perf vendor events intel: Update tigerlake events/metrics

Update tigerlake events to v1.12 including the new events
MEM_LOAD_MISC_RETIRED.UC and SQ_MISC.BUS_LOCK. Metrics are updated to
make TMA info metric names synchronized. Events and metrics were
generated by:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230517173805.602113-14-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

4 files changed, 505 insertions, 486 deletions

diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 4a1a2b8d6201..6543a68d4a17 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -29,7 +29,7 @@ GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core
 GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v56,skylake,core
 GenuineIntel-6-55-[01234],v1.30,skylakex,core
 GenuineIntel-6-86,v1.21,snowridgex,core
-GenuineIntel-6-8[CD],v1.10,tigerlake,core
+GenuineIntel-6-8[CD],v1.12,tigerlake,core
 GenuineIntel-6-2C,v4,westmereep-dp,core
 GenuineIntel-6-25,v3,westmereep-sp,core
 GenuineIntel-6-2F,v3,westmereex,core
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/cache.json b/tools/perf/pmu-events/arch/x86/tigerlake/cache.json
index 738249a6f488..c54fb65d3259 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/cache.json
@@ -323,6 +323,16 @@
         "UMask": "0x2"
     },
     {
+        "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.",
+        "Data_LA": "1",
+        "EventCode": "0xd4",
+        "EventName": "MEM_LOAD_MISC_RETIRED.UC",
+        "PEBS": "1",
+        "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access",
+        "SampleAfterValue": "100007",
+        "UMask": "0x4"
+    },
+    {
         "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.",
         "Data_LA": "1",
         "EventCode": "0xd1",
@@ -511,6 +521,14 @@
         "UMask": "0x4"
     },
     {
+        "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.",
+        "EventCode": "0xf4",
+        "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.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x10"
+    },
+    {
         "BriefDescription": "Cycles the superQ cannot take any more entries.",
         "EventCode": "0xf4",
         "EventName": "SQ_MISC.SQ_FULL",
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json
index a0aeeb801fd7..020801cbd7e3 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json
@@ -395,6 +395,7 @@
     {
         "BriefDescription": "Clears speculative count",
         "CounterMask": "1",
+        "EdgeDetect": "1",
         "EventCode": "0x0d",
         "EventName": "INT_MISC.CLEARS_COUNT",
         "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
index ae62bacf9f5e..d0538a754288 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json
@@ -79,7 +79,7 @@
     },
     {
         "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset",
-        "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks",
+        "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))",
@@ -88,7 +88,7 @@
     },
     {
         "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 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_clks)",
+        "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)",
         "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
         "MetricName": "tma_alu_op_utilization",
         "MetricThreshold": "tma_alu_op_utilization > 0.6",
@@ -96,7 +96,7 @@
     },
     {
         "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists",
-        "MetricExpr": "100 * ASSISTS.ANY / tma_info_slots",
+        "MetricExpr": "100 * ASSISTS.ANY / tma_info_thread_slots",
         "MetricGroup": "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)",
@@ -105,7 +105,7 @@
     },
     {
         "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",
-        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_slots",
+        "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_thread_slots",
         "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_backend_bound",
         "MetricThreshold": "tma_backend_bound > 0.2",
@@ -125,7 +125,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.",
-        "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)",
         "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
         "MetricName": "tma_branch_instructions",
         "MetricThreshold": "tma_branch_instructions > 0.1 & tma_light_operations > 0.6",
@@ -138,12 +138,12 @@
         "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_info_branch_misprediction_cost, tma_info_mispredictions, 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_info_bottleneck_mispredictions, tma_mispredicts_resteers",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers",
-        "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches",
+        "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)",
@@ -161,7 +161,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears",
-        "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks",
+        "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))",
@@ -171,7 +171,7 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(49 * tma_info_average_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))) + 48 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks",
+        "MetricExpr": "(49 * tma_info_system_average_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))) + 48 * tma_info_system_average_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": "DataSharing;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))",
@@ -191,7 +191,7 @@
     {
         "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "48 * tma_info_average_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_clks",
+        "MetricExpr": "48 * tma_info_system_average_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": "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))",
@@ -200,16 +200,16 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder",
-        "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_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 > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))",
+        "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35))",
         "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
-        "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks",
+        "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks",
         "MetricGroup": "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)",
@@ -219,7 +219,7 @@
     {
         "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound",
+        "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)",
@@ -228,43 +228,43 @@
     },
     {
         "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
-        "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2",
+        "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / 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 > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)",
+        "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)",
         "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%"
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines",
-        "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks",
+        "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_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp",
+        "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_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\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks",
+        "MetricExpr": "min(7 * 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": "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_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs",
+        "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, tma_info_bottleneck_memory_data_tlbs",
         "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\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks",
+        "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_core_clks",
         "MetricGroup": "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_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs",
+        "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, tma_info_bottleneck_memory_data_tlbs",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
-        "MetricExpr": "54 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks",
+        "MetricExpr": "54 * tma_info_system_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks",
         "MetricGroup": "DataSharing;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))",
@@ -273,11 +273,11 @@
     },
     {
         "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
-        "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks",
+        "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks",
         "MetricGroup": "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_dram_bw_use, tma_info_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_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
         "ScaleUnit": "100%"
     },
     {
@@ -285,14 +285,14 @@
         "MetricExpr": "max(0, 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 > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35",
+        "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35",
         "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_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_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_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
         "ScaleUnit": "100%"
     },
     {
         "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
-        "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_slots",
+        "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.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",
@@ -321,7 +321,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired",
-        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (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)",
@@ -330,7 +330,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths",
-        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (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)",
@@ -339,7 +339,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 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))",
@@ -348,7 +348,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + 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))",
@@ -357,7 +357,7 @@
     },
     {
         "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors",
-        "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)",
+        "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_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_512b",
         "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))",
@@ -366,7 +366,7 @@
     },
     {
         "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
-        "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots",
+        "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots",
         "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group",
         "MetricName": "tma_frontend_bound",
         "MetricThreshold": "tma_frontend_bound > 0.15",
@@ -386,7 +386,7 @@
     },
     {
         "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
-        "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_clks",
+        "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_thread_clks",
         "MetricGroup": "BigFoot;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)",
@@ -394,696 +394,696 @@
         "ScaleUnit": "100%"
     },
     {
-        "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
-        "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time",
-        "MetricGroup": "Power;Summary",
-        "MetricName": "tma_info_average_frequency"
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(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_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
+        "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
+        "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers"
+    },
+    {
+        "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).",
+        "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).",
+        "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 < 1e3"
+    },
+    {
+        "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",
+        "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500"
+    },
+    {
+        "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"
+    },
+    {
+        "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
+        "MetricGroup": "Cor;SMT",
+        "MetricName": "tma_info_botlnk_l0_core_bound_likely",
+        "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5"
+    },
+    {
+        "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_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))",
+        "MetricGroup": "DSBmiss;Fed;tma_issueFB",
+        "MetricName": "tma_info_botlnk_l2_dsb_misses",
+        "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
+        "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
+        "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: "
     },
     {
         "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
         "MetricConstraint": "NO_GROUP_EVENTS",
         "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": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC",
-        "MetricName": "tma_info_big_code",
-        "MetricThreshold": "tma_info_big_code > 20",
-        "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead"
+        "MetricName": "tma_info_bottleneck_big_code",
+        "MetricThreshold": "tma_info_bottleneck_big_code > 20",
+        "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead"
     },
     {
-        "BriefDescription": "Branch instructions per taken branch.",
-        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
-        "MetricGroup": "Branches;Fed;PGO",
-        "MetricName": "tma_info_bptkbranch"
+        "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
+        "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_thread_slots)",
+        "MetricGroup": "Ret;tma_issueBC",
+        "MetricName": "tma_info_bottleneck_branching_overhead",
+        "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10",
+        "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code"
     },
     {
-        "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
+        "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks",
         "MetricConstraint": "NO_GROUP_EVENTS",
-        "MetricExpr": "(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_info_slots / BR_MISP_RETIRED.ALL_BRANCHES",
-        "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
-        "MetricName": "tma_info_branch_misprediction_cost",
-        "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers"
+        "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_bottleneck_big_code",
+        "MetricGroup": "Fed;FetchBW;Frontend",
+        "MetricName": "tma_info_bottleneck_instruction_fetch_bw",
+        "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20"
     },
     {
-        "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
-        "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)",
-        "MetricGroup": "Ret;tma_issueBC",
-        "MetricName": "tma_info_branching_overhead",
-        "MetricThreshold": "tma_info_branching_overhead > 10",
-        "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code"
+        "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks",
+        "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_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_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_lock_latency + tma_split_loads + tma_store_fwd_blk))",
+        "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW",
+        "MetricName": "tma_info_bottleneck_memory_bandwidth",
+        "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20",
+        "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full"
     },
     {
-        "BriefDescription": "Fraction of branches that are CALL or RET",
-        "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES",
-        "MetricGroup": "Bad;Branches",
-        "MetricName": "tma_info_callret"
+        "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "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_lock_latency + tma_split_loads + tma_store_fwd_blk)) + 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": "Mem;MemoryTLB;Offcore;tma_issueTLB",
+        "MetricName": "tma_info_bottleneck_memory_data_tlbs",
+        "MetricThreshold": "tma_info_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"
     },
     {
-        "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
-        "MetricGroup": "Pipeline",
-        "MetricName": "tma_info_clks"
+        "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)",
+        "MetricConstraint": "NO_GROUP_EVENTS",
+        "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) *