diff options
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/haswell')
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/haswell/cache.json | 175 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/haswell/floating-point.json | 33 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json | 234 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/haswell/memory.json | 172 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/haswell/pipeline.json | 33 |
5 files changed, 412 insertions, 235 deletions
diff --git a/tools/perf/pmu-events/arch/x86/haswell/cache.json b/tools/perf/pmu-events/arch/x86/haswell/cache.json index da4d6ddd4f92..7fb0ad8d8ca1 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/cache.json +++ b/tools/perf/pmu-events/arch/x86/haswell/cache.json @@ -63,10 +63,10 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Demand data read requests that hit L2 cache.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x41", + "UMask": "0xc1", "Errata": "HSD78", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", "SampleAfterValue": "200003", @@ -77,7 +77,7 @@ "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x42", + "UMask": "0xc2", "EventName": "L2_RQSTS.RFO_HIT", "SampleAfterValue": "200003", "BriefDescription": "RFO requests that hit L2 cache", @@ -87,7 +87,7 @@ "PublicDescription": "Number of instruction fetches that hit the L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x44", + "UMask": "0xc4", "EventName": "L2_RQSTS.CODE_RD_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 cache hits when fetching instructions, code reads.", @@ -97,7 +97,7 @@ "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x50", + "UMask": "0xd0", "EventName": "L2_RQSTS.L2_PF_HIT", "SampleAfterValue": "200003", "BriefDescription": "L2 prefetch requests that hit L2 cache", @@ -610,7 +610,7 @@ "Errata": "HSD29, HSD25, HSM26, HSM30", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ", + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, @@ -623,7 +623,7 @@ "Errata": "HSD29, HSD25, HSM26, HSM30", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, @@ -792,7 +792,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "", "EventCode": "0xf4", "Counter": "0,1,2,3", "UMask": "0x10", @@ -802,262 +801,262 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c8fff", + "MSRValue": "0x3F803C8FFF", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all requests that hit in the L3", + "BriefDescription": "Counts all requests hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c07f7", + "MSRValue": "0x10003C07F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c07f7", + "MSRValue": "0x04003C07F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0244", + "MSRValue": "0x04003C0244", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0122", + "MSRValue": "0x10003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0122", + "MSRValue": "0x04003C0122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0091", + "MSRValue": "0x10003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0091", + "MSRValue": "0x04003C0091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0200", + "MSRValue": "0x3F803C0200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0100", + "MSRValue": "0x3F803C0100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0080", + "MSRValue": "0x3F803C0080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0040", + "MSRValue": "0x3F803C0040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0020", + "MSRValue": "0x3F803C0020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3f803c0010", + "MSRValue": "0x3F803C0010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0004", + "MSRValue": "0x10003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0004", + "MSRValue": "0x04003C0004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0002", + "MSRValue": "0x10003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0002", + "MSRValue": "0x04003C0002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10003c0001", + "MSRValue": "0x10003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04003c0001", + "MSRValue": "0x04003C0001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json index f9843e5a9b42..f5a3beaa19fc 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json @@ -1,22 +1,26 @@ [ { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x8", "Errata": "HSD56, HSM57", "EventName": "OTHER_ASSISTS.AVX_TO_SSE", "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x10", "Errata": "HSD56, HSM57", "EventName": "OTHER_ASSISTS.SSE_TO_AVX", "SampleAfterValue": "100003", - "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -30,53 +34,58 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of X87 FP assists due to output values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x2", "EventName": "FP_ASSIST.X87_OUTPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to output value.", + "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of X87 FP assists due to input values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x4", "EventName": "FP_ASSIST.X87_INPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of X87 assists due to input value.", + "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of SIMD FP assists due to output values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x8", "EventName": "FP_ASSIST.SIMD_OUTPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to Output values", + "BriefDescription": "SSE* FP micro-code assist when output value is invalid.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of SIMD FP assists due to input values.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x10", "EventName": "FP_ASSIST.SIMD_INPUT", "SampleAfterValue": "100003", - "BriefDescription": "Number of SIMD FP assists due to input values", + "BriefDescription": "Any input SSE* FP Assist", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles with any input/output SSE* or FP assists.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xCA", "Counter": "0,1,2,3", "UMask": "0x1e", "EventName": "FP_ASSIST.ANY", "SampleAfterValue": "100003", - "BriefDescription": "Cycles with any input/output SSE or FP assist", + "BriefDescription": "Counts any FP_ASSIST umask was incrementing", "CounterMask": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 5ab5c78fe580..21b27488b621 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -1,158 +1,322 @@ [ { - "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "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-ops (uops). Ideally the Frontend can issue 4 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.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound" + }, + { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "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-ops (uops). Ideally the Frontend can issue 4 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. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "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.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation" + }, + { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "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. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "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.", + "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", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound" + }, + { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "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. SMT version; use when SMT is enabled and measuring per logical CPU.", + "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. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "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 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring" + }, + { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "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 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT" + }, + { "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Instructions Per Cycle (per logical thread)", "MetricGroup": "TopDownL1", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline", + "BriefDescription": "Uops Per Instruction", + "MetricGroup": "Pipeline;Retiring", "MetricName": "UPI" }, { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", + "MetricGroup": "Branches;PGO", + "MetricName": "IpTB" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTB" + }, + { "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", - "MetricGroup": "Frontend", + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricGroup": "PGO", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", - "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { - "BriefDescription": "Cycles Per Instruction (threaded)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "BriefDescription": "Cycles Per Instruction (threaded)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, { - "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-thread actual clocks when the logical processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots", - "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per core)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Total issue-pipeline slots (per core)", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means loads are more frequent)", + "MetricGroup": "Instruction_Type;L1_Bound", + "MetricName": "IpL" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store", + "MetricGroup": "Instruction_Type;Store_Bound", + "MetricName": "IpS" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch", + "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6", + "MetricName": "IpB" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instruction per (near) call", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", "MetricGroup": "Summary", "MetricName": "Instructions" }, { + "MetricExpr": "INST_RETIRED.ANY / cycles", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)", - "MetricGroup": "Unknown_Branches", - "MetricName": "BAClear_Cost" + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricGroup": "Branch_Mispredicts", + "MetricName": "IpMispredict" }, { + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, { - "BriefDescription": "Average CPU Utilization", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2HPKI_All" + }, + { + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "BriefDescription": "Average CPU Utilization", "MetricGroup": "Summary", "MetricName": "CPU_Utilization" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { - "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "BriefDescription": "Fraction of cycles where both hardware threads were active", "MetricGroup": "SMT;Summary", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "C3 residency percent per core", + "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per core", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per core", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per core", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C2 residency percent per package", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C3 residency percent per package", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C6 residency percent per package", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", "MetricGroup": "Power", + "BriefDescription": "C7 residency percent per package", "MetricName": "C7_Pkg_Residency" } ] diff --git a/tools/perf/pmu-events/arch/x86/haswell/memory.json b/tools/perf/pmu-events/arch/x86/haswell/memory.json index e5f9fa6655b3..ef13ed88e2ea 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/memory.json +++ b/tools/perf/pmu-events/arch/x86/haswell/memory.json @@ -298,7 +298,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "SampleAfterValue": "100003", - "BriefDescription": "Loads with latency value being above 4.", + "BriefDescription": "Randomly selected loads with latency value being above 4.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -312,7 +312,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "SampleAfterValue": "50021", - "BriefDescription": "Loads with latency value being above 8.", + "BriefDescription": "Randomly selected loads with latency value being above 8.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -326,7 +326,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "SampleAfterValue": "20011", - "BriefDescription": "Loads with latency value being above 16.", + "BriefDescription": "Randomly selected loads with latency value being above 16.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -340,7 +340,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "SampleAfterValue": "100003", - "BriefDescription": "Loads with latency value being above 32.", + "BriefDescription": "Randomly selected loads with latency value being above 32.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -354,7 +354,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "SampleAfterValue": "2003", - "BriefDescription": "Loads with latency value being above 64.", + "BriefDescription": "Randomly selected loads with latency value being above 64.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -368,7 +368,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "SampleAfterValue": "1009", - "BriefDescription": "Loads with latency value being above 128.", + "BriefDescription": "Randomly selected loads with latency value being above 128.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -382,7 +382,7 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "SampleAfterValue": "503", - "BriefDescription": "Loads with latency value being above 256.", + "BriefDescription": "Randomly selected loads with latency value being above 256.", "TakenAlone": "1", "CounterHTOff": "3" }, @@ -396,280 +396,280 @@ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "SampleAfterValue": "101", - "BriefDescription": "Loads with latency value being above 512.", + "BriefDescription": "Randomly selected loads with latency value being above 512.", "TakenAlone": "1", "CounterHTOff": "3" }, { - "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all requests miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc08fff", + "MSRValue": "0x3FFFC08FFF", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all requests that miss in the L3", + "BriefDescription": "Counts all requests miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01004007f7", + "MSRValue": "0x01004007F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram", + "BriefDescription": "miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc007f7", + "MSRValue": "0x3FFFC007F7", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3", + "BriefDescription": "miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400244", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00244", + "MSRValue": "0x3FFFC00244", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3", + "BriefDescription": "Counts all demand & prefetch code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00122", + "MSRValue": "0x3FFFC00122", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3", + "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand & prefetch data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00091", + "MSRValue": "0x3FFFC00091", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3", + "BriefDescription": "Counts all demand & prefetch data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00200", + "MSRValue": "0x3FFFC00200", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00100", + "MSRValue": "0x3FFFC00100", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00080", + "MSRValue": "0x3FFFC00080", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00040", + "MSRValue": "0x3FFFC00040", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00020", + "MSRValue": "0x3FFFC00020", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00010", + "MSRValue": "0x3FFFC00010", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand code reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00004", + "MSRValue": "0x3FFFC00004", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand code reads that miss in the L3", + "BriefDescription": "Counts all demand code reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00002", + "MSRValue": "0x3FFFC00002", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3", + "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.LOCAL_DRAM", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "Offcore": "1", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "PublicDescription": "Counts demand data reads miss in the L3", "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3fffc00001", + "MSRValue": "0x3FFFC00001", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", + "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads that miss in the L3", + "BriefDescription": "Counts demand data reads miss in the L3", "Offcore": "1", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json index a4dcfce4a512..734d3873729e 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json @@ -1,7 +1,6 @@ [ { "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. INST_RETIRED.ANY is counted by a designated fixed counter, leaving the programmable counters available for other events. Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", - "EventCode": "0x00", "Counter": "Fixed counter 0", "UMask": "0x1", "Errata": "HSD140, HSD143", @@ -12,7 +11,6 @@ }, { "PublicDescription": "This event 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.", - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", @@ -21,7 +19,6 @@ "CounterHTOff": "Fixed counter 1" }, { - "EventCode": "0x00", "Counter": "Fixed counter 1", "UMask": "0x2", "AnyThread": "1", @@ -32,7 +29,6 @@ }, { "PublicDescription": "This event 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.", - "EventCode": "0x00", "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", @@ -1071,7 +1067,8 @@ "CounterHTOff": "1" }, { - "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", + "PEBS": "1", + "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", "EventCode": "0xC0", "Counter": "0,1,2,3", "UMask": "0x2", @@ -1081,13 +1078,13 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC1", "Counter": "0,1,2,3", "UMask": "0x40", "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", "SampleAfterValue": "100003", - "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1102,28 +1099,34 @@ "Data_LA": "1" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "UOPS_RETIRED.STALL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", + "BriefDescription": "Cycles no executable uops retired", "CounterMask": "1", "CounterHTOff": "0,1,2,3" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", "UMask": "0x1", "EventName": "UOPS_RETIRED.TOTAL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 10 actually retired uops.", + "BriefDescription": "Number of cycles using always true condition applied to PEBS uops retired event.", "CounterMask": "10", "CounterHTOff": "0,1,2,3" }, { + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", @@ -1131,7 +1134,7 @@ "AnyThread": "1", "EventName": "UOPS_RETIRED.CORE_STALL_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", + "BriefDescription": "Cycles no executable uops retired on core", "CounterMask": "1", "CounterHTOff": "0,1,2,3" }, @@ -1245,13 +1248,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of not taken branch instructions retired.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x10", "EventName": "BR_INST_RETIRED.NOT_TAKEN", "SampleAfterValue": "400009", - "BriefDescription": "Not taken branch instructions retired.", + "BriefDescription": "Counts all not taken macro branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -1265,13 +1269,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Number of far branches retired.", + "PEBS": "1", + "PublicDescription": "", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x40", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "SampleAfterValue": "100003", - "BriefDescription": "Far branch instructions retired.", + "BriefDescription": "Counts the number of far branch instructions retired.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { |