diff options
Diffstat (limited to 'tools')
16 files changed, 1693 insertions, 66 deletions
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/cache.json b/tools/perf/pmu-events/arch/x86/grandridge/cache.json index f937ba0e50e1..04802e254e51 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/cache.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/cache.json @@ -1,22 +1,25 @@ [ { "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", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", "SampleAfterValue": "200003", "UMask": "0x41" }, { "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", "SampleAfterValue": "200003", "UMask": "0x4f" }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an instruction cache or TLB miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.ALL", "SampleAfterValue": "1000003", @@ -24,6 +27,7 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.L2_HIT", "PublicDescription": "Counts the number of cycles the core is stalled due to an instruction cache or Translation Lookaside Buffer (TLB) miss which hit in the L2 cache.", @@ -32,6 +36,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which hit in the LLC.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_HIT", "SampleAfterValue": "1000003", @@ -39,6 +44,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which missed all the caches.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_MISS", "SampleAfterValue": "1000003", @@ -46,6 +52,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an L1 demand load miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.ALL", "SampleAfterValue": "1000003", @@ -53,6 +60,7 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.L2_HIT", "PublicDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 cache.", @@ -61,6 +69,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT", "SampleAfterValue": "1000003", @@ -68,6 +77,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS", "SampleAfterValue": "1000003", @@ -75,62 +85,63 @@ }, { "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", "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1" }, { "BriefDescription": "Counts the number of load ops retired that hit the L1 data cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x1" }, { "BriefDescription": "Counts the number of load ops retired that miss in the L1 data cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x40" }, { "BriefDescription": "Counts the number of load ops retired that hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x2" }, { "BriefDescription": "Counts the number of load ops retired that miss in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x80" }, { "BriefDescription": "Counts the number of load ops retired that hit in the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x1c" }, { "BriefDescription": "Counts the number of loads that hit in a write combining buffer (WCB), excluding the first load that caused the WCB to allocate.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x20" }, { "BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x04", "EventName": "MEM_SCHEDULER_BLOCK.ALL", "SampleAfterValue": "20003", @@ -138,6 +149,7 @@ }, { "BriefDescription": "Counts the number of cycles that uops are blocked due to a load buffer full condition.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x04", "EventName": "MEM_SCHEDULER_BLOCK.LD_BUF", "SampleAfterValue": "20003", @@ -145,6 +157,7 @@ }, { "BriefDescription": "Counts the number of cycles that uops are blocked due to an RSV full condition.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x04", "EventName": "MEM_SCHEDULER_BLOCK.RSV", "SampleAfterValue": "20003", @@ -152,6 +165,7 @@ }, { "BriefDescription": "Counts the number of cycles that uops are blocked due to a store buffer full condition.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x04", "EventName": "MEM_SCHEDULER_BLOCK.ST_BUF", "SampleAfterValue": "20003", @@ -159,179 +173,210 @@ }, { "BriefDescription": "Counts the number of load ops retired.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x81" }, { "BriefDescription": "Counts the number of store ops retired.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x82" }, { "BriefDescription": "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.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5" }, { "BriefDescription": "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.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5" }, { "BriefDescription": "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.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5" }, { "BriefDescription": "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.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5" }, { "BriefDescription": "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.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5" }, { "BriefDescription": "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.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5" }, { "BriefDescription": "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.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5" }, { "BriefDescription": "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.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5" }, { "BriefDescription": "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.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5" }, { "BriefDescription": "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.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5" }, { "BriefDescription": "Counts the number of load uops retired that performed one or more locks", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x21" }, { "BriefDescription": "Counts the number of memory uops retired that were splits.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x43" }, { "BriefDescription": "Counts the number of retired split load uops.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x41" }, { "BriefDescription": "Counts the number of retired split store uops.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x42" }, { "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", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x6" }, { + "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", + "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 non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "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.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to an icache miss", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.ICACHE", "SampleAfterValue": "1000003", diff --git a/tools/perf/pmu-events/arch/x86/grandridge/counter.json b/tools/perf/pmu-events/arch/x86/grandridge/counter.json new file mode 100644 index 000000000000..9fd5d8ad6d3b --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/grandridge/counter.json @@ -0,0 +1,42 @@ +[ + { + "Unit": "core", + "CountersNumFixed": "3", + "CountersNumGeneric": "8" + }, + { + "Unit": "B2CMI", + "CountersNumFixed": "0", + "CountersNumGeneric": "4" + }, + { + "Unit": "CHA", + "CountersNumFixed": "0", + "CountersNumGeneric": "4" + }, + { + "Unit": "IMC", + "CountersNumFixed": "0", + "CountersNumGeneric": "4" + }, + { + "Unit": "IIO", + "CountersNumFixed": "0", + "CountersNumGeneric": "4" + }, + { + "Unit": "IRP", + "CountersNumFixed": "0", + "CountersNumGeneric": "4" + }, + { + "Unit": "PCU", + "CountersNumFixed": "0", + "CountersNumGeneric": 4 + }, + { + "Unit": "CHACMS", + "CountersNumFixed": "0", + "CountersNumGeneric": 4 + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/grandridge/floating-point.json b/tools/perf/pmu-events/arch/x86/grandridge/floating-point.json index 00c9a8ae0f53..5266eed969be 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/floating-point.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of cycles when any of the floating point dividers are active.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xcd", "EventName": "ARITH.FPDIV_ACTIVE", @@ -9,48 +10,89 @@ }, { "BriefDescription": "Counts the number of all types of floating point operations per uop with all default weighting", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc8", "EventName": "FP_FLOPS_RETIRED.ALL", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x3" }, { "BriefDescription": "This event is deprecated. [This event is alias to FP_FLOPS_RETIRED.FP64]", + "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", "EventCode": "0xc8", "EventName": "FP_FLOPS_RETIRED.DP", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1" }, { "BriefDescription": "Counts the number of floating point operations that produce 32 bit single precision results [This event is alias to FP_FLOPS_RETIRED.SP]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc8", "EventName": "FP_FLOPS_RETIRED.FP32", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x2" }, { "BriefDescription": "Counts the number of floating point operations that produce 64 bit double precision results [This event is alias to FP_FLOPS_RETIRED.DP]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc8", "EventName": "FP_FLOPS_RETIRED.FP64", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1" }, { "BriefDescription": "This event is deprecated. [This event is alias to FP_FLOPS_RETIRED.FP32]", + "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", "EventCode": "0xc8", "EventName": "FP_FLOPS_RETIRED.SP", - "PEBS": "1", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the total number of floating point retired instructions.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit single precision floating point. This may be SSE or AVX.128 operations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit double precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.256B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 32bit single precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.32B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 64 bit double precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.64B_DP", "SampleAfterValue": "1000003", "UMask": "0x2" }, { "BriefDescription": "Counts the number of floating point operations retired that required microcode assist.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.FP_ASSIST", "PublicDescription": "Counts the number of floating point operations retired that required microcode assist, which is not a reflection of the number of FP operations, instructions or uops.", @@ -59,9 +101,9 @@ }, { "BriefDescription": "Counts the number of floating point divide uops retired (x87 and sse, including x87 sqrt).", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.FPDIV", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x8" } diff --git a/tools/perf/pmu-events/arch/x86/grandridge/frontend.json b/tools/perf/pmu-events/arch/x86/grandridge/frontend.json index 356d36aecc81..7cdf611efb23 100644 --- a/tools/perf/pmu-events/arch/x86/grandridge/frontend.json +++ b/tools/perf/pmu-events/arch/x86/grandridge/frontend.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the total number of BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe6", "EventName": "BACLEARS.ANY", "PublicDescription": "Counts the total number of BACLEARS, which occur 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.", @@ -9,14 +10,15 @@ }, { "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.ITLB_MISS", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x10" }, { "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x80", "EventName": "ICACHE.ACCESSES", "SampleAfterValue": "200003", @@ -24,6 +26,7 @@ }, { "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x80", "EventName": "ICACHE.MISSES", "SampleAfterValue": "200003", diff --git a/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json new file mode 100644 index 000000000000..07e542297e93 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/grandridge/grr-metrics.json @@ -0,0 +1,849 @@ +[ + { + "BriefDescription": "C1 residency percent per core", + "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C1_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per module", + "MetricExpr": "cstate_module@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Module_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", + "MetricName": "cpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "CPU operating frequency (in GHz)", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9", + "MetricName": "cpu_operating_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Percentage of time spent in the active CPU power state C0", + "MetricExpr": "tma_info_system_cpu_utilization", + "MetricName": "cpu_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_load_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", + "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "dtlb_2nd_level_store_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e6 / duration_time", + "MetricName": "io_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricName": "itlb_2nd_level_large_page_mpi", + "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricName": "itlb_2nd_level_mpi", + "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", + "MetricExpr": "ICACHE.MISSES / INST_RETIRED.ANY", + "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L1_HIT / INST_RETIRED.ANY", + "MetricName": "l1d_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L2_HIT / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricName": "l2_demand_data_read_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "LONGEST_LAT_CACHE.REFERENCE / INST_RETIRED.ANY", + "MetricName": "l2_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_CRD + UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF) / INST_RETIRED.ANY", + "MetricName": "llc_code_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF + UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA) / INST_RETIRED.ANY", + "MetricName": "llc_data_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) in nano seconds", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT) * #num_packages)) * duration_time", + "MetricName": "llc_demand_data_read_miss_latency", + " |