)
-		goto out;
+		goto out_reset;
 
 	if (set_tracing_options(ftrace) < 0)
-		return -1;
+		goto out_reset;
 
 	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
 		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
@@ -1323,7 +1396,7 @@ static int __cmd_profile(struct perf_ftrace *ftrace)
 
 	setup_pager();
 
-	trace_file = get_tracing_file("trace_pipe");
+	trace_file = get_tracing_instance_file("trace_pipe");
 	if (!trace_file) {
 		pr_err("failed to open trace_pipe\n");
 		goto out_reset;
@@ -1385,7 +1458,7 @@ out_free_line:
 out_close_fd:
 	close(trace_fd);
 out_reset:
-	reset_tracing_files(ftrace);
+	exit_tracing_instance();
 out:
 	return (done && !workload_exec_errno) ? 0 : -1;
 }
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index fed482adb039..e9b595d75df2 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -197,7 +197,8 @@ static void default_print_metric(void *ps,
 				const char *long_desc,
 				const char *expr,
 				const char *threshold,
-				const char *unit __maybe_unused)
+				const char *unit __maybe_unused,
+				const char *pmu_name __maybe_unused)
 {
 	struct print_state *print_state = ps;
 	FILE *fp = print_state->fp;
@@ -433,7 +434,8 @@ static void json_print_event(void *ps, const char *topic, const char *pmu_name,
 static void json_print_metric(void *ps __maybe_unused, const char *group,
 			      const char *name, const char *desc,
 			      const char *long_desc, const char *expr,
-			      const char *threshold, const char *unit)
+			      const char *threshold, const char *unit,
+			      const char *pmu_name)
 {
 	struct json_print_state *print_state = ps;
 	bool need_sep = false;
@@ -483,6 +485,12 @@ static void json_print_metric(void *ps __maybe_unused, const char *group,
 				   long_desc);
 		need_sep = true;
 	}
+	if (pmu_name) {
+		fix_escape_fprintf(fp, &buf, "%s\t\"Unit\": \"%S\"",
+				   need_sep ? ",\n" : "",
+				   pmu_name);
+		need_sep = true;
+	}
 	fprintf(fp, "%s}", need_sep ? "\n" : "");
 	strbuf_release(&buf);
 }
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 05e7bc30488a..3b3ade7a39ca 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -62,6 +62,8 @@ static const char *output_name = NULL;
 static FILE *lock_output;
 
 static struct lock_filter filters;
+static struct lock_delay *delays;
+static int nr_delays;
 
 static enum lock_aggr_mode aggr_mode = LOCK_AGGR_ADDR;
 
@@ -2001,6 +2003,8 @@ static int __cmd_contention(int argc, const char **argv)
 		.max_stack = max_stack_depth,
 		.stack_skip = stack_skip,
 		.filters = &filters,
+		.delays = delays,
+		.nr_delays = nr_delays,
 		.save_callstack = needs_callstack(),
 		.owner = show_lock_owner,
 		.cgroups = RB_ROOT,
@@ -2504,6 +2508,79 @@ static int parse_cgroup_filter(const struct option *opt __maybe_unused, const ch
 	return ret;
 }
 
+static bool add_lock_delay(char *spec)
+{
+	char *at, *pos;
+	struct lock_delay *tmp;
+	unsigned long duration;
+
+	at = strchr(spec, '@');
+	if (at == NULL) {
+		pr_err("lock delay should have '@' sign: %s\n", spec);
+		return false;
+	}
+	if (at == spec) {
+		pr_err("lock delay should have time before '@': %s\n", spec);
+		return false;
+	}
+
+	*at = '\0';
+	duration = strtoul(spec, &pos, 0);
+	if (!strcmp(pos, "ns"))
+		duration *= 1;
+	else if (!strcmp(pos, "us"))
+		duration *= 1000;
+	else if (!strcmp(pos, "ms"))
+		duration *= 1000 * 1000;
+	else if (*pos) {
+		pr_err("invalid delay time: %s@%s\n", spec, at + 1);
+		return false;
+	}
+
+	if (duration > 10 * 1000 * 1000) {
+		pr_err("lock delay is too long: %s (> 10ms)\n", spec);
+		return false;
+	}
+
+	tmp = realloc(delays, (nr_delays + 1) * sizeof(*delays));
+	if (tmp == NULL) {
+		pr_err("Memory allocation failure\n");
+		return false;
+	}
+	delays = tmp;
+
+	delays[nr_delays].sym = strdup(at + 1);
+	if (delays[nr_delays].sym == NULL) {
+		pr_err("Memory allocation failure\n");
+		return false;
+	}
+	delays[nr_delays].time = duration;
+
+	nr_delays++;
+	return true;
+}
+
+static int parse_lock_delay(const struct option *opt __maybe_unused, const char *str,
+			    int unset __maybe_unused)
+{
+	char *s, *tmp, *tok;
+	int ret = 0;
+
+	s = strdup(str);
+	if (s == NULL)
+		return -1;
+
+	for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) {
+		if (!add_lock_delay(tok)) {
+			ret = -1;
+			break;
+		}
+	}
+
+	free(s);
+	return ret;
+}
+
 int cmd_lock(int argc, const char **argv)
 {
 	const struct option lock_options[] = {
@@ -2580,6 +2657,8 @@ int cmd_lock(int argc, const char **argv)
 	OPT_BOOLEAN(0, "lock-cgroup", &show_lock_cgroups, "show lock stats by cgroup"),
 	OPT_CALLBACK('G', "cgroup-filter", NULL, "CGROUPS",
 		     "Filter specific cgroups", parse_cgroup_filter),
+	OPT_CALLBACK('J', "inject-delay", NULL, "TIME@FUNC",
+		     "Inject delays to specific locks", parse_lock_delay),
 	OPT_PARENT(lock_options)
 	};
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ba20bf7c011d..8059bce85a51 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -26,6 +26,7 @@
 #include "util/target.h"
 #include "util/session.h"
 #include "util/tool.h"
+#include "util/stat.h"
 #include "util/symbol.h"
 #include "util/record.h"
 #include "util/cpumap.h"
@@ -51,6 +52,7 @@
 #include "util/clockid.h"
 #include "util/off_cpu.h"
 #include "util/bpf-filter.h"
+#include "util/strbuf.h"
 #include "asm/bug.h"
 #include "perf.h"
 #include "cputopo.h"
@@ -648,14 +650,27 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 	struct record *rec = to;
 
 	if (record__comp_enabled(rec)) {
+		struct perf_record_compressed2 *event = map->data;
+		size_t padding = 0;
+		u8 pad[8] = {0};
 		ssize_t compressed = zstd_compress(rec->session, map, map->data,
 						   mmap__mmap_len(map), bf, size);
 
 		if (compressed < 0)
 			return (int)compressed;
 
-		size = compressed;
-		bf   = map->data;
+		bf = event;
+		thread->samples++;
+
+		/*
+		 * The record from `zstd_compress` is not 8 bytes aligned, which would cause asan
+		 * error. We make it aligned here.
+		 */
+		event->data_size = compressed - sizeof(struct perf_record_compressed2);
+		event->header.size = PERF_ALIGN(compressed, sizeof(u64));
+		padding = event->header.size - compressed;
+		return record__write(rec, map, bf, compressed) ||
+		       record__write(rec, map, &pad, padding);
 	}
 
 	thread->samples++;
@@ -1534,7 +1549,7 @@ static void record__adjust_affinity(struct record *rec, struct mmap *map)
 
 static size_t process_comp_header(void *record, size_t increment)
 {
-	struct perf_record_compressed *event = record;
+	struct perf_record_compressed2 *event = record;
 	size_t size = sizeof(*event);
 
 	if (increment) {
@@ -1542,7 +1557,7 @@ static size_t process_comp_header(void *record, size_t increment)
 		return increment;
 	}
 
-	event->header.type = PERF_RECORD_COMPRESSED;
+	event->header.type = PERF_RECORD_COMPRESSED2;
 	event->header.size = size;
 
 	return size;
@@ -1552,7 +1567,7 @@ static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size)
 {
 	ssize_t compressed;
-	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1;
+	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed2) - 1;
 	struct zstd_data *zstd_data = &session->zstd_data;
 
 	if (map && map->file)
@@ -2483,7 +2498,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		pr_warning("WARNING: --timestamp-filename option is not available in pipe mode.\n");
 	}
 
-	evlist__uniquify_name(rec->evlist);
+	/*
+	 * Use global stat_config that is zero meaning aggr_mode is AGGR_NONE
+	 * and hybrid_merge is false.
+	 */
+	evlist__uniquify_evsel_names(rec->evlist, &stat_config);
 
 	evlist__config(rec->evlist, opts, &callchain_param);
 
@@ -2569,6 +2588,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		evlist__enable(rec->evlist);
 
 	/*
+	 * offcpu-time does not call execve, so enable_on_exe wouldn't work
+	 * when recording a workload, do it manually
+	 */
+	if (rec->off_cpu)
+		evlist__enable_evsel(rec->evlist, (char *)OFFCPU_EVENT);
+
+	/*
 	 * Let the child rip
 	 */
 	if (forks) {
@@ -2784,13 +2810,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		record__auxtrace_snapshot_exit(rec);
 
 	if (forks && workload_exec_errno) {
-		char msg[STRERR_BUFSIZE], strevsels[2048];
+		char msg[STRERR_BUFSIZE];
 		const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));
+		struct strbuf sb = STRBUF_INIT;
 
-		evlist__scnprintf_evsels(rec->evlist, sizeof(strevsels), strevsels);
+		evlist__format_evsels(rec->evlist, &sb, 2048);
 
 		pr_err("Failed to collect '%s' for the '%s' workload: %s\n",
-			strevsels, argv[0], emsg);
+			sb.buf, argv[0], emsg);
+		strbuf_release(&sb);
 		err = -1;
 		goto out_child;
 	}
@@ -3155,6 +3183,28 @@ out_free:
 	return ret;
 }
 
+static int record__parse_off_cpu_thresh(const struct option *opt,
+					const char *str,
+					int unset __maybe_unused)
+{
+	struct record_opts *opts = opt->value;
+	char *endptr;
+	u64 off_cpu_thresh_ms;
+
+	if (!str)
+		return -EINVAL;
+
+	off_cpu_thresh_ms = strtoull(str, &endptr, 10);
+
+	/* the threshold isn't string "0", yet strtoull() returns 0, parsing failed */
+	if (*endptr || (off_cpu_thresh_ms == 0 && strcmp(str, "0")))
+		return -EINVAL;
+	else
+		opts->off_cpu_thresh_ns = off_cpu_thresh_ms * NSEC_PER_MSEC;
+
+	return 0;
+}
+
 void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused)
 {
 }
@@ -3348,6 +3398,7 @@ static struct record record = {
 		.ctl_fd              = -1,
 		.ctl_fd_ack          = -1,
 		.synth               = PERF_SYNTH_ALL,
+		.off_cpu_thresh_ns   = OFFCPU_THRESH,
 	},
 };
 
@@ -3436,6 +3487,8 @@ static struct option __record_options[] = {
 		    "Record the sampled data address data page size"),
 	OPT_BOOLEAN(0, "code-page-size", &record.opts.sample_code_page_size,
 		    "Record the sampled code address (ip) page size"),
+	OPT_BOOLEAN(0, "sample-mem-info", &record.opts.sample_data_src,
+		    "Record the data source for memory operations"),
 	OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
 	OPT_BOOLEAN(0, "sample-identifier", &record.opts.sample_identifier,
 		    "Record the sample identifier"),
@@ -3480,7 +3533,7 @@ static struct option __record_options[] = {
 		    "sample selected machine registers on interrupt,"
 		    " use '-I?' to list register names", parse_intr_regs),
 	OPT_CALLBACK_OPTARG(0, "user-regs", &record.opts.sample_user_regs, NULL, "any register",
-		    "sample selected machine registers on interrupt,"
+		    "sample selected machine registers in user space,"
 		    " use '--user-regs=?' to list register names", parse_user_regs),
 	OPT_BOOLEAN(0, "running-time", &record.opts.running_time,
 		    "Record running/enabled time of read (:S) events"),
@@ -3573,6 +3626,9 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN(0, "off-cpu", &record.off_cpu, "Enable off-cpu analysis"),
 	OPT_STRING(0, "setup-filter", &record.filter_action, "pin|unpin",
 		   "BPF filter action"),
+	OPT_CALLBACK(0, "off-cpu-thresh", &record.opts, "ms",
+		     "Dump off-cpu samples if off-cpu time exceeds this threshold (in milliseconds). (Default: 500ms)",
+		     record__parse_off_cpu_thresh),
 	OPT_END()
 };
 
@@ -4130,6 +4186,10 @@ int cmd_record(int argc, const char **argv)
 		goto out_opts;
 	}
 
+	/* For backward compatibility, -d implies --mem-info */
+	if (rec->opts.sample_address)
+		rec->opts.sample_data_src = true;
+
 	/*
 	 * Allow aliases to facilitate the lookup of symbols for address
 	 * filters. Refer to auxtrace_parse_filters().
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b030ce72e13e..e662e1c3a7c6 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -413,7 +413,7 @@ static int report__setup_sample_type(struct report *rep)
 		/* Silently ignore if callchain is missing */
 		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 			symbol_conf.cumulate_callchain = false;
-			perf_hpp__cancel_cumulate();
+			perf_hpp__cancel_cumulate(session->evlist);
 		}
 	}
 
@@ -529,7 +529,10 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 
 	if (rep->mem_mode) {
 		ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events);
-		ret += fprintf(fp, "\n# Sort order   : %s", sort_order ? : default_mem_sort_order);
+		if (sort_order || !field_order) {
+			ret += fprintf(fp, "\n# Sort order   : %s",
+				       sort_order ? : default_mem_sort_order);
+		}
 	} else
 		ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
 
@@ -1088,7 +1091,7 @@ static int __cmd_report(struct report *rep)
 	/* Don't show Latency column for non-parallel profiles by default. */
 	if (!symbol_conf.prefer_latency && rep->total_samples &&
 		rep->singlethreaded_samples * 100 / rep->total_samples >= 99)
-		perf_hpp__cancel_latency();
+		perf_hpp__cancel_latency(session->evlist);
 
 	evlist__check_mem_load_aux(session->evlist);
 
@@ -1672,14 +1675,10 @@ repeat:
 	}
 
 	if (symbol_conf.report_hierarchy) {
-		/* disable incompatible options */
-		if (field_order) {
-			pr_err("Error: --hierarchy and --fields options cannot be used together\n");
-			parse_options_usage(report_usage, options, "F", 1);
-			parse_options_usage(NULL, options, "hierarchy", 0);
-			goto error;
-		}
-
+		/*
+		 * The hist entries in hierarchy are added during the collpase
+		 * phase.  Let's enable it even if no sort keys require it.
+		 */
 		perf_hpp_list.need_collapse = true;
 	}
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9b16df881af8..6c3bf74dd78c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -680,7 +680,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 
 		evlist__for_each_entry(session->evlist, evsel) {
 			not_pipe = true;
-			if (evsel__has_callchain(evsel)) {
+			if (evsel__has_callchain(evsel) || evsel__is_offcpu_event(evsel)) {
 				use_callchain = true;
 				break;
 			}
@@ -2295,7 +2295,7 @@ static void process_event(struct perf_script *script,
 	else if (PRINT_FIELD(BRSTACKOFF))
 		perf_sample__fprintf_brstackoff(sample, thread, evsel, fp);
 
-	if (evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
+	if (evsel__is_bpf_output(evsel) && !evsel__is_offcpu_event(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		perf_sample__fprintf_bpf_output(sample, fp);
 	perf_sample__fprintf_insn(sample, evsel, attr, thread, machine, fp, al);
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 68ea7589c143..bf0e5e12d992 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -681,8 +681,6 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
 	if (child_pid != -1)
 		kill(child_pid, SIGTERM);
 
-	tpebs_delete();
-
 	return COUNTER_FATAL;
 }
 
@@ -1856,7 +1854,7 @@ static int add_default_events(void)
 		 * will use this approach. To determine transaction support
 		 * on an architecture test for such a metric name.
 		 */
-		if (!metricgroup__has_metric(pmu, "transaction")) {
+		if (!metricgroup__has_metric_or_groups(pmu, "transaction")) {
 			pr_err("Missing transaction metrics\n");
 			ret = -1;
 			goto out;
@@ -1890,7 +1888,7 @@ static int add_default_events(void)
 			smi_reset = true;
 		}
 
-		if (!metricgroup__has_metric(pmu, "smi")) {
+		if (!metricgroup__has_metric_or_groups(pmu, "smi")) {
 			pr_err("Missing smi metrics\n");
 			ret = -1;
 			goto out;
@@ -1980,7 +1978,7 @@ static int add_default_events(void)
 		 * Add TopdownL1 metrics if they exist. To minimize
 		 * multiplexing, don't request threshold computation.
 		 */
-		if (metricgroup__has_metric(pmu, "Default")) {
+		if (metricgroup__has_metric_or_groups(pmu, "Default")) {
 			struct evlist *metric_evlist = evlist__new();
 
 			if (!metric_evlist) {
@@ -2329,6 +2327,32 @@ static void setup_system_wide(int forks)
 	}
 }
 
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+static int parse_tpebs_mode(const struct option *opt, const char *str,
+			    int unset __maybe_unused)
+{
+	enum tpebs_mode *mode = opt->value;
+
+	if (!strcasecmp("mean", str)) {
+		*mode = TPEBS_MODE__MEAN;
+		return 0;
+	}
+	if (!strcasecmp("min", str)) {
+		*mode = TPEBS_MODE__MIN;
+		return 0;
+	}
+	if (!strcasecmp("max", str)) {
+		*mode = TPEBS_MODE__MAX;
+		return 0;
+	}
+	if (!strcasecmp("last", str)) {
+		*mode = TPEBS_MODE__LAST;
+		return 0;
+	}
+	return -1;
+}
+#endif // HAVE_ARCH_X86_64_SUPPORT
+
 int cmd_stat(int argc, const char **argv)
 {
 	struct opt_aggr_mode opt_mode = {};
@@ -2433,6 +2457,9 @@ int cmd_stat(int argc, const char **argv)
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 		OPT_BOOLEAN(0, "record-tpebs", &tpebs_recording,
 			"enable recording for tpebs when retire_latency required"),
+		OPT_CALLBACK(0, "tpebs-mode", &tpebs_mode, "tpebs-mode",
+			"Mode of TPEBS recording: mean, min or max",
+			parse_tpebs_mode),
 #endif
 		OPT_UINTEGER(0, "td-level", &stat_config.topdown_level,
 			"Set the metrics level for the top-down statistics (0: max level)"),
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1061f4eebc3f..7b6cde87d2af 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -35,6 +35,7 @@
 #include "util/mmap.h"
 #include "util/session.h"
 #include "util/thread.h"
+#include "util/stat.h"
 #include "util/symbol.h"
 #include "util/synthetic-events.h"
 #include "util/top.h"
@@ -1309,7 +1310,11 @@ static int __cmd_top(struct perf_top *top)
 		}
 	}
 
-	evlist__uniquify_name(top->evlist);
+	/*
+	 * Use global stat_config that is zero meaning aggr_mode is AGGR_NONE
+	 * and hybrid_merge is false.
+	 */
+	evlist__uniquify_evsel_names(top->evlist, &stat_config);
 	ret = perf_top__start_counters(top);
 	if (ret)
 		return ret;
@@ -1790,7 +1795,7 @@ int cmd_top(int argc, const char **argv)
 
 	if (!callchain_param.enabled) {
 		symbol_conf.cumulate_callchain = false;
-		perf_hpp__cancel_cumulate();
+		perf_hpp__cancel_cumulate(top.evlist);
 	}
 
 	if (symbol_conf.cumulate_callchain && !callchain_param.order_set)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6ac51925ea42..2ab1b8e05ad3 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -55,6 +55,7 @@
 #include "util/thread_map.h"
 #include "util/stat.h"
 #include "util/tool.h"
+#include "util/trace.h"
 #include "util/util.h"
 #include "trace/beauty/beauty.h"
 #include "trace-event.h"
@@ -141,12 +142,6 @@ struct syscall_fmt {
 	bool	   hexret;
 };
 
-enum summary_mode {
-	SUMMARY__NONE = 0,
-	SUMMARY__BY_TOTAL,
-	SUMMARY__BY_THREAD,
-};
-
 struct trace {
 	struct perf_tool	tool;
 	struct {
@@ -205,7 +200,7 @@ struct trace {
 	} stats;
 	unsigned int		max_stack;
 	unsigned int		min_stack;
-	enum summary_mode	summary_mode;
+	enum trace_summary_mode	summary_mode;
 	int			raw_augmented_syscalls_args_size;
 	bool			raw_augmented_syscalls;
 	bool			fd_path_disabled;
@@ -234,6 +229,7 @@ struct trace {
 	bool			force;
 	bool			vfs_getname;
 	bool			force_btf;
+	bool			summary_bpf;
 	int			trace_pgfaults;
 	char			*perfconfig_events;
 	struct {
@@ -1352,7 +1348,7 @@ static const struct syscall_fmt syscall_fmts[] = {
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* olddirfd */ },
 		   [2] = { .scnprintf = SCA_FDAT, /* newdirfd */ },
 		   [4] = { .scnprintf = SCA_RENAMEAT2_FLAGS, /* flags */ }, }, },
-	{ .name	    = "rseq",	    .errpid = true,
+	{ .name	    = "rseq",
 	  .arg = { [0] = { .from_user = true /* rseq */, }, }, },
 	{ .name	    = "rt_sigaction",
 	  .arg = { [0] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
@@ -1376,7 +1372,7 @@ static const struct syscall_fmt syscall_fmts[] = {
 	{ .name	    = "sendto",
 	  .arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ },
 		   [4] = SCA_SOCKADDR_FROM_USER(addr), }, },
-	{ .name	    = "set_robust_list",	    .errpid = true,
+	{ .name	    = "set_robust_list",
 	  .arg = { [0] = { .from_user = true /* head */, }, }, },
 	{ .name	    = "set_tid_address", .errpid = true, },
 	{ .name	    = "setitimer",
@@ -1657,7 +1653,7 @@ static const size_t trace__entry_str_size = 2048;
 
 static void thread_trace__free_files(struct thread_trace *ttrace)
 {
-	for (int i = 0; i < ttrace->files.max; ++i) {
+	for (int i = 0; i <= ttrace->files.max; ++i) {
 		struct file *file = ttrace->files.table + i;
 		zfree(&file->pathname);
 	}
@@ -1703,6 +1699,7 @@ static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pat
 
 	if (file != NULL) {
 		struct stat st;
+
 		if (stat(pathname, &st) == 0)
 			file->dev_maj = major(st.st_rdev);
 		file->pathname = strdup(pathname);
@@ -2614,6 +2611,9 @@ static void thread__update_stats(struct thread *thread, struct thread_trace *ttr
 	struct syscall_stats *stats = NULL;
 	u64 duration = 0;
 
+	if (trace->summary_bpf)
+		return;
+
 	if (trace->summary_mode == SUMMARY__BY_TOTAL)
 		syscall_stats = trace->syscall_stats;
 
@@ -2842,7 +2842,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct evsel *evsel,
 	e_machine = thread__e_machine(thread, trace->host);
 	sc = trace__syscall_info(trace, evsel, e_machine, id);
 	if (sc == NULL)
-		return -1;
+		goto out_put;
 	ttrace = thread__trace(thread, trace);
 	/*
 	 * We need to get ttrace just to make sure it is there when syscall__scnprintf_args()
@@ -3005,8 +3005,8 @@ errno_print: {
 	else if (sc->fmt->errpid) {
 		struct thread *child = machine__find_thread(trace->host, ret, ret);
 
+		fprintf(trace->output, "%ld", ret);
 		if (child != NULL) {
-			fprintf(trace->output, "%ld", ret);
 			if (thread__comm_set(child))
 				fprintf(trace->output, " (%s)", thread__comm_str(child));
 			thread__put(child);
@@ -4128,10 +4128,13 @@ static int trace__set_filter_loop_pids(struct trace *trace)
 		if (!strcmp(thread__comm_str(parent), "sshd") ||
 		    strstarts(thread__comm_str(parent), "gnome-terminal")) {
 			pids[nr++] = thread__tid(parent);
+			thread__put(parent);
 			break;
 		}
+		thread__put(thread);
 		thread = parent;
 	}
+	thread__put(thread);
 
 	err = evlist__append_tp_filter_pids(trace->evlist, nr, pids);
 	if (!err && trace->filter_pids.map)
@@ -4377,6 +4380,14 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 	trace->live = true;
 
+	if (trace->summary_bpf) {
+		if (trace_prepare_bpf_summary(trace->summary_mode) < 0)
+			goto out_delete_evlist;
+
+		if (trace->summary_only)
+			goto create_maps;
+	}
+
 	if (!trace->raw_augmented_syscalls) {
 		if (trace->trace_syscalls && trace__add_syscall_newtp(trace))
 			goto out_error_raw_syscalls;
@@ -4435,6 +4446,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (trace->cgroup)
 		evlist__set_default_cgroup(trace->evlist, trace->cgroup);
 
+create_maps:
 	err = evlist__create_maps(evlist, &trace->opts.target);
 	if (err < 0) {
 		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
@@ -4447,7 +4459,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
-	if (trace->summary_mode == SUMMARY__BY_TOTAL) {
+	if (trace->summary_mode == SUMMARY__BY_TOTAL && !trace->summary_bpf) {
 		trace->syscall_stats = alloc_syscall_stats();
 		if (trace->syscall_stats == NULL)
 			goto out_delete_evlist;
@@ -4535,9 +4547,11 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_apply_filters;
 
-	err = evlist__mmap(evlist, trace->opts.mmap_pages);
-	if (err < 0)
-		goto out_error_mmap;
+	if (!trace->summary_only || !trace->summary_bpf) {
+		err = evlist__mmap(evlist, trace->opts.mmap_pages);
+		if (err < 0)
+			goto out_error_mmap;
+	}
 
 	if (!target__none(&trace->opts.target) && !trace->opts.target.initial_delay)
 		evlist__enable(evlist);
@@ -4550,6 +4564,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		evlist__enable(evlist);
 	}
 
+	if (trace->summary_bpf)
+		trace_start_bpf_summary();
+
 	trace->multiple_threads = perf_thread_map__pid(evlist->core.threads, 0) == -1 ||
 		perf_thread_map__nr(evlist->core.threads) > 1 ||
 		evlist__first(evlist)->core.attr.inherit;
@@ -4617,12 +4634,17 @@ out_disable:
 
 	evlist__disable(evlist);
 
+	if (trace->summary_bpf)
+		trace_end_bpf_summary();
+
 	if (trace->sort_events)
 		ordered_events__flush(&trace->oe.data, OE_FLUSH__FINAL);
 
 	if (!err) {
 		if (trace->summary) {
-			if (trace->summary_mode == SUMMARY__BY_TOTAL)
+			if (trace->summary_bpf)
+				trace_print_bpf_summary(trace->output);
+			else if (trace->summary_mode == SUMMARY__BY_TOTAL)
 				trace__fprintf_total_summary(trace, trace->output);
 			else
 				trace__fprintf_thread_summary(trace, trace->output);
@@ -4638,6 +4660,7 @@ out_disable:
 	}
 
 out_delete_evlist:
+	trace_cleanup_bpf_summary();
 	delete_syscall_stats(trace->syscall_stats);
 	trace__symbols__exit(trace);
 	evlist__free_syscall_tp_fields(evlist);
@@ -5279,6 +5302,8 @@ static int trace__parse_summary_mode(const struct option *opt, const char *str,
 		trace->summary_mode = SUMMARY__BY_THREAD;
 	} else if (!strcmp(str, "total")) {
 		trace->summary_mode = SUMMARY__BY_TOTAL;
+	} else if (!strcmp(str, "cgroup")) {
+		trace->summary_mode = SUMMARY__BY_CGROUP;
 	} else {
 		pr_err("Unknown summary mode: %s\n", str);
 		return -1;
@@ -5438,7 +5463,7 @@ int cmd_trace(int argc, const char **argv)
 	OPT_BOOLEAN(0, "errno-summary", &trace.errno_summary,
 		    "Show errno stats per syscall, use with -s or -S"),
 	OPT_CALLBACK(0, "summary-mode", &trace, "mode",
-		     "How to show summary: select thread (default) or total",
+		     "How to show summary: select thread (default), total or cgroup",
 		     trace__parse_summary_mode),
 	OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min",
 		     "Trace pagefaults", parse_pagefaults, "maj"),
@@ -5473,6 +5498,7 @@ int cmd_trace(int argc, const char **argv)
 		     "start"),
 	OPT_BOOLEAN(0, "force-btf", &trace.force_btf, "Prefer btf_dump general pretty printer"
 		       "to customized ones"),
+	OPT_BOOLEAN(0, "bpf-summary", &trace.summary_bpf, "Summary syscall stats in BPF"),
 	OPTS_EVSWITCH(&trace.evswitch),
 	OPT_END()
 	};
@@ -5564,6 +5590,16 @@ int cmd_trace(int argc, const char **argv)
 		goto skip_augmentation;
 	}
 
+	if (trace.summary_bpf) {
+		if (!trace.opts.target.system_wide) {
+			/* TODO: Add filters in the BPF to support other targets. */
+			pr_err("Error: --bpf-summary only works for system-wide mode.\n");
+			goto out;
+		}
+		if (trace.summary_only)
+			goto skip_augmentation;
+	}
+
 	trace.skel = augmented_raw_syscalls_bpf__open();
 	if (!trace.skel) {
 		pr_debug("Failed to open augmented syscalls BPF skeleton");
@@ -5741,6 +5777,12 @@ init_augmented_syscall_tp:
 		symbol_conf.keep_exited_threads = true;
 		if (trace.summary_mode == SUMMARY__NONE)
 			trace.summary_mode = SUMMARY__BY_THREAD;
+
+		if (!trace.summary_bpf && trace.summary_mode == SUMMARY__BY_CGROUP) {
+			pr_err("Error: --summary-mode=cgroup only works with --bpf-summary\n");
+			err = -EINVAL;
+			goto out;
+		}
 	}
 
 	if (output_name != NULL) {
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index e149d96c6dc5..10f25c6705b1 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -26,38 +26,10 @@ static const char * const version_usage[] = {
 	NULL
 };
 
-static void on_off_print(const char *status)
-{
-	printf("[ ");
-
-	if (!strcmp(status, "OFF"))
-		color_fprintf(stdout, PERF_COLOR_RED, "%-3s", status);
-	else
-		color_fprintf(stdout, PERF_COLOR_GREEN, "%-3s", status);
-
-	printf(" ]");
-}
-
-static void status_print(const char *name, const char *macro,
-			 const char *status)
-{
-	printf("%22s: ", name);
-	on_off_print(status);
-	printf("  # %s\n", macro);
-}
-
-#define STATUS(feature)                                   \
-do {                                                      \
-	if (feature.is_builtin)                               \
-		status_print(feature.name, feature.macro, "on");  \
-	else                                                  \
-		status_print(feature.name, feature.macro, "OFF"); \
-} while (0)
-
 static void library_status(void)
 {
 	for (int i = 0; supported_features[i].name; ++i)
-		STATUS(supported_features[i]);
+		feature_status__printf(&supported_features[i]);
 }
 
 int cmd_version(int argc, const char **argv)
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index a07e93c53848..40c4078c295f 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -5,15 +5,14 @@
 struct feature_status {
 	const char *name;
 	const char *macro;
+	const char *tip;
 	int is_builtin;
 };
 
-#define FEATURE_STATUS(name_, macro_) {    \
-	.name = name_,                     \
-	.macro = #macro_,                  \
-	.is_builtin = IS_BUILTIN(macro_) }
-
 extern struct feature_status supported_features[];
+
+void feature_status__printf(const struct feature_status *feature);
+
 struct cmdnames;
 
 void list_common_cmds_help(void);
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 857f6646cc23..e9fab20e9330 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -186,7 +186,7 @@ done
 # diff with extra ignore lines
 check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))" -I"^#include <linux/cfi_types.h>"'
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
-check arch/x86/include/asm/amd-ibs.h  '-I "^#include [<\"]\(asm/\)*msr-index.h"'
+check arch/x86/include/asm/amd/ibs.h  '-I "^#include [<\"]\(asm/\)*msr-index.h"'
 check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"'
 check include/linux/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"'
 check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
index 2b3cb55df288..014454d78293 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-ddrc.json
@@ -3,56 +3,48 @@
 	    "ConfigCode": "0x00",
 	    "EventName": "flux_wr",
 	    "BriefDescription": "DDRC total write operations",
-	    "PublicDescription": "DDRC total write operations",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x01",
 	    "EventName": "flux_rd",
 	    "BriefDescription": "DDRC total read operations",
-	    "PublicDescription": "DDRC total read operations",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x02",
 	    "EventName": "flux_wcmd",
 	    "BriefDescription": "DDRC write commands",
-	    "PublicDescription": "DDRC write commands",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x03",
 	    "EventName": "flux_rcmd",
 	    "BriefDescription": "DDRC read commands",
-	    "PublicDescription": "DDRC read commands",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x04",
 	    "EventName": "pre_cmd",
 	    "BriefDescription": "DDRC precharge commands",
-	    "PublicDescription": "DDRC precharge commands",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x05",
 	    "EventName": "act_cmd",
 	    "BriefDescription": "DDRC active commands",
-	    "PublicDescription": "DDRC active commands",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x06",
 	    "EventName": "rnk_chg",
 	    "BriefDescription": "DDRC rank commands",
-	    "PublicDescription": "DDRC rank commands",
 	    "Unit": "hisi_sccl,ddrc"
    },
    {
 	    "ConfigCode": "0x07",
 	    "EventName": "rw_chg",
 	    "BriefDescription": "DDRC read and write changes",
-	    "PublicDescription": "DDRC read and write changes",
 	    "Unit": "hisi_sccl,ddrc"
    }
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
index 9a7ec7af2060..b2b895fa670e 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
@@ -3,42 +3,41 @@
 	    "ConfigCode": "0x00",
 	    "EventName": "rx_ops_num",
 	    "BriefDescription": "The number of all operations received by the HHA",
-	    "PublicDescription": "The number of all operations received by the HHA",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x01",
 	    "EventName": "rx_outer",
 	    "BriefDescription": "The number of all operations received by the HHA from another socket",
-	    "PublicDescription": "The number of all operations received by the HHA from another socket",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x02",
 	    "EventName": "rx_sccl",
 	    "BriefDescription": "The number of all operations received by the HHA from another SCCL in this socket",
-	    "PublicDescription": "The number of all operations received by the HHA from another SCCL in this socket",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x03",
 	    "EventName": "rx_ccix",
 	    "BriefDescription": "Count of the number of operations that HHA has received from CCIX",
-	    "PublicDescription": "Count of the number of operations that HHA has received from CCIX",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x4",
 	    "EventName": "rx_wbi",
+	    "BriefDescription": "Count of the number of WriteBackI operations that HHA has received",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x5",
 	    "EventName": "rx_wbip",
+	    "BriefDescription": "Count of the number of WriteBackIPtl operations that HHA has received",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x11",
+	    "BriefDescription": "Count of the number of WriteThruIStash operations that HHA has received",
 	    "EventName": "rx_wtistash",
 	    "Unit": "hisi_sccl,hha"
    },
@@ -46,107 +45,114 @@
 	    "ConfigCode": "0x1c",
 	    "EventName": "rd_ddr_64b",
 	    "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 64 bytes",
-	    "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 64bytes",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x1d",
 	    "EventName": "wr_ddr_64b",
 	    "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
-	    "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 64 bytes",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x1e",
 	    "EventName": "rd_ddr_128b",
 	    "BriefDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes",
-	    "PublicDescription": "The number of read operations sent by HHA to DDRC which size is 128 bytes",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x1f",
 	    "EventName": "wr_ddr_128b",
 	    "BriefDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
-	    "PublicDescription": "The number of write operations sent by HHA to DDRC which size is 128 bytes",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x20",
 	    "EventName": "spill_num",
 	    "BriefDescription": "Count of the number of spill operations that the HHA has sent",
-	    "PublicDescription": "Count of the number of spill operations that the HHA has sent",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x21",
 	    "EventName": "spill_success",
 	    "BriefDescription": "Count of the number of successful spill operations that the HHA has sent",
-	    "PublicDescription": "Count of the number of successful spill operations that the HHA has sent",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x23",
 	    "EventName": "bi_num",
+	    "BriefDescription": "Count of the number of HHA BackInvalid operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x32",
 	    "EventName": "mediated_num",
+	    "BriefDescription": "Count of the number of Mediated operations that the HHA has forwarded",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x33",
 	    "EventName": "tx_snp_num",
+	    "BriefDescription": "Count of the number of Snoop operations that the HHA has sent",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x34",
 	    "EventName": "tx_snp_outer",
+	    "BriefDescription": "Count of the number of Snoop operations that the HHA has sent to another socket",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x35",
 	    "EventName": "tx_snp_ccix",
+	    "BriefDescription": "Count of the number of Snoop operations that the HHA has sent to CCIX",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x38",
 	    "EventName": "rx_snprspdata",
+	    "BriefDescription": "Count of the number of SnprspData flit operations that HHA has received",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x3c",
 	    "EventName": "rx_snprsp_outer",
+	    "BriefDescription": "Count of the number of SnprspData operations that HHA has received from another socket",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x40",
 	    "EventName": "sdir-lookup",
+	    "BriefDescription": "Count of the number of HHA S-Dir lookup operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x41",
 	    "EventName": "edir-lookup",
+	    "BriefDescription": "Count of the number of HHA E-Dir lookup operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x42",
 	    "EventName": "sdir-hit",
+	    "BriefDescription": "Count of the number of HHA S-Dir hit operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x43",
 	    "EventName": "edir-hit",
+	    "BriefDescription": "Count of the number of HHA E-Dir hit operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x4c",
 	    "EventName": "sdir-home-migrate",
+	    "BriefDescription": "Count of the number of HHA S-Dir read home migrate operations",
 	    "Unit": "hisi_sccl,hha"
    },
    {
 	    "ConfigCode": "0x4d",
 	    "EventName": "edir-home-migrate",
+	    "BriefDescription": "Count of the number of HHA E-Dir read home migrate operations",
 	    "Unit": "hisi_sccl,hha"
    }
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
index e3479b65be9a..d83c22eb1d15 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-l3c.json
@@ -3,91 +3,78 @@
 	    "ConfigCode": "0x00",
 	    "EventName": "rd_cpipe",
 	    "BriefDescription": "Total read accesses",
-	    "PublicDescription": "Total read accesses",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x01",
 	    "EventName": "wr_cpipe",
 	    "BriefDescription": "Total write accesses",
-	    "PublicDescription": "Total write accesses",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x02",
 	    "EventName": "rd_hit_cpipe",
 	    "BriefDescription": "Total read hits",
-	    "PublicDescription": "Total read hits",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x03",
 	    "EventName": "wr_hit_cpipe",
 	    "BriefDescription": "Total write hits",
-	    "PublicDescription": "Total write hits",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x04",
 	    "EventName": "victim_num",
 	    "BriefDescription": "l3c precharge commands",
-	    "PublicDescription": "l3c precharge commands",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x20",
 	    "EventName": "rd_spipe",
 	    "BriefDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe",
-	    "PublicDescription": "Count of the number of read lines that come from this cluster of CPU core in spipe",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x21",
 	    "EventName": "wr_spipe",
 	    "BriefDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe",
-	    "PublicDescription": "Count of the number of write lines that come from this cluster of CPU core in spipe",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x22",
 	    "EventName": "rd_hit_spipe",
 	    "BriefDescription": "Count of the number of read lines that hits in spipe of this L3C",
-	    "PublicDescription": "Count of the number of read lines that hits in spipe of this L3C",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x23",
 	    "EventName": "wr_hit_spipe",
 	    "BriefDescription": "Count of the number of write lines that hits in spipe of this L3C",
-	    "PublicDescription": "Count of the number of write lines that hits in spipe of this L3C",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x29",
 	    "EventName": "back_invalid",
 	    "BriefDescription": "Count of the number of L3C back invalid operations",
-	    "PublicDescription": "Count of the number of L3C back invalid operations",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x40",
 	    "EventName": "retry_cpu",
 	    "BriefDescription": "Count of the number of retry that L3C suppresses the CPU operations",
-	    "PublicDescription": "Count of the number of retry that L3C suppresses the CPU operations",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x41",
 	    "EventName": "retry_ring",
 	    "BriefDescription": "Count of the number of retry that L3C suppresses the ring operations",
-	    "PublicDescription": "Count of the number of retry that L3C suppresses the ring operations",
 	    "Unit": "hisi_sccl,l3c"
    },
    {
 	    "ConfigCode": "0x42",
 	    "EventName": "prefetch_drop",
 	    "BriefDescription": "Count of the number of prefetch drops from this L3C",
-	    "PublicDescription": "Count of the number of prefetch drops from this L3C",
 	    "Unit": "hisi_sccl,l3c"
    }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
index 147379cae37b..377dfecd96bd 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json
@@ -103,7 +103,7 @@
         "MetricExpr": "tma_core_bound",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
-        "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -113,7 +113,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "(tma_backend_bound >0.10)",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%",
@@ -125,7 +125,7 @@
         "MetricExpr": "(5 * cpu_atom@CPU_CLK_UNHALTED.CORE@ - (cpu_atom@TOPDOWN_FE_BOUND.ALL@ + cpu_atom@TOPDOWN_BE_BOUND.ALL@ + cpu_atom@TOPDOWN_RETIRING.ALL@)) / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "(tma_bad_speculation >0.15)",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%",
@@ -136,7 +136,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -146,7 +146,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -156,7 +156,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
-        "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -165,7 +165,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -174,7 +174,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -184,7 +184,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
-        "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -193,7 +193,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
-        "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -203,7 +203,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "(tma_frontend_bound >0.20)",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -213,7 +213,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -222,7 +222,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
-        "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -232,7 +232,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
-        "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -567,7 +567,7 @@
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
         "MetricName": "tma_info_system_mux",
-        "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9",
         "Unit": "cpu_atom"
     },
     {
@@ -606,7 +606,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -615,7 +615,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -625,7 +625,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
-        "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -634,7 +634,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
-        "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -643,7 +643,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
-        "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -652,7 +652,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
-        "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -661,7 +661,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
-        "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -670,7 +670,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
-        "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -679,7 +679,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
-        "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -688,7 +688,7 @@
         "MetricExpr": "tma_backend_bound - tma_core_bound",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
-        "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -699,7 +699,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "(tma_retiring >0.75)",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -709,7 +709,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (5 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
-        "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -721,7 +721,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(cpu_core@UOPS_DISPATCHED.PORT_0@ + cpu_core@UOPS_DISPATCHED.PORT_1@ + cpu_core@UOPS_DISPATCHED.PORT_5_11@ + cpu_core@UOPS_DISPATCHED.PORT_6@) / (5 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -734,13 +734,13 @@
         "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -751,7 +751,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -768,13 +768,13 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20",
@@ -791,7 +791,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -800,7 +800,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -809,16 +809,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy",
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20",
@@ -826,7 +826,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -835,7 +835,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -844,16 +844,16 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
-        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -866,11 +866,11 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls",
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -879,7 +879,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -893,26 +893,26 @@
         "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -921,7 +921,7 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -931,26 +931,26 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -959,7 +959,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -968,35 +968,36 @@
         "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((28 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + (27 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(25 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) + 24 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1007,26 +1008,27 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricExpr": "(27 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "24 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (1 - cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ / (cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM@ + cpu_core@OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD@))) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1036,7 +1038,7 @@
         "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1046,7 +1048,7 @@
         "MetricExpr": "cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1057,7 +1059,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1066,28 +1068,28 @@
         "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks",
+        "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1096,8 +1098,8 @@
         "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1118,18 +1120,18 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
-        "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
+        "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1149,7 +1151,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1159,16 +1161,16 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1177,8 +1179,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1187,8 +1189,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1197,8 +1199,8 @@
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1207,41 +1209,41 @@
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
+        "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) - cpu_core@INT_MISC.UOP_DROPPING@ / tma_info_thread_slots",
         "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1250,8 +1252,8 @@
         "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1264,7 +1266,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
@@ -1272,7 +1274,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
@@ -1280,15 +1282,15 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -1320,7 +1322,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -1329,7 +1331,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -1338,10 +1340,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
         "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
@@ -1412,12 +1415,12 @@
         "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.PORT_0@ + cpu_core@FP_ARITH_DISPATCHED.PORT_1@ + cpu_core@FP_ARITH_DISPATCHED.PORT_5@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)",
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
@@ -1432,22 +1435,22 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency",
         "Unit": "cpu_core"
@@ -1497,14 +1500,14 @@
     },
     {
         "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
-        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed",
         "MetricName": "tma_info_frontend_unknown_branch_cost",
-        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node",
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch",
@@ -1524,7 +1527,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW",
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.",
         "Unit": "cpu_core"
     },
     {
@@ -1533,7 +1536,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1542,7 +1545,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1551,7 +1554,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1560,7 +1563,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1623,7 +1626,7 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 13",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
         "Unit": "cpu_core"
     },
@@ -1769,7 +1772,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp",
         "Unit": "cpu_core"
@@ -1849,7 +1852,7 @@
     },
     {
         "BriefDescription": "",
-        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / (cpu_core@UOPS_EXECUTED.CORE_CYCLES_GE_1@ / 2 if #SMT_on else cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute",
         "Unit": "cpu_core"
@@ -1880,20 +1883,20 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "MicroSeq;Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
@@ -1946,23 +1949,22 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000",
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_utilization",
         "MetricThreshold": "tma_info_system_kernel_utilization > 0.05",
@@ -2030,7 +2032,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks",
@@ -2041,7 +2043,6 @@
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
         "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
@@ -2049,7 +2050,7 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage",
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
         "Unit": "cpu_core"
     },
     {
@@ -2061,14 +2062,14 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "cpu_core@TOPDOWN.SLOTS@",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (cpu_core@TOPDOWN.SLOTS@ / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization",
         "Unit": "cpu_core"
@@ -2086,15 +2087,15 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5",
+        "MetricThreshold": "tma_info_thread_uptb < 9",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2104,7 +2105,7 @@
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_int_operations",
         "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2113,8 +2114,8 @@
         "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_128@ + cpu_core@INT_VEC_RETIRED.VNNI_128@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
-        "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2123,8 +2124,8 @@
         "MetricExpr": "(cpu_core@INT_VEC_RETIRED.ADD_256@ + cpu_core@INT_VEC_RETIRED.MUL_256@ + cpu_core@INT_VEC_RETIRED.VNNI_256@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
-        "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2133,8 +2134,8 @@
         "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2143,7 +2144,7 @@
         "MetricExpr": "max((cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2153,7 +2154,7 @@
         "MetricExpr": "min(2 * (cpu_core@MEM_INST_RETIRED.ALL_LOADS@ - cpu_core@MEM_LOAD_RETIRED.FB_HIT@ - cpu_core@MEM_LOAD_RETIRED.L1_MISS@) * 20 / 100, max(cpu_core@CYCLE_ACTIVITY.CYCLES_MEM_ANY@ - cpu_core@MEMORY_ACTIVITY.CYCLES_L1D_MISS@, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2163,17 +2164,18 @@
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L1D_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "3 * tma_info_system_core_frequency * cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2183,18 +2185,19 @@
         "MetricExpr": "(cpu_core@MEMORY_ACTIVITY.STALLS_L2_MISS@ - cpu_core@MEMORY_ACTIVITY.STALLS_L3_MISS@) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(12 * tma_info_system_core_frequency - 3 * tma_info_system_core_frequency) * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "9 * tma_info_system_core_frequency * (cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2203,19 +2206,19 @@
         "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2234,7 +2237,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2243,34 +2246,34 @@
         "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2279,7 +2282,7 @@
         "MetricExpr": "(16 * max(0, cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ - cpu_core@L2_RQSTS.ALL_RFO@) + cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@ * (10 * cpu_core@L2_RQSTS.RFO_HIT@ + min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2290,7 +2293,7 @@
         "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_lsd",
         "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2301,16 +2304,16 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2320,34 +2323,34 @@
         "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
-        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
-        "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -2370,7 +2373,7 @@
         "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2386,18 +2389,18 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "max(cpu_core@IDQ.MS_CYCLES_ANY@, cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@)) / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -2406,10 +2409,10 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
-        "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks",
+        "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (cpu_core@UOPS_RETIRED.SLOTS@ / cpu_core@UOPS_ISSUED.ANY@) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2420,7 +2423,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2429,7 +2432,7 @@
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2445,20 +2448,20 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2468,7 +2471,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2478,7 +2481,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2488,7 +2491,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2498,7 +2501,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2507,8 +2510,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2517,8 +2520,8 @@
         "MetricExpr": "(cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + max(cpu_core@RS.EMPTY_RESOURCE@ - cpu_core@RESOURCE_STALLS.SCOREBOARD@, 0)) / tma_info_thread_clks * (cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2527,7 +2530,7 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2538,8 +2541,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2549,7 +2552,7 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2557,7 +2560,7 @@
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2571,7 +2574,7 @@
         "MetricExpr": "cpu_core@RESOURCE_STALLS.SCOREBOARD@ / tma_info_thread_clks + tma_c02_wait",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2581,8 +2584,8 @@
         "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_shuffles_256b",
-        "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+        "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2592,7 +2595,7 @@
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2603,7 +2606,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2612,8 +2615,8 @@
         "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2622,7 +2625,7 @@
         "MetricExpr": "(cpu_core@XQ.FULL_CYCLES@ + cpu_core@L1D_PEND_MISS.L2_STALLS@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2632,8 +2635,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2642,8 +2645,8 @@
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2652,8 +2655,8 @@
         "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2672,7 +2675,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2681,34 +2684,34 @@
         "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2717,7 +2720,7 @@
         "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2727,7 +2730,7 @@
         "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2737,8 +2740,8 @@
         "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     }
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/cache.json b/tools/perf/pmu-events/arch/x86/alderlake/cache.json
index a20e19738046..c2802fbb853b 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/cache.json
@@ -4,6 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.HWPF_MISS",
+        "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -13,7 +14,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.REPLACEMENT",
-        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -23,7 +24,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -35,7 +36,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
-        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -46,6 +47,7 @@
         "Deprecated": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALL",
+        "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -55,7 +57,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALLS",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -65,7 +67,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -76,7 +78,7 @@
         "CounterMask": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -86,7 +88,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x25",
         "EventName": "L2_LINES_IN.ALL",
-        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1f",
         "Unit": "cpu_core"
@@ -96,7 +98,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.NON_SILENT",
-        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -106,7 +108,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -116,7 +118,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.USELESS_HWPF",
-        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
+        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -135,7 +137,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.ALL",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff",
         "Unit": "cpu_core"
@@ -165,7 +167,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f",
         "Unit": "cpu_core"
@@ -175,7 +177,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "PublicDescription": "Counts the total number of L2 code requests.",
+        "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe4",
         "Unit": "cpu_core"
@@ -185,7 +187,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe1",
         "Unit": "cpu_core"
@@ -195,7 +197,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "PublicDescription": "Counts demand requests that miss L2 cache.",
+        "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x27",
         "Unit": "cpu_core"
@@ -205,6 +207,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_HWPF",
+        "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf0",
         "Unit": "cpu_core"
@@ -214,7 +217,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_RFO",
-        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe2",
         "Unit": "cpu_core"
@@ -224,7 +227,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc4",
         "Unit": "cpu_core"
@@ -234,7 +237,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x24",
         "Unit": "cpu_core"
@@ -244,7 +247,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc1",
         "Unit": "cpu_core"
@@ -254,7 +257,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
-        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -264,6 +267,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HWPF_MISS",
+        "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x30",
         "Unit": "cpu_core"
@@ -273,7 +277,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f",
         "Unit": "cpu_core"
@@ -283,7 +287,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.REFERENCES",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff",
         "Unit": "cpu_core"
@@ -293,7 +297,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_HIT",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc2",
         "Unit": "cpu_core"
@@ -303,7 +307,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_MISS",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x22",
         "Unit": "cpu_core"
@@ -313,7 +317,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_HIT",
-        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc8",
         "Unit": "cpu_core"
@@ -323,7 +327,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_MISS",
-        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x28",
         "Unit": "cpu_core"
@@ -333,7 +337,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x23",
         "EventName": "L2_TRANS.L2_WB",
-        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -353,7 +357,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.MISS",
-        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -373,7 +377,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4f",
         "Unit": "cpu_core"
@@ -461,7 +465,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
+        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81",
         "Unit": "cpu_core"
@@ -472,7 +476,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82",
         "Unit": "cpu_core"
@@ -483,7 +487,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x83",
         "Unit": "cpu_core"
@@ -494,7 +498,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -505,7 +509,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -516,7 +520,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x42",
         "Unit": "cpu_core"
@@ -527,7 +531,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -538,7 +542,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12",
         "Unit": "cpu_core"
@@ -548,7 +552,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
-        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
+        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfd",
         "Unit": "cpu_core"
@@ -559,7 +563,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -570,7 +574,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -581,7 +585,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -592,7 +596,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -603,7 +607,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
+        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -614,7 +618,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -625,7 +629,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -636,7 +640,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -647,7 +651,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -658,7 +662,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -669,7 +673,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -680,7 +684,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -691,7 +695,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -702,7 +706,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -713,7 +717,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -724,6 +728,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80",
         "Unit": "cpu_atom"
@@ -734,6 +739,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x20",
         "Unit": "cpu_atom"
@@ -744,6 +750,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -754,6 +761,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8",
         "Unit": "cpu_atom"
@@ -764,6 +772,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_atom"
@@ -774,6 +783,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x10",
         "Unit": "cpu_atom"
@@ -784,6 +794,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4",
         "Unit": "cpu_atom"
@@ -794,6 +805,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.HIT_E_F",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_atom"
@@ -804,6 +816,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.L3_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_atom"
@@ -849,6 +862,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x44",
         "EventName": "MEM_STORE_RETIRED.L2_HIT",
+        "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -859,7 +873,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts the total number of load uops retired.",
+        "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x81",
         "Unit": "cpu_atom"
@@ -870,7 +884,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts the total number of store uops retired.",
+        "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x82",
         "Unit": "cpu_atom"
@@ -883,7 +897,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -896,7 +910,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -909,7 +923,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -922,7 +936,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -935,7 +949,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -948,7 +962,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -961,7 +975,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -974,7 +988,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
@@ -985,6 +999,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+        "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21",
         "Unit": "cpu_atom"
@@ -995,6 +1010,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x41",
         "Unit": "cpu_atom"
@@ -1005,6 +1021,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS",
+        "PublicDescription": "Counts the total number of load and store uops retired that missed in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13",
         "Unit": "cpu_atom"
@@ -1015,6 +1032,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+        "PublicDescription": "Counts the number of load ops retired that miss in the second Level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11",
         "Unit": "cpu_atom"
@@ -1025,6 +1043,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+        "PublicDescription": "Counts the number of store ops retired that miss in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12",
         "Unit": "cpu_atom"
@@ -1035,7 +1054,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
-        "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6",
         "Unit": "cpu_atom"
@@ -1045,18 +1064,43 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe5",
         "EventName": "MEM_UOP_RETIRED.ANY",
-        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
+        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10008",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1068,6 +1112,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1079,6 +1124,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1090,17 +1136,43 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1112,6 +1184,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1123,6 +1196,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1134,6 +1208,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1145,6 +1220,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1156,6 +1232,31 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1167,6 +1268,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1178,6 +1280,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1189,6 +1292,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1200,6 +1304,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1211,6 +1316,19 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x14000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1222,6 +1340,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1233,6 +1352,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1244,6 +1364,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1255,6 +1376,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1264,6 +1386,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+        "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -1273,7 +1396,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DATA_RD",
-        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1283,7 +1406,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
-        "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
+        "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1293,7 +1416,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1303,7 +1426,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
-        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1315,6 +1438,7 @@
         "Errata": "ADL038",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1326,6 +1450,7 @@
         "Errata": "ADL038",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1336,7 +1461,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1347,6 +1472,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1357,7 +1483,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1368,6 +1494,7 @@
         "Errata": "ADL038",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1377,7 +1504,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1387,7 +1514,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1397,7 +1524,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x2c",
         "EventName": "SQ_MISC.BUS_LOCK",
-        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1407,6 +1534,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.ANY",
+        "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xf",
         "Unit": "cpu_core"
@@ -1416,7 +1544,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.NTA",
-        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1426,7 +1554,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
-        "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1436,7 +1564,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T0",
-        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1446,7 +1574,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T1_T2",
-        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json
index 62fd70f220e5..ce570b96360a 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json
@@ -14,6 +14,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FPDIV_ACTIVE",
+        "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -32,7 +33,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.FP",
-        "PublicDescription": "Counts all microcode Floating Point assists.",
+        "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -42,6 +43,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.SSE_AVX_MIX",
+        "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -51,6 +53,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -60,6 +63,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -69,6 +73,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -78,6 +83,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -87,6 +93,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -96,6 +103,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V2",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -105,7 +113,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -115,7 +123,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -125,7 +133,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -135,7 +143,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -145,7 +153,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x18",
         "Unit": "cpu_core"
@@ -155,7 +163,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -165,7 +173,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -175,7 +183,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -185,7 +193,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
-        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfc",
         "Unit": "cpu_core"
@@ -205,6 +213,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.FPDIV",
+        "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_atom"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json
index c5b3818ad479..dae3174a74fb 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json
@@ -14,7 +14,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x60",
         "EventName": "BACLEARS.ANY",
-        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -24,7 +24,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.LCP",
-        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -34,6 +34,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.MS_BUSY",
+        "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -43,7 +44,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x61",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
+        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -55,7 +56,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -67,7 +68,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -79,7 +80,7 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -91,7 +92,7 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -103,7 +104,7 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -115,7 +116,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600106",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -127,7 +128,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -139,7 +140,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -151,7 +152,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -163,7 +164,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -175,7 +176,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -187,7 +188,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -199,7 +200,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -211,7 +212,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -223,7 +224,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -235,7 +236,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -247,6 +248,7 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -258,7 +260,7 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -270,6 +272,7 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
+        "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -299,7 +302,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALLS",
-        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
+        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -311,6 +314,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALL_PERIODS",
+        "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -320,7 +324,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x83",
         "EventName": "ICACHE_TAG.STALLS",
-        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -331,7 +335,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -342,7 +346,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -352,7 +356,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -363,7 +367,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -374,7 +378,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -384,7 +388,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -395,7 +399,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_CYCLES_ANY",
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -407,7 +411,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_SWITCHES",
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -417,7 +421,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -427,7 +431,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -438,7 +442,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -450,7 +454,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -460,7 +464,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -471,7 +475,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -483,7 +487,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json
index fa15f5797bed..07f5786bdbc0 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json
@@ -5,6 +5,7 @@
         "CounterMask": "6",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6",
         "Unit": "cpu_core"
@@ -78,7 +79,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -89,6 +90,7 @@
         "CounterMask": "2",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -99,6 +101,7 @@
         "CounterMask": "3",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -109,7 +112,7 @@
         "CounterMask": "5",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
-        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_core"
@@ -120,7 +123,7 @@
         "CounterMask": "9",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
-        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -248,29 +251,67 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -282,6 +323,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -293,6 +335,19 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -304,6 +359,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -315,6 +371,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -326,6 +383,19 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.SWPF_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784004000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -337,6 +407,7 @@
         "EventName": "OCR.SWPF_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84404000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -346,6 +417,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -355,7 +427,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
+        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/other.json b/tools/perf/pmu-events/arch/x86/alderlake/other.json
index a8b23e92408c..e4e75b088ccc 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/other.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.HARDWARE",
-        "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.  This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count.",
+        "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.  This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists. the event also counts for Machine Ordering count. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -14,6 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.PAGE_FAULT",
+        "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -23,6 +24,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LICENSE_1",
+        "PublicDescription": "CORE_POWER.LICENSE_1 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -32,6 +34,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LICENSE_2",
+        "PublicDescription": "CORE_POWER.LICENSE_2 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -41,6 +44,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LICENSE_3",
+        "PublicDescription": "CORE_POWER.LICENSE_3 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -51,127 +55,19 @@
         "Deprecated": "1",
         "EventCode": "0xe4",
         "EventName": "LBR_INSERTS.ANY",
+        "PublicDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10008",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -183,6 +79,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -194,6 +91,7 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -205,103 +103,18 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x14000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.SWPF_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784004000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_COUNT",
-        "Invert": "1",
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_RESOURCE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "Deprecated": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS_EMPTY.COUNT",
-        "Invert": "1",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "Deprecated": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS_EMPTY.CYCLES",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "200003",
-        "UMask": "0x4",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "Cycles the uncore cannot take further requests",
         "Counter": "0,1,2,3",
         "CounterMask": "1",
         "EventCode": "0x2d",
         "EventName": "XQ.FULL_CYCLES",
-        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
+        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
index f5bf0816f190..7e0e33792c45 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json
@@ -6,6 +6,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -26,7 +27,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIV_ACTIVE",
-        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -56,6 +57,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FP_DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -76,6 +78,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.IDIV_ACTIVE",
+        "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -105,6 +108,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.INT_DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -114,7 +118,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.ANY",
-        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.",
+        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1b",
         "Unit": "cpu_core"
@@ -124,7 +128,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for.",
+        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "Unit": "cpu_atom"
     },
@@ -133,7 +137,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all branch instructions retired.",
+        "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -143,6 +147,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9",
         "Unit": "cpu_atom"
@@ -152,6 +157,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
+        "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e",
         "Unit": "cpu_atom"
@@ -161,7 +167,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PublicDescription": "Counts conditional branch instructions retired.",
+        "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -171,7 +177,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts not taken branch instructions retired.",
+        "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -181,6 +187,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
+        "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe",
         "Unit": "cpu_atom"
@@ -190,7 +197,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional branch instructions retired.",
+        "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -200,6 +207,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xbf",
         "Unit": "cpu_atom"
@@ -209,7 +217,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PublicDescription": "Counts far branch instructions retired.",
+        "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -219,6 +227,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
+        "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb",
         "Unit": "cpu_atom"
@@ -228,7 +237,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -238,6 +247,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT_CALL",
+        "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb",
         "Unit": "cpu_atom"
@@ -248,6 +258,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.IND_CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb",
         "Unit": "cpu_atom"
@@ -258,6 +269,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e",
         "Unit": "cpu_atom"
@@ -267,6 +279,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
+        "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9",
         "Unit": "cpu_atom"
@@ -276,7 +289,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -286,6 +299,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7",
         "Unit": "cpu_atom"
@@ -295,7 +309,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts return instructions retired.",
+        "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -305,6 +319,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Counts the number of near taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc0",
         "Unit": "cpu_atom"
@@ -314,7 +329,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts taken branch instructions retired.",
+        "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -325,6 +340,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb",
         "Unit": "cpu_atom"
@@ -334,6 +350,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.REL_CALL",
+        "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfd",
         "Unit": "cpu_atom"
@@ -344,6 +361,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.RETURN",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_RETURN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7",
         "Unit": "cpu_atom"
@@ -354,6 +372,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.TAKEN_JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND_TAKEN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe",
         "Unit": "cpu_atom"
@@ -363,7 +382,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "Unit": "cpu_atom"
     },
@@ -372,7 +391,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -381,6 +400,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
+        "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e",
         "Unit": "cpu_atom"
@@ -390,7 +410,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -400,7 +420,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -410,6 +430,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
+        "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe",
         "Unit": "cpu_atom"
@@ -419,7 +440,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -429,6 +450,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
+        "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb",
         "Unit": "cpu_atom"
@@ -438,7 +460,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -448,6 +470,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
+        "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb",
         "Unit": "cpu_atom"
@@ -457,7 +480,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -468,6 +491,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.IND_CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb",
         "Unit": "cpu_atom"
@@ -478,6 +502,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e",
         "Unit": "cpu_atom"
@@ -487,6 +512,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Counts the number of mispredicted near taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80",
         "Unit": "cpu_atom"
@@ -496,7 +522,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -507,6 +533,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb",
         "Unit": "cpu_atom"
@@ -516,7 +543,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -526,6 +553,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RETURN",
+        "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7",
         "Unit": "cpu_atom"
@@ -536,6 +564,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND_TAKEN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe",
         "Unit": "cpu_atom"
@@ -545,7 +574,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C01",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -555,7 +584,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C02",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -565,7 +594,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C0_WAIT",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x70",
         "Unit": "cpu_core"
@@ -593,7 +622,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED",
-        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -603,7 +632,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.",
+        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0",
         "SampleAfterValue": "25003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -613,6 +642,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -624,6 +654,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE_INST",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -643,7 +674,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED",
-        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -681,7 +712,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
-        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -718,7 +749,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_core"
     },
@@ -728,6 +759,7 @@
         "CounterMask": "8",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -738,6 +770,7 @@
         "CounterMask": "1",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -748,6 +781,7 @@
         "CounterMask": "16",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -758,6 +792,7 @@
         "CounterMask": "12",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc",
         "Unit": "cpu_core"
@@ -768,6 +803,7 @@
         "CounterMask": "5",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5",
         "Unit": "cpu_core"
@@ -778,6 +814,7 @@
         "CounterMask": "4",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "PublicDescription": "Total execution stalls. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -787,7 +824,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -797,6 +834,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0xc",
         "Unit": "cpu_core"
@@ -806,7 +844,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -816,7 +854,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -826,7 +864,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -837,6 +875,7 @@
         "CounterMask": "5",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS",
+        "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -847,7 +886,7 @@
         "CounterMask": "2",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
-        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
+        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -857,7 +896,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
-        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.",
+        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -867,7 +906,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x75",
         "EventName": "INST_DECODED.DECODERS",
-        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
+        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -876,7 +915,7 @@
         "BriefDescription": "Counts the total number of instructions retired. (Fixed event)",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -885,7 +924,7 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -895,7 +934,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_atom"
     },
@@ -913,6 +952,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -922,7 +962,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -931,7 +971,7 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -941,7 +981,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -953,7 +993,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEARS_COUNT",
-        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
+        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -963,7 +1003,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
-        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -973,7 +1013,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.RECOVERY_CYCLES",
-        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -985,6 +1025,7 @@
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x7",
+        "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -994,7 +1035,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UOP_DROPPING",
-        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons",
+        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1004,6 +1045,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.128BIT",
+        "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x13",
         "Unit": "cpu_core"
@@ -1013,6 +1055,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.256BIT",
+        "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xac",
         "Unit": "cpu_core"
@@ -1022,7 +1065,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_128",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -1032,7 +1075,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_256",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc",
         "Unit": "cpu_core"
@@ -1042,6 +1085,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.MUL_256",
+        "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -1051,6 +1095,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.SHUFFLES",
+        "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -1060,6 +1105,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_128",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1069,6 +1115,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_256",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1079,6 +1126,7 @@
         "Deprecated": "1",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.4K_ALIAS",
+        "PublicDescription": "This event is deprecated. Refer to new event LD_BLOCKS.ADDRESS_ALIAS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_atom"
@@ -1088,6 +1136,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
+        "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4",
         "Unit": "cpu_atom"
@@ -1097,7 +1146,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
-        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1107,6 +1156,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+        "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1116,7 +1166,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.NO_SR",
-        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x88",
         "Unit": "cpu_core"
@@ -1126,7 +1176,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x82",
         "Unit": "cpu_core"
@@ -1136,7 +1186,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x4c",
         "EventName": "LOAD_HIT_PREFETCH.SWPF",
-        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1147,7 +1197,7 @@
         "CounterMask": "1",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_ACTIVE",
-        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1158,7 +1208,7 @@
         "CounterMask": "6",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_OK",
-        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1168,7 +1218,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa8",
         "EventName": "LSD.UOPS",
-        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1180,7 +1230,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.COUNT",
-        "PublicDescription": "Counts the number of machine clears (nukes) of any type.",
+        "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1213,8 +1263,9 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+        "BriefDescription": "This event is deprecated.",
         "Counter": "0,1,2,3,4,5",
+        "Deprecated": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SLOW",
         "SampleAfterValue": "20003",
@@ -1235,7 +1286,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SMC",
-        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1245,7 +1296,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe0",
         "EventName": "MISC2_RETIRED.LFENCE",
-        "PublicDescription": "number of LFENCE retired instructions",
+        "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1255,7 +1306,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xe4",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY]",
+        "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1265,7 +1316,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcc",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1275,7 +1326,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SB",
-        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1285,11 +1336,79 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SCOREBOARD",
+        "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_COUNT",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "Deprecated": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS_EMPTY.COUNT",
+        "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Deprecated": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS_EMPTY.CYCLES",
+        "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x75",
@@ -1304,7 +1423,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
-        "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.",
+        "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1314,7 +1433,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BAD_SPEC_SLOTS",
-        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.",
+        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1324,7 +1443,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
-        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
+        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1334,6 +1453,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS",
+        "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1352,7 +1472,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.SLOTS_P",
-        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
+        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1561,6 +1681,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "TOPDOWN_RETIRING.ALL",
+        "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "Unit": "cpu_atom"
     },
@@ -1569,6 +1690,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x76",
         "EventName": "UOPS_DECODED.DEC0_UOPS",
+        "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1578,7 +1700,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_0",
-        "PublicDescription": "Number of uops dispatch to execution  port 0.",
+        "PublicDescription": "Number of uops dispatch to execution  port 0. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1588,7 +1710,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_1",
-        "PublicDescription": "Number of uops dispatch to execution  port 1.",
+        "PublicDescription": "Number of uops dispatch to execution  port 1. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1598,7 +1720,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_2_3_10",
-        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10",
+        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1608,7 +1730,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_4_9",
-        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9",
+        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1618,7 +1740,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_5_11",
-        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11",
+        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1628,7 +1750,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_6",
-        "PublicDescription": "Number of uops dispatch to execution  port 6.",
+        "PublicDescription": "Number of uops dispatch to execution  port 6. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -1638,7 +1760,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_7_8",
-        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8.",
+        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -1649,7 +1771,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1660,7 +1782,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1671,7 +1793,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1682,7 +1804,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1693,7 +1815,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_1",
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1704,7 +1826,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_2",
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1715,7 +1837,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_3",
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1726,7 +1848,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_4",
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1738,7 +1860,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALLS",
         "Invert": "1",
-        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1751,6 +1873,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALL_CYCLES",
         "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1760,6 +1883,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1769,7 +1893,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.X87",
-        "PublicDescription": "Counts the number of x87 uops executed.",
+        "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1788,7 +1912,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.ANY",
-        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1799,6 +1923,7 @@
         "CounterMask": "1",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.CYCLES",
+        "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1808,6 +1933,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.ALL",
+        "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_atom"
     },
@@ -1817,7 +1943,7 @@
         "CounterMask": "1",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.CYCLES",
-        "PublicDescription": "Counts cycles where at least one uop has retired.",
+        "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1827,7 +1953,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.HEAVY",
-        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.",
+        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1837,6 +1963,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.IDIV",
+        "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10",
         "Unit": "cpu_atom"
@@ -1846,7 +1973,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.MS",
-        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
+        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -1858,6 +1985,7 @@
         "EventName": "UOPS_RETIRED.MS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -1867,7 +1995,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.SLOTS",
-        "PublicDescription": "Counts the retirement slots used each cycle.",
+        "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1879,7 +2007,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALLS",
         "Invert": "1",
-        "PublicDescription": "This event counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1892,6 +2020,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1901,6 +2030,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.X87",
+        "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_atom"
diff --git a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json
index 132ce48af6d9..3d15275eca61 100644
--- a/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlake/virtual-memory.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -15,7 +15,7 @@
         "CounterMask": "1",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -35,7 +35,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -45,7 +45,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -55,7 +55,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -65,7 +65,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -75,7 +75,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -85,7 +85,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -96,7 +96,7 @@
         "CounterMask": "1",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -116,7 +116,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -126,7 +126,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -136,7 +136,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -146,7 +146,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -156,7 +156,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -184,7 +184,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.STLB_HIT",
-        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
+        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -195,7 +195,7 @@
         "CounterMask": "1",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -215,7 +215,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe",
         "Unit": "cpu_core"
@@ -225,7 +225,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -235,7 +235,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -245,7 +245,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -266,6 +266,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13",
         "Unit": "cpu_atom"
@@ -277,6 +278,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_LOADS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11",
         "Unit": "cpu_atom"
@@ -288,6 +290,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_STORES Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12",
         "Unit": "cpu_atom"
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
index ad04b1e3881e..ce93648043ef 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json
@@ -75,7 +75,7 @@
         "MetricExpr": "tma_core_bound",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
-        "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
@@ -84,7 +84,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "(tma_backend_bound >0.10)",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%"
@@ -95,7 +95,7 @@
         "MetricExpr": "(5 * CPU_CLK_UNHALTED.CORE - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "(tma_bad_speculation >0.15)",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%"
@@ -105,7 +105,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%"
     },
@@ -114,7 +114,7 @@
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -123,7 +123,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
-        "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -131,7 +131,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -139,7 +139,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -148,7 +148,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
-        "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -156,7 +156,7 @@
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
-        "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -165,7 +165,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "(tma_frontend_bound >0.20)",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%"
     },
@@ -174,7 +174,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -182,7 +182,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
-        "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -191,7 +191,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
-        "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -473,7 +473,7 @@
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE",
         "MetricName": "tma_info_system_mux",
-        "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))"
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
     },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
@@ -506,7 +506,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -514,7 +514,7 @@
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -523,7 +523,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
-        "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
@@ -531,7 +531,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
-        "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
@@ -539,7 +539,7 @@
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
-        "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -547,7 +547,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
-        "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -555,7 +555,7 @@
         "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
-        "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -563,7 +563,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
-        "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
@@ -571,7 +571,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
-        "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
@@ -579,7 +579,7 @@
         "MetricExpr": "tma_backend_bound - tma_core_bound",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
-        "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -589,7 +589,7 @@
         "MetricExpr": "TOPDOWN_RETIRING.ALL / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "(tma_retiring >0.75)",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%"
     },
@@ -598,7 +598,7 @@
         "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (5 * CPU_CLK_UNHALTED.CORE)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
-        "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
index fd9ed58c2f90..bf691aee1ef4 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/cache.json
@@ -118,6 +118,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80"
     },
@@ -127,6 +128,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },
@@ -136,6 +138,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -145,6 +148,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
     },
@@ -154,6 +158,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -163,6 +168,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x10"
     },
@@ -172,6 +178,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -181,6 +188,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.HIT_E_F",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -190,6 +198,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_UOPS_RETIRED_MISC.L3_MISS",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -231,7 +240,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts the total number of load uops retired.",
+        "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x81"
     },
@@ -241,7 +250,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts the total number of store uops retired.",
+        "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x82"
     },
@@ -253,7 +262,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 128 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -265,7 +274,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 16 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -277,7 +286,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 256 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -289,7 +298,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 32 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -301,7 +310,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 4 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -313,7 +322,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 512 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -325,7 +334,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 64 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -337,7 +346,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of tagged loads with an instruction latency that exceeds or equals the threshold of 8 cycles as defined in MEC_CR_PEBS_LD_LAT_THRESHOLD (3F6H). Only counts with PEBS enabled. If a PEBS record is generated, will populate the PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -347,6 +356,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+        "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21"
     },
@@ -356,6 +366,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x41"
     },
@@ -365,6 +376,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS",
+        "PublicDescription": "Counts the total number of load and store uops retired that missed in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13"
     },
@@ -374,6 +386,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+        "PublicDescription": "Counts the number of load ops retired that miss in the second Level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11"
     },
@@ -383,6 +396,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+        "PublicDescription": "Counts the number of store ops retired that miss in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12"
     },
@@ -392,17 +406,40 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
-        "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly.",
+        "PublicDescription": "Counts the number of stores uops retired. Counts with or without PEBS enabled. If PEBS is enabled and a PEBS record is generated, will populate PEBS Latency and PEBS Data Source fields accordingly. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6"
     },
     {
+        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10008",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -413,6 +450,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -423,6 +461,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -433,6 +472,18 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -443,6 +494,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -453,6 +505,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -463,6 +516,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -473,6 +527,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -483,6 +549,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -493,6 +560,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -503,6 +571,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -513,6 +582,18 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x14000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -523,6 +604,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -533,6 +615,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -543,6 +626,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -553,6 +637,7 @@
         "EventName": "OCR.SWPF_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C4000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json
index ed963fcb6485..f44da31ff1f1 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/floating-point.json
@@ -29,6 +29,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.FPDIV",
+        "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     }
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
index 3b46b048dfb2..049c5e2630d7 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json
@@ -57,12 +57,35 @@
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -73,6 +96,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -83,6 +107,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -93,6 +129,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -103,6 +140,18 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84400002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS] Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0xB7",
+        "EventName": "OCR.SWPF_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x784004000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -113,6 +162,7 @@
         "EventName": "OCR.SWPF_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F84404000",
+        "PublicDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/other.json b/tools/perf/pmu-events/arch/x86/alderlaken/other.json
index f8c21b7f8f40..8c2b5a284f2a 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/other.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/other.json
@@ -5,86 +5,18 @@
         "Deprecated": "1",
         "EventCode": "0xe4",
         "EventName": "LBR_INSERTS.ANY",
+        "PublicDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10008",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xB7",
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -95,6 +27,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -105,35 +38,8 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.SWPF_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x14000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache software prefetches which include T0/T1/T2 and NTA (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0xB7",
-        "EventName": "OCR.SWPF_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x784004000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
-        "Counter": "0,1,2,3,4,5",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "200003",
-        "UMask": "0x4"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
index 713ebc21cec0..9616bf0e9f1f 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json
@@ -54,7 +54,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for.",
+        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for. Available PDIST counters: 0",
         "SampleAfterValue": "200003"
     },
     {
@@ -63,6 +63,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9"
     },
@@ -71,6 +72,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
+        "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -79,6 +81,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
+        "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -87,6 +90,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xbf"
     },
@@ -95,6 +99,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
+        "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -103,6 +108,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT_CALL",
+        "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -112,6 +118,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.IND_CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -121,6 +128,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -129,6 +137,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
+        "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9"
     },
@@ -137,6 +146,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -145,6 +155,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Counts the number of near taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc0"
     },
@@ -154,6 +165,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -162,6 +174,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.REL_CALL",
+        "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfd"
     },
@@ -171,6 +184,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.RETURN",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.NEAR_RETURN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -180,6 +194,7 @@
         "Deprecated": "1",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.TAKEN_JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.COND_TAKEN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -188,7 +203,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "200003"
     },
     {
@@ -196,6 +211,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
+        "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -204,6 +220,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
+        "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -212,6 +229,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
+        "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -220,6 +238,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
+        "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -229,6 +248,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.IND_CALL",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT_CALL Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -238,6 +258,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -246,6 +267,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Counts the number of mispredicted near taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80"
     },
@@ -255,6 +277,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -263,6 +286,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RETURN",
+        "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -272,6 +296,7 @@
         "Deprecated": "1",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
+        "PublicDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.COND_TAKEN Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -337,7 +362,7 @@
         "BriefDescription": "Counts the total number of instructions retired. (Fixed event)",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -346,7 +371,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -355,6 +380,7 @@
         "Deprecated": "1",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.4K_ALIAS",
+        "PublicDescription": "This event is deprecated. Refer to new event LD_BLOCKS.ADDRESS_ALIAS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -363,6 +389,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
+        "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -371,6 +398,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+        "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -399,8 +427,9 @@
         "UMask": "0x20"
     },
     {
-        "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+        "BriefDescription": "This event is deprecated.",
         "Counter": "0,1,2,3,4,5",
+        "Deprecated": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SLOW",
         "SampleAfterValue": "20003",
@@ -419,11 +448,19 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xe4",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY]",
+        "PublicDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. This event is PDIR on GP0 and NPEBS on all other GPs [This event is alias to LBR_INSERTS.ANY] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
+        "Counter": "0,1,2,3,4,5",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.",
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0x75",
@@ -614,6 +651,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "TOPDOWN_RETIRING.ALL",
+        "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0",
         "SampleAfterValue": "1000003"
     },
     {
@@ -629,6 +667,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.ALL",
+        "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -636,6 +675,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.IDIV",
+        "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -644,7 +684,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.MS",
-        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
+        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -653,6 +693,7 @@
         "Counter": "0,1,2,3,4,5",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.X87",
+        "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     }
diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json
index d9c737a17df0..c348046696bf 100644
--- a/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/alderlaken/virtual-memory.json
@@ -57,6 +57,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13"
     },
@@ -67,6 +68,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_LOADS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11"
     },
@@ -77,6 +79,7 @@
         "Deprecated": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
+        "PublicDescription": "This event is deprecated. Refer to new event MEM_UOPS_RETIRED.STLB_MISS_STORES Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12"
     }
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json b/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json
index 7ddb89dd1871..b22a02450e6c 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/arl-metrics.json
@@ -75,7 +75,7 @@
         "MetricExpr": "tma_core_bound",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
-        "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -85,7 +85,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "(tma_backend_bound >0.10)",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%",
@@ -97,7 +97,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "(tma_bad_speculation >0.15)",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%",
@@ -108,7 +108,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -118,7 +118,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MISPREDICT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "(tma_branch_mispredicts >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -128,7 +128,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
-        "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -137,7 +137,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.CISC@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "(tma_cisc >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -146,7 +146,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "(tma_core_bound >0.10) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -156,7 +156,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
-        "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -165,7 +165,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
-        "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -175,7 +175,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "(tma_frontend_bound >0.20)",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -185,7 +185,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ICACHE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "(tma_icache_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -194,7 +194,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
-        "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -204,7 +204,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
-        "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -590,7 +590,7 @@
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE_P@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
         "MetricName": "tma_info_system_mux",
-        "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9",
         "Unit": "cpu_atom"
     },
     {
@@ -629,7 +629,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.ITLB_MISS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "(tma_itlb_misses >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -638,7 +638,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "(tma_machine_clears >0.05) & ((tma_bad_speculation >0.15))",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -648,7 +648,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
-        "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -657,7 +657,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
-        "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -666,7 +666,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
-        "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -675,7 +675,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
-        "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -684,7 +684,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
-        "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -693,7 +693,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
-        "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -702,7 +702,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
-        "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -711,7 +711,7 @@
         "MetricExpr": "tma_backend_bound - tma_core_bound",
         "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
-        "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -722,7 +722,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "Default;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "(tma_retiring >0.75)",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1;Default",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
@@ -732,7 +732,7 @@
         "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
         "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
-        "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%",
         "Unit": "cpu_atom"
     },
@@ -744,7 +744,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "cpu_core@UOPS_DISPATCHED.ALU@ / (6 * tma_info_thread_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -757,13 +757,13 @@
         "MetricExpr": "78 * cpu_core@ASSISTS.ANY@ / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -774,7 +774,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-be\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -786,18 +786,18 @@
     {
         "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-bad\\-spec / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-bad\\-spec@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20",
@@ -814,11 +814,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
-        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full",
+        "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full",
         "Unit": "cpu_core"
     },
     {
@@ -826,22 +826,22 @@
         "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
-        "MetricThreshold": "(tma_bottleneck_cache_memory_latency > 20)",
+        "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
         "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy",
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20",
@@ -849,7 +849,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_lsd + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + cpu_core@RS.EMPTY_RESOURCE@ / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -861,7 +861,7 @@
         "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_capacity + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
-        "MetricThreshold": "(tma_bottleneck_memory_data_tlbs > 20)",
+        "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
         "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store",
         "Unit": "cpu_core"
     },
@@ -870,13 +870,13 @@
         "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
-        "MetricThreshold": "(tma_bottleneck_memory_synchronization > 10)",
+        "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
         "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -888,12 +888,12 @@
         "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)",
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
-        "MetricThreshold": "(tma_bottleneck_other_bottlenecks > 20)",
+        "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
         "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls.",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ + 2 * cpu_core@BR_INST_RETIRED.NEAR_CALL@ + cpu_core@INST_RETIRED.NOP@) / tma_info_thread_slots - tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -902,7 +902,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-br\\-mispredict@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -916,26 +916,26 @@
         "MetricExpr": "cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C01@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.C02@ / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -944,8 +944,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -954,99 +954,100 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
-        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@frontend_retired.l1i_miss@R / tma_info_thread_clks - tma_code_l2_miss)",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
+        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.L1I_MISS@ * cpu_core@FRONTEND_RETIRED.L1I_MISS@R / tma_info_thread_clks - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@frontend_retired.l2_miss@R / tma_info_thread_clks",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.L2_MISS@ * cpu_core@FRONTEND_RETIRED.L2_MISS@R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
-        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@frontend_retired.itlb_miss@R / tma_info_thread_clks - tma_code_stlb_miss)",
+        "MetricExpr": "max(0, cpu_core@FRONTEND_RETIRED.ITLB_MISS@ * cpu_core@FRONTEND_RETIRED.ITLB_MISS@R / tma_info_thread_clks - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@frontend_retired.stlb_miss@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.STLB_MISS@ * cpu_core@FRONTEND_RETIRED.STLB_MISS@R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "cpu_core@ITLB_MISSES.WALK_ACTIVE@ / tma_info_thread_clks * cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ / (cpu_core@ITLB_MISSES.WALK_COMPLETED_4K@ + cpu_core@ITLB_MISSES.WALK_COMPLETED_2M_4M@)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@br_misp_retired.cond_ntaken_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@ * cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_nt_mispredicts",
-        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@br_misp_retired.cond_taken_bwd_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_tk_bwd_mispredicts",
-        "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@br_misp_retired.cond_taken_fwd_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@ * cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_tk_fwd_mispredicts",
-        "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * cpu_core@mem_load_l3_hit_retired.xsnp_miss@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_miss@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_hitm@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1057,17 +1058,18 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricExpr": "((min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_no_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R, cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_l3_hit_retired.xsnp_fwd@R else cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, 24 * tma_info_system_core_frequency) + cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@ * min(cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, 25 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1076,7 +1078,7 @@
         "MetricExpr": "cpu_core@ARITH.DIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1086,7 +1088,7 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.MEM@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1097,7 +1099,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1106,28 +1108,28 @@
         "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * cpu_core@mem_inst_retired.stlb_hit_loads@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_loads@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * 7) / tma_info_thread_clks + tma_load_stlb_miss",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R, 7) / tma_info_thread_clks + tma_load_stlb_miss",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * cpu_core@mem_inst_retired.stlb_hit_stores@R, cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) if 0 < cpu_core@mem_inst_retired.stlb_hit_stores@R else cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * 7) / tma_info_thread_clks + tma_store_stlb_miss",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R, 7) / tma_info_thread_clks + tma_store_stlb_miss",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1136,7 +1138,7 @@
         "MetricExpr": "28 * tma_info_system_core_frequency * cpu_core@OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM@ / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "(tma_false_sharing > 0.05) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -1147,7 +1149,7 @@
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1158,18 +1160,18 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
-        "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-fetch\\-lat@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1179,7 +1181,7 @@
         "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0",
         "MetricName": "tma_few_uops_instructions",
         "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1189,7 +1191,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1199,16 +1201,16 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "cpu_core@ARITH.FPDIV_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1217,8 +1219,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1227,8 +1229,8 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1237,8 +1239,8 @@
         "MetricExpr": "(cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE@) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1247,15 +1249,15 @@
         "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-fe\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvFB;BvIO;Default;PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
@@ -1265,23 +1267,23 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.MACRO_FUSED@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
+        "MetricExpr": "cpu_core@topdown\\-heavy\\-ops@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1290,26 +1292,26 @@
         "MetricExpr": "cpu_core@ICACHE_DATA.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_call_mispredicts",
-        "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions",
-        "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@br_misp_retired.indirect_cost@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@br_misp_retired.indirect_call_cost@R) / tma_info_thread_clks, 0)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions.",
+        "MetricExpr": "max((cpu_core@BR_MISP_RETIRED.INDIRECT_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_COST@R - cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@ * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R) / tma_info_thread_clks, 0)",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ind_jump_mispredicts",
-        "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -1322,7 +1324,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_NTAKEN@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
@@ -1330,29 +1332,29 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_bwd",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_fwd",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.INDIRECT@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_MISP_RETIRED.RET@",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -1376,7 +1378,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_lsd + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -1385,7 +1387,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -1394,10 +1396,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
         "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ",
         "Unit": "cpu_core"
     },
     {
@@ -1463,12 +1466,12 @@
         "MetricExpr": "(cpu_core@FP_ARITH_DISPATCHED.V0@ + cpu_core@FP_ARITH_DISPATCHED.V1@ + cpu_core@FP_ARITH_DISPATCHED.V2@ + cpu_core@FP_ARITH_DISPATCHED.V3@) / (4 * tma_info_thread_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)",
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp",
         "Unit": "cpu_core"
@@ -1483,15 +1486,15 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES@ / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@frontend_retired.any_dsb_miss@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@ * cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@R / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;Fed;FetchLat",
         "MetricName": "tma_info_frontend_dsb_switches_ret",
         "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05",
@@ -1499,7 +1502,7 @@
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@UOPS_ISSUED.ANY@ / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc",
         "Unit": "cpu_core"
@@ -1549,7 +1552,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@frontend_retired.ms_flows@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.MS_FLOWS@ * cpu_core@FRONTEND_RETIRED.MS_FLOWS@R / tma_info_thread_clks",
         "MetricGroup": "Fed;FetchLat;MicroSeq",
         "MetricName": "tma_info_frontend_ms_latency_ret",
         "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05",
@@ -1564,21 +1567,21 @@
     },
     {
         "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
-        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed",
         "MetricName": "tma_info_frontend_unknown_branch_cost",
-        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node",
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node.",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears",
-        "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@frontend_retired.unknown_branch@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@ * cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@R / tma_info_thread_clks",
         "MetricGroup": "Fed;FetchLat",
         "MetricName": "tma_info_frontend_unknown_branches_ret",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "cpu_core@BR_INST_RETIRED.ALL_BRANCHES@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch",
@@ -1598,7 +1601,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW",
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW.",
         "Unit": "cpu_core"
     },
     {
@@ -1607,7 +1610,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1616,7 +1619,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1625,7 +1628,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1634,7 +1637,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting.",
         "Unit": "cpu_core"
     },
     {
@@ -1697,7 +1700,7 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 8 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 17",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
         "Unit": "cpu_core"
     },
@@ -1709,6 +1712,13 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricExpr": "64 * cpu_core@L1D.REPLACEMENT@ / 1e9 / tma_info_system_time",
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l1d_cache_fill_bw",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Average per-thread data fill bandwidth to the Level 0 within L1D cache [GB / sec]",
         "MetricExpr": "64 * cpu_core@L1D.L0_REPLACEMENT@ / 1e9 / tma_info_system_time",
         "MetricGroup": "Mem;MemoryBW",
@@ -1815,7 +1825,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD@ / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp",
         "Unit": "cpu_core"
@@ -1873,7 +1883,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@mem_inst_retired.stlb_miss_loads@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@R / tma_info_thread_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret",
         "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05",
@@ -1896,7 +1906,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@mem_inst_retired.stlb_miss_stores@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@ * cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@R / tma_info_thread_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret",
         "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05",
@@ -1935,20 +1945,20 @@
         "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@ASSISTS.ANY@",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "MetricExpr": "cpu_core@INST_RETIRED.REP_ITERATION@ / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "MicroSeq;Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
@@ -1993,23 +2003,22 @@
     },
     {
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
-        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / BR_INST_RETIRED.FAR_BRANCH:u",
+        "MetricExpr": "cpu_core@INST_RETIRED.ANY@ / cpu_core@BR_INST_RETIRED.FAR_BRANCH@u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000",
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@INST_RETIRED.ANY_P@k",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
+        "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD_P@k / cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_utilization",
         "MetricThreshold": "tma_info_system_kernel_utilization > 0.05",
@@ -2053,7 +2062,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.THREAD@",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks",
@@ -2064,7 +2073,6 @@
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
         "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr",
         "Unit": "cpu_core"
     },
     {
@@ -2072,7 +2080,7 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.THREAD@ / cpu_core@UOPS_ISSUED.ANY@",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage",
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.",
         "Unit": "cpu_core"
     },
     {
@@ -2084,7 +2092,7 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "cpu_core@TOPDOWN.SLOTS@",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots",
         "Unit": "cpu_core"
@@ -2102,15 +2110,15 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu_core@BR_INST_RETIRED.NEAR_TAKEN@",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 8 * 1.5",
+        "MetricThreshold": "tma_info_thread_uptb < 12",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2120,7 +2128,7 @@
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_int_operations",
         "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2129,8 +2137,8 @@
         "MetricExpr": "cpu_core@INT_VEC_RETIRED.128BIT@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
-        "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2139,8 +2147,8 @@
         "MetricExpr": "cpu_core@INT_VEC_RETIRED.256BIT@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
-        "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2149,8 +2157,8 @@
         "MetricExpr": "cpu_core@ICACHE_TAG.STALLS@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2159,17 +2167,17 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.L1@ / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * cpu_core@mem_load_retired.l1_hit_l1@R, cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) if 0 < cpu_core@mem_load_retired.l1_hit_l1@R else cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * 9) / tma_info_thread_clks",
+        "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache.",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@ * min(cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@R, 9) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_capacity",
-        "MetricThreshold": "tma_l1_latency_capacity > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_capacity > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2178,8 +2186,8 @@
         "MetricExpr": "4 * cpu_core@DEPENDENT_LOADS.ANY@ / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: DEPENDENT_LOADS.ANY",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2188,17 +2196,18 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.L2@ / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * cpu_core@mem_load_retired.l2_hit@R, cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@mem_load_retired.l2_hit@R else cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * (3 * tma_info_system_core_frequency)) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L2_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2208,18 +2217,19 @@
         "MetricExpr": "cpu_core@MEMORY_STALLS.L3@ / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * cpu_core@mem_load_retired.l3_hit@R, cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@mem_load_retired.l3_hit@R else cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "cpu_core@MEM_LOAD_RETIRED.L3_HIT@ * min(cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, 9 * tma_info_system_core_frequency) * (1 + cpu_core@MEM_LOAD_RETIRED.FB_HIT@ / cpu_core@MEM_LOAD_RETIRED.L1_MISS@ / 2) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2228,19 +2238,19 @@
         "MetricExpr": "cpu_core@DECODE.LCP@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2250,7 +2260,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_load_op_utilization",
         "MetricThreshold": "tma_load_op_utilization > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.LOAD",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2259,7 +2269,7 @@
         "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2268,43 +2278,43 @@
         "MetricExpr": "cpu_core@DTLB_LOAD_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_LOAD_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
-        "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@mem_inst_retired.lock_loads@R / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2315,7 +2325,7 @@
         "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_lsd",
         "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit.  LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2326,17 +2336,17 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2345,34 +2355,34 @@
         "MetricExpr": "min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD@) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
-        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-mem\\-bound@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * cpu_core@MISC2_RETIRED.LFENCE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
-        "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * cpu_core@MEM_UOP_RETIRED.ANY@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -2395,14 +2405,14 @@
         "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * cpu_core@INT_MISC.CLEAR_RESTEER_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)",
-        "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks",
+        "MetricExpr": "(cpu_core@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / 2 + cpu_core@IDQ.MITE_UOPS@ / (cpu_core@IDQ.DSB_UOPS@ + cpu_core@IDQ.MITE_UOPS@) * (cpu_core@IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE@ - cpu_core@IDQ_BUBBLES.FETCH_LATENCY@)) / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
@@ -2411,17 +2421,17 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "160 * cpu_core@ASSISTS.SSE_AVX_MIX@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
         "MetricExpr": "cpu_core@IDQ.MS_CYCLES_ANY@ / tma_info_thread_clks",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
@@ -2434,7 +2444,7 @@
         "MetricExpr": "3 * cpu_core@IDQ.MS_SWITCHES@ / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2445,7 +2455,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2454,7 +2464,7 @@
         "MetricExpr": "tma_light_operations * cpu_core@INST_RETIRED.NOP@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2470,20 +2480,20 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - cpu_core@BR_MISP_RETIRED.ALL_BRANCHES@ / (cpu_core@INT_MISC.CLEARS_COUNT@ - cpu_core@MACHINE_CLEARS.COUNT@)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - cpu_core@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_core@MACHINE_CLEARS.COUNT@), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2493,7 +2503,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2502,8 +2512,8 @@
         "MetricExpr": "((cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ + (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@)) / tma_info_thread_clks if cpu_core@ARITH.DIV_ACTIVE@ < cpu_core@CYCLE_ACTIVITY.STALLS_TOTAL@ - cpu_core@EXE_ACTIVITY.BOUND_ON_LOADS@ else (cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ + tma_retiring * cpu_core@EXE_ACTIVITY.2_3_PORTS_UTIL@) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2512,8 +2522,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.EXE_BOUND_0_PORTS@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2522,7 +2532,7 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.1_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2533,8 +2543,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.2_PORTS_UTIL@ / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2544,24 +2554,24 @@
         "MetricExpr": "cpu_core@UOPS_EXECUTED.CYCLES_GE_3@ / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions",
-        "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@br_misp_retired.ret_cost@R / tma_info_thread_clks",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions.",
+        "MetricExpr": "cpu_core@BR_MISP_RETIRED.RET_COST@ * cpu_core@BR_MISP_RETIRED.RET_COST@R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_ret_mispredicts",
-        "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_ret_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "cpu_core@topdown\\-retiring@ / (cpu_core@topdown\\-fe\\-bound@ + cpu_core@topdown\\-bad\\-spec@ + cpu_core@topdown\\-retiring@ + cpu_core@topdown\\-be\\-bound@) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2575,8 +2585,8 @@
         "MetricExpr": "(cpu_core@BE_STALLS.SCOREBOARD@ + cpu_core@CPU_CLK_UNHALTED.C02@) / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: BE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2585,8 +2595,8 @@
         "MetricExpr": "tma_light_operations * cpu_core@INT_VEC_RETIRED.SHUFFLES@ / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_shuffles_256b",
-        "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+        "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2596,28 +2606,28 @@
         "MetricExpr": "cpu_core@CPU_CLK_UNHALTED.PAUSE@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * cpu_core@mem_inst_retired.split_loads@R, cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@mem_inst_retired.split_loads@R else cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R, tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
         "BriefDescription": "This metric represents rate of split store accesses",
-        "MetricExpr": "(min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * cpu_core@mem_inst_retired.split_stores@R, cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) if 0 < cpu_core@mem_inst_retired.split_stores@R else cpu_core@MEM_INST_RETIRED.SPLIT_STORES@) / tma_info_thread_clks",
+        "MetricExpr": "cpu_core@MEM_INST_RETIRED.SPLIT_STORES@ * min(cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R, 1) / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2626,8 +2636,8 @@
         "MetricExpr": "(cpu_core@XQ.FULL@ + cpu_core@L1D_MISS.L2_STALLS@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2636,8 +2646,8 @@
         "MetricExpr": "cpu_core@EXE_ACTIVITY.BOUND_ON_STORES@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2646,8 +2656,8 @@
         "MetricExpr": "13 * cpu_core@LD_BLOCKS.STORE_FORWARD@ / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2656,8 +2666,8 @@
         "MetricExpr": "(cpu_core@MEM_STORE_RETIRED.L2_HIT@ * 10 * (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) + (1 - cpu_core@MEM_INST_RETIRED.LOCK_LOADS@ / cpu_core@MEM_INST_RETIRED.ALL_STORES@) * min(cpu_core@CPU_CLK_UNHALTED.THREAD@, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO@)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2667,7 +2677,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_store_op_utilization",
         "MetricThreshold": "tma_store_op_utilization > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.STD, UOPS_DISPATCHED.STA",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2676,7 +2686,7 @@
         "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2685,34 +2695,34 @@
         "MetricExpr": "cpu_core@DTLB_STORE_MISSES.WALK_ACTIVE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ / (cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_4K@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M@ + cpu_core@DTLB_STORE_MISSES.WALK_COMPLETED_1G@)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     },
@@ -2721,7 +2731,7 @@
         "MetricExpr": "9 * cpu_core@OCR.STREAMING_WR.ANY_RESPONSE@ / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2731,7 +2741,7 @@
         "MetricExpr": "cpu_core@INT_MISC.UNKNOWN_BRANCH_CYCLES@ / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
@@ -2741,8 +2751,8 @@
         "MetricExpr": "tma_retiring * cpu_core@UOPS_EXECUTED.X87@ / cpu_core@UOPS_EXECUTED.THREAD@",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%",
         "Unit": "cpu_core"
     }
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json
index f63594b2cca8..70175404540d 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/cache.json
@@ -9,6 +9,16 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x51",
+        "EventName": "DL1.DIRTY_EVICTION",
+        "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.  Does not count evictions or dirty writebacks caused by snoops.  Does not count a replacement unless a (dirty) line was written back.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Counts the number of cache lines replaced in L0 data cache.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x51",
@@ -19,6 +29,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Cachelines replaced into the L0 and L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x51",
+        "EventName": "L1D.REPLACEMENT",
+        "PublicDescription": "Counts cachelines replaced into the L0 and L1 d-cache.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x49",
@@ -80,6 +100,46 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.E",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.F",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x10",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.M",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.S",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x26",
@@ -90,6 +150,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x26",
+        "EventName": "L2_LINES_OUT.NON_SILENT",
+        "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x26",
@@ -100,6 +170,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x26",
+        "EventName": "L2_LINES_OUT.SILENT",
+        "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill.  Increments on the core that brought the line in originally.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x26",
@@ -129,6 +209,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.HIT",
+        "SampleAfterValue": "200003",
+        "UMask": "0x2",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x24",
@@ -139,6 +228,34 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.MISS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject  short and long rejects (includes those counted in L2_reject_XQ.any), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.REJECTS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "L2 code requests",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x24",
+        "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "PublicDescription": "Counts the total number of L2 code requests.",
+        "SampleAfterValue": "200003",
+        "UMask": "0xe4",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Demand Data Read access L2 cache",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0x24",
@@ -409,12 +526,21 @@
         "Unit": "cpu_lowpower"
     },
     {
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x80",
+        "Unit": "cpu_lowpower"
+    },
+    {
         "BriefDescription": "Counts all retired load instructions.",
         "Counter": "0,1,2,3",
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts Instructions with at least one architecturally visible load retired.",
+        "PublicDescription": "Counts Instructions with at least one architecturally visible load retired. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81",
         "Unit": "cpu_core"
@@ -425,7 +551,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82",
         "Unit": "cpu_core"
@@ -435,7 +561,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_SWPF",
-        "PublicDescription": "Counts all retired software prefetch instructions.",
+        "PublicDescription": "Counts all retired software prefetch instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x84",
         "Unit": "cpu_core"
@@ -446,7 +572,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x87",
         "Unit": "cpu_core"
@@ -457,7 +583,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x21",
         "Unit": "cpu_core"
@@ -468,7 +594,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41",
         "Unit": "cpu_core"
@@ -479,7 +605,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x42",
         "Unit": "cpu_core"
@@ -490,7 +616,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
-        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x9",
         "Unit": "cpu_core"
@@ -501,7 +627,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES",
-        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xa",
         "Unit": "cpu_core"
@@ -512,7 +638,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11",
         "Unit": "cpu_core"
@@ -523,7 +649,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12",
         "Unit": "cpu_core"
@@ -534,7 +660,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)",
+        "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$) Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -545,7 +671,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -556,7 +682,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -567,7 +693,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -578,7 +704,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -589,7 +715,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -600,7 +726,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -610,6 +736,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "Unit": "cpu_core"
     },
@@ -619,7 +746,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -630,7 +757,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -641,7 +768,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -652,7 +779,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x4",
         "Unit": "cpu_core"
@@ -663,7 +790,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -1246,12 +1373,25 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x40001E00001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1263,6 +1403,19 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x20001E00001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1274,6 +1427,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x40001E00002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json
index fc5f4dd50fe6..67cc83de18d3 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/frontend.json
@@ -65,7 +65,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
+        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -77,7 +77,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -89,7 +89,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -119,7 +119,7 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -140,7 +140,7 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -152,7 +152,7 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -164,7 +164,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -176,7 +176,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -188,7 +188,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -200,7 +200,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -212,7 +212,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -224,7 +224,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -236,7 +236,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -248,7 +248,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -260,7 +260,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -272,7 +272,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -284,7 +284,7 @@
         "EventName": "FRONTEND_RETIRED.MISP_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "ANT retired branches that got just mispredicted",
+        "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -296,6 +296,7 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "Counts flows delivered by the Microcode Sequencer Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -307,7 +308,7 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
@@ -319,7 +320,7 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
-        "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/memory.json b/tools/perf/pmu-events/arch/x86/arrowlake/memory.json
index 08f01fc66fef..fb8d4ac69bda 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/memory.json
@@ -163,7 +163,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x400",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "53",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -176,7 +176,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "1009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -189,7 +189,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -202,7 +202,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x800",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "23",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -215,7 +215,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "503",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -228,7 +228,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -241,7 +241,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -254,7 +254,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "101",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -267,7 +267,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "2003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -280,7 +280,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
-        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -291,7 +291,7 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -333,12 +333,25 @@
         "Unit": "cpu_lowpower"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1E780000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0xFE7F8000001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -350,6 +363,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0xFE7F8000002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/other.json b/tools/perf/pmu-events/arch/x86/arrowlake/other.json
index 0175b2193201..51bc763a5887 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/other.json
@@ -19,71 +19,6 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0xa2",
-        "EventName": "BE_STALLS.SCOREBOARD",
-        "SampleAfterValue": "100003",
-        "UMask": "0x2",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or  2 cycles back. This event supports in-direct dependency through a single uop.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x02",
-        "EventName": "DEPENDENT_LOADS.ANY",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on secondary integer ports 0,1,2,3.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.2ND",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x80",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on a load port.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.LD",
-        "PublicDescription": "Counts the number of uops executed on a load port.  This event counts for integer uops even if the destination is FP/vector",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on integer port  0,1, 2, 3.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.PRIMARY",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x78",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on a Store address port.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.STA",
-        "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb3",
-        "EventName": "INT_UOPS_EXECUTED.STD_JMP",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS]",
         "Counter": "0,1,2,3,4,5,6,7",
         "Deprecated": "1",
@@ -94,81 +29,13 @@
         "Unit": "cpu_lowpower"
     },
     {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.L1",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.L2",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.L3",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0x46",
-        "EventName": "MEMORY_STALLS.MEM",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x8",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1E780000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
         "BriefDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -180,6 +47,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -191,6 +59,7 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -202,70 +71,12 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "CounterMask": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_COUNT",
-        "Invert": "1",
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
-        "Counter": "0,1,2,3,4,5,6,7,8,9",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_RESOURCE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_core"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x4",
-        "Unit": "cpu_atom"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "200003",
-        "UMask": "0x4",
-        "Unit": "cpu_lowpower"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots where no uop could issue due to an IQ scoreboard that stalls allocation until a specified older uop retires or (in the case of jump scoreboard) executes. Commonly executed instructions with IQ scoreboards include LFENCE and MFENCE.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.IQ_JEU_SCB",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1",
-        "Unit": "cpu_atom"
-    },
-    {
         "BriefDescription": "Cycles the uncore cannot take further requests",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "CounterMask": "1",
diff --git a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json
index 6dbde51e7ead..18a22368b99b 100644
--- a/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/arrowlake/pipeline.json
@@ -52,6 +52,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0xa2",
+        "EventName": "BE_STALLS.SCOREBOARD",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts the total number of branch instructions retired for all branch types.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
@@ -65,7 +74,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all branch instructions retired.",
+        "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -92,7 +101,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PublicDescription": "Counts conditional branch instructions retired.",
+        "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x111",
         "Unit": "cpu_core"
@@ -111,7 +120,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts not taken branch instructions retired.",
+        "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -130,7 +139,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional branch instructions retired.",
+        "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x101",
         "Unit": "cpu_core"
@@ -149,7 +158,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD",
-        "PublicDescription": "Counts taken backward conditional branch instructions retired.",
+        "PublicDescription": "Counts taken backward conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -159,7 +168,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD",
-        "PublicDescription": "Counts taken forward conditional branch instructions retired.",
+        "PublicDescription": "Counts taken forward conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x102",
         "Unit": "cpu_core"
@@ -178,7 +187,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PublicDescription": "Counts far branch instructions retired.",
+        "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40",
         "Unit": "cpu_core"
@@ -206,7 +215,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -261,7 +270,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -289,7 +298,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts return instructions retired.",
+        "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -308,7 +317,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts taken branch instructions retired.",
+        "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -363,7 +372,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -381,6 +390,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST",
+        "PublicDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x44",
         "Unit": "cpu_core"
@@ -399,7 +409,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x111",
         "Unit": "cpu_core"
@@ -418,6 +428,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_COST",
+        "PublicDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x151",
         "Unit": "cpu_core"
@@ -427,7 +438,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -437,6 +448,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST",
+        "PublicDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x50",
         "Unit": "cpu_core"
@@ -455,7 +467,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x101",
         "Unit": "cpu_core"
@@ -474,7 +486,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD",
-        "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -484,6 +496,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST",
+        "PublicDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x8001",
         "Unit": "cpu_core"
@@ -493,6 +506,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST",
+        "PublicDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x141",
         "Unit": "cpu_core"
@@ -502,7 +516,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD",
-        "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "Unit": "cpu_core"
     },
@@ -511,6 +525,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST",
+        "PublicDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x8002",
         "Unit": "cpu_core"
@@ -529,7 +544,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80",
         "Unit": "cpu_core"
@@ -557,7 +572,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -576,6 +591,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST",
+        "PublicDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x42",
         "Unit": "cpu_core"
@@ -585,6 +601,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_COST",
+        "PublicDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xc0",
         "Unit": "cpu_core"
@@ -603,7 +620,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20",
         "Unit": "cpu_core"
@@ -622,6 +639,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST",
+        "PublicDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x60",
         "Unit": "cpu_core"
@@ -631,7 +649,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -659,6 +677,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET_COST",
+        "PublicDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x48",
         "Unit": "cpu_core"
@@ -889,6 +908,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or  2 cycles back. This event supports in-direct dependency through a single uop.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x02",
+        "EventName": "DEPENDENT_LOADS.ANY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xa6",
@@ -982,6 +1010,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired.",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -990,7 +1019,7 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -999,6 +1028,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_lowpower"
@@ -1016,7 +1046,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_core"
     },
@@ -1033,6 +1063,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.BR_FUSED",
+        "PublicDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10",
         "Unit": "cpu_core"
@@ -1042,6 +1073,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x30",
         "Unit": "cpu_core"
@@ -1051,7 +1083,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1060,7 +1092,7 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1070,7 +1102,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -1140,6 +1172,53 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of uops executed on secondary integer ports 0,1,2,3.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.2ND",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x80",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on a load port.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.LD",
+        "PublicDescription": "Counts the number of uops executed on a load port.  This event counts for integer uops even if the destination is FP/vector",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on integer port  0,1, 2, 3.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.PRIMARY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x78",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on a Store address port.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.STA",
+        "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb3",
+        "EventName": "INT_UOPS_EXECUTED.STD_JMP",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Number of vector integer instructions retired of 128-bit vector-width.",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xe7",
@@ -1405,8 +1484,9 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+        "BriefDescription": "This event is deprecated.",
         "Counter": "0,1,2,3,4,5,6,7",
+        "Deprecated": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SLOW",
         "SampleAfterValue": "20003",
@@ -1433,6 +1513,42 @@
         "Unit": "cpu_lowpower"
     },
     {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.L1",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.L2",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.L3",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0x46",
+        "EventName": "MEMORY_STALLS.MEM",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "LFENCE instructions retired",
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xe0",
@@ -1447,6 +1563,7 @@
         "Counter": "0,1,2,3,4,5,6,7,8,9",
         "EventCode": "0xe4",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
+        "PublicDescription": "LBR record is inserted Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -1461,6 +1578,65 @@
         "Unit": "cpu_lowpower"
     },
     {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_COUNT",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
+        "Counter": "0,1,2,3,4,5,6,7,8,9",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4",
+        "Unit": "cpu_lowpower"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots where no uop could issue due to an IQ scoreboard that stalls allocation until a specified older uop retires or (in the case of jump scoreboard) executes. Commonly executed instructions with IQ scoreboards include LFENCE and MFENCE.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.IQ_JEU_SCB",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x75",
diff --git a/tools/perf/pmu-events/arch/x86/bonnell/other.json b/tools/perf/pmu-events/arch/x86/bonnell/other.json
index 3a55c101fbf7..6e6f64b96834 100644
--- a/tools/perf/pmu-events/arch/x86/bonnell/other.json
+++ b/tools/perf/pmu-events/arch/x86/bonnell/other.json
@@ -324,14 +324,6 @@
         "UMask": "0x2"
     },
     {
-        "BriefDescription": "Memory cluster signals to block micro-op dispatch for any reason",
-        "Counter": "0,1",
-        "EventCode": "0x9",
-        "EventName": "DISPATCH_BLOCKED.ANY",
-        "SampleAfterValue": "200000",
-        "UMask": "0x20"
-    },
-    {
         "BriefDescription": "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions",
         "Counter": "0,1",
         "EventCode": "0x3A",
diff --git a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
index 9ff032ab11e2..48d3d053a369 100644
--- a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
@@ -212,6 +212,14 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Memory cluster signals to block micro-op dispatch for any reason",
+        "Counter": "0,1",
+        "EventCode": "0x9",
+        "EventName": "DISPATCH_BLOCKED.ANY",
+        "SampleAfterValue": "200000",
+        "UMask": "0x20"
+    },
+    {
         "BriefDescription": "Divide operations retired",
         "Counter": "0,1",
         "EventCode": "0x13",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
index 40970fa5566c..89750117a7f6 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
@@ -74,12 +74,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
@@ -92,8 +92,8 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
@@ -104,7 +104,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
     {
@@ -114,7 +114,7 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
@@ -125,7 +125,7 @@
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_mispredicts_resteers",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
     {
@@ -133,8 +133,8 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -143,8 +143,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -152,7 +152,7 @@
         "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -162,8 +162,8 @@
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -174,7 +174,7 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
@@ -183,8 +183,8 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -192,8 +192,8 @@
         "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.FPU_DIV_ACTIVE",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -202,8 +202,8 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -212,7 +212,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -220,26 +220,26 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -247,18 +247,18 @@
         "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -287,7 +287,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -295,8 +295,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -304,8 +304,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -313,8 +313,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -322,8 +322,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -333,33 +333,33 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.",
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -370,7 +370,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -391,11 +391,11 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -420,7 +420,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -438,7 +438,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -446,7 +446,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -454,7 +454,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -462,7 +462,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -470,7 +470,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -512,7 +512,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -634,20 +634,20 @@
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks",
+        "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_page_walks_utilization",
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -688,14 +688,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -743,7 +742,7 @@
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -752,15 +751,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -786,14 +784,14 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
-        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
         "ScaleUnit": "100%"
     },
@@ -802,8 +800,8 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -811,8 +809,8 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -821,8 +819,8 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -831,8 +829,8 @@
         "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -840,18 +838,18 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -870,8 +868,8 @@
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -882,15 +880,15 @@
         "MetricName": "tma_machine_clears",
         "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -899,7 +897,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -911,7 +909,7 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
@@ -928,8 +926,8 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
     {
@@ -938,7 +936,7 @@
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.",
         "ScaleUnit": "100%"
     },
     {
@@ -946,8 +944,8 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
     {
@@ -956,7 +954,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -965,7 +963,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1001,7 +999,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1010,7 +1008,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1028,43 +1026,43 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1084,7 +1082,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1092,8 +1090,8 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1101,7 +1099,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1110,8 +1108,8 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1119,8 +1117,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1129,8 +1127,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1146,7 +1144,7 @@
         "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -1155,8 +1153,8 @@
         "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
index b03a5f2bcd82..81175f0f2603 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
@@ -74,7 +74,7 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "(tma_4k_aliasing > 0.2) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
@@ -84,7 +84,7 @@
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
-        "MetricThreshold": "(tma_alu_op_utilization > 0.4)",
+        "MetricThreshold": "tma_alu_op_utilization > 0.4",
         "ScaleUnit": "100%"
     },
     {
@@ -92,7 +92,7 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "(tma_assists > 0.1) & ((tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1)))",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -102,7 +102,7 @@
         "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)",
         "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
-        "MetricThreshold": "(tma_backend_bound > 0.2)",
+        "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
         "ScaleUnit": "100%"
@@ -112,7 +112,7 @@
         "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots",
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
-        "MetricThreshold": "(tma_bad_speculation > 0.15)",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
@@ -123,7 +123,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
-        "MetricThreshold": "(tma_branch_mispredicts > 0.1) & ((tma_bad_speculation > 0.15))",
+        "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
@@ -133,7 +133,7 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "(tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
@@ -143,7 +143,7 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "(tma_cisc > 0.1) & ((tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1)))",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
@@ -152,7 +152,7 @@
         "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "(tma_clears_resteers > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -162,7 +162,7 @@
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "(tma_contested_accesses > 0.05) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -172,7 +172,7 @@
         "MetricExpr": "tma_backend_bound - tma_memory_bound",
         "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
-        "MetricThreshold": "(tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
@@ -183,7 +183,7 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "(tma_data_sharing > 0.05) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -192,7 +192,7 @@
         "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "(tma_divider > 0.2) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -202,7 +202,7 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "(tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -211,7 +211,7 @@
         "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
-        "MetricThreshold": "(tma_dsb > 0.15) & ((tma_fetch_bandwidth > 0.2))",
+        "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
         "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
@@ -220,7 +220,7 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "(tma_dsb_switches > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
@@ -229,7 +229,7 @@
         "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "(tma_dtlb_load > 0.1) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
@@ -238,7 +238,7 @@
         "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "(tma_dtlb_store > 0.05) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
@@ -248,7 +248,7 @@
         "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
-        "MetricThreshold": "(tma_fb_full > 0.3)",
+        "MetricThreshold": "tma_fb_full > 0.3",
         "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
@@ -257,7 +257,7 @@
         "MetricExpr": "tma_frontend_bound - tma_fetch_latency",
         "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
         "MetricName": "tma_fetch_bandwidth",
-        "MetricThreshold": "(tma_fetch_bandwidth > 0.2)",
+        "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
@@ -267,7 +267,7 @@
         "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_thread_slots",
         "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_fetch_latency",
-        "MetricThreshold": "(tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))",
+        "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
@@ -277,7 +277,7 @@
         "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector",
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
-        "MetricThreshold": "(tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))",
+        "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
         "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
@@ -286,7 +286,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "(tma_fp_scalar > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -295,7 +295,7 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "(tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -304,7 +304,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "(tma_fp_vector_128b > 0.1) & ((tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))))",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -313,7 +313,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "(tma_fp_vector_256b > 0.1) & ((tma_fp_vector > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6))))",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -322,7 +322,7 @@
         "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots",
         "MetricGroup": "BvFB;BvIO;PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
-        "MetricThreshold": "(tma_frontend_bound > 0.15)",
+        "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
@@ -332,7 +332,7 @@
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
-        "MetricThreshold": "(tma_heavy_operations > 0.1)",
+        "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%"
@@ -342,7 +342,7 @@
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "(tma_icache_misses > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
@@ -351,14 +351,14 @@
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "(tma_info_bad_spec_ipmisp_indirect < 1000)"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Bad;BadSpec;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmispredict",
-        "MetricThreshold": "(tma_info_bad_spec_ipmispredict < 200)"
+        "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200"
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
@@ -396,7 +396,7 @@
         "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_frontend_dsb_coverage",
-        "MetricThreshold": "(tma_info_frontend_dsb_coverage < 0.7) & ((tma_info_thread_ipc / 4) > 0.35)",
+        "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35",
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
@@ -429,7 +429,7 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
-        "MetricThreshold": "(tma_info_inst_mix_iparith < 10)",
+        "MetricThreshold": "tma_info_inst_mix_iparith < 10",
         "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
@@ -437,7 +437,7 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
-        "MetricThreshold": "(tma_info_inst_mix_iparith_avx128 < 10)",
+        "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
         "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
@@ -445,7 +445,7 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)",
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
-        "MetricThreshold": "(tma_info_inst_mix_iparith_avx256 < 10)",
+        "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
         "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
@@ -453,7 +453,7 @@
         "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
-        "MetricThreshold": "(tma_info_inst_mix_iparith_scalar_dp < 10)",
+        "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
         "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
@@ -461,7 +461,7 @@
         "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
-        "MetricThreshold": "(tma_info_inst_mix_iparith_scalar_sp < 10)",
+        "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
         "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
@@ -469,42 +469,42 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
         "MetricGroup": "Branches;Fed;InsType",
         "MetricName": "tma_info_inst_mix_ipbranch",
-        "MetricThreshold": "(tma_info_inst_mix_ipbranch < 8)"
+        "MetricThreshold": "tma_info_inst_mix_ipbranch < 8"
     },
     {
         "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_ipcall",
-        "MetricThreshold": "(tma_info_inst_mix_ipcall < 200)"
+        "MetricThreshold": "tma_info_inst_mix_ipcall < 200"
     },
     {
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_ipflop",
-        "MetricThreshold": "(tma_info_inst_mix_ipflop < 10)"
+        "MetricThreshold": "tma_info_inst_mix_ipflop < 10"
     },
     {
         "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipload",
-        "MetricThreshold": "(tma_info_inst_mix_ipload < 3)"
+        "MetricThreshold": "tma_info_inst_mix_ipload < 3"
     },
     {
         "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
         "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
         "MetricGroup": "InsType",
         "MetricName": "tma_info_inst_mix_ipstore",
-        "MetricThreshold": "(tma_info_inst_mix_ipstore < 8)"
+        "MetricThreshold": "tma_info_inst_mix_ipstore < 8"
     },
     {
         "BriefDescription": "Instructions per taken branch",
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "(tma_info_inst_mix_iptb < 4 * 2 + 1)",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -629,7 +629,7 @@
         "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_core_clks",
         "MetricGroup": "Mem;MemoryTLB",
         "MetricName": "tma_info_memory_tlb_page_walks_utilization",
-        "MetricThreshold": "(tma_info_memory_tlb_page_walks_utilization > 0.5)"
+        "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
         "BriefDescription": "",
@@ -680,7 +680,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "(tma_info_system_ipfarbranch < 1000000)"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
@@ -693,14 +693,14 @@
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "OS",
         "MetricName": "tma_info_system_kernel_utilization",
-        "MetricThreshold": "(tma_info_system_kernel_utilization > 0.05)"
+        "MetricThreshold": "tma_info_system_kernel_utilization > 0.05"
     },
     {
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Summary",
         "MetricName": "tma_info_system_mux",
-        "MetricThreshold": "((tma_info_system_mux > 1.1)|(tma_info_system_mux < 0.9))"
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
     },
     {
         "BriefDescription": "Total package Power in Watts",
@@ -725,7 +725,7 @@
         "MetricExpr": "duration_time",
         "MetricGroup": "Summary",
         "MetricName": "tma_info_system_time",
-        "MetricThreshold": "(tma_info_system_time < 1)"
+        "MetricThreshold": "tma_info_system_time < 1"
     },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
@@ -769,21 +769,21 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;Ret;Retire",
         "MetricName": "tma_info_thread_uoppi",
-        "MetricThreshold": "(tma_info_thread_uoppi > 1.05)"
+        "MetricThreshold": "tma_info_thread_uoppi > 1.05"
     },
     {
         "BriefDescription": "Uops per taken branch",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "(tma_info_thread_uptb < 4 * 1.5)"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "(tma_itlb_misses > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
@@ -792,7 +792,7 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "(tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -801,7 +801,7 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "(tma_l2_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -811,7 +811,7 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "(tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
@@ -821,7 +821,7 @@
         "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "(tma_l3_hit_latency > 0.1) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
         "ScaleUnit": "100%"
     },
@@ -830,7 +830,7 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "(tma_lcp > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
@@ -839,7 +839,7 @@
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
-        "MetricThreshold": "(tma_light_operations > 0.6)",
+        "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
@@ -850,7 +850,7 @@
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_load_op_utilization",
-        "MetricThreshold": "(tma_load_op_utilization > 0.6)",
+        "MetricThreshold": "tma_load_op_utilization > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10",
         "ScaleUnit": "100%"
     },
@@ -860,7 +860,7 @@
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "(tma_lock_latency > 0.2) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -870,7 +870,7 @@
         "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts",
         "MetricGroup": "BadSpec;BvMS;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
         "MetricName": "tma_machine_clears",
-        "MetricThreshold": "(tma_machine_clears > 0.1) & ((tma_bad_speculation > 0.15))",
+        "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears.  These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache",
         "ScaleUnit": "100%"
@@ -880,7 +880,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "(tma_mem_bandwidth > 0.2) & ((tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -889,7 +889,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "(tma_mem_latency > 0.1) & ((tma_dram_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -899,7 +899,7 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound",
         "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
-        "MetricThreshold": "(tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))",
+        "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
@@ -909,7 +909,7 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
         "MetricName": "tma_microcode_sequencer",
-        "MetricThreshold": "(tma_microcode_sequencer > 0.05) & ((tma_heavy_operations > 0.1))",
+        "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
         "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit.  The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -918,7 +918,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "(tma_mispredicts_resteers > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -927,7 +927,7 @@
         "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
-        "MetricThreshold": "(tma_mite > 0.1) & ((tma_fetch_bandwidth > 0.2))",
+        "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
         "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS",
         "ScaleUnit": "100%"
     },
@@ -936,7 +936,7 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "(tma_ms_switches > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15)))",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -945,7 +945,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks",
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
-        "MetricThreshold": "(tma_port_0 > 0.6)",
+        "MetricThreshold": "tma_port_0 > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -954,7 +954,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
-        "MetricThreshold": "(tma_port_1 > 0.6)",
+        "MetricThreshold": "tma_port_1 > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -963,7 +963,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group",
         "MetricName": "tma_port_2",
-        "MetricThreshold": "(tma_port_2 > 0.6)",
+        "MetricThreshold": "tma_port_2 > 0.6",
         "ScaleUnit": "100%"
     },
     {
@@ -971,7 +971,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group",
         "MetricName": "tma_port_3",
-        "MetricThreshold": "(tma_port_3 > 0.6)",
+        "MetricThreshold": "tma_port_3 > 0.6",
         "ScaleUnit": "100%"
     },
     {
@@ -979,7 +979,7 @@
         "MetricExpr": "tma_store_op_utilization",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group",
         "MetricName": "tma_port_4",
-        "MetricThreshold": "(tma_port_4 > 0.6)",
+        "MetricThreshold": "tma_port_4 > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Related metrics: tma_split_stores",
         "ScaleUnit": "100%"
     },
@@ -988,7 +988,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
-        "MetricThreshold": "(tma_port_5 > 0.6)",
+        "MetricThreshold": "tma_port_5 > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -997,7 +997,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
-        "MetricThreshold": "(tma_port_6 > 0.6)",
+        "MetricThreshold": "tma_port_6 > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -1006,7 +1006,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group",
         "MetricName": "tma_port_7",
-        "MetricThreshold": "(tma_port_7 > 0.6)",
+        "MetricThreshold": "tma_port_7 > 0.6",
         "ScaleUnit": "100%"
     },
     {
@@ -1015,7 +1015,7 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "(tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
@@ -1024,7 +1024,7 @@
         "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "(tma_ports_utilized_0 > 0.2) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
@@ -1033,7 +1033,7 @@
         "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "(tma_ports_utilized_1 > 0.2) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1042,7 +1042,7 @@
         "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "(tma_ports_utilized_2 > 0.15) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
@@ -1051,7 +1051,7 @@
         "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "(tma_ports_utilized_3m > 0.4) & ((tma_ports_utilization > 0.15) & ((tma_core_bound > 0.1) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%"
     },
@@ -1060,7 +1060,7 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots",
         "MetricGroup": "BvUW;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
-        "MetricThreshold": "((tma_retiring > 0.7)|(tma_heavy_operations > 0.1))",
+        "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved.  Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
         "ScaleUnit": "100%"
@@ -1071,7 +1071,7 @@
         "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
-        "MetricThreshold": "(tma_split_loads > 0.3)",
+        "MetricThreshold": "tma_split_loads > 0.3",
         "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
@@ -1080,7 +1080,7 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "(tma_split_stores > 0.2) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
@@ -1089,7 +1089,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "(tma_sq_full > 0.3) & ((tma_l3_bound > 0.05) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1098,7 +1098,7 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "(tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2)))",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
@@ -1107,7 +1107,7 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "(tma_store_fwd_blk > 0.1) & ((tma_l1_bound > 0.1) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
@@ -1117,7 +1117,7 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "(tma_store_latency > 0.1) & ((tma_store_bound > 0.2) & ((tma_memory_bound > 0.2) & ((tma_backend_bound > 0.2))))",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
@@ -1126,7 +1126,7 @@
         "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_store_op_utilization",
-        "MetricThreshold": "(tma_store_op_utilization > 0.6)",
+        "MetricThreshold": "tma_store_op_utilization > 0.6",
         "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8",
         "ScaleUnit": "100%"
     },
@@ -1135,7 +1135,7 @@
         "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "(tma_unknown_branches > 0.05) & ((tma_branch_resteers > 0.05) & ((tma_fetch_latency > 0.1) & ((tma_frontend_bound > 0.15))))",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%"
     },
@@ -1144,7 +1144,7 @@
         "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "(tma_x87_use > 0.1) & ((tma_fp_arith > 0.2) & ((tma_light_operations > 0.6)))",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
index 8016202bad1f..5d06a3f72be2 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
@@ -276,12 +276,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
@@ -294,8 +294,8 @@
         "MetricExpr": "66 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY_WB_ASSIST",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
@@ -306,7 +306,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
     {
@@ -316,7 +316,7 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
@@ -327,7 +327,7 @@
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_mispredicts_resteers",
+        "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction.  These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
     {
@@ -335,8 +335,8 @@
         "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -345,8 +345,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -354,7 +354,7 @@
         "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -364,8 +364,8 @@
         "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -376,7 +376,7 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
@@ -385,8 +385,8 @@
         "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -394,8 +394,8 @@
         "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.FPU_DIV_ACTIVE",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -404,8 +404,8 @@
         "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -414,7 +414,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -422,26 +422,26 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS. Related metrics: tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES. Related metrics: tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -449,18 +449,18 @@
         "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE, OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -489,7 +489,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -497,8 +497,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -506,8 +506,8 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -515,8 +515,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -524,8 +524,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -535,33 +535,33 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "tma_microcode_sequencer",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.",
         "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -572,7 +572,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -593,11 +593,11 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -622,7 +622,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -640,7 +640,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -648,7 +648,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -656,7 +656,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -664,7 +664,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -672,7 +672,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -714,7 +714,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -842,14 +842,14 @@
         "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -890,14 +890,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -908,14 +907,14 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@",
+        "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
     },
     {
         "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)",
-        "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)",
+        "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_system_socket_clks / tma_info_system_time)",
         "MetricGroup": "Mem;MemoryLat;SoC",
         "MetricName": "tma_info_system_mem_read_latency",
         "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)"
@@ -965,7 +964,7 @@
         "MetricName": "tma_info_system_uncore_frequency"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -974,15 +973,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1008,14 +1006,14 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
-        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
+        "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED",
         "ScaleUnit": "100%"
     },
@@ -1024,8 +1022,8 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
     {
@@ -1033,8 +1031,8 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1043,8 +1041,8 @@
         "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1053,8 +1051,8 @@
         "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT. Related metrics: tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1062,18 +1060,18 @@
         "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1091,8 +1089,8 @@
         "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1101,8 +1099,8 @@
         "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1118,10 +1116,10 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1130,7 +1128,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1142,7 +1140,7 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
@@ -1159,8 +1157,8 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
     {
@@ -1169,7 +1167,7 @@
         "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_mite",
         "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.",
         "ScaleUnit": "100%"
     },
     {
@@ -1177,8 +1175,8 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
     {
@@ -1187,7 +1185,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1196,7 +1194,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1232,7 +1230,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1241,7 +1239,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1259,43 +1257,43 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_thread_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
+        "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks)",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
-        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
+        "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1304,8 +1302,8 @@
         "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
@@ -1313,8 +1311,8 @@
         "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1334,7 +1332,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1342,8 +1340,8 @@
         "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1351,7 +1349,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1360,8 +1358,8 @@
         "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1369,8 +1367,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1379,8 +1377,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1396,7 +1394,7 @@
         "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -1405,8 +1403,8 @@
         "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json b/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json
index 8bad700ff8ea..d113c14aa7c9 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json
@@ -1,5 +1,79 @@
 [
     {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x20"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x10"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITI",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x40"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x8"
+    },
+    {
+        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xEF",
+        "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xFE",
+        "EventName": "IDI_MISC.WB_DOWNGRADE",
+        "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xFE",
+        "EventName": "IDI_MISC.WB_UPGRADE",
+        "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2"
+    },
+    {
         "BriefDescription": "L1D data line replacements",
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
@@ -2344,6 +2418,16 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all demand code reads have any response type.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP OCR.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -2704,6 +2788,116 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80400004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80400004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100400004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x800020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x400020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x200020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand code reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80020004",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads have any response type.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP OCR.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -3064,6 +3258,116 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80400001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80400001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100400001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x800020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x400020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x200020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80020001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.L3_HIT.ANY_SNOOP OCR.DEMAND_RFO.L3_HIT.ANY_SNOOP",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -3424,6 +3728,106 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80400002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80400002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100400002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F80020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x800020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x400020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x200020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x80020002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts any other requests OCR.OTHER.L3_HIT.ANY_SNOOP OCR.OTHER.L3_HIT.ANY_SNOOP",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 5729b93a9c68..6485b565acbc 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -313,12 +313,12 @@
         "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_4k_aliasing",
-        "MetricThreshold": "tma_4k_aliasing > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound)",
+        "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -330,7 +330,7 @@
         "MetricExpr": "34 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
@@ -341,7 +341,7 @@
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
         "ScaleUnit": "100%"
     },
     {
@@ -351,12 +351,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -371,7 +371,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -379,7 +379,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -387,22 +387,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * (tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * (10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts)) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + tma_core_bound * RS_EVENTS.EMPTY_CYCLES / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -410,7 +410,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_4k_aliasing + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -418,7 +418,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -426,7 +426,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -438,10 +438,10 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -463,8 +463,8 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
@@ -472,8 +472,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -481,7 +481,7 @@
         "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -490,7 +490,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -498,33 +498,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "((47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + (47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + 44 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -535,25 +535,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(47.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "44 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -562,7 +562,7 @@
         "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
         "ScaleUnit": "100%"
     },
@@ -572,7 +572,7 @@
         "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -582,7 +582,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -590,27 +590,27 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
@@ -619,18 +619,18 @@
         "MetricExpr": "(110 * tma_info_system_core_frequency * (OCR.DEMAND_RFO.L3_MISS.REMOTE_HITM + OCR.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_system_core_frequency * (OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM, OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / tma_info_thread_clks",
+        "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
         "MetricName": "tma_fb_full",
         "MetricThreshold": "tma_fb_full > 0.3",
-        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency",
+        "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -640,7 +640,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -650,7 +650,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -670,7 +670,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -679,7 +679,7 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
@@ -687,17 +687,17 @@
         "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@ / UOPS_RETIRED.RETIRE_SLOTS",
+        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -706,7 +706,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -715,7 +715,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -724,7 +724,7 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
         "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
@@ -735,35 +735,35 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_thread_slots",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+])",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
-        "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / tma_info_thread_clks",
+        "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -774,11 +774,11 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * BR_MISP_EXEC.INDIRECT)",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
@@ -803,7 +803,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -812,7 +812,7 @@
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -820,10 +820,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -852,7 +853,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },
@@ -877,14 +878,14 @@
     },
     {
         "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@) / (2 * tma_info_core_core_clks)",
+        "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -897,20 +898,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@ + 2",
+        "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -946,7 +947,7 @@
         "MetricName": "tma_info_frontend_tbpc"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -961,11 +962,11 @@
     {
         "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xFC@)",
+        "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)",
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -973,7 +974,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -981,7 +982,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -989,7 +990,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -997,7 +998,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -1005,7 +1006,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -1061,7 +1062,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 4 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 9",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1248,8 +1249,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1270,12 +1271,12 @@
         "MetricExpr": "INST_RETIRED.ANY / (FP_ASSIST.ANY + OTHER_ASSISTS.ANY)",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
@@ -1331,14 +1332,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1356,7 +1356,7 @@
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@",
+        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
@@ -1386,7 +1386,7 @@
         "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks)",
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license0_utilization",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
@@ -1394,7 +1394,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license1_utilization",
         "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
@@ -1402,7 +1402,7 @@
         "MetricGroup": "Power",
         "MetricName": "tma_info_system_power_license2_utilization",
         "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5",
-        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions"
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions."
     },
     {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
@@ -1436,7 +1436,7 @@
         "MetricName": "tma_info_system_uncore_frequency"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1445,15 +1445,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1479,15 +1478,15 @@
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 4 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 6"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1495,7 +1494,7 @@
         "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1504,17 +1503,17 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
+        "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1523,7 +1522,7 @@
         "MetricExpr": "3.5 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1532,17 +1531,17 @@
         "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(20.5 * tma_info_system_core_frequency - 3.5 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricExpr": "17 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1550,18 +1549,18 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "MetricExpr": "tma_retiring - tma_heavy_operations",
         "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1579,7 +1578,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1587,39 +1586,39 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory",
-        "MetricExpr": "(80 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "59.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
@@ -1628,7 +1627,7 @@
         "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1645,10 +1644,10 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1657,7 +1656,7 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
@@ -1669,11 +1668,11 @@
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1695,7 +1694,7 @@
         "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1709,12 +1708,12 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
@@ -1722,7 +1721,7 @@
         "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
         "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
@@ -1732,7 +1731,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%"
     },
     {
@@ -1740,8 +1739,8 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1754,19 +1753,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -1775,7 +1774,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1784,7 +1783,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1820,7 +1819,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_5",
         "MetricThreshold": "tma_port_5 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1829,7 +1828,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1846,8 +1845,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -1855,8 +1854,8 @@
         "MetricExpr": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -1864,7 +1863,7 @@
         "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -1873,35 +1872,35 @@
         "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_core_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+        "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).",
         "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_core_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
-        "MetricExpr": "((110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (110 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory",
-        "MetricExpr": "(147.5 * tma_info_system_core_frequency - 20.5 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "127 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1919,7 +1918,7 @@
         "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_thread_clks",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -1928,8 +1927,8 @@
         "MetricExpr": "40 * ROB_MISC_EVENTS.PAUSE_INST / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: ROB_MISC_EVENTS.PAUSE_INST",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST",
         "ScaleUnit": "100%"
     },
     {
@@ -1939,7 +1938,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1947,8 +1946,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES. Related metrics: tma_port_4",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -1956,7 +1955,7 @@
         "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -1965,8 +1964,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1974,8 +1973,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -1984,8 +1983,8 @@
         "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -2001,7 +2000,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -2009,31 +2008,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -2041,7 +2040,7 @@
         "MetricExpr": "9 * BACLEARS.ANY / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: BACLEARS.ANY",
         "ScaleUnit": "100%"
     },
@@ -2050,8 +2049,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/other.json b/tools/perf/pmu-events/arch/x86/cascadelakex/other.json
index f25693b17b8b..51833bce994e 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/other.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/other.json
@@ -36,62 +36,6 @@
         "UMask": "0x40"
     },
     {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDFE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x20"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IFWDM",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x10"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITFSE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_IHITI",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_IHITI",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDFE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x40"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_SFWDM",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x8"
-    },
-    {
-        "BriefDescription": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xEF",
-        "EventName": "CORE_SNOOP_RESPONSE.RSP_SHITFSE",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x4"
-    },
-    {
         "BriefDescription": "Number of hardware interrupts received by the processor.",
         "Counter": "0,1,2,3",
         "EventCode": "0xCB",
@@ -101,24 +45,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xFE",
-        "EventName": "IDI_MISC.WB_DOWNGRADE",
-        "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.",
-        "SampleAfterValue": "100003",
-        "UMask": "0x4"
-    },
-    {
-        "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xFE",
-        "EventName": "IDI_MISC.WB_UPGRADE",
-        "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.",
-        "SampleAfterValue": "100003",
-        "UMask": "0x2"
-    },
-    {
         "BriefDescription": "OCR.ALL_DATA_RD.ANY_RESPONSE have any response type.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
@@ -669,336 +595,6 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts all demand code reads have any response type.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80400004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80400004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100400004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1000020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x800020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x400020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads  OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x200020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand code reads",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80020004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads have any response type.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80400001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80400001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100400001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1000020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x800020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x400020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads  OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x200020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80020001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80400002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80400002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs) OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.PMM_HIT_LOCAL_PMM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100400002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F80020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1000020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x800020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x400020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)  OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x200020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all demand data writes (RFOs)",
-        "Counter": "0,1,2,3",
-        "EventCode": "0xB7, 0xBB",
-        "EventName": "OCR.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x80020002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts any other requests have any response type.",
         "Counter": "0,1,2,3",
         "EventCode": "0xB7, 0xBB",
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json
index 875361b30f1d..ecb7dc252208 100644
--- a/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json
@@ -22,6 +22,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+        "PublicDescription": "Counts the number of load ops retired. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x81"
     },
@@ -30,6 +31,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+        "PublicDescription": "Counts the number of store ops retired. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x82"
     },
@@ -40,6 +42,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x400",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -50,6 +53,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -60,6 +64,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -70,6 +75,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x800",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -80,6 +86,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -90,6 +97,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -100,6 +108,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -110,6 +119,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -120,6 +130,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -130,6 +141,7 @@
         "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
+        "PublicDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -138,7 +150,30 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
+        "PublicDescription": "Counts the number of  stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003",
         "UMask": "0x6"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json
index f5007e56f39b..58e543550279 100644
--- a/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json
@@ -6,6 +6,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x33FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -16,6 +17,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x33FBFC00002",
+        "PublicDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json
deleted file mode 100644
index 80454e497f83..000000000000
--- a/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json
+++ /dev/null
@@ -1,22 +0,0 @@
-[
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    }
-]
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json
index 6a5faa704b85..26bd12fefa3d 100644
--- a/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for.",
+        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003"
     },
     {
@@ -12,7 +12,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003"
     },
     {
@@ -63,6 +63,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired.",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired. Available PDIST counters: 32",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -71,6 +72,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
+        "PublicDescription": "Counts the number of instructions retired. Available PDIST counters: 0,1",
         "SampleAfterValue": "1000003"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json b/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json
index 7882dca9d5e1..3410caf8a57a 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/cache.json
@@ -161,6 +161,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x80"
     },
@@ -171,6 +172,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache, in which a snoop was required and modified data was forwarded from another core or module. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },
@@ -181,6 +183,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -191,6 +194,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L1 data cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
     },
@@ -201,6 +205,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -211,6 +216,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that miss in the L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x10"
     },
@@ -221,6 +227,7 @@
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -231,7 +238,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL",
         "PEBS": "1",
-        "PublicDescription": "Counts the number of memory uops retired.  A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST)",
+        "PublicDescription": "Counts the number of memory uops retired.  A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST) Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x83"
     },
@@ -242,7 +249,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of load uops retired.",
+        "PublicDescription": "Counts the total number of load uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x81"
     },
@@ -253,7 +260,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of store uops retired.",
+        "PublicDescription": "Counts the total number of store uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x82"
     },
@@ -264,6 +271,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that performed one or more locks. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21"
     },
@@ -274,6 +282,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of memory uops retired that were splits. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x43"
     },
@@ -284,6 +293,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired split load uops. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x41"
     },
@@ -294,6 +304,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired split store uops. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x42"
     },
@@ -304,6 +315,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -314,6 +326,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -324,6 +337,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -334,6 +348,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -344,6 +359,7 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -354,6 +370,18 @@
         "EventName": "OCR.ALL_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0044",
+        "PublicDescription": "Counts all code reads that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3000000010000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -364,6 +392,29 @@
         "EventName": "OCR.COREWB_M.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3001F803C0000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.COREWB_M.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8003000000000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -374,6 +425,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -384,6 +436,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -394,6 +447,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -404,6 +458,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -414,6 +469,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -424,6 +480,18 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -434,6 +502,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -444,6 +513,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -454,6 +524,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -464,6 +535,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -474,6 +546,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -484,6 +557,30 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -495,6 +592,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -506,6 +604,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HITM Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -517,6 +616,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_NO_FWD Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -528,6 +628,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_HIT_WITH_FWD Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -539,6 +640,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_MISS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -550,6 +652,30 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_HIT.SNOOP_NOT_NEEDED Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -560,6 +686,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -570,6 +697,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -580,6 +708,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -590,6 +719,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -600,6 +730,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -610,6 +741,18 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -620,6 +763,18 @@
         "EventName": "OCR.FULL_STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x801F803C0000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10400",
+        "PublicDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -630,6 +785,18 @@
         "EventName": "OCR.HWPF_L1D_AND_SWPF.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0400",
+        "PublicDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -640,6 +807,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -650,6 +818,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -660,6 +829,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -670,6 +840,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -680,6 +851,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -690,6 +862,29 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -700,6 +895,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -710,6 +906,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -720,6 +917,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -730,6 +928,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -740,6 +939,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -750,6 +950,18 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -760,6 +972,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -770,6 +983,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -780,6 +994,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -790,6 +1005,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -800,6 +1016,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -810,6 +1027,29 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.L1WB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1000000010000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -820,6 +1060,18 @@
         "EventName": "OCR.L1WB_M.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1001F803C0000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.L2WB_M.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x2000000010000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -830,6 +1082,7 @@
         "EventName": "OCR.L2WB_M.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2001F803C0000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -840,6 +1093,18 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x401F803C0000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -850,6 +1115,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -860,6 +1126,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -870,6 +1137,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -880,6 +1148,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -890,6 +1159,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -900,6 +1170,18 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1003C0477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.OUTSTANDING",
+        "MSRIndex": "0x1a6",
+        "MSRValue": "0x8000000000000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -910,6 +1192,7 @@
         "EventName": "OCR.STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F803C0800",
+        "PublicDescription": "Counts streaming stores that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -920,6 +1203,7 @@
         "EventName": "OCR.UC_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x101F803C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -930,6 +1214,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1010003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -940,6 +1225,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1004003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -950,6 +1236,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -960,6 +1247,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1002003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where a snoop was sent but the snoop missed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -970,6 +1258,7 @@
         "EventName": "OCR.UC_RD.L3_HIT.SNOOP_NOT_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1001003C0000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by the L3 cache where no snoop was needed to satisfy the request. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -980,6 +1269,7 @@
         "EventName": "OCR.UC_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x201F803C0000",
+        "PublicDescription": "Counts uncached memory writes that were supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json b/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json
index 79a4beba4b78..f47d97dfe0d9 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/floating-point.json
@@ -23,6 +23,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.FPDIV",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of floating point divide uops retired (x87 and SSE, including x87 sqrt). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     }
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json b/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json
index 34306ec24e9b..417cd78fc048 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/memory.json
@@ -13,6 +13,7 @@
         "EventCode": "0x13",
         "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of misaligned load uops that are 4K page splits. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -22,16 +23,29 @@
         "EventCode": "0x13",
         "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of misaligned store uops that are 4K page splits. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
     {
+        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.ALL_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000044",
+        "PublicDescription": "Counts all code reads that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all code reads that were not supplied by the L3 cache.",
         "Counter": "0,1,2,3",
         "EventCode": "0XB7",
         "EventName": "OCR.ALL_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000044",
+        "PublicDescription": "Counts all code reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -42,6 +56,18 @@
         "EventName": "OCR.ALL_CODE_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000044",
+        "PublicDescription": "Counts all code reads that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.ALL_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000044",
+        "PublicDescription": "Counts all code reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -52,6 +78,7 @@
         "EventName": "OCR.COREWB_M.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -62,6 +89,18 @@
         "EventName": "OCR.COREWB_M.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache and L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -72,6 +111,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -82,6 +122,29 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -92,6 +155,7 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -102,6 +166,30 @@
         "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -113,6 +201,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -124,6 +213,30 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.L3_MISS_LOCAL Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
+        "Counter": "0,1,2,3",
+        "Deprecated": "1",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "PublicDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -134,6 +247,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -144,6 +258,18 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -154,6 +280,7 @@
         "EventName": "OCR.FULL_STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x802184000000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -164,6 +291,18 @@
         "EventName": "OCR.FULL_STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x802184000000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -174,6 +313,7 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -184,6 +324,29 @@
         "EventName": "OCR.HWPF_L2_CODE_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000040",
+        "PublicDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -194,6 +357,7 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -204,6 +368,29 @@
         "EventName": "OCR.HWPF_L2_DATA_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000010",
+        "PublicDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -214,6 +401,7 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -224,6 +412,18 @@
         "EventName": "OCR.HWPF_L2_RFO.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000020",
+        "PublicDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -234,6 +434,7 @@
         "EventName": "OCR.L1WB_M.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -244,6 +445,7 @@
         "EventName": "OCR.L1WB_M.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1002184000000",
+        "PublicDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -254,6 +456,7 @@
         "EventName": "OCR.L2WB_M.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2002184000000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -264,6 +467,7 @@
         "EventName": "OCR.L2WB_M.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2002184000000",
+        "PublicDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -274,6 +478,7 @@
         "EventName": "OCR.OTHER.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184008000",
+        "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -284,6 +489,7 @@
         "EventName": "OCR.OTHER.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184008000",
+        "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -294,6 +500,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x402184000000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -304,6 +511,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x402184000000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -314,6 +522,18 @@
         "EventName": "OCR.PREFETCHES.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000470",
+        "PublicDescription": "Counts all hardware and software prefetches that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -324,6 +544,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -334,6 +555,18 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000477",
+        "PublicDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -344,6 +577,7 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000800",
+        "PublicDescription": "Counts streaming stores that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -354,6 +588,18 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x2184000800",
+        "PublicDescription": "Counts streaming stores that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.UC_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100184000000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -364,6 +610,7 @@
         "EventName": "OCR.UC_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x102184000000",
+        "PublicDescription": "Counts uncached memory reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -374,6 +621,18 @@
         "EventName": "OCR.UC_RD.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x102184000000",
+        "PublicDescription": "Counts uncached memory reads that were not supplied by the L3 cache. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0XB7",
+        "EventName": "OCR.UC_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x100184000000",
+        "PublicDescription": "Counts uncached memory reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -384,6 +643,7 @@
         "EventName": "OCR.UC_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x202184000000",
+        "PublicDescription": "Counts uncached memory writes that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -394,6 +654,7 @@
         "EventName": "OCR.UC_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x202184000000",
+        "PublicDescription": "Counts uncached memory writes that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/other.json b/tools/perf/pmu-events/arch/x86/elkhartlake/other.json
index 57613207f7ad..2cdc6b64f31d 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/other.json
@@ -113,26 +113,7 @@
         "EventName": "OCR.ALL_CODE_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10044",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.ALL_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000044",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all code reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.ALL_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000044",
+        "PublicDescription": "Counts all code reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -143,180 +124,7 @@
         "EventName": "OCR.ALL_CODE_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "MSRValue": "0x8000000000000044",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.COREWB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3000000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writebacks from L1 cache and L2 cache that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.COREWB_M.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8003000000000000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts cacheable demand data reads, L1 data cache hardware prefetches and software prefetches (except PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.ANY_RESPONSE",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.DRAM",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.LOCAL_DRAM",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event OCR.DEMAND_DATA_AND_L1PF_RD.OUTSTANDING",
-        "Counter": "0,1,2,3",
-        "Deprecated": "1",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.DEMAND_RFO.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000002",
+        "PublicDescription": "Counts all code reads that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -327,146 +135,7 @@
         "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x800000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L1 data cache hardware prefetches and software prefetches (except PREFETCHW and PFRFO) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L1D_AND_SWPF.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch code reads (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_CODE_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000040",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch data reads (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000010",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts L2 cache hardware prefetch RFOs (written to the L2 cache only) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.HWPF_L2_RFO.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000020",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writebacks from L1 cache that miss the L2 cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.L1WB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x1000000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts modified writeBacks from L2 cache that miss the L3 cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.L2WB_M.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x2000000010000",
+        "PublicDescription": "Counts streaming stores which modify a full 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -477,6 +146,7 @@
         "EventName": "OCR.OTHER.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x18000",
+        "PublicDescription": "Counts miscellaneous requests, such as I/O accesses, that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -487,6 +157,7 @@
         "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x400000010000",
+        "PublicDescription": "Counts streaming stores which modify only part of a 64 byte cacheline that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -497,46 +168,7 @@
         "EventName": "OCR.PREFETCHES.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10470",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency).",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.READS_TO_CORE.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "MSRValue": "0x8000000000000477",
+        "PublicDescription": "Counts all hardware and software prefetches that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -547,6 +179,7 @@
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -557,26 +190,7 @@
         "EventName": "OCR.UC_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x100000010000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.UC_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100184000000",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts uncached memory reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0XB7",
-        "EventName": "OCR.UC_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x100184000000",
+        "PublicDescription": "Counts uncached memory reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -587,6 +201,7 @@
         "EventName": "OCR.UC_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "MSRValue": "0x8000100000000000",
+        "PublicDescription": "Counts uncached memory reads that have an outstanding request. Returns the number of cycles until the response is received (i.e. XQ to XQ latency). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -597,6 +212,7 @@
         "EventName": "OCR.UC_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x200000010000",
+        "PublicDescription": "Counts uncached memory writes that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json b/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json
index e4e7902c1162..0fc2e821b14a 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/pipeline.json
@@ -5,7 +5,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for.",
+        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for. Available PDIST counters: 0",
         "SampleAfterValue": "200003"
     },
     {
@@ -14,6 +14,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf9"
     },
@@ -23,6 +24,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xbf"
     },
@@ -32,6 +34,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.IND_CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -41,6 +44,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -50,6 +54,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NON_RETURN_IND",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -59,6 +64,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.REL_CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near relative CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfd"
     },
@@ -68,6 +74,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.RETURN",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -77,6 +84,7 @@
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.TAKEN_JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -86,7 +94,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "200003"
     },
     {
@@ -95,6 +103,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.IND_CALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfb"
     },
@@ -104,6 +113,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x7e"
     },
@@ -113,6 +123,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NON_RETURN_IND",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xeb"
     },
@@ -122,6 +133,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RETURN",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted near RET branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf7"
     },
@@ -131,6 +143,7 @@
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.TAKEN_JCC",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xfe"
     },
@@ -206,7 +219,7 @@
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses fixed counter 0. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -216,7 +229,7 @@
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.ANY_P",
         "PEBS": "1",
-        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter.",
+        "PublicDescription": "Counts the total number of instructions that retired. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. This event continues counting during hardware interrupts, traps, and inside interrupt handlers. This event uses a programmable general purpose performance counter. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -225,6 +238,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.4K_ALIAS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -234,6 +248,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked for any of the following reasons:  DTLB miss, address alias, store forward or data unknown (includes memory disambiguation blocks and ESP consuming load blocks). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -243,6 +258,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.DATA_UNKNOWN",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -252,6 +268,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked because its address partially overlapped with an older store. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -464,6 +481,7 @@
         "EventCode": "0xc2",
         "EventName": "TOPDOWN_RETIRING.ALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the total number of consumed retirement slots. Available PDIST counters: 0",
         "SampleAfterValue": "1000003"
     },
     {
@@ -480,6 +498,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.ALL",
         "PEBS": "1",
+        "PublicDescription": "Counts the total number of uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -488,6 +507,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.IDIV",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of integer divide uops retired. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -497,7 +517,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.MS",
         "PEBS": "1",
-        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
+        "PublicDescription": "Counts the number of uops that are from complex flows issued by the Microcode Sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -507,6 +527,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.X87",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of x87 uops retired, includes those in MS flows. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     }
diff --git a/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json
index f9a6caed8776..bf56d72bb4a7 100644
--- a/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/elkhartlake/virtual-memory.json
@@ -242,6 +242,7 @@
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.DTLB_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of retired loads that are blocked due to a first level TLB miss. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -252,6 +253,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of memory uops retired that missed in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x13"
     },
@@ -262,6 +264,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of load uops retired that miss in the second Level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x11"
     },
@@ -272,6 +275,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
         "PEBS": "1",
+        "PublicDescription": "Counts the number of store uops retired that miss in the second level TLB. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x12"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json
index 3b0581151d63..10bdb193c16f 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json
@@ -4,6 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.HWPF_MISS",
+        "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -12,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.REPLACEMENT",
-        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -21,7 +22,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -32,7 +33,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
-        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -42,6 +43,7 @@
         "Deprecated": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALL",
+        "PublicDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -50,7 +52,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALLS",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -59,7 +61,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -69,7 +71,7 @@
         "CounterMask": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -78,7 +80,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x25",
         "EventName": "L2_LINES_IN.ALL",
-        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1f"
     },
@@ -87,7 +89,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.NON_SILENT",
-        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -96,7 +98,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -105,7 +107,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.USELESS_HWPF",
-        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
+        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -114,7 +116,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.ALL",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff"
     },
@@ -123,7 +125,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f"
     },
@@ -132,7 +134,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "PublicDescription": "Counts the total number of L2 code requests.",
+        "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe4"
     },
@@ -141,7 +143,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe1"
     },
@@ -150,7 +152,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "PublicDescription": "Counts demand requests that miss L2 cache.",
+        "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x27"
     },
@@ -159,7 +161,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "PublicDescription": "Counts demand requests to L2 cache.",
+        "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe7"
     },
@@ -168,6 +170,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_HWPF",
+        "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf0"
     },
@@ -176,7 +179,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_RFO",
-        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe2"
     },
@@ -185,7 +188,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc4"
     },
@@ -194,7 +197,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x24"
     },
@@ -203,7 +206,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc1"
     },
@@ -212,7 +215,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
-        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21"
     },
@@ -221,6 +224,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HWPF_MISS",
+        "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x30"
     },
@@ -229,7 +233,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f"
     },
@@ -238,7 +242,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.REFERENCES",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff"
     },
@@ -247,7 +251,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_HIT",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc2"
     },
@@ -256,7 +260,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_MISS",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x22"
     },
@@ -265,7 +269,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_HIT",
-        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc8"
     },
@@ -274,7 +278,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_MISS",
-        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x28"
     },
@@ -283,7 +287,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x23",
         "EventName": "L2_TRANS.L2_WB",
-        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x40"
     },
@@ -292,7 +296,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.MISS",
-        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
     },
@@ -301,7 +305,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4f"
     },
@@ -311,7 +315,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
+        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81"
     },
@@ -321,7 +325,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82"
     },
@@ -331,7 +335,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x83"
     },
@@ -341,7 +345,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x21"
     },
@@ -351,7 +355,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
     },
@@ -361,7 +365,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x42"
     },
@@ -371,7 +375,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11"
     },
@@ -381,7 +385,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12"
     },
@@ -390,7 +394,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
-        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
+        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfd"
     },
@@ -400,7 +404,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x4"
     },
@@ -410,7 +414,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x1"
     },
@@ -420,7 +424,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
+        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -430,7 +434,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
         "SampleAfterValue": "20011",
         "UMask": "0x2"
     },
@@ -440,7 +444,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -450,6 +454,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -459,7 +464,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
-        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
+        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -469,6 +474,7 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
+        "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -478,7 +484,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4"
     },
@@ -488,7 +494,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
     },
@@ -498,7 +504,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -508,7 +514,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
     },
@@ -518,7 +524,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -528,7 +534,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10"
     },
@@ -538,7 +544,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x4"
     },
@@ -548,7 +554,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20"
     },
@@ -557,6 +563,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x44",
         "EventName": "MEM_STORE_RETIRED.L2_HIT",
+        "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -565,17 +572,29 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe5",
         "EventName": "MEM_UOP_RETIRED.ANY",
-        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
+        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -586,6 +605,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -596,6 +616,7 @@
         "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -606,6 +627,18 @@
         "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -616,6 +649,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0001",
+        "PublicDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -626,6 +660,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -636,6 +671,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -646,6 +682,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -656,6 +693,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1030000001",
+        "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -666,6 +704,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x830000001",
+        "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -676,6 +715,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008000001",
+        "PublicDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -686,6 +726,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808000001",
+        "PublicDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -696,6 +748,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -706,6 +759,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -716,6 +770,7 @@
         "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -726,6 +781,40 @@
         "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L1D.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10400",
+        "PublicDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L2.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10070",
+        "PublicDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L3.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x12380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -736,6 +825,40 @@
         "EventName": "OCR.HWPF_L3.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x80082380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.HWPF_L3.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x90002380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10808",
+        "PublicDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -746,6 +869,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -756,6 +880,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -766,6 +891,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -776,6 +902,18 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F33004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -786,6 +924,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1830004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -796,6 +935,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1030004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -806,6 +946,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x830004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -816,6 +957,7 @@
         "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -826,6 +968,7 @@
         "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -836,6 +979,7 @@
         "EventName": "OCR.RFO_TO_CORE.L3_HIT_M",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F80040022",
+        "PublicDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -846,6 +990,7 @@
         "EventName": "OCR.STREAMING_WR.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x80080800",
+        "PublicDescription": "Counts streaming stores that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -854,6 +999,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+        "PublicDescription": "OFFCORE_REQUESTS.ALL_REQUESTS Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -862,7 +1008,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DATA_RD",
-        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -871,7 +1017,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
-        "PublicDescription": "Counts both cacheable and non-cacheable code read requests.",
+        "PublicDescription": "Counts both cacheable and non-cacheable code read requests. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -880,7 +1026,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -889,7 +1035,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
-        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -899,6 +1045,7 @@
         "Deprecated": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "PublicDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -908,6 +1055,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -917,7 +1065,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -927,6 +1075,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -936,6 +1085,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -944,6 +1094,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -952,7 +1103,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -961,7 +1112,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -970,7 +1121,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x2c",
         "EventName": "SQ_MISC.BUS_LOCK",
-        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -979,6 +1130,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.ANY",
+        "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xf"
     },
@@ -987,7 +1139,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.NTA",
-        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -996,7 +1148,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
-        "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -1005,7 +1157,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T0",
-        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -1014,7 +1166,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T1_T2",
-        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json
index d3b51fa6ec1c..34e1cbcd722c 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/emr-metrics.json
@@ -300,7 +300,7 @@
         "ScaleUnit": "1per_instr"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -312,7 +312,7 @@
         "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks",
         "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_amx_busy",
-        "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -320,12 +320,12 @@
         "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -335,7 +335,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -351,12 +351,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -371,7 +371,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -379,7 +379,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -387,22 +387,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -410,7 +410,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -418,7 +418,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -426,7 +426,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -438,10 +438,10 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -450,7 +450,7 @@
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -463,24 +463,24 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -488,8 +488,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -497,24 +497,24 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, tma_icache_misses - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -522,7 +522,7 @@
         "MetricExpr": "max(0, tma_itlb_misses - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -530,32 +530,33 @@
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "tma_code_stlb_miss * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((81 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(76.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 74.6 * tma_info_system_core_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_contested_accesses",
-        "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
+        "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
@@ -566,24 +567,25 @@
         "MetricName": "tma_core_bound",
         "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+        "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck.  Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
-        "MetricExpr": "(79 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "74.6 * tma_info_system_core_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
         "MetricName": "tma_data_sharing",
-        "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / tma_info_core_core_clks / 2",
+        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_core_clks / 2",
         "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group",
         "MetricName": "tma_decoder0_alone",
-        "MetricThreshold": "tma_decoder0_alone > 0.1 & tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & tma_fetch_bandwidth > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
@@ -592,8 +594,8 @@
         "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_divider",
-        "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE",
+        "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
         "ScaleUnit": "100%"
     },
     {
@@ -601,7 +603,7 @@
         "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_dram_bound",
-        "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
         "ScaleUnit": "100%"
     },
@@ -611,7 +613,7 @@
         "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_dsb",
         "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
-        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here",
+        "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline.  For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.",
         "ScaleUnit": "100%"
     },
     {
@@ -619,34 +621,34 @@
         "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
         "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_dsb_switches",
-        "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
-        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
+        "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
         "MetricName": "tma_dtlb_load",
-        "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+        "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
-        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
+        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
         "MetricName": "tma_dtlb_store",
-        "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+        "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses.  As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead.  Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page.  Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
-        "MetricExpr": "(170 * tma_info_system_core_frequency * cpu@OCR.DEMAND_RFO.L3_MISS\\,offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
+        "MetricExpr": "(170 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_MISS@offcore_rsp\\=0x103b800002@ + 81 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM) / tma_info_thread_clks",
         "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
         "MetricName": "tma_false_sharing",
-        "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache",
         "ScaleUnit": "100%"
     },
@@ -667,7 +669,7 @@
         "MetricName": "tma_fetch_bandwidth",
         "MetricThreshold": "tma_fetch_bandwidth > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1, FRONTEND_RETIRED.LATENCY_GE_1, FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues.  For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1;FRONTEND_RETIRED.LATENCY_GE_1;FRONTEND_RETIRED.LATENCY_GE_2. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
@@ -678,7 +680,7 @@
         "MetricName": "tma_fetch_latency",
         "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+        "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues.  For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -696,7 +698,7 @@
         "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fp_arith",
         "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+        "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.",
         "ScaleUnit": "100%"
     },
     {
@@ -705,15 +707,15 @@
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_fp_assists",
         "MetricThreshold": "tma_fp_assists > 0.1",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active.",
         "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_fp_divider",
-        "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_fp_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -721,8 +723,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_scalar",
-        "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -730,8 +732,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.VECTOR + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
         "MetricName": "tma_fp_vector",
-        "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -739,8 +741,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_128b",
-        "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -748,8 +750,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_256b",
-        "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -757,8 +759,8 @@
         "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
         "MetricName": "tma_fp_vector_512b",
-        "MetricThreshold": "tma_fp_vector_512b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
+        "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -769,27 +771,27 @@
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions",
         "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_fused_instructions",
         "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_heavy_operations",
         "MetricThreshold": "tma_heavy_operations > 0.1",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
         "ScaleUnit": "100%"
     },
     {
@@ -797,8 +799,8 @@
         "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_icache_misses",
-        "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -809,28 +811,28 @@
         "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for conditional taken branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_cond_taken",
         "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_indirect",
-        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000"
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3"
     },
     {
-        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+        "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate).",
         "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
         "MetricGroup": "Bad;BrMispredicts",
         "MetricName": "tma_info_bad_spec_ipmisp_ret",
@@ -858,7 +860,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_ms)))",
+        "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_bandwidth + tma_fetch_latency)) * (tma_dsb / (tma_dsb + tma_mite + tma_ms)))",
         "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
@@ -866,7 +868,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_ms))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite + tma_ms))",
         "MetricGroup": "DSBmiss;Fed;tma_issueFB",
         "MetricName": "tma_info_botlnk_l2_dsb_misses",
         "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
@@ -874,10 +876,11 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
-        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
         "MetricName": "tma_info_botlnk_l2_ic_misses",
-        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5"
+        "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+        "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: "
     },
     {
         "BriefDescription": "Fraction of branches that are CALL or RET",
@@ -938,11 +941,11 @@
         "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_core_clks)",
         "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "tma_info_core_fp_arith_utilization",
-        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)"
+        "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
     },
     {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
         "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "tma_info_core_ilp"
     },
@@ -955,20 +958,20 @@
         "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp"
     },
     {
-        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "DSBmiss",
         "MetricName": "tma_info_frontend_dsb_switch_cost"
     },
     {
         "BriefDescription": "Average number of Uops issued by front-end when it issued something",
-        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
         "MetricGroup": "Fed;FetchBW",
         "MetricName": "tma_info_frontend_fetch_upc"
     },
     {
         "BriefDescription": "Average Latency for L1 instruction cache misses",
-        "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed;FetchLat;IcMiss",
         "MetricName": "tma_info_frontend_icache_miss_latency"
     },
@@ -1005,13 +1008,13 @@
     },
     {
         "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
-        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+        "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=1\\,edge@",
         "MetricGroup": "Fed",
         "MetricName": "tma_info_frontend_unknown_branch_cost",
-        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node"
+        "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node."
     },
     {
-        "BriefDescription": "Branch instructions per taken branch",
+        "BriefDescription": "Branch instructions per taken branch.",
         "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "tma_info_inst_mix_bptkbranch"
@@ -1029,7 +1032,7 @@
         "MetricGroup": "Flops;InsType",
         "MetricName": "tma_info_inst_mix_iparith",
         "MetricThreshold": "tma_info_inst_mix_iparith < 10",
-        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW"
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
@@ -1037,7 +1040,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx128",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
@@ -1045,7 +1048,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx256",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
@@ -1053,7 +1056,7 @@
         "MetricGroup": "Flops;FpVector;InsType",
         "MetricName": "tma_info_inst_mix_iparith_avx512",
         "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10",
-        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
@@ -1061,7 +1064,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate)",
@@ -1069,7 +1072,7 @@
         "MetricGroup": "Flops;FpScalar;InsType;Server",
         "MetricName": "tma_info_inst_mix_iparith_scalar_hp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_hp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Half-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
@@ -1077,7 +1080,7 @@
         "MetricGroup": "Flops;FpScalar;InsType",
         "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
         "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
-        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting"
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting."
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -1132,7 +1135,7 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
         "MetricName": "tma_info_inst_mix_iptb",
-        "MetricThreshold": "tma_info_inst_mix_iptb < 6 * 2 + 1",
+        "MetricThreshold": "tma_info_inst_mix_iptb < 13",
         "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp"
     },
     {
@@ -1269,7 +1272,7 @@
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
-        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+        "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@",
         "MetricGroup": "Memory_BW;Offcore",
         "MetricName": "tma_info_memory_latency_load_l2_mlp"
     },
@@ -1334,21 +1337,21 @@
         "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_dram_bw",
-        "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW"
+        "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW."
     },
     {
         "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)",
         "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_l3m_bw",
-        "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW"
+        "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW."
     },
     {
         "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)",
         "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / tma_info_system_time",
         "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_soc_r2c_offcore_bw",
-        "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches"
+        "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches."
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
@@ -1376,8 +1379,8 @@
         "MetricName": "tma_info_memory_tlb_store_stlb_mpki"
     },
     {
-        "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per core",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@)",
+        "BriefDescription": "",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@)",
         "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
         "MetricName": "tma_info_pipeline_execute"
     },
@@ -1398,18 +1401,18 @@
         "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
         "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
         "MetricName": "tma_info_pipeline_ipassist",
-        "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+        "MetricThreshold": "tma_info_pipeline_ipassist < 100e3",
         "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)"
     },
     {
-        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
-        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+        "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "Pipeline;Ret",
         "MetricName": "tma_info_pipeline_retire"
     },
     {
         "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
-        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+        "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@",
         "MetricGroup": "MicroSeq;Pipeline;Ret",
         "MetricName": "tma_info_pipeline_strings_cycles",
         "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1"
@@ -1472,14 +1475,13 @@
         "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "tma_info_system_ipfarbranch",
-        "MetricThreshold": "tma_info_system_ipfarbranch < 1000000"
+        "MetricThreshold": "tma_info_system_ipfarbranch < 1e6"
     },
     {
         "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
         "MetricGroup": "OS",
-        "MetricName": "tma_info_system_kernel_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_system_kernel_cpi"
     },
     {
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
@@ -1490,7 +1492,7 @@
     },
     {
         "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]",
-        "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@",
+        "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@",
         "MetricGroup": "MemOffcore;MemoryLat;Server;SoC",
         "MetricName": "tma_info_system_mem_dram_read_latency",
         "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches"
@@ -1500,11 +1502,11 @@
         "MetricExpr": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH / UNC_CHA_CLOCKTICKS",
         "MetricGroup": "LockCont;MemOffcore;Server;SoC",
         "MetricName": "tma_info_system_mem_irq_duplicate_address",
-        "MetricThreshold": "(tma_info_system_mem_irq_duplicate_address > 0.1)"
+        "MetricThreshold": "tma_info_system_mem_irq_duplicate_address > 0.1"
     },
     {
         "BriefDescription": "Average number of parallel data read requests to external memory",
-        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=0x1@",
+        "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@",
         "MetricGroup": "Mem;MemoryBW;SoC",
         "MetricName": "tma_info_system_mem_parallel_reads",
         "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches"
@@ -1538,7 +1540,7 @@
     },
     {
         "BriefDescription": "Socket actual clocks when any core is active on that socket",
-        "MetricExpr": "cha_0@event\\=0x0@",
+        "MetricExpr": "uncore_cha_0@event\\=0x1@",
         "MetricGroup": "SoC",
         "MetricName": "tma_info_system_socket_clks"
     },
@@ -1568,7 +1570,7 @@
         "MetricName": "tma_info_system_upi_data_transmit_bw"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "tma_info_thread_clks"
@@ -1577,15 +1579,14 @@
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
         "MetricExpr": "1 / tma_info_thread_ipc",
         "MetricGroup": "Mem;Pipeline",
-        "MetricName": "tma_info_thread_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_thread_cpi"
     },
     {
         "BriefDescription": "The ratio of Executed- by Issued-Uops",
         "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
         "MetricGroup": "Cor;Pipeline",
         "MetricName": "tma_info_thread_execute_per_issue",
-        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage"
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
     },
     {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
@@ -1595,13 +1596,13 @@
     },
     {
         "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
-        "MetricExpr": "slots",
+        "MetricExpr": "TOPDOWN.SLOTS",
         "MetricGroup": "TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots"
     },
     {
         "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
-        "MetricExpr": "(tma_info_thread_slots / (slots / 2) if #SMT_on else 1)",
+        "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)",
         "MetricGroup": "SMT;TmaL1;tma_L1_group",
         "MetricName": "tma_info_thread_slots_utilization"
     },
@@ -1617,14 +1618,14 @@
         "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
         "MetricGroup": "Branches;Fed;FetchBW",
         "MetricName": "tma_info_thread_uptb",
-        "MetricThreshold": "tma_info_thread_uptb < 6 * 1.5"
+        "MetricThreshold": "tma_info_thread_uptb < 9"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+        "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active.",
         "MetricExpr": "tma_divider - tma_fp_divider",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
         "MetricName": "tma_int_divider",
-        "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_int_divider > 0.2 & (tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -1633,7 +1634,7 @@
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_int_operations",
         "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+        "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.",
         "ScaleUnit": "100%"
     },
     {
@@ -1641,8 +1642,8 @@
         "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_128b",
-        "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1650,8 +1651,8 @@
         "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
         "MetricName": "tma_int_vector_256b",
-        "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1659,8 +1660,8 @@
         "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_itlb_misses",
-        "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -1668,7 +1669,7 @@
         "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
         "MetricName": "tma_l1_bound",
-        "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache.  The L1D cache typically has the shortest latency.  However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
         "ScaleUnit": "100%"
     },
@@ -1677,7 +1678,7 @@
         "MetricExpr": "min(2 * (MEM_INST_RETIRED.ALL_LOADS - MEM_LOAD_RETIRED.FB_HIT - MEM_LOAD_RETIRED.L1_MISS) * 20 / 100, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_l1_latency_dependency",
-        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l1_latency_dependency > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: MEM_LOAD_RETIRED.L1_HIT",
         "ScaleUnit": "100%"
     },
@@ -1686,16 +1687,17 @@
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks",
         "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l2_bound",
-        "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads.  Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
         "MetricExpr": "4.4 * tma_info_system_core_frequency * MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
         "MetricName": "tma_l2_hit_latency",
-        "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_l2_hit_latency > 0.05 & (tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited).  Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
         "ScaleUnit": "100%"
     },
@@ -1704,17 +1706,18 @@
         "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks",
         "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_l3_bound",
-        "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+        "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core.  Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
-        "MetricExpr": "(37 * tma_info_system_core_frequency - 4.4 * tma_info_system_core_frequency) * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "32.6 * tma_info_system_core_frequency * (MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2)) / tma_info_thread_clks",
         "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
         "MetricName": "tma_l3_hit_latency",
-        "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+        "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited).  Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance.  Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_bottleneck_cache_memory_latency, tma_mem_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -1722,19 +1725,19 @@
         "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
         "MetricName": "tma_lcp",
-        "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+        "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)",
         "DefaultMetricgroupName": "TopdownL2",
         "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
         "MetricGroup": "Default;Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
         "MetricName": "tma_light_operations",
         "MetricThreshold": "tma_light_operations > 0.6",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
         "ScaleUnit": "100%"
     },
     {
@@ -1751,7 +1754,7 @@
         "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_hit",
-        "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -1759,39 +1762,39 @@
         "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
         "MetricName": "tma_load_stlb_miss",
-        "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_1g",
-        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_2m",
-        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses.",
         "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
         "MetricName": "tma_load_stlb_miss_4k",
-        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & (tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory",
-        "MetricExpr": "(109 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "72 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_local_mem",
-        "MetricThreshold": "tma_local_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_local_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
         "ScaleUnit": "100%"
     },
@@ -1800,7 +1803,7 @@
         "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_thread_clks",
         "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
         "MetricName": "tma_lock_latency",
-        "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
         "ScaleUnit": "100%"
     },
@@ -1816,19 +1819,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling)",
+        "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).",
         "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group",
         "MetricName": "tma_mba_stalls",
-        "MetricThreshold": "tma_mba_stalls > 0.1 & tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
-        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+        "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
         "MetricName": "tma_mem_bandwidth",
-        "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM).  The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full",
         "ScaleUnit": "100%"
     },
@@ -1837,32 +1840,32 @@
         "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
         "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
         "MetricName": "tma_mem_latency",
-        "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM).  This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "Backend;Default;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_memory_bound",
         "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2;Default",
-        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+        "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck.  Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.",
         "MetricConstraint": "NO_GROUP_EVENTS_NMI",
         "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_memory_fence",
-        "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+        "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.",
         "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_memory_operations",
@@ -1883,7 +1886,7 @@
         "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
         "MetricName": "tma_mispredicts_resteers",
-        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
         "ScaleUnit": "100%"
     },
@@ -1897,17 +1900,17 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+        "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles)",
         "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
         "MetricName": "tma_mixing_vectors",
         "MetricThreshold": "tma_mixing_vectors > 0.05",
-        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+        "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued -- the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
-        "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2",
+        "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details.",
+        "MetricExpr": "max(IDQ.MS_CYCLES_ANY, cpu@UOPS_RETIRED.MS\\,cmask\\=1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY)) / tma_info_core_core_clks / 2",
         "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
         "MetricName": "tma_ms",
         "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
@@ -1915,11 +1918,11 @@
     },
     {
         "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
-        "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks",
+        "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
         "MetricName": "tma_ms_switches",
-        "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+        "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
         "ScaleUnit": "100%"
     },
     {
@@ -1928,7 +1931,7 @@
         "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_non_fused_branches",
         "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.",
         "ScaleUnit": "100%"
     },
     {
@@ -1936,7 +1939,7 @@
         "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_nop_instructions",
-        "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+        "MetricThreshold": "tma_nop_instructions > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
         "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
         "ScaleUnit": "100%"
     },
@@ -1950,19 +1953,19 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+        "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types).",
         "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
         "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_other_mispredicts",
-        "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+        "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering.",
         "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
         "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_other_nukes",
-        "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_other_nukes > 0.05 & (tma_machine_clears > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
@@ -1971,7 +1974,7 @@
         "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_page_faults",
         "MetricThreshold": "tma_page_faults > 0.05",
-        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+        "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.",
         "ScaleUnit": "100%"
     },
     {
@@ -1980,7 +1983,7 @@
         "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_0",
         "MetricThreshold": "tma_port_0 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1989,7 +1992,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_1",
         "MetricThreshold": "tma_port_1 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_6, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -1998,7 +2001,7 @@
         "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P",
         "MetricName": "tma_port_6",
         "MetricThreshold": "tma_port_6 > 0.6",
-        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_ports_utilized_2",
+        "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+] Primary Branch and simple ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2",
         "ScaleUnit": "100%"
     },
     {
@@ -2006,8 +2009,8 @@
         "MetricExpr": "((tma_ports_utilized_0 * tma_info_thread_clks + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)",
         "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_ports_utilization",
-        "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+        "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related).  Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.",
         "ScaleUnit": "100%"
     },
     {
@@ -2015,8 +2018,8 @@
         "MetricExpr": "(EXE_ACTIVITY.EXE_BOUND_0_PORTS + max(RS.EMPTY_RESOURCE - RESOURCE_STALLS.SCOREBOARD, 0)) / tma_info_thread_clks * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_0",
-        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+        "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.",
         "ScaleUnit": "100%"
     },
     {
@@ -2024,7 +2027,7 @@
         "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_1",
-        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
         "ScaleUnit": "100%"
     },
@@ -2034,8 +2037,8 @@
         "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
         "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_2",
-        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_6",
+        "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).  Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6",
         "ScaleUnit": "100%"
     },
     {
@@ -2044,32 +2047,32 @@
         "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
         "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
         "MetricName": "tma_ports_utilized_3m",
-        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_ports_utilized_3m > 0.4 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues",
-        "MetricExpr": "((170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (170 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "(133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 133 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group",
         "MetricName": "tma_remote_cache",
-        "MetricThreshold": "tma_remote_cache > 0.05 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM, MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+        "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory",
-        "MetricExpr": "(190 * tma_info_system_core_frequency - 37 * tma_info_system_core_frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricExpr": "153 * tma_info_system_core_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
         "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group",
         "MetricName": "tma_remote_mem",
-        "MetricThreshold": "tma_remote_mem > 0.1 & tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "MetricThreshold": "tma_remote_mem > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
+        "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvUW;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
         "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
@@ -2082,7 +2085,7 @@
         "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks + tma_c02_wait",
         "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
         "MetricName": "tma_serializing_operation",
-        "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
         "ScaleUnit": "100%"
     },
@@ -2091,8 +2094,8 @@
         "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
         "MetricName": "tma_shuffles_256b",
-        "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+        "MetricThreshold": "tma_shuffles_256b > 0.1 & (tma_other_light_ops > 0.3 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers.",
         "ScaleUnit": "100%"
     },
     {
@@ -2101,7 +2104,7 @@
         "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_slow_pause",
-        "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
         "ScaleUnit": "100%"
     },
@@ -2111,7 +2114,7 @@
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_split_loads",
         "MetricThreshold": "tma_split_loads > 0.3",
-        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+        "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -2119,8 +2122,8 @@
         "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
         "MetricName": "tma_split_stores",
-        "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+        "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric represents rate of split store accesses.  Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4",
         "ScaleUnit": "100%"
     },
     {
@@ -2128,7 +2131,7 @@
         "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_thread_clks",
         "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
         "MetricName": "tma_sq_full",
-        "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth",
         "ScaleUnit": "100%"
     },
@@ -2137,8 +2140,8 @@
         "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
         "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
         "MetricName": "tma_store_bound",
-        "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+        "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
+        "PublicDescription": "This metric estimates how often CPU was stalled  due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS",
         "ScaleUnit": "100%"
     },
     {
@@ -2146,8 +2149,8 @@
         "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
         "MetricName": "tma_store_fwd_blk",
-        "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+        "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.",
         "ScaleUnit": "100%"
     },
     {
@@ -2155,8 +2158,8 @@
         "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
         "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
         "MetricName": "tma_store_latency",
-        "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+        "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency",
         "ScaleUnit": "100%"
     },
     {
@@ -2173,7 +2176,7 @@
         "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_hit",
-        "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
@@ -2181,31 +2184,31 @@
         "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_core_clks",
         "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
         "MetricName": "tma_store_stlb_miss",
-        "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_1g",
-        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_2m",
-        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses.",
         "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
         "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
         "MetricName": "tma_store_stlb_miss_4k",
-        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & (tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))))",
         "ScaleUnit": "100%"
     },
     {
@@ -2213,7 +2216,7 @@
         "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
         "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
         "MetricName": "tma_streaming_stores",
-        "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))",
         "PublicDescription": "This metric estimates how often CPU was stalled  due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
         "ScaleUnit": "100%"
     },
@@ -2222,7 +2225,7 @@
         "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
         "MetricName": "tma_unknown_branches",
-        "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "ScaleUnit": "100%"
     },
@@ -2231,8 +2234,8 @@
         "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
         "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
         "MetricName": "tma_x87_use",
-        "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
-        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+        "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)",
+        "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
index bc475e163227..8c9207750c82 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json
@@ -5,6 +5,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FPDIV_ACTIVE",
+        "PublicDescription": "ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -13,7 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.FP",
-        "PublicDescription": "Counts all microcode Floating Point assists.",
+        "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -22,6 +23,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.SSE_AVX_MIX",
+        "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -30,6 +32,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -38,6 +41,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -46,6 +50,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -54,6 +59,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -62,6 +68,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -70,6 +77,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V2",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -78,7 +86,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -87,7 +95,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -96,7 +104,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -105,7 +113,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -114,7 +122,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x18"
     },
@@ -123,7 +131,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x40"
     },
@@ -132,7 +140,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -141,7 +149,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x60"
     },
@@ -150,7 +158,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -159,7 +167,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -168,7 +176,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -177,7 +185,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
-        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfc"
     },
@@ -186,6 +194,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -194,6 +203,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -202,6 +212,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -210,6 +221,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -218,7 +230,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.SCALAR",
-        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x3"
     },
@@ -227,6 +239,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -235,7 +248,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.VECTOR",
-        "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1c"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json
index bf68493d4509..9fe9d62b867a 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x60",
         "EventName": "BACLEARS.ANY",
-        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -13,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.LCP",
-        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -22,6 +22,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.MS_BUSY",
+        "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x2"
     },
@@ -30,7 +31,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x61",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
+        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -41,7 +42,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -52,7 +53,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -63,7 +64,7 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -74,7 +75,7 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -85,7 +86,7 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -96,7 +97,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600106",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -107,7 +108,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -118,7 +119,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -129,7 +130,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -140,7 +141,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -151,7 +152,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -162,7 +163,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -173,7 +174,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -184,7 +185,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -195,7 +196,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -206,7 +207,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -217,6 +218,7 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -227,7 +229,7 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -238,6 +240,7 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
+        "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -246,7 +249,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALLS",
-        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
+        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4"
     },
@@ -257,6 +260,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALL_PERIODS",
+        "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4"
     },
@@ -265,7 +269,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x83",
         "EventName": "ICACHE_TAG.STALLS",
-        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -275,7 +279,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -285,7 +289,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -294,7 +298,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -304,7 +308,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -314,7 +318,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -323,7 +327,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -333,7 +337,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_CYCLES_ANY",
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -344,7 +348,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_SWITCHES",
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -353,7 +357,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -362,7 +366,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -372,7 +376,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -383,7 +387,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -392,7 +396,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -402,7 +406,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -413,7 +417,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
index 41d4120d4dae..7c3f9b76d367 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
@@ -5,6 +5,7 @@
         "CounterMask": "6",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
+        "PublicDescription": "Execution stalls while L3 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x6"
     },
@@ -13,7 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
-        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+        "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -23,6 +24,7 @@
         "CounterMask": "2",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -32,6 +34,7 @@
         "CounterMask": "3",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -41,7 +44,7 @@
         "CounterMask": "5",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
-        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -51,7 +54,7 @@
         "CounterMask": "9",
         "EventCode": "0x47",
         "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
-        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
+        "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -169,17 +172,62 @@
         "Data_LA": "1",
         "EventCode": "0xcd",
         "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
-        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
+        "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -190,6 +238,51 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000001",
+        "PublicDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -200,6 +293,29 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F3FC00002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708000002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -210,6 +326,7 @@
         "EventName": "OCR.HWPF_L3.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x94002380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that missed the local socket's L1, L2, and L3 caches. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -220,6 +337,18 @@
         "EventName": "OCR.HWPF_L3.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x84002380",
+        "PublicDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x73C004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -230,6 +359,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F3FC04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -240,6 +370,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F04C04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -250,6 +381,62 @@
         "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x70CC04477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster.  It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x104004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x70C004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x730004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x733004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.SNC_DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x708004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -260,6 +447,7 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x94000800",
+        "PublicDescription": "Counts streaming stores that missed the local socket's L1, L2, and L3 caches. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -270,6 +458,18 @@
         "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x84000800",
+        "PublicDescription": "Counts streaming stores that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.WRITE_ESTIMATE.MEMORY",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0xFBFF80822",
+        "PublicDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM) Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -278,6 +478,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+        "PublicDescription": "Counts demand data read requests that miss the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -286,7 +487,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
+        "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.  Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -295,7 +496,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PublicDescription": "Counts the number of times RTM abort was triggered.",
+        "PublicDescription": "Counts the number of times RTM abort was triggered. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -304,7 +505,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_EVENTS",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt).",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 3 categories (e.g. interrupt). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -313,7 +514,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_MEM",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -322,7 +523,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_MEMTYPE",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x40"
     },
@@ -331,7 +532,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY",
-        "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.",
+        "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -340,7 +541,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.COMMIT",
-        "PublicDescription": "Counts the number of times RTM commit succeeded.",
+        "PublicDescription": "Counts the number of times RTM commit succeeded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -349,7 +550,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.START",
-        "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.",
+        "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -358,7 +559,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CAPACITY_READ",
-        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
+        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -367,7 +568,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
-        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
+        "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -376,7 +577,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x54",
         "EventName": "TX_MEM.ABORT_CONFLICT",
-        "PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
+        "PublicDescription": "Counts the number of times a TSX line had a cache conflict. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json
index c424facf1b95..a58d65556609 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json
@@ -4,354 +4,28 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.PAGE_FAULT",
+        "PublicDescription": "ASSISTS.PAGE_FAULT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
     {
-        "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xb7",
-        "EventName": "EXE.AMX_BUSY",
-        "SampleAfterValue": "2000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000004",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F3FFC0002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.DEMAND_RFO.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708000002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L1D.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10400",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L2.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10070",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L3.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x12380",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.HWPF_L3.REMOTE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x90002380",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10808",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F3FFC4477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x73C004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x104004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode.  In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x70C004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3F33004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x730004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x733004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.READS_TO_CORE.SNC_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x708004477",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)",
-        "Counter": "0,1,2,3",
-        "EventCode": "0x2A,0x2B",
-        "EventName": "OCR.WRITE_ESTIMATE.MEMORY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0xFBFF80822",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_COUNT",
-        "Invert": "1",
-        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xa5",
-        "EventName": "RS.EMPTY_RESOURCE",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "CounterMask": "1",
-        "Deprecated": "1",
-        "EdgeDetect": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS_EMPTY.COUNT",
-        "Invert": "1",
-        "SampleAfterValue": "100003",
-        "UMask": "0x7"
-    },
-    {
-        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "Deprecated": "1",
-        "EventCode": "0xa5",
-        "EventName": "RS_EMPTY.CYCLES",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x7"
-    },
-    {
         "BriefDescription": "Cycles the uncore cannot take further requests",
         "Counter": "0,1,2,3",
         "CounterMask": "1",
         "EventCode": "0x2d",
         "EventName": "XQ.FULL_CYCLES",
-        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
+        "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
index 50cacfbbc7cf..00b05a77c289 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
@@ -6,6 +6,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -15,7 +16,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.DIV_ACTIVE",
-        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+        "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x9"
     },
@@ -26,6 +27,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FP_DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -35,6 +37,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.IDIV_ACTIVE",
+        "PublicDescription": "This event counts the cycles the integer divider is busy. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -45,6 +48,7 @@
         "Deprecated": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.INT_DIVIDER_ACTIVE",
+        "PublicDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -53,7 +57,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.ANY",
-        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.",
+        "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1b"
     },
@@ -62,7 +66,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all branch instructions retired.",
+        "PublicDescription": "Counts all branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009"
     },
     {
@@ -70,7 +74,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND",
-        "PublicDescription": "Counts conditional branch instructions retired.",
+        "PublicDescription": "Counts conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
     },
@@ -79,7 +83,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts not taken branch instructions retired.",
+        "PublicDescription": "Counts not taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
     },
@@ -88,7 +92,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional branch instructions retired.",
+        "PublicDescription": "Counts taken conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
     },
@@ -97,7 +101,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "PublicDescription": "Counts far branch instructions retired.",
+        "PublicDescription": "Counts far branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
     },
@@ -106,7 +110,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.INDIRECT",
-        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -115,7 +119,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "Counts both direct and indirect near call instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2"
     },
@@ -124,7 +128,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "Counts return instructions retired.",
+        "PublicDescription": "Counts return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -133,7 +137,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc4",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts taken branch instructions retired.",
+        "PublicDescription": "Counts taken branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -142,7 +146,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+        "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch.  When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path. Available PDIST counters: 0",
         "SampleAfterValue": "400009"
     },
     {
@@ -150,7 +154,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND",
-        "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "Counts mispredicted conditional branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x11"
     },
@@ -159,7 +163,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
-        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+        "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x10"
     },
@@ -168,7 +172,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.COND_TAKEN",
-        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+        "PublicDescription": "Counts taken conditional mispredicted branch instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x1"
     },
@@ -177,7 +181,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT",
-        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+        "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -186,7 +190,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
-        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+        "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x2"
     },
@@ -195,7 +199,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+        "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken. Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -204,7 +208,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -213,7 +217,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C01",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -222,7 +226,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C02",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.  This state can be entered via the TPAUSE or UMWAIT instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -231,7 +235,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.C0_WAIT",
-        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.",
+        "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x70"
     },
@@ -240,7 +244,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED",
-        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0.  A hyperthread becomes inactive when it executes the HLT or MWAIT instructions.  If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -249,7 +253,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
-        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.",
+        "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted. Available PDIST counters: 0",
         "SampleAfterValue": "25003",
         "UMask": "0x2"
     },
@@ -258,6 +262,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -268,6 +273,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xec",
         "EventName": "CPU_CLK_UNHALTED.PAUSE_INST",
+        "PublicDescription": "CPU_CLK_UNHALTED.PAUSE_INST Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -276,7 +282,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED",
-        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.",
+        "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -293,7 +299,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
-        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+        "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -310,7 +316,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. Available PDIST counters: 0",
         "SampleAfterValue": "2000003"
     },
     {
@@ -319,6 +325,7 @@
         "CounterMask": "8",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS",
+        "PublicDescription": "Cycles while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -328,6 +335,7 @@
         "CounterMask": "1",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS",
+        "PublicDescription": "Cycles while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -337,6 +345,7 @@
         "CounterMask": "16",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+        "PublicDescription": "Cycles while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -346,6 +355,7 @@
         "CounterMask": "12",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS",
+        "PublicDescription": "Execution stalls while L1 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc"
     },
@@ -355,6 +365,7 @@
         "CounterMask": "5",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS",
+        "PublicDescription": "Execution stalls while L2 cache miss demand load is outstanding. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x5"
     },
@@ -364,15 +375,25 @@
         "CounterMask": "4",
         "EventCode": "0xa3",
         "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+        "PublicDescription": "Total execution stalls. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
     {
+        "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xb7",
+        "EventName": "EXE.AMX_BUSY",
+        "PublicDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation. Available PDIST counters: 0",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2"
+    },
+    {
         "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -381,6 +402,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL",
+        "PublicDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0xc"
     },
@@ -389,7 +411,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
-        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -398,7 +420,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -407,7 +429,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
-        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+        "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -417,6 +439,7 @@
         "CounterMask": "5",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS",
+        "PublicDescription": "Execution stalls while memory subsystem has an outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x21"
     },
@@ -426,7 +449,7 @@
         "CounterMask": "2",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
-        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
+        "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -435,7 +458,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa6",
         "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
-        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.",
+        "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80"
     },
@@ -444,7 +467,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x75",
         "EventName": "INST_DECODED.DECODERS",
-        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
+        "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -452,7 +475,7 @@
         "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
-        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+        "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -469,6 +492,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PublicDescription": "INST_RETIRED.MACRO_FUSED Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -477,7 +501,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
-        "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
+        "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -485,7 +509,7 @@
         "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.PREC_DIST",
-        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+        "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0. Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -494,7 +518,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
-        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+        "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -505,7 +529,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEARS_COUNT",
-        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
+        "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -514,7 +538,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
-        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+        "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x80"
     },
@@ -523,6 +547,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.MBA_STALLS",
+        "PublicDescription": "INT_MISC.MBA_STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -531,7 +556,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.RECOVERY_CYCLES",
-        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+        "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -542,6 +567,7 @@
         "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x7",
+        "PublicDescription": "Bubble cycles of BAClear (Unknown Branch). Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -550,7 +576,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xad",
         "EventName": "INT_MISC.UOP_DROPPING",
-        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons",
+        "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -559,6 +585,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.128BIT",
+        "PublicDescription": "INT_VEC_RETIRED.128BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x13"
     },
@@ -567,6 +594,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.256BIT",
+        "PublicDescription": "INT_VEC_RETIRED.256BIT Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xac"
     },
@@ -575,7 +603,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_128",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -584,7 +612,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.ADD_256",
-        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.",
+        "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xc"
     },
@@ -593,6 +621,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.MUL_256",
+        "PublicDescription": "INT_VEC_RETIRED.MUL_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x80"
     },
@@ -601,6 +630,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.SHUFFLES",
+        "PublicDescription": "INT_VEC_RETIRED.SHUFFLES Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x40"
     },
@@ -609,6 +639,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_128",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_128 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -617,6 +648,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe7",
         "EventName": "INT_VEC_RETIRED.VNNI_256",
+        "PublicDescription": "INT_VEC_RETIRED.VNNI_256 Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -625,7 +657,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
-        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+        "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -634,7 +666,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.NO_SR",
-        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x88"
     },
@@ -643,7 +675,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
         "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+        "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x82"
     },
@@ -652,7 +684,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x4c",
         "EventName": "LOAD_HIT_PREFETCH.SWPF",
-        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.",
+        "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -662,7 +694,7 @@
         "CounterMask": "1",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_ACTIVE",
-        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -672,7 +704,7 @@
         "CounterMask": "6",
         "EventCode": "0xa8",
         "EventName": "LSD.CYCLES_OK",
-        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -681,7 +713,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa8",
         "EventName": "LSD.UOPS",
-        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+        "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -692,7 +724,7 @@
         "EdgeDetect": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.COUNT",
-        "PublicDescription": "Counts the number of machine clears (nukes) of any type.",
+        "PublicDescription": "Counts the number of machine clears (nukes) of any type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -701,7 +733,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SMC",
-        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+        "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -710,7 +742,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe0",
         "EventName": "MISC2_RETIRED.LFENCE",
-        "PublicDescription": "number of LFENCE retired instructions",
+        "PublicDescription": "number of LFENCE retired instructions Available PDIST counters: 0",
         "SampleAfterValue": "400009",
         "UMask": "0x20"
     },
@@ -719,7 +751,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcc",
         "EventName": "MISC_RETIRED.LBR_INSERTS",
-        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+        "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -728,7 +760,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SB",
-        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -737,15 +769,69 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa2",
         "EventName": "RESOURCE_STALLS.SCOREBOARD",
+        "PublicDescription": "Counts cycles where the pipeline is stalled due to serializing operations. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses) Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_COUNT",
+        "Invert": "1",
+        "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events) Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa5",
+        "EventName": "RS.EMPTY_RESOURCE",
+        "PublicDescription": "Cycles when Reservation Station (RS) is empty due to a resource in the back-end Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "CounterMask": "1",
+        "Deprecated": "1",
+        "EdgeDetect": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS_EMPTY.COUNT",
+        "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x7"
+    },
+    {
+        "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Deprecated": "1",
+        "EventCode": "0xa5",
+        "EventName": "RS_EMPTY.CYCLES",
+        "PublicDescription": "This event is deprecated. Refer to new event RS.EMPTY Available PDIST counters: 0",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7"
+    },
+    {
         "BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
-        "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.",
+        "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x2"
     },
@@ -754,7 +840,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BAD_SPEC_SLOTS",
-        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.",
+        "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x4"
     },
@@ -763,7 +849,7 @@
         "Counter": "0",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
-        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
+        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x8"
     },
@@ -772,6 +858,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS",
+        "PublicDescription": "TOPDOWN.MEMORY_BOUND_SLOTS Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x10"
     },
@@ -788,7 +875,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.SLOTS_P",
-        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.",
+        "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Available PDIST counters: 0",
         "SampleAfterValue": "10000003",
         "UMask": "0x1"
     },
@@ -797,6 +884,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x76",
         "EventName": "UOPS_DECODED.DEC0_UOPS",
+        "PublicDescription": "UOPS_DECODED.DEC0_UOPS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -805,7 +893,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_0",
-        "PublicDescription": "Number of uops dispatch to execution  port 0.",
+        "PublicDescription": "Number of uops dispatch to execution  port 0. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -814,7 +902,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_1",
-        "PublicDescription": "Number of uops dispatch to execution  port 1.",
+        "PublicDescription": "Number of uops dispatch to execution  port 1. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -823,7 +911,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_2_3_10",
-        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10",
+        "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -832,7 +920,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_4_9",
-        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9",
+        "PublicDescription": "Number of uops dispatch to execution ports 4 and 9 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -841,7 +929,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_5_11",
-        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11",
+        "PublicDescription": "Number of uops dispatch to execution ports 5 and 11 Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -850,7 +938,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_6",
-        "PublicDescription": "Number of uops dispatch to execution  port 6.",
+        "PublicDescription": "Number of uops dispatch to execution  port 6. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x40"
     },
@@ -859,7 +947,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb2",
         "EventName": "UOPS_DISPATCHED.PORT_7_8",
-        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8.",
+        "PublicDescription": "Number of uops dispatch to execution  ports 7 and 8. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x80"
     },
@@ -868,7 +956,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE",
-        "PublicDescription": "Counts the number of uops executed from any thread.",
+        "PublicDescription": "Counts the number of uops executed from any thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -878,7 +966,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -888,7 +976,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -898,7 +986,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -908,7 +996,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.",
+        "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -918,7 +1006,7 @@
         "CounterMask": "1",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_1",
-        "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
+        "PublicDescription": "Cycles where at least 1 uop was executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -928,7 +1016,7 @@
         "CounterMask": "2",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_2",
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -938,7 +1026,7 @@
         "CounterMask": "3",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_3",
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -948,7 +1036,7 @@
         "CounterMask": "4",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.CYCLES_GE_4",
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -959,7 +1047,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALLS",
         "Invert": "1",
-        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -971,6 +1059,7 @@
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.STALL_CYCLES",
         "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -979,6 +1068,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Counts the number of uops to be executed per-thread each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -987,7 +1077,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb1",
         "EventName": "UOPS_EXECUTED.X87",
-        "PublicDescription": "Counts the number of x87 uops executed.",
+        "PublicDescription": "Counts the number of x87 uops executed. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -996,7 +1086,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.ANY",
-        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1006,6 +1096,7 @@
         "CounterMask": "1",
         "EventCode": "0xae",
         "EventName": "UOPS_ISSUED.CYCLES",
+        "PublicDescription": "UOPS_ISSUED.CYCLES Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1015,7 +1106,7 @@
         "CounterMask": "1",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.CYCLES",
-        "PublicDescription": "Counts cycles where at least one uop has retired.",
+        "PublicDescription": "Counts cycles where at least one uop has retired. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -1024,7 +1115,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.HEAVY",
-        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.",
+        "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -1035,6 +1126,7 @@
         "EventName": "UOPS_RETIRED.MS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "UOPS_RETIRED.MS Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -1043,7 +1135,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.SLOTS",
-        "PublicDescription": "Counts the retirement slots used each cycle.",
+        "PublicDescription": "Counts the retirement slots used each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -1054,7 +1146,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALLS",
         "Invert": "1",
-        "PublicDescription": "This event counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -1066,6 +1158,7 @@
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "Invert": "1",
+        "PublicDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     }
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json
index 609a9549cbf3..3d3f88600e26 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
-        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+        "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -14,7 +14,7 @@
         "CounterMask": "1",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -23,7 +23,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -32,7 +32,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -41,7 +41,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -50,7 +50,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -59,7 +59,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x12",
         "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -68,7 +68,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.STLB_HIT",
-        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+        "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -78,7 +78,7 @@
         "CounterMask": "1",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -87,7 +87,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -96,7 +96,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
-        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -105,7 +105,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -114,7 +114,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks  (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -123,7 +123,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x13",
         "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -132,7 +132,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.STLB_HIT",
-        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
+        "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -142,7 +142,7 @@
         "CounterMask": "1",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_ACTIVE",
-        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
+        "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -151,7 +151,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED",
-        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xe"
     },
@@ -160,7 +160,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
-        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -169,7 +169,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
-        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+        "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -178,7 +178,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x11",
         "EventName": "ITLB_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
+        "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     }
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/cache.json b/tools/perf/pmu-events/arch/x86/grandridge/cache.json
index 04802e254e51..877052db1490 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/cache.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/cache.json
@@ -1,5 +1,92 @@
 [
     {
+        "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x51",
+        "EventName": "DL1.DIRTY_EVICTION",
+        "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.  Does not count evictions or dirty writebacks caused by snoops.  Does not count a replacement unless a (dirty) line was written back.",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.E",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.F",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x10"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.M",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x8"
+    },
+    {
+        "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x25",
+        "EventName": "L2_LINES_IN.S",
+        "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x26",
+        "EventName": "L2_LINES_OUT.NON_SILENT",
+        "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x26",
+        "EventName": "L2_LINES_OUT.SILENT",
+        "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill.  Increments on the core that brought the line in originally.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.HIT",
+        "SampleAfterValue": "200003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.MISS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject  short and long rejects, per core event",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x24",
+        "EventName": "L2_REQUEST.REJECTS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
@@ -35,7 +122,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which hit in the LLC.",
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x35",
         "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_HIT",
@@ -43,7 +130,7 @@
         "UMask": "0x6"
     },
     {
-        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which missed all the caches.",
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an ICACHE or ITLB miss which missed all the caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x35",
         "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_MISS",
@@ -68,7 +155,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC.",
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC. If the core has access to an L3 cache, an LLC hit refers to an L3 cache hit, otherwise it counts zeros.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x34",
         "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT",
@@ -76,7 +163,7 @@
         "UMask": "0x6"
     },
     {
-        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.",
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches. If the core has access to an L3 cache, an LLC miss refers to an L3 cache miss, otherwise it is an L2 cache miss.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x34",
         "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS",
@@ -84,6 +171,14 @@
         "UMask": "0x78"
     },
     {
+        "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x34",
+        "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x80"
+    },
+    {
         "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xd3",
@@ -336,6 +431,33 @@
         "UMask": "0x42"
     },
     {
+        "BriefDescription": "Counts the number of memory uops retired that missed in the second level TLB.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Data_LA": "1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.STLB_MISS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x13"
+    },
+    {
+        "BriefDescription": "Counts the number of load uops retired that miss in the second Level TLB.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Data_LA": "1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+        "SampleAfterValue": "200003",
+        "UMask": "0x11"
+    },
+    {
+        "BriefDescription": "Counts the number of store uops retired that miss in the second level TLB.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "Data_LA": "1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+        "SampleAfterValue": "200003",
+        "UMask": "0x12"
+    },
+    {
         "BriefDescription": "Counts the number of  stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES",
         "Counter": "0,1,2,3,4,5,6,7",
         "Data_LA": "1",
@@ -345,12 +467,24 @@
         "UMask": "0x6"
     },
     {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -361,6 +495,18 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -371,6 +517,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/counter.json b/tools/perf/pmu-events/arch/x86/grandridge/counter.json
index 9fd5d8ad6d3b..d9ac3aca5bd5 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/counter.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/counter.json
@@ -37,6 +37,6 @@
     {
         "Unit": "CHACMS",
         "CountersNumFixed": "0",
-        "CountersNumGeneric": 4
+        "CountersNumGeneric": "4"
     }
 ]
 \ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/frontend.json b/tools/perf/pmu-events/arch/x86/grandridge/frontend.json
index 7cdf611efb23..fef5cba533bb 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/frontend.json
@@ -31,5 +31,13 @@
         "EventName": "ICACHE.MISSES",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the micro-sequencer is busy.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xe7",
+        "EventName": "MS_DECODED.MS_BUSY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json
index 2f9959c61718..1c6dba7b2822 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json
@@ -216,15 +216,17 @@
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions",
         "MetricExpr": "tma_core_bound",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_core_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_allocation_restriction",
+        "MetricThreshold": "tma_allocation_restriction > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls",
         "MetricExpr": "TOPDOWN_BE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
+        "MetricThreshold": "tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count",
         "ScaleUnit": "100%"
@@ -232,92 +234,104 @@
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_bad_speculation",
+        "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1",
-        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_detect",
-        "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches",
+        "MetricThreshold": "tma_branch_detect > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
+        "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_branch_mispredicts",
+        "MetricThreshold": "tma_branch_mispredicts > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
         "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_branch_resteer",
+        "MetricThreshold": "tma_branch_resteer > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS)",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).",
         "MetricExpr": "TOPDOWN_FE_BOUND.CISC / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_cisc",
+        "MetricThreshold": "tma_cisc > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of cycles due to backend bound stalls that are bounded by core restrictions and not attributed to an outstanding load or stores, or resource limitation",
         "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_core_bound",
+        "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.",
         "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_decode",
+        "MetricThreshold": "tma_decode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_fast_nuke",
+        "MetricThreshold": "tma_fast_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls",
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.",
         "MetricExpr": "TOPDOWN_FE_BOUND.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
+        "MetricThreshold": "tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.",
         "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_icache_misses",
+        "MetricThreshold": "tma_icache_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_bandwidth",
+        "MetricThreshold": "tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.",
         "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_frontend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
         "MetricName": "tma_ifetch_latency",
+        "MetricThreshold": "tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
@@ -348,33 +362,28 @@
     {
         "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss",
         "MetricExpr": "100 * (LD_HEAD.DTLB_MISS_AT_RET + LD_HEAD.PGWALK_AT_RET) / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles",
-        "MetricName": "tma_info_bottleneck_dtlb_miss_bound_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles"
     },
     {
         "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss",
         "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.ALL / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles;Ifetch",
-        "MetricName": "tma_info_bottleneck_ifetch_miss_bound_cycles",
-        "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound",
-        "ScaleUnit": "100%"
+        "MetricGroup": "Ifetch",
+        "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles",
+        "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound"
     },
     {
         "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss",
         "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.ALL / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles;Load_Store_Miss",
-        "MetricName": "tma_info_bottleneck_load_miss_bound_cycles",
-        "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound",
-        "ScaleUnit": "100%"
+        "MetricGroup": "Load_Store_Miss",
+        "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles",
+        "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound"
     },
     {
         "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall",
         "MetricExpr": "100 * LD_HEAD.ANY_AT_RET / CPU_CLK_UNHALTED.CORE",
-        "MetricGroup": "Cycles;Mem_Exec",
-        "MetricName": "tma_info_bottleneck_mem_exec_bound_cycles",
-        "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound",
-        "ScaleUnit": "100%"
+        "MetricGroup": "Mem_Exec",
+        "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles",
+        "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound"
     },
     {
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
@@ -429,26 +438,22 @@
     {
         "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full",
         "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.LD_BUF / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_buffer_stalls_load_buffer_stall_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles"
     },
     {
         "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full",
         "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.RSV / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_buffer_stalls_mem_rsv_stall_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles"
     },
     {
         "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full",
         "MetricExpr": "100 * MEM_SCHEDULER_BLOCK.ST_BUF / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_buffer_stalls_store_buffer_stall_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles"
     },
     {
         "BriefDescription": "Cycles Per Instruction",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE / INST_RETIRED.ANY",
-        "MetricName": "tma_info_core_cpi",
-        "ScaleUnit": "1per_instr"
+        "MetricName": "tma_info_core_cpi"
     },
     {
         "BriefDescription": "Floating Point Operations Per Cycle",
@@ -469,28 +474,46 @@
     {
         "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2",
         "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.L2_HIT / MEM_BOUND_STALLS_IFETCH.ALL",
-        "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l2hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit"
+    },
+    {
+        "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2",
+        "MetricExpr": "100 * (MEM_BOUND_STALLS_IFETCH.LLC_HIT + MEM_BOUND_STALLS_IFETCH.LLC_MISS) / MEM_BOUND_STALLS_IFETCH.ALL",
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss"
     },
     {
         "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L3",
         "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_HIT / MEM_BOUND_STALLS_IFETCH.ALL",
-        "MetricName": "tma_info_ifetch_miss_bound_ifetchmissbound_with_l3hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3hit"
+    },
+    {
+        "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss subsequently misses in the L3",
+        "MetricExpr": "100 * MEM_BOUND_STALLS_IFETCH.LLC_MISS / MEM_BOUND_STALLS_IFETCH.ALL",
+        "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l3miss"
     },
     {
         "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2",
         "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.L2_HIT / MEM_BOUND_STALLS_LOAD.ALL",
         "MetricGroup": "load_store_bound",
-        "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l2hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit"
+    },
+    {
+        "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2",
+        "MetricExpr": "100 * (MEM_BOUND_STALLS_LOAD.LLC_HIT + MEM_BOUND_STALLS_LOAD.LLC_MISS) / MEM_BOUND_STALLS_LOAD.ALL",
+        "MetricGroup": "load_store_bound",
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss"
     },
     {
         "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L3",
         "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_HIT / MEM_BOUND_STALLS_LOAD.ALL",
         "MetricGroup": "load_store_bound",
-        "MetricName": "tma_info_load_miss_bound_loadmissbound_with_l3hit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3hit"
+    },
+    {
+        "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses the L3",
+        "MetricExpr": "100 * MEM_BOUND_STALLS_LOAD.LLC_MISS / MEM_BOUND_STALLS_LOAD.ALL",
+        "MetricGroup": "load_store_bound",
+        "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l3miss"
     },
     {
         "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a pipeline block",
@@ -528,44 +551,37 @@
     {
         "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block",
         "MetricExpr": "100 * LD_BLOCKS.ADDRESS_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_mem_exec_blocks_loads_with_adressaliasing",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing"
     },
     {
         "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block",
         "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS",
-        "MetricName": "tma_info_mem_exec_blocks_loads_with_storefwdblk",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss",
         "MetricExpr": "100 * LD_HEAD.L1_MISS_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_l1miss",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc",
         "MetricExpr": "100 * LD_HEAD.OTHER_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_otherpipelineblks",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk",
         "MetricExpr": "100 * LD_HEAD.PGWALK_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_pagewalk",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss",
         "MetricExpr": "100 * LD_HEAD.DTLB_MISS_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_stlbhit",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit"
     },
     {
         "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match",
         "MetricExpr": "100 * LD_HEAD.ST_ADDR_AT_RET / LD_HEAD.ANY_AT_RET",
-        "MetricName": "tma_info_mem_exec_bound_loadhead_with_storefwding",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding"
     },
     {
         "BriefDescription": "Instructions per Load",
@@ -595,8 +611,7 @@
     {
         "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction",
         "MetricExpr": "100 * SERIALIZATION.C01_MS_SCB / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricName": "tma_info_serialization_tpause_cycles",
-        "ScaleUnit": "100%"
+        "MetricName": "tma_info_serialization_%_tpause_cycles"
     },
     {
         "BriefDescription": "Average CPU Utilization",
@@ -612,17 +627,20 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.CORE_P:k / CPU_CLK_UNHALTED.CORE",
+        "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE_P@k / CPU_CLK_UNHALTED.CORE",
+        "MetricGroup": "Summary",
         "MetricName": "tma_info_system_kernel_utilization"
     },
     {
         "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE_P / CPU_CLK_UNHALTED.CORE",
-        "MetricName": "tma_info_system_mux"
+        "MetricName": "tma_info_system_mux",
+        "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9"
     },
     {
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.CORE / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricGroup": "Power",
         "MetricName": "tma_info_system_turbo_utilization"
     },
     {
@@ -646,90 +664,102 @@
         "MetricName": "tma_info_uop_mix_x87_uop_ratio"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.",
         "MetricExpr": "TOPDOWN_FE_BOUND.ITLB_MISS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
         "MetricName": "tma_itlb_misses",
+        "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_ifetch_latency > 0.15 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_bad_speculation_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
         "MetricName": "tma_machine_clears",
+        "MetricThreshold": "tma_machine_clears > 0.05 & tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops",
         "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_mem_scheduler",
+        "MetricThreshold": "tma_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops",
         "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_non_mem_scheduler",
+        "MetricThreshold": "tma_non_mem_scheduler > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)",
         "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_machine_clears_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
         "MetricName": "tma_nuke",
+        "MetricThreshold": "tma_nuke > 0.05 & (tma_machine_clears > 0.05 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.",
         "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_other_fb",
+        "MetricThreshold": "tma_other_fb > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes",
+        "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.",
         "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
         "MetricName": "tma_predecode",
+        "MetricThreshold": "tma_predecode > 0.05 & (tma_ifetch_bandwidth > 0.1 & tma_frontend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)",
         "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_register",
+        "MetricThreshold": "tma_register > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)",
         "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_reorder_buffer",
+        "MetricThreshold": "tma_reorder_buffer > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation",
         "MetricExpr": "tma_backend_bound - tma_core_bound",
-        "MetricGroup": "Slots;TopdownL2;tma_L2_group;tma_backend_bound_group",
+        "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
         "MetricName": "tma_resource_bound",
+        "MetricThreshold": "tma_resource_bound > 0.2 & tma_backend_bound > 0.1",
         "MetricgroupNoGroup": "TopdownL2",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that result in retirement slots",
         "MetricExpr": "TOPDOWN_RETIRING.ALL_P / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL1;tma_L1_group",
+        "MetricGroup": "TopdownL1;tma_L1_group",
         "MetricName": "tma_retiring",
+        "MetricThreshold": "tma_retiring > 0.75",
         "MetricgroupNoGroup": "TopdownL1",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)",
         "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / (6 * CPU_CLK_UNHALTED.CORE)",
-        "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_resource_bound_group",
+        "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
         "MetricName": "tma_serialization",
+        "MetricThreshold": "tma_serialization > 0.1 & (tma_resource_bound > 0.2 & tma_backend_bound > 0.1)",
         "ScaleUnit": "100%"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/memory.json b/tools/perf/pmu-events/arch/x86/grandridge/memory.json
index 22d23077618e..48b6301e7696 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/memory.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/memory.json
@@ -79,6 +79,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00001",
+        "PublicDescription": "Counts demand data reads that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -89,6 +90,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3FBFC00002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/other.json b/tools/perf/pmu-events/arch/x86/grandridge/other.json
index 28f9a4c3ea84..ea34103a8292 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/other.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/other.json
@@ -9,41 +9,14 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts demand data reads that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10001",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0xB7",
-        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x10002",
-        "SampleAfterValue": "100003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xB7",
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10800",
+        "PublicDescription": "Counts streaming stores that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
-    },
-    {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
-        "Counter": "0,1,2,3,4,5,6,7",
-        "EventCode": "0x75",
-        "EventName": "SERIALIZATION.C01_MS_SCB",
-        "SampleAfterValue": "200003",
-        "UMask": "0x4"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json
index 40fa4f5ae261..f56d8d816e53 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json
@@ -57,6 +57,14 @@
         "UMask": "0xfb"
     },
     {
+        "BriefDescription": "Counts the number of near indirect JMP branch instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc4",
+        "EventName": "BR_INST_RETIRED.INDIRECT_JMP",
+        "SampleAfterValue": "200003",
+        "UMask": "0xef"
+    },
+    {
         "BriefDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL",
         "Counter": "0,1,2,3,4,5,6,7",
         "Deprecated": "1",
@@ -82,6 +90,30 @@
         "UMask": "0xf7"
     },
     {
+        "BriefDescription": "Counts the number of near taken branch instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc4",
+        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "SampleAfterValue": "200003",
+        "UMask": "0xc0"
+    },
+    {
+        "BriefDescription": "Counts the number of near relative CALL branch instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc4",
+        "EventName": "BR_INST_RETIRED.REL_CALL",
+        "SampleAfterValue": "200003",
+        "UMask": "0xfd"
+    },
+    {
+        "BriefDescription": "Counts the number of near relative JMP branch instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc4",
+        "EventName": "BR_INST_RETIRED.REL_JMP",
+        "SampleAfterValue": "200003",
+        "UMask": "0xdf"
+    },
+    {
         "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
@@ -122,6 +154,14 @@
         "UMask": "0xfb"
     },
     {
+        "BriefDescription": "Counts the number of mispredicted near indirect JMP branch instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc5",
+        "EventName": "BR_MISP_RETIRED.INDIRECT_JMP",
+        "SampleAfterValue": "200003",
+        "UMask": "0xef"
+    },
+    {
         "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired.",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc5",
@@ -185,6 +225,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired",
         "Counter": "Fixed counter 0",
         "EventName": "INST_RETIRED.ANY",
+        "PublicDescription": "Fixed Counter: Counts the number of instructions retired Available PDIST counters: 32",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -236,8 +277,9 @@
         "UMask": "0x20"
     },
     {
-        "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+        "BriefDescription": "This event is deprecated.",
         "Counter": "0,1,2,3,4,5,6,7",
+        "Deprecated": "1",
         "EventCode": "0xc3",
         "EventName": "MACHINE_CLEARS.SLOW",
         "SampleAfterValue": "20003",
@@ -260,6 +302,14 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x75",
+        "EventName": "SERIALIZATION.C01_MS_SCB",
+        "SampleAfterValue": "200003",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x73",
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json
index 6a80cf6cbd36..b89ab6e5cfb5 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json
@@ -9,6 +9,16 @@
         "Unit": "CHACMS"
     },
     {
+        "BriefDescription": "Counts the number of cycles FAST trigger is received from the global FAST distress wire.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x34",
+        "EventName": "UNC_CHACMS_RING_SRC_THRTL",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PortMask": "0x000",
+        "Unit": "CHACMS"
+    },
+    {
         "BriefDescription": "Number of CHA clock cycles while the event is enabled",
         "Counter": "0,1,2,3",
         "EventCode": "0x01",
@@ -531,6 +541,26 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x13",
+        "EventName": "UNC_CHA_RxC_INSERTS.IRQ",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.",
+        "Counter": "0",
+        "EventCode": "0x11",
+        "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "All TOR Inserts",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
@@ -603,7 +633,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Data read opt prefetch from local IA that miss the cache",
+        "BriefDescription": "Data read opt prefetch from local IA",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF",
@@ -764,7 +794,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Last level cache prefetch read for ownership from local IA that miss the cache",
+        "BriefDescription": "Last level cache prefetch read for ownership from local IA",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO",
@@ -859,7 +889,7 @@
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_LOCAL",
         "PerPkg": "1",
-        "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC",
+        "PublicDescription": "TOR Inserts : Data read opt prefetch from local iA that missed the LLC targeting local memory",
         "UMask": "0xc8a6fe01",
         "Unit": "CHA"
     },
@@ -934,7 +964,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Read for ownership from local IA that miss the cache",
+        "BriefDescription": "Read for ownership from local IA that miss the LLC targeting local memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL",
@@ -954,7 +984,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Read for ownership prefetch from local IA that miss the cache",
+        "BriefDescription": "Read for ownership prefetch from local IA that miss the LLC targeting local memory",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL",
@@ -1024,7 +1054,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Read for ownership from local IA that miss the cache",
+        "BriefDescription": "Read for ownership from local IA",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO",
@@ -1034,7 +1064,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "Read for ownership prefetch from local IA that miss the cache",
+        "BriefDescription": "Read for ownership prefetch from local IA",
         "Counter": "0,1,2,3",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF",
@@ -1406,7 +1436,6 @@
         "Counter": "0",
         "EventCode": "0x36",
         "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT",
-        "Experimental": "1",
         "PerPkg": "1",
         "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores",
         "UMask": "0xc827ff01",
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json
index e75b3050ccd5..6a11e5505957 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-memory.json
@@ -189,6 +189,256 @@
         "Unit": "IMC"
     },
     {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH0_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 temp readings forced 2x refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA7",
+        "EventName": "UNC_M_MR4_2XREF_CYCLES.SCH1_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH0_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles MR4 MRRs was triggered/running",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA6",
+        "EventName": "UNC_M_PDC_MR4ACTIVE_CYCLES.SCH1_DIMM1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK2",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH0_RANK3",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x10",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x20",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK2",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x40",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x47",
+        "EventName": "UNC_M_POWERDOWN_CYCLES.SCH1_RANK3",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x80",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles a given rank is in Power Down Mode and all pages are closed",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x88",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD_CYCLES",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x89",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM and throttle level is zero.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x89",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.BW_SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "MR4 temp reading is throttling",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.MR4BLKEN",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x8",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "RAPL is throttling",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x46",
+        "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RAPLBLK",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x4",
+        "Unit": "IMC"
+    },
+    {
         "BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.",
         "Counter": "0,1,2,3",
         "EventCode": "0x03",
@@ -361,6 +611,94 @@
         "Unit": "IMC"
     },
     {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8e",
+        "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Critical level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8e",
+        "EventName": "UNC_M_THROTTLE_CRIT_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at High level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8d",
+        "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at High level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8d",
+        "EventName": "UNC_M_THROTTLE_HIGH_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8b",
+        "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Normal level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8b",
+        "EventName": "UNC_M_THROTTLE_LOW_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8c",
+        "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT0",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x1",
+        "Unit": "IMC"
+    },
+    {
+        "BriefDescription": "# of cycles Throttling at Mid level on specified DIMM",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x8c",
+        "EventName": "UNC_M_THROTTLE_MID_CYCLES.SLOT1",
+        "Experimental": "1",
+        "PerPkg": "1",
+        "PublicDescription": "-",
+        "UMask": "0x2",
+        "Unit": "IMC"
+    },
+    {
         "BriefDescription": "Write Pending Queue Allocations",
         "Counter": "0,1,2,3",
         "EventCode": "0x22",
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json
index d155da8610d8..32f99a8a3871 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json
@@ -4,6 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.HWPF_MISS",
+        "PublicDescription": "L1D.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -12,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x51",
         "EventName": "L1D.REPLACEMENT",
-        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+        "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -21,7 +22,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -32,7 +33,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
-        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -41,7 +42,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.L2_STALLS",
-        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+        "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -50,7 +51,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -60,7 +61,7 @@
         "CounterMask": "1",
         "EventCode": "0x48",
         "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -69,7 +70,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x25",
         "EventName": "L2_LINES_IN.ALL",
-        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+        "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1f"
     },
@@ -78,7 +79,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.NON_SILENT",
-        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3 Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -87,7 +88,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.SILENT",
-        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -96,7 +97,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x26",
         "EventName": "L2_LINES_OUT.USELESS_HWPF",
-        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
+        "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -105,7 +106,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.ALL",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff"
     },
@@ -114,7 +115,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.HIT",
-        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]",
+        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xdf"
     },
@@ -123,7 +124,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_REQUEST.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f"
     },
@@ -132,7 +133,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "PublicDescription": "Counts the total number of L2 code requests.",
+        "PublicDescription": "Counts the total number of L2 code requests. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe4"
     },
@@ -141,7 +142,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe1"
     },
@@ -150,7 +151,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_MISS",
-        "PublicDescription": "Counts demand requests that miss L2 cache.",
+        "PublicDescription": "Counts demand requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x27"
     },
@@ -159,7 +160,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
-        "PublicDescription": "Counts demand requests to L2 cache.",
+        "PublicDescription": "Counts demand requests to L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe7"
     },
@@ -168,6 +169,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_HWPF",
+        "PublicDescription": "L2_RQSTS.ALL_HWPF Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xf0"
     },
@@ -176,7 +178,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.ALL_RFO",
-        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
+        "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xe2"
     },
@@ -185,7 +187,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
+        "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc4"
     },
@@ -194,7 +196,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+        "PublicDescription": "Counts L2 cache misses when fetching instructions. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x24"
     },
@@ -203,7 +205,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc1"
     },
@@ -212,7 +214,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
-        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
+        "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x21"
     },
@@ -221,7 +223,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HIT",
-        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]",
+        "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xdf"
     },
@@ -230,6 +232,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.HWPF_MISS",
+        "PublicDescription": "L2_RQSTS.HWPF_MISS Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x30"
     },
@@ -238,7 +241,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.MISS",
-        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
+        "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x3f"
     },
@@ -247,7 +250,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.REFERENCES",
-        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
+        "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL] Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xff"
     },
@@ -256,7 +259,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_HIT",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc2"
     },
@@ -265,7 +268,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.RFO_MISS",
-        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+        "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x22"
     },
@@ -274,7 +277,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_HIT",
-        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0xc8"
     },
@@ -283,7 +286,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x24",
         "EventName": "L2_RQSTS.SWPF_MISS",
-        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
+        "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x28"
     },
@@ -292,7 +295,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x23",
         "EventName": "L2_TRANS.L2_WB",
-        "PublicDescription": "Counts L2 writebacks that access L2 cache.",
+        "PublicDescription": "Counts L2 writebacks that access L2 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x40"
     },
@@ -301,7 +304,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.MISS",
-        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x41"
     },
@@ -310,7 +313,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2.  It does not include hardware prefetches to the L3, and may not count other types of requests to the L3. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4f"
     },
@@ -320,7 +323,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_LOADS",
-        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
+        "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x81"
     },
@@ -330,7 +333,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ALL_STORES",
-        "PublicDescription": "Counts all retired store instructions.",
+        "PublicDescription": "Counts all retired store instructions. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x82"
     },
@@ -340,7 +343,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.ANY",
-        "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+        "PublicDescription": "Counts all retired memory instructions - loads and stores. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x83"
     },
@@ -350,7 +353,10 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
-        "PublicDescription": "Counts retired load instructions with locked access.",
+        "PublicDescription": "Counts retired load instructions with locked access. Available PDIST counters: 0",
+        "RetirementLatencyMax": 5156,
+        "RetirementLatencyMean": 63.76,
+        "RetirementLatencyMin": 15,
         "SampleAfterValue": "100007",
         "UMask": "0x21"
     },
@@ -360,7 +366,10 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired load instructions that split across a cacheline boundary. Available PDIST counters: 0",
+        "RetirementLatencyMax": 4704,
+        "RetirementLatencyMean": 3.97,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100003",
         "UMask": "0x41"
     },
@@ -370,7 +379,10 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
-        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+        "PublicDescription": "Counts retired store instructions that split across a cacheline boundary. Available PDIST counters: 0",
+        "RetirementLatencyMax": 65535,
+        "RetirementLatencyMean": 19.0,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100003",
         "UMask": "0x42"
     },
@@ -380,7 +392,10 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
-        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
+        "RetirementLatencyMax": 3424,
+        "RetirementLatencyMean": 1.57,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100003",
         "UMask": "0x9"
     },
@@ -390,7 +405,10 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES",
-        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB). Available PDIST counters: 0",
+        "RetirementLatencyMax": 65535,
+        "RetirementLatencyMean": 5.24,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100003",
         "UMask": "0xa"
     },
@@ -400,7 +418,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x11"
     },
@@ -410,7 +428,7 @@
         "Data_LA": "1",
         "EventCode": "0xd0",
         "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+        "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x12"
     },
@@ -419,7 +437,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x43",
         "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
-        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
+        "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss) Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfd"
     },
@@ -429,7 +447,10 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
+        "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3. Available PDIST counters: 0",
+        "RetirementLatencyMax": 4472,
+        "RetirementLatencyMean": 353.04,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "20011",
         "UMask": "0x4"
     },
@@ -439,7 +460,10 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
-        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+        "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache. Available PDIST counters: 0",
+        "RetirementLatencyMax": 830,
+        "RetirementLatencyMean": 125.27,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "20011",
         "UMask": "0x1"
     },
@@ -449,7 +473,7 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
-        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
+        "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -459,7 +483,10 @@
         "Data_LA": "1",
         "EventCode": "0xd2",
         "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
-        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+        "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache. Available PDIST counters: 0",
+        "RetirementLatencyMax": 3939,
+        "RetirementLatencyMean": 289.9,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "20011",
         "UMask": "0x2"
     },
@@ -469,7 +496,10 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
-        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
+        "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM. Available PDIST counters: 0",
+        "RetirementLatencyMax": 4146,
+        "RetirementLatencyMean": 115.83,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x1"
     },
@@ -479,6 +509,10 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
+        "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM Available PDIST counters: 0",
+        "RetirementLatencyMax": 3572,
+        "RetirementLatencyMean": 430.22,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -488,7 +522,10 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
-        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
+        "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache. Available PDIST counters: 0",
+        "RetirementLatencyMax": 8552,
+        "RetirementLatencyMean": 125.36,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x8"
     },
@@ -498,6 +535,10 @@
         "Data_LA": "1",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
+        "PublicDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM Available PDIST counters: 0",
+        "RetirementLatencyMax": 2580,
+        "RetirementLatencyMean": 135.29,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -507,7 +548,7 @@
         "Data_LA": "1",
         "EventCode": "0xd4",
         "EventName": "MEM_LOAD_MISC_RETIRED.UC",
-        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock). Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x4"
     },
@@ -517,7 +558,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x40"
     },
@@ -527,7 +568,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -537,7 +578,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L1_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x8"
     },
@@ -547,7 +588,10 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_HIT",
-        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+        "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources. Available PDIST counters: 0",
+        "RetirementLatencyMax": 7140,
+        "RetirementLatencyMean": 5.71,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "200003",
         "UMask": "0x2"
     },
@@ -557,7 +601,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L2_MISS",
-        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+        "PublicDescription": "Counts retired load instructions missed L2 cache as data sources. Available PDIST counters: 0",
         "SampleAfterValue": "100021",
         "UMask": "0x10"
     },
@@ -567,7 +611,10 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache. Available PDIST counters: 0",
+        "RetirementLatencyMax": 5630,
+        "RetirementLatencyMean": 57.64,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100021",
         "UMask": "0x4"
     },
@@ -577,7 +624,7 @@
         "Data_LA": "1",
         "EventCode": "0xd1",
         "EventName": "MEM_LOAD_RETIRED.L3_MISS",
-        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+        "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache. Available PDIST counters: 0",
         "SampleAfterValue": "50021",
         "UMask": "0x20"
     },
@@ -586,6 +633,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x44",
         "EventName": "MEM_STORE_RETIRED.L2_HIT",
+        "PublicDescription": "MEM_STORE_RETIRED.L2_HIT Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x1"
     },
@@ -594,17 +642,29 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xe5",
         "EventName": "MEM_UOP_RETIRED.ANY",
-        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
+        "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
     {
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.",
         "Counter": "0,1,2,3",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -615,6 +675,18 @@
         "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0004",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "PublicDescription": "Counts demand data reads that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -625,6 +697,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0001",
+        "PublicDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -635,6 +708,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -645,6 +719,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x4003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -655,6 +730,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x8003C0001",
+        "PublicDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -665,6 +741,7 @@
         "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1030000001",
+        "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -675,6 +752,40 @@
         "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x830000001",
+        "PublicDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x1008000001",
+        "PublicDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x808000001",
+        "PublicDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -685,6 +796,7 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F803C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -695,6 +807,29 @@
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C0002",
+        "PublicDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10808",
+        "PublicDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F3FFC4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -705,6 +840,7 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x3F003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -715,6 +851,18 @@
         "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x10003C4477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2A,0x2B",
+        "EventName": "OCR.READS_TO_CORE.REMOTE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F33004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -725,6 +873,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1830004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified). Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -735,6 +884,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1030004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -745,6 +895,7 @@
         "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x830004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -755,6 +906,7 @@
         "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1008004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -765,6 +917,7 @@
         "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x808004477",
+        "PublicDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -775,6 +928,7 @@
         "EventName": "OCR.RFO_TO_CORE.L3_HIT_M",
         "MSRIndex": "0x1a6,0x1a7",
         "MSRValue": "0x1F80040022",
+        "PublicDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -783,7 +937,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
-        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
+        "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc.. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -792,7 +946,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DATA_RD",
-        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+        "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -801,7 +955,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
-        "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.",
+        "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -810,7 +964,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+        "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -819,7 +973,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x21",
         "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
-        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+        "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -829,7 +983,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
-        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -839,7 +993,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -849,6 +1003,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "PublicDescription": "Cycles where at least 1 outstanding demand data read request is pending. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -858,7 +1013,7 @@
         "CounterMask": "1",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -867,6 +1022,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+        "PublicDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x8"
     },
@@ -875,7 +1031,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+        "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x2"
     },
@@ -884,7 +1040,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+        "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.   Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -893,7 +1049,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x20",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
-        "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.",
+        "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x4"
     },
@@ -902,7 +1058,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x2c",
         "EventName": "SQ_MISC.BUS_LOCK",
-        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+        "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically.  Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -911,6 +1067,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.ANY",
+        "PublicDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0xf"
     },
@@ -919,7 +1076,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.NTA",
-        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHNTA instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -928,7 +1085,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
-        "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHW instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -937,7 +1094,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T0",
-        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT0 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -946,7 +1103,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x40",
         "EventName": "SW_PREFETCH_ACCESS.T1_T2",
-        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+        "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     }
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/counter.json b/tools/perf/pmu-events/arch/x86/graniterapids/counter.json
index 137da7efa8b1..5d3b202eadd3 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/counter.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/counter.json
@@ -73,5 +73,10 @@
         "Unit": "MDF",
         "CountersNumFixed": "0",
         "CountersNumGeneric": "4"
+    },
+    {
+        "Unit": "UBOX",
+        "CountersNumFixed": "0",
+        "CountersNumGeneric": "2"
     }
 ]
 \ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json b/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json
index 59789eee060c..1832dd952f66 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json
@@ -5,6 +5,7 @@
         "CounterMask": "1",
         "EventCode": "0xb0",
         "EventName": "ARITH.FPDIV_ACTIVE",
+        "PublicDescription": "This event counts the cycles the floating point divider is busy. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -13,7 +14,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.FP",
-        "PublicDescription": "Counts all microcode Floating Point assists.",
+        "PublicDescription": "Counts all microcode Floating Point assists. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -22,6 +23,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc1",
         "EventName": "ASSISTS.SSE_AVX_MIX",
+        "PublicDescription": "ASSISTS.SSE_AVX_MIX Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x10"
     },
@@ -30,6 +32,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -38,6 +41,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -46,6 +50,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.PORT_5",
+        "PublicDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -54,6 +59,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V0",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -62,6 +68,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V1",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
@@ -70,6 +77,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xb3",
         "EventName": "FP_ARITH_DISPATCHED.V2",
+        "PublicDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5] Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -78,7 +86,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -87,7 +95,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -96,7 +104,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -105,7 +113,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -114,7 +122,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x18"
     },
@@ -123,7 +131,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x40"
     },
@@ -132,7 +140,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x80"
     },
@@ -141,7 +149,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS",
-        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x60"
     },
@@ -150,7 +158,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x3"
     },
@@ -159,7 +167,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -168,7 +176,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
-        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -177,7 +185,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xc7",
         "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
-        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "PublicDescription": "Number of any Vector retired FP arithmetic instructions.  The DAZ and FTZ flags in the MXCSR register need to be set when using these events. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0xfc"
     },
@@ -186,6 +194,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
     },
@@ -194,6 +203,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x8"
     },
@@ -202,6 +212,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
@@ -210,6 +221,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -218,7 +230,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.SCALAR",
-        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x3"
     },
@@ -227,6 +239,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -235,7 +248,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0xcf",
         "EventName": "FP_ARITH_INST_RETIRED2.VECTOR",
-        "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR",
+        "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1c"
     }
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json
index dc81055941b1..b7cd92fbecd5 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json
@@ -4,7 +4,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x60",
         "EventName": "BACLEARS.ANY",
-        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+        "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x1"
     },
@@ -13,7 +13,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.LCP",
-        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+        "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x1"
     },
@@ -22,6 +22,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x87",
         "EventName": "DECODE.MS_BUSY",
+        "PublicDescription": "Cycles the Microcode Sequencer is busy. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x2"
     },
@@ -30,7 +31,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x61",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
+        "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x2"
     },
@@ -41,7 +42,7 @@
         "EventName": "FRONTEND_RETIRED.ANY_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
+        "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted) Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -52,7 +53,10 @@
         "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Available PDIST counters: 0",
+        "RetirementLatencyMax": 65535,
+        "RetirementLatencyMean": 2.46,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -63,7 +67,7 @@
         "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x11",
-        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+        "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -74,7 +78,10 @@
         "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x14",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss. Available PDIST counters: 0",
+        "RetirementLatencyMax": 980,
+        "RetirementLatencyMean": 41.96,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -85,7 +92,10 @@
         "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x12",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss. Available PDIST counters: 0",
+        "RetirementLatencyMax": 1785,
+        "RetirementLatencyMean": 9.83,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -96,7 +106,10 @@
         "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x13",
-        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+        "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss. Available PDIST counters: 0",
+        "RetirementLatencyMax": 2854,
+        "RetirementLatencyMean": 137.41,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -107,7 +120,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600106",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -118,7 +131,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x608006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -129,7 +142,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x601006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -140,7 +153,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600206",
-        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -151,7 +164,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x610006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -162,7 +175,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x100206",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -173,7 +186,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x602006",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -184,7 +197,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600406",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -195,7 +208,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x620006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -206,7 +219,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x604006",
-        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+        "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -217,7 +230,7 @@
         "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x600806",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -228,7 +241,7 @@
         "EventName": "FRONTEND_RETIRED.LATE_SWPF",
         "MSRIndex": "0x3F7",
         "MSRValue": "0xA",
-        "PublicDescription": "Number of Instruction Cache demand miss in shadow of an on-going i-fetch cache-line triggered by PREFETCHIT0/1 instructions",
+        "PublicDescription": "Number of Instruction Cache demand miss in shadow of an on-going i-fetch cache-line triggered by PREFETCHIT0/1 instructions Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -239,7 +252,7 @@
         "EventName": "FRONTEND_RETIRED.MISP_ANT",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x9",
-        "PublicDescription": "ANT retired branches that got just mispredicted",
+        "PublicDescription": "ANT retired branches that got just mispredicted Available PDIST counters: 0",
         "SampleAfterValue": "100007",
         "UMask": "0x2"
     },
@@ -250,6 +263,10 @@
         "EventName": "FRONTEND_RETIRED.MS_FLOWS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x8",
+        "PublicDescription": "FRONTEND_RETIRED.MS_FLOWS Available PDIST counters: 0",
+        "RetirementLatencyMax": 65535,
+        "RetirementLatencyMean": 77.14,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -260,7 +277,10 @@
         "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x15",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss. Available PDIST counters: 0",
+        "RetirementLatencyMax": 754,
+        "RetirementLatencyMean": 206.85,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -271,6 +291,10 @@
         "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
         "MSRIndex": "0x3F7",
         "MSRValue": "0x17",
+        "PublicDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH Available PDIST counters: 0",
+        "RetirementLatencyMax": 532,
+        "RetirementLatencyMean": 3.85,
+        "RetirementLatencyMin": 0,
         "SampleAfterValue": "100007",
         "UMask": "0x3"
     },
@@ -279,7 +303,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALLS",
-        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
+        "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity. Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4"
     },
@@ -290,6 +314,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x80",
         "EventName": "ICACHE_DATA.STALL_PERIODS",
+        "PublicDescription": "ICACHE_DATA.STALL_PERIODS Available PDIST counters: 0",
         "SampleAfterValue": "500009",
         "UMask": "0x4"
     },
@@ -298,7 +323,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x83",
         "EventName": "ICACHE_TAG.STALLS",
-        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+        "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. Available PDIST counters: 0",
         "SampleAfterValue": "200003",
         "UMask": "0x4"
     },
@@ -308,7 +333,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -318,7 +343,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -327,7 +352,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
@@ -337,7 +362,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_ANY",
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -347,7 +372,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -356,7 +381,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB). Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },
@@ -366,7 +391,7 @@
         "CounterMask": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_CYCLES_ANY",
-        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+        "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE. Available PDIST counters: 0",
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
@@ -377,7 +402,7 @@
         "EdgeDetect": "1",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_SWITCHES",
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer. Available PDIST counters: 0",
         "SampleAfterValue": "100003",
         "UMask": "0x20"
     },
@@ -386,7 +411,7 @@
         "Counter": "0,1,2,3",
         "EventCode": "0x79",
         "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+        "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x20"
     },
@@ -395,7 +420,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -405,7 +430,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -416,7 +441,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -425,7 +450,7 @@
         "Counter": "0,1,2,3,4,5,6,7",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
+        "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -435,7 +460,7 @@
         "CounterMask": "6",
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+        "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -446,7 +471,7 @@
         "EventCode": "0x9c",
         "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "Invert": "1",
-        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
+        "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK] Available PDIST counters: 0",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     }
diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json
index a345b6874606..af527f7f9d0c 100644
--- a/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/graniterapids/gnr-metrics.json
@@ -310,7 +310,7 @@
         "ScaleUnit": "1per_instr"
     },
     {
-        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+        "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.",
         "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
@@ -322,7 +322,7 @@
         "MetricExpr": "EXE.AMX_BUSY / tma_info_core_core_clks",
         "MetricGroup": "BvCB;Compute;HPC;Server;TopdownL3;tma_L3_group;tma_core_bound_group",
         "MetricName": "tma_amx_busy",
-        "MetricThreshold": "tma_amx_busy > 0.5 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_amx_busy > 0.5 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)",
         "ScaleUnit": "100%"
     },
     {
@@ -330,12 +330,12 @@
         "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots",
         "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_assists",
-        "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+        "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
         "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+        "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.",
         "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots",
         "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
         "MetricName": "tma_avx_assists",
@@ -345,7 +345,7 @@
     {
         "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
         "DefaultMetricgroupName": "TopdownL1",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BvOB;Default;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -361,12 +361,12 @@
         "MetricName": "tma_bad_speculation",
         "MetricThreshold": "tma_bad_speculation > 0.15",
         "MetricgroupNoGroup": "TopdownL1;Default",
-        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
-        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+        "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)",
         "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
         "MetricName": "tma_bottleneck_big_code",
         "MetricThreshold": "tma_bottleneck_big_code > 20"
@@ -381,7 +381,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)))",
         "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
         "MetricName": "tma_bottleneck_cache_memory_bandwidth",
         "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
@@ -389,7 +389,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_split_stores / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_store_latency / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
         "MetricName": "tma_bottleneck_cache_memory_latency",
         "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
@@ -397,22 +397,22 @@
     },
     {
         "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
-        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * tma_amx_busy / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+        "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * tma_amx_busy / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_core_bound * (tma_ports_utilization / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
         "MetricGroup": "BvCB;Cor;tma_issueComp",
         "MetricName": "tma_bottleneck_compute_bound_est",
         "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
-        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy"
+        "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy. Related metrics: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
-        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms))) - tma_bottleneck_big_code",
+        "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms))) - tma_bottleneck_big_code",
         "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
         "MetricName": "tma_bottleneck_instruction_fetch_bw",
         "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20"
     },
     {
         "BriefDescription": "Total pipeline cost of irregular execution (e.g",
-        "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_amx_busy + tma_ports_utilization) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+        "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_clears_resteers + tma_mispredicts_resteers + tma_unknown_branches)) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_ms / (tma_dsb + tma_mite + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_amx_busy + tma_divider + tma_ports_utilization + tma_serializing_operation) + tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
         "MetricName": "tma_bottleneck_irregular_overhead",
         "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
@@ -420,7 +420,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_fb_full + tma_l1_latency_dependency + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_memory_bound * (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))",
         "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
         "MetricName": "tma_bottleneck_memory_data_tlbs",
         "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
@@ -428,7 +428,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
-        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_mem + tma_remote_cache) + tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+        "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) * tma_remote_cache / (tma_local_mem + tma_remote_cache + tma_remote_mem) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * tma_false_sharing / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
         "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
         "MetricName": "tma_bottleneck_memory_synchronization",
         "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
@@ -436,7 +436,7 @@
     },
     {
         "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
-        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+        "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))",
         "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
         "MetricName": "tma_bottleneck_mispredictions",
         "MetricThreshold": "tma_bottleneck_mispredictions > 20",
@@ -448,10 +448,10 @@
         "MetricGroup": "BvOB;Cor;Offcore",
         "MetricName": "tma_bottleneck_other_bottlenecks",
         "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
-        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls"
+        "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls."
     },
     {
-        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+        "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead.",
         "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_few_uops_instructions + tma_microcode_sequencer) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
         "MetricGroup": "BvUW;Ret",
         "MetricName": "tma_bottleneck_useful_work",
@@ -460,7 +460,7 @@
     {
         "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
         "DefaultMetricgroupName": "TopdownL2",
-        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+        "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots",
         "MetricGroup": "BadSpec;BrMispredicts;BvMP;Default;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
         "MetricName": "tma_branch_mispredicts",
         "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
@@ -473,24 +473,24 @@
         "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
         "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
         "MetricName": "tma_branch_resteers",
-        "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
-        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+        "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)",
+        "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings).",
         "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c01_wait",
-        "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c01_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings).",
         "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks",
         "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
         "MetricName": "tma_c02_wait",
-        "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+        "MetricThreshold": "tma_c02_wait > 0.05 & (tma_serializing_operation > 0.1 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))",
         "ScaleUnit": "100%"
     },
     {
@@ -498,8 +498,8 @@
         "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
         "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
         "MetricName": "tma_cisc",
-        "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
-        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+        "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)",
+        "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.",
         "ScaleUnit": "100%"
     },
     {
@@ -507,24 +507,24 @@
         "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
         "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
         "MetricName": "tma_clears_resteers",
-        "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache.",
         "MetricExpr": "max(0, FRONTEND_RETIRED.L1I_MISS * FRONTEND_RETIRED.L1I_MISS:R / tma_info_thread_clks - tma_code_l2_miss)",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_hit",
-        "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_hit > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+        "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache.",
         "MetricExpr": "FRONTEND_RETIRED.L2_MISS * FRONTEND_RETIRED.L2_MISS:R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
         "MetricName": "tma_code_l2_miss",
-        "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_l2_miss > 0.05 & (tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -532,7 +532,7 @@
         "MetricExpr": "max(0, FRONTEND_RETIRED.ITLB_MISS * FRONTEND_RETIRED.ITLB_MISS:R / tma_info_thread_clks - tma_code_stlb_miss)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_hit",
-        "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_hit > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
@@ -540,48 +540,49 @@
         "MetricExpr": "FRONTEND_RETIRED.STLB_MISS * FRONTEND_RETIRED.STLB_MISS:R / tma_info_thread_clks",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
         "MetricName": "tma_code_stlb_miss",
-        "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses.",
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_2m",
-        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+        "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses.",
         "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
         "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
         "MetricName": "tma_code_stlb_miss_4k",
-        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+        "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & (tma_code_stlb_miss > 0.05 & (tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)))",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches.",
         "MetricExpr": "BR_MISP_RETIRED.COND_NTAKEN_COST * BR_MISP_RETIRED.COND_NTAKEN_COST:R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_nt_mispredicts",
-        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches",
+        "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by taken conditional branches.",
         "MetricExpr": "BR_MISP_RETIRED.COND_TAKEN_COST * BR_MISP_RETIRED.COND_TAKEN_COST:R / tma_info_thread_clks",
         "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
         "MetricName": "tma_cond_tk_mispredicts",
-        "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+        "MetricThreshold": "tma_cond_tk_mispredicts > 0.05 & (tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15)",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
-        "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (79 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R, MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (81 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) if 0 < MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD:R else MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (81 * tma_info_system_core_frequency) - 4.4 * tma_info_system_core_frequency) * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(MEM_LOAD_
author	Jani Nikula <jani.nikula@intel.com>	2025-06-09 12:40:46 +0300
committer	Jani Nikula <jani.nikula@intel.com>	2025-06-09 12:40:46 +0300
commit	34c55367af96f62e89221444f04487440ebc6487 (patch)
tree	fdb36ba67d7dea09455b55037e26043b7e051ef9 /tools/perf
parent	7247efca0dcbc8ac6147db9200ed1549c0662465 (diff)
parent	19272b37aa4f83ca52bdf9c16d5d81bdd1354494 (diff)