Commit-ID: 032c16b296d512d151a3276ab3c53d4a4d65e2ed Gitweb: https://git.kernel.org/tip/032c16b296d512d151a3276ab3c53d4a4d65e2ed Author: Andi Kleen <a...@linux.intel.com> AuthorDate: Thu, 18 Jan 2018 04:49:26 -0800 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> CommitDate: Thu, 25 Jan 2018 06:36:50 -0300
perf vendor events intel: Update HaswellX events to V19 Signed-off-by: Andi Kleen <a...@linux.intel.com> Link: https://lkml.kernel.org/r/20180118234518.ga27...@tassilo.jf.intel.com Signed-off-by: Arnaldo Carvalho de Melo <a...@redhat.com> --- tools/perf/pmu-events/arch/x86/haswellx/cache.json | 377 ++++--- .../arch/x86/haswellx/floating-point.json | 20 +- .../pmu-events/arch/x86/haswellx/frontend.json | 132 +-- .../perf/pmu-events/arch/x86/haswellx/memory.json | 28 + tools/perf/pmu-events/arch/x86/haswellx/other.json | 20 +- .../pmu-events/arch/x86/haswellx/pipeline.json | 1133 ++++++++++---------- .../arch/x86/haswellx/virtual-memory.json | 212 ++-- 7 files changed, 991 insertions(+), 931 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/haswellx/cache.json b/tools/perf/pmu-events/arch/x86/haswellx/cache.json index f1bae08..b2fbd61 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/cache.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/cache.json @@ -12,12 +12,32 @@ }, { "EventCode": "0x24", - "UMask": "0x41", - "BriefDescription": "Demand Data Read requests that hit L2 cache", + "UMask": "0x22", + "BriefDescription": "RFO requests that miss L2 cache", "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x24", + "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Number of instruction fetches that missed the L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x27", + "BriefDescription": "Demand requests that miss L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", "Errata": "HSD78", - "PublicDescription": "Demand data read requests that hit L2 cache.", + "PublicDescription": "Demand requests that miss L2 cache.", "SampleAfterValue": "200003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -33,6 +53,48 @@ }, { "EventCode": "0x24", + "UMask": "0x3f", + "BriefDescription": "All requests that miss L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.MISS", + "Errata": "HSD78", + "PublicDescription": "All requests that missed L2.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x41", + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "Errata": "HSD78", + "PublicDescription": "Demand data read requests that hit L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x42", + "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "UMask": "0x44", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Number of instruction fetches that hit the L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", "UMask": "0x50", "BriefDescription": "L2 prefetch requests that hit L2 cache", "Counter": "0,1,2,3", @@ -74,6 +136,17 @@ }, { "EventCode": "0x24", + "UMask": "0xe7", + "BriefDescription": "Demand requests to L2 cache", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "Errata": "HSD78", + "PublicDescription": "Demand requests to L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", "UMask": "0xf8", "BriefDescription": "Requests from L2 hardware prefetchers", "Counter": "0,1,2,3", @@ -83,6 +156,17 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x24", + "UMask": "0xff", + "BriefDescription": "All L2 requests", + "Counter": "0,1,2,3", + "EventName": "L2_RQSTS.REFERENCES", + "Errata": "HSD78", + "PublicDescription": "All requests to L2 cache.", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x27", "UMask": "0x50", "BriefDescription": "Not rejected writebacks that hit L2 cache", @@ -124,6 +208,27 @@ }, { "EventCode": "0x48", + "UMask": "0x1", + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "2", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "2" + }, + { + "EventCode": "0x48", + "UMask": "0x1", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "Counter": "2", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "AnyThread": "1", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "2" + }, + { + "EventCode": "0x48", "UMask": "0x2", "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch. HWP are e.", "Counter": "0,1,2,3", @@ -133,13 +238,13 @@ }, { "EventCode": "0x48", - "UMask": "0x1", - "BriefDescription": "Cycles with L1D load Misses outstanding.", - "Counter": "2", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "UMask": "0x2", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "Counter": "0,1,2,3", + "EventName": "L1D_PEND_MISS.FB_FULL", "CounterMask": "1", "SampleAfterValue": "2000003", - "CounterHTOff": "2" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x51", @@ -164,6 +269,28 @@ }, { "EventCode": "0x60", + "UMask": "0x1", + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "CounterMask": "1", + "Errata": "HSD78, HSD62, HSD61", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "UMask": "0x1", + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "CounterMask": "6", + "Errata": "HSD78, HSD62, HSD61", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", "UMask": "0x2", "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle", "Counter": "0,1,2,3", @@ -186,23 +313,23 @@ }, { "EventCode": "0x60", - "UMask": "0x8", - "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "UMask": "0x4", + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "CounterMask": "1", "Errata": "HSD62, HSD61", - "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x60", - "UMask": "0x1", - "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "UMask": "0x8", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "CounterMask": "1", - "Errata": "HSD78, HSD62, HSD61", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "Errata": "HSD62, HSD61", + "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -218,17 +345,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x60", - "UMask": "0x4", - "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "CounterMask": "1", - "Errata": "HSD62, HSD61", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0x63", "UMask": "0x2", "BriefDescription": "Cycles when L1D is locked", @@ -289,9 +405,18 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xB7, 0xBB", + "UMask": "0x1", + "BriefDescription": "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.", + "Counter": "0,1,2,3", + "EventName": "OFFCORE_RESPONSE", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3" + }, + { "EventCode": "0xD0", "UMask": "0x11", - "BriefDescription": "Retired load uops that miss the STLB.", + "BriefDescription": "Retired load uops that miss the STLB. (precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -303,20 +428,20 @@ { "EventCode": "0xD0", "UMask": "0x12", - "BriefDescription": "Retired store uops that miss the STLB.", + "BriefDescription": "Retired store uops that miss the STLB. (precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", "Errata": "HSD29, HSM30", - "SampleAfterValue": "100003", "L1_Hit_Indication": "1", + "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x21", - "BriefDescription": "Retired load uops with locked access.", + "BriefDescription": "Retired load uops with locked access. (precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -328,32 +453,34 @@ { "EventCode": "0xD0", "UMask": "0x41", - "BriefDescription": "Retired load uops that split across a cacheline boundary.", + "BriefDescription": "Retired load uops that split across a cacheline boundary. (precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "Errata": "HSD29, HSM30", + "PublicDescription": "This event counts load uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x42", - "BriefDescription": "Retired store uops that split across a cacheline boundary.", + "BriefDescription": "Retired store uops that split across a cacheline boundary. (precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "Errata": "HSD29, HSM30", - "SampleAfterValue": "100003", "L1_Hit_Indication": "1", + "PublicDescription": "This event counts store uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.", + "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD0", "UMask": "0x81", - "BriefDescription": "All retired load uops.", + "BriefDescription": "All retired load uops. (precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -365,14 +492,15 @@ { "EventCode": "0xD0", "UMask": "0x82", - "BriefDescription": "All retired store uops.", + "BriefDescription": "All retired store uops. (precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "Errata": "HSD29, HSM30", - "SampleAfterValue": "2000003", "L1_Hit_Indication": "1", + "PublicDescription": "This event counts all store uops retired. This is a precise event.", + "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { @@ -402,13 +530,13 @@ { "EventCode": "0xD1", "UMask": "0x4", - "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.", + "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30", - "PublicDescription": "Retired load uops with L3 cache hits as data sources.", + "PublicDescription": "This event counts retired load uops in which data sources were data hits in the L3 cache without snoops required. This does not include hardware prefetches. This is a precise event.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, @@ -421,20 +549,19 @@ "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "Errata": "HSM30", - "PublicDescription": "Retired load uops missed L1 cache as data sources.", + "PublicDescription": "This event counts retired load uops in which data sources missed in the L1 cache. This does not include hardware prefetches. This is a precise event.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD1", "UMask": "0x10", - "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.", + "BriefDescription": "Retired load uops with L2 cache misses as data sources.", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "Errata": "HSD29, HSM30", - "PublicDescription": "Retired load uops missed L2. Unknown data source excluded.", "SampleAfterValue": "50021", "CounterHTOff": "0,1,2,3" }, @@ -447,7 +574,6 @@ "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_MISS", "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30", - "PublicDescription": "Retired load uops missed L3. Excludes unknown data source .", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -478,24 +604,26 @@ { "EventCode": "0xD2", "UMask": "0x2", - "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. ", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", "Errata": "HSD29, HSD25, HSM26, HSM30", + "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HIT in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD2", "UMask": "0x4", - "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. ", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", "Errata": "HSD29, HSD25, HSM26, HSM30", + "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HITM (hit modified) in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.", "SampleAfterValue": "20011", "CounterHTOff": "0,1,2,3" }, @@ -514,20 +642,19 @@ { "EventCode": "0xD3", "UMask": "0x1", - "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", "Errata": "HSD74, HSD29, HSD25, HSM30", - "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches.", + "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xD3", "UMask": "0x4", - "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)", + "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -539,7 +666,7 @@ { "EventCode": "0xD3", "UMask": "0x10", - "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM", + "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -551,7 +678,7 @@ { "EventCode": "0xD3", "UMask": "0x20", - "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache", + "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)", "Data_LA": "1", "PEBS": "1", "Counter": "0,1,2,3", @@ -706,135 +833,11 @@ "BriefDescription": "Split locks in SQ", "Counter": "0,1,2,3", "EventName": "SQ_MISC.SPLIT_LOCK", + "PublicDescription": "", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x24", - "UMask": "0x42", - "BriefDescription": "RFO requests that hit L2 cache", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0x22", - "BriefDescription": "RFO requests that miss L2 cache", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0x44", - "BriefDescription": "L2 cache hits when fetching instructions, code reads.", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Number of instruction fetches that hit the L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0x24", - "BriefDescription": "L2 cache misses when fetching instructions", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Number of instruction fetches that missed the L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0x27", - "BriefDescription": "Demand requests that miss L2 cache", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "Errata": "HSD78", - "PublicDescription": "Demand requests that miss L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0xe7", - "BriefDescription": "Demand requests to L2 cache", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "Errata": "HSD78", - "PublicDescription": "Demand requests to L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0x3f", - "BriefDescription": "All requests that miss L2 cache", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.MISS", - "Errata": "HSD78", - "PublicDescription": "All requests that missed L2.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x24", - "UMask": "0xff", - "BriefDescription": "All L2 requests", - "Counter": "0,1,2,3", - "EventName": "L2_RQSTS.REFERENCES", - "Errata": "HSD78", - "PublicDescription": "All requests to L2 cache.", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xB7, 0xBB", - "UMask": "0x1", - "BriefDescription": "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.", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_RESPONSE", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0x60", - "UMask": "0x1", - "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", - "Counter": "0,1,2,3", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", - "CounterMask": "6", - "Errata": "HSD78, HSD62, HSD61", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x48", - "UMask": "0x1", - "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", - "Counter": "2", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", - "AnyThread": "1", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "2" - }, - { - "EventCode": "0x48", - "UMask": "0x2", - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", - "Counter": "0,1,2,3", - "EventName": "L1D_PEND_MISS.FB_FULL", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "Offcore": "1", "EventCode": "0xB7, 0xBB", "UMask": "0x1", @@ -843,6 +846,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -855,6 +859,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -867,6 +872,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -879,6 +885,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -891,6 +898,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -903,6 +911,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -915,6 +924,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -927,6 +937,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -939,6 +950,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -951,6 +963,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -963,6 +976,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -975,6 +989,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -987,6 +1002,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -999,6 +1015,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1011,6 +1028,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1023,6 +1041,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1035,6 +1054,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1047,6 +1067,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1059,6 +1080,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -1071,6 +1093,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswellx/floating-point.json b/tools/perf/pmu-events/arch/x86/haswellx/floating-point.json index 6282aed..bc08cc1 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/floating-point.json @@ -20,6 +20,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xC6", + "UMask": "0x7", + "BriefDescription": "Approximate counts of AVX & AVX2 256-bit instructions, including non-arithmetic instructions, loads, and stores. May count non-AVX instructions that employ 256-bit operations, including (but not necessarily limited to) rep string instructions that use 256-bit loads and stores for optimized performance, XSAVE* and XRSTOR*, and operations that transition the x87 FPU data registers between x87 and MMX.", + "Counter": "0,1,2,3", + "EventName": "AVX_INSTS.ALL", + "PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xCA", "UMask": "0x2", "BriefDescription": "Number of X87 assists due to output value.", @@ -69,15 +79,5 @@ "PublicDescription": "Cycles with any input/output SSE* or FP assists.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xC6", - "UMask": "0x7", - "BriefDescription": "Approximate counts of AVX & AVX2 256-bit instructions, including non-arithmetic instructions, loads, and stores. May count non-AVX instructions that employ 256-bit operations, including (but not necessarily limited to) rep string instructions that use 256-bit loads and stores for optimized performance, XSAVE* and XRSTOR*, and operations that transition the x87 FPU data registers between x87 and MMX.", - "Counter": "0,1,2,3", - "EventName": "AVX_INSTS.ALL", - "PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" } ] \ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/haswellx/frontend.json b/tools/perf/pmu-events/arch/x86/haswellx/frontend.json index 2d0c7aa..a4d9f1f 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/frontend.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/frontend.json @@ -22,72 +22,41 @@ }, { "EventCode": "0x79", - "UMask": "0x8", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", - "Counter": "0,1,2,3", - "EventName": "IDQ.DSB_UOPS", - "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x79", - "UMask": "0x10", - "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "Counter": "0,1,2,3", - "EventName": "IDQ.MS_DSB_UOPS", - "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x79", - "UMask": "0x20", - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "Counter": "0,1,2,3", - "EventName": "IDQ.MS_MITE_UOPS", - "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x79", - "UMask": "0x30", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "UMask": "0x4", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_UOPS", - "PublicDescription": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.", + "EventName": "IDQ.MITE_CYCLES", + "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", - "UMask": "0x30", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "UMask": "0x8", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "EventName": "IDQ.MS_CYCLES", - "CounterMask": "1", - "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", - "UMask": "0x4", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", + "UMask": "0x8", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", "Counter": "0,1,2,3", - "EventName": "IDQ.MITE_CYCLES", + "EventName": "IDQ.DSB_CYCLES", "CounterMask": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", - "UMask": "0x8", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", + "UMask": "0x10", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "EventName": "IDQ.DSB_CYCLES", - "CounterMask": "1", + "EventName": "IDQ.MS_DSB_UOPS", + "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -136,6 +105,16 @@ }, { "EventCode": "0x79", + "UMask": "0x20", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", "UMask": "0x24", "BriefDescription": "Cycles MITE is delivering 4 Uops", "Counter": "0,1,2,3", @@ -158,6 +137,38 @@ }, { "EventCode": "0x79", + "UMask": "0x30", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "UMask": "0x30", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_CYCLES", + "CounterMask": "1", + "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EdgeDetect": "1", + "EventCode": "0x79", + "UMask": "0x30", + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "Counter": "0,1,2,3", + "EventName": "IDQ.MS_SWITCHES", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", "UMask": "0x3c", "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", @@ -195,6 +206,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x80", + "UMask": "0x4", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.", + "Counter": "0,1,2,3", + "EventName": "ICACHE.IFDATA_STALL", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x9C", "UMask": "0x1", "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", @@ -270,25 +290,5 @@ "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EdgeDetect": "1", - "EventCode": "0x79", - "UMask": "0x30", - "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", - "Counter": "0,1,2,3", - "EventName": "IDQ.MS_SWITCHES", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x80", - "UMask": "0x4", - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.", - "Counter": "0,1,2,3", - "EventName": "ICACHE.IFDATA_STALL", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" } ] \ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/haswellx/memory.json b/tools/perf/pmu-events/arch/x86/haswellx/memory.json index 0886cc0..56b0f24 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/memory.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/memory.json @@ -409,6 +409,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -421,6 +422,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -433,6 +435,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -445,6 +448,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -457,6 +461,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache 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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -469,6 +474,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -481,6 +487,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -493,6 +500,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -505,6 +513,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -517,6 +526,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -529,6 +539,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -541,6 +552,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -553,6 +565,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -565,6 +578,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -577,6 +591,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -589,6 +604,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote 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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -601,6 +617,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache 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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -613,6 +630,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache 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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -625,6 +643,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -637,6 +656,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -649,6 +669,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -661,6 +682,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -673,6 +695,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -685,6 +708,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -697,6 +721,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM", "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote 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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -709,6 +734,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache 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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -721,6 +747,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache 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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" }, @@ -733,6 +760,7 @@ "Counter": "0,1,2,3", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", + "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.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3" } diff --git a/tools/perf/pmu-events/arch/x86/haswellx/other.json b/tools/perf/pmu-events/arch/x86/haswellx/other.json index 4e1b6ce..800e65d 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/other.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/other.json @@ -10,16 +10,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x5C", - "UMask": "0x2", - "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3", - "Counter": "0,1,2,3", - "EventName": "CPL_CYCLES.RING123", - "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EdgeDetect": "1", "EventCode": "0x5C", "UMask": "0x1", @@ -31,6 +21,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x5C", + "UMask": "0x2", + "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3", + "Counter": "0,1,2,3", + "EventName": "CPL_CYCLES.RING123", + "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x63", "UMask": "0x1", "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock", diff --git a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json index c3a163d..8a18bfe 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json @@ -3,32 +3,42 @@ "EventCode": "0x00", "UMask": "0x1", "BriefDescription": "Instructions retired from execution.", - "Counter": "Fixed counter 1", + "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", "Errata": "HSD140, HSD143", "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.", "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 1" + "CounterHTOff": "Fixed counter 0" }, { "EventCode": "0x00", "UMask": "0x2", "BriefDescription": "Core cycles when the thread is not in halt state.", - "Counter": "Fixed counter 2", + "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", "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.", "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 2" + "CounterHTOff": "Fixed counter 1" + }, + { + "EventCode": "0x00", + "UMask": "0x2", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "Fixed counter 1" }, { "EventCode": "0x00", "UMask": "0x3", "BriefDescription": "Reference cycles when the core is not in halt state.", - "Counter": "Fixed counter 3", + "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", "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.", "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 3" + "CounterHTOff": "Fixed counter 2" }, { "EventCode": "0x03", @@ -63,7 +73,7 @@ { "EventCode": "0x0D", "UMask": "0x3", - "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...)", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", "Counter": "0,1,2,3", "EventName": "INT_MISC.RECOVERY_CYCLES", "CounterMask": "1", @@ -72,6 +82,18 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x0D", + "UMask": "0x3", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke)", + "Counter": "0,1,2,3", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "AnyThread": "1", + "CounterMask": "1", + "PublicDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x0E", "UMask": "0x1", "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", @@ -82,6 +104,29 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "Invert": "1", + "EventCode": "0x0E", + "UMask": "0x1", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.", + "Counter": "0,1,2,3", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { + "Invert": "1", + "EventCode": "0x0E", + "UMask": "0x1", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.", + "Counter": "0,1,2,3", + "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES", + "AnyThread": "1", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" + }, + { "EventCode": "0x0E", "UMask": "0x10", "BriefDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive; added by GSR u-arch.", @@ -112,34 +157,31 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", - "EventCode": "0x0E", - "UMask": "0x1", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.", + "EventCode": "0x14", + "UMask": "0x2", + "BriefDescription": "Any uop executed by the Divider. (This includes all divide uops, sqrt, ...)", "Counter": "0,1,2,3", - "EventName": "UOPS_ISSUED.STALL_CYCLES", - "CounterMask": "1", + "EventName": "ARITH.DIVIDER_UOPS", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "Invert": "1", - "EventCode": "0x0E", - "UMask": "0x1", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.", + "EventCode": "0x3C", + "UMask": "0x0", + "BriefDescription": "Thread cycles when thread is not in halt state", "Counter": "0,1,2,3", - "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES", - "AnyThread": "1", - "CounterMask": "1", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "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.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x14", - "UMask": "0x2", - "BriefDescription": "Any uop executed by the Divider. (This includes all divide uops, sqrt, ...)", + "EventCode": "0x3C", + "UMask": "0x0", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "0,1,2,3", - "EventName": "ARITH.DIVIDER_UOPS", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "AnyThread": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -154,6 +196,38 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "AnyThread": "1", + "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "UMask": "0x1", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "AnyThread": "1", + "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x3c", "UMask": "0x2", "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", @@ -163,6 +237,15 @@ "CounterHTOff": "0,1,2,3" }, { + "EventCode": "0x3C", + "UMask": "0x2", + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", + "Counter": "0,1,2,3", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x4c", "UMask": "0x1", "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch", @@ -233,6 +316,18 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EdgeDetect": "1", + "Invert": "1", + "EventCode": "0x5E", + "UMask": "0x1", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "Counter": "0,1,2,3", + "EventName": "RS_EVENTS.EMPTY_END", + "CounterMask": "1", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x87", "UMask": "0x1", "BriefDescription": "Stalls caused by changing prefix length of the instruction.", @@ -408,6 +503,15 @@ }, { "EventCode": "0x89", + "UMask": "0xa0", + "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", + "Counter": "0,1,2,3", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", "UMask": "0xc1", "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", "Counter": "0,1,2,3", @@ -446,135 +550,281 @@ }, { "EventCode": "0xA1", - "UMask": "0x2", - "BriefDescription": "Cycles per thread when uops are executed in port 1", + "UMask": "0x1", + "BriefDescription": "Cycles per core when uops are executed in port 0.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_1", - "PublicDescription": "Cycles which a uop is dispatched on port 1 in this thread.", + "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE", + "AnyThread": "1", + "PublicDescription": "Cycles per core when uops are exectuted in port 0.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", - "UMask": "0x4", - "BriefDescription": "Cycles per thread when uops are executed in port 2", + "UMask": "0x1", + "BriefDescription": "Cycles per thread when uops are executed in port 0.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_2", - "PublicDescription": "Cycles which a uop is dispatched on port 2 in this thread.", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", - "UMask": "0x8", - "BriefDescription": "Cycles per thread when uops are executed in port 3", + "UMask": "0x2", + "BriefDescription": "Cycles per thread when uops are executed in port 1", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_3", - "PublicDescription": "Cycles which a uop is dispatched on port 3 in this thread.", + "EventName": "UOPS_EXECUTED_PORT.PORT_1", + "PublicDescription": "Cycles which a uop is dispatched on port 1 in this thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", - "UMask": "0x10", - "BriefDescription": "Cycles per thread when uops are executed in port 4", + "UMask": "0x2", + "BriefDescription": "Cycles per core when uops are executed in port 1.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_4", - "PublicDescription": "Cycles which a uop is dispatched on port 4 in this thread.", + "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE", + "AnyThread": "1", + "PublicDescription": "Cycles per core when uops are exectuted in port 1.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", - "UMask": "0x20", - "BriefDescription": "Cycles per thread when uops are executed in port 5", + "UMask": "0x2", + "BriefDescription": "Cycles per thread when uops are executed in port 1.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_5", - "PublicDescription": "Cycles which a uop is dispatched on port 5 in this thread.", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", - "UMask": "0x40", - "BriefDescription": "Cycles per thread when uops are executed in port 6", + "UMask": "0x4", + "BriefDescription": "Cycles per thread when uops are executed in port 2", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_6", - "PublicDescription": "Cycles which a uop is dispatched on port 6 in this thread.", + "EventName": "UOPS_EXECUTED_PORT.PORT_2", + "PublicDescription": "Cycles which a uop is dispatched on port 2 in this thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA1", - "UMask": "0x80", - "BriefDescription": "Cycles per thread when uops are executed in port 7", + "UMask": "0x4", + "BriefDescription": "Cycles per core when uops are dispatched to port 2.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_7", - "PublicDescription": "Cycles which a uop is dispatched on port 7 in this thread.", + "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE", + "AnyThread": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", - "UMask": "0x1", - "BriefDescription": "Resource-related stall cycles", + "EventCode": "0xA1", + "UMask": "0x4", + "BriefDescription": "Cycles per thread when uops are executed in port 2.", "Counter": "0,1,2,3", - "EventName": "RESOURCE_STALLS.ANY", - "Errata": "HSD135", - "PublicDescription": "Cycles allocation is stalled due to resource related reason.", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", - "UMask": "0x4", - "BriefDescription": "Cycles stalled due to no eligible RS entry available.", + "EventCode": "0xA1", + "UMask": "0x8", + "BriefDescription": "Cycles per thread when uops are executed in port 3", "Counter": "0,1,2,3", - "EventName": "RESOURCE_STALLS.RS", + "EventName": "UOPS_EXECUTED_PORT.PORT_3", + "PublicDescription": "Cycles which a uop is dispatched on port 3 in this thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xA1", "UMask": "0x8", - "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "BriefDescription": "Cycles per core when uops are dispatched to port 3.", "Counter": "0,1,2,3", - "EventName": "RESOURCE_STALLS.SB", - "PublicDescription": "This event counts cycles during which no instructions were allocated because no Store Buffers (SB) were available.", + "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE", + "AnyThread": "1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xA1", + "UMask": "0x8", + "BriefDescription": "Cycles per thread when uops are executed in port 3.", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", "UMask": "0x10", - "BriefDescription": "Cycles stalled due to re-order buffer full.", + "BriefDescription": "Cycles per thread when uops are executed in port 4", "Counter": "0,1,2,3", - "EventName": "RESOURCE_STALLS.ROB", + "EventName": "UOPS_EXECUTED_PORT.PORT_4", + "PublicDescription": "Cycles which a uop is dispatched on port 4 in this thread.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", - "UMask": "0x1", - "BriefDescription": "Cycles with pending L2 cache miss loads.", + "EventCode": "0xA1", + "UMask": "0x10", + "BriefDescription": "Cycles per core when uops are executed in port 4.", "Counter": "0,1,2,3", - "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", - "CounterMask": "1", - "Errata": "HSD78", - "PublicDescription": "Cycles with pending L2 miss loads. Set Cmask=2 to count cycle.", + "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE", + "AnyThread": "1", + "PublicDescription": "Cycles per core when uops are exectuted in port 4.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA3", + "EventCode": "0xA1", + "UMask": "0x10", + "BriefDescription": "Cycles per thread when uops are executed in port 4.", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x20", + "BriefDescription": "Cycles per thread when uops are executed in port 5", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_5", + "PublicDescription": "Cycles which a uop is dispatched on port 5 in this thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x20", + "BriefDescription": "Cycles per core when uops are executed in port 5.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE", + "AnyThread": "1", + "PublicDescription": "Cycles per core when uops are exectuted in port 5.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x20", + "BriefDescription": "Cycles per thread when uops are executed in port 5.", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x40", + "BriefDescription": "Cycles per thread when uops are executed in port 6", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_6", + "PublicDescription": "Cycles which a uop is dispatched on port 6 in this thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x40", + "BriefDescription": "Cycles per core when uops are executed in port 6.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE", + "AnyThread": "1", + "PublicDescription": "Cycles per core when uops are exectuted in port 6.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x40", + "BriefDescription": "Cycles per thread when uops are executed in port 6.", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_6", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x80", + "BriefDescription": "Cycles per thread when uops are executed in port 7", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_7", + "PublicDescription": "Cycles which a uop is dispatched on port 7 in this thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x80", + "BriefDescription": "Cycles per core when uops are dispatched to port 7.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE", + "AnyThread": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "UMask": "0x80", + "BriefDescription": "Cycles per thread when uops are executed in port 7.", + "Counter": "0,1,2,3", + "EventName": "UOPS_DISPATCHED_PORT.PORT_7", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "UMask": "0x1", + "BriefDescription": "Resource-related stall cycles", + "Counter": "0,1,2,3", + "EventName": "RESOURCE_STALLS.ANY", + "Errata": "HSD135", + "PublicDescription": "Cycles allocation is stalled due to resource related reason.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "UMask": "0x4", + "BriefDescription": "Cycles stalled due to no eligible RS entry available.", + "Counter": "0,1,2,3", + "EventName": "RESOURCE_STALLS.RS", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", "UMask": "0x8", - "BriefDescription": "Cycles with pending L1 cache miss loads.", - "Counter": "2", - "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", - "CounterMask": "8", - "PublicDescription": "Cycles with pending L1 data cache miss loads. Set Cmask=8 to count cycle.", + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "Counter": "0,1,2,3", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "This event counts cycles during which no instructions were allocated because no Store Buffers (SB) were available.", "SampleAfterValue": "2000003", - "CounterHTOff": "2" + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "UMask": "0x10", + "BriefDescription": "Cycles stalled due to re-order buffer full.", + "Counter": "0,1,2,3", + "EventName": "RESOURCE_STALLS.ROB", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "UMask": "0x1", + "BriefDescription": "Cycles with pending L2 cache miss loads.", + "Counter": "0,1,2,3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", + "CounterMask": "1", + "Errata": "HSD78", + "PublicDescription": "Cycles with pending L2 miss loads. Set Cmask=2 to count cycle.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xA3", @@ -590,7 +840,7 @@ { "EventCode": "0xA3", "UMask": "0x4", - "BriefDescription": "Total execution stalls", + "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.", "Counter": "0,1,2,3", "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE", "CounterMask": "4", @@ -622,6 +872,17 @@ }, { "EventCode": "0xA3", + "UMask": "0x8", + "BriefDescription": "Cycles with pending L1 cache miss loads.", + "Counter": "2", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", + "CounterMask": "8", + "PublicDescription": "Cycles with pending L1 data cache miss loads. Set Cmask=8 to count cycle.", + "SampleAfterValue": "2000003", + "CounterHTOff": "2" + }, + { + "EventCode": "0xA3", "UMask": "0xc", "BriefDescription": "Execution stalls due to L1 data cache misses", "Counter": "2", @@ -642,13 +903,22 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xB1", - "UMask": "0x2", - "BriefDescription": "Number of uops executed on the core.", + "EventCode": "0xA8", + "UMask": "0x1", + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE", - "Errata": "HSD30, HSM31", - "PublicDescription": "Counts total number of uops to be executed per-core each cycle.", + "EventName": "LSD.CYCLES_ACTIVE", + "CounterMask": "1", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA8", + "UMask": "0x1", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3", + "EventName": "LSD.CYCLES_4_UOPS", + "CounterMask": "4", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -665,68 +935,169 @@ "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xC0", - "UMask": "0x0", - "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", "Counter": "0,1,2,3", - "EventName": "INST_RETIRED.ANY_P", - "Errata": "HSD11, HSD140", - "PublicDescription": "Number of instructions at retirement.", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "CounterMask": "1", + "Errata": "HSD144, HSD30, HSM31", + "PublicDescription": "This events counts the cycles where at least one uop was executed. It is counted per thread.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xC0", - "UMask": "0x2", - "BriefDescription": "FP operations retired. X87 FP operations that have no exceptions: Counts also flows that have several X87 or flows that use X87 uops in the exception handling.", + "EventCode": "0xB1", + "UMask": "0x1", + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "INST_RETIRED.X87", - "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.", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "CounterMask": "2", + "Errata": "HSD144, HSD30, HSM31", + "PublicDescription": "This events counts the cycles where at least two uop were executed. It is counted per thread.", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xC0", + "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", - "PEBS": "2", - "Counter": "1", - "EventName": "INST_RETIRED.PREC_DIST", - "Errata": "HSD140", - "PublicDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution.", - "SampleAfterValue": "2000003", - "CounterHTOff": "1" - }, - { - "EventCode": "0xC1", - "UMask": "0x40", - "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", "Counter": "0,1,2,3", - "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", - "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "CounterMask": "3", + "Errata": "HSD144, HSD30, HSM31", + "PublicDescription": "This events counts the cycles where at least three uop were executed. It is counted per thread.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xC2", + "EventCode": "0xB1", "UMask": "0x1", - "BriefDescription": "Actually retired uops.", - "Data_LA": "1", - "PEBS": "1", + "BriefDescription": "Cycles where at least 4 uops were executed per-thread.", "Counter": "0,1,2,3", - "EventName": "UOPS_RETIRED.ALL", - "PublicDescription": "Counts the number of micro-ops retired. Use Cmask=1 and invert to count active cycles or stalled cycles.", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "CounterMask": "4", + "Errata": "HSD144, HSD30, HSM31", "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xC2", + "EventCode": "0xB1", "UMask": "0x2", - "BriefDescription": "Retirement slots used.", - "PEBS": "1", + "BriefDescription": "Number of uops executed on the core.", "Counter": "0,1,2,3", - "EventName": "UOPS_RETIRED.RETIRE_SLOTS", - "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 uops or 4 instructions could retire each cycle.", + "EventName": "UOPS_EXECUTED.CORE", + "Errata": "HSD30, HSM31", + "PublicDescription": "Counts total number of uops to be executed per-core each cycle.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xb1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "CounterMask": "1", + "Errata": "HSD30, HSM31", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xb1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "CounterMask": "2", + "Errata": "HSD30, HSM31", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xb1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "CounterMask": "3", + "Errata": "HSD30, HSM31", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xb1", + "UMask": "0x2", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "CounterMask": "4", + "Errata": "HSD30, HSM31", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "Invert": "1", + "EventCode": "0xb1", + "UMask": "0x2", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "Counter": "0,1,2,3", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "Errata": "HSD30, HSM31", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC0", + "UMask": "0x0", + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3", + "EventName": "INST_RETIRED.ANY_P", + "Errata": "HSD11, HSD140", + "PublicDescription": "Number of instructions at retirement.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC0", + "UMask": "0x1", + "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", + "PEBS": "2", + "Counter": "1", + "EventName": "INST_RETIRED.PREC_DIST", + "Errata": "HSD140", + "PublicDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution.", + "SampleAfterValue": "2000003", + "CounterHTOff": "1" + }, + { + "EventCode": "0xC0", + "UMask": "0x2", + "BriefDescription": "FP operations retired. X87 FP operations that have no exceptions: Counts also flows that have several X87 or flows that use X87 uops in the exception handling.", + "Counter": "0,1,2,3", + "EventName": "INST_RETIRED.X87", + "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.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC1", + "UMask": "0x40", + "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", + "Counter": "0,1,2,3", + "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", + "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC2", + "UMask": "0x1", + "BriefDescription": "Actually retired uops.", + "Data_LA": "1", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "UOPS_RETIRED.ALL", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -765,6 +1136,16 @@ "CounterHTOff": "0,1,2,3" }, { + "EventCode": "0xC2", + "UMask": "0x2", + "BriefDescription": "Retirement slots used.", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xC3", "UMask": "0x1", "BriefDescription": "Cycles there was a Nuke. Account for both thread-specific and All Thread Nukes.", @@ -774,6 +1155,17 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EdgeDetect": "1", + "EventCode": "0xC3", + "UMask": "0x1", + "BriefDescription": "Number of machine clears (nukes) of any type.", + "Counter": "0,1,2,3", + "EventName": "MACHINE_CLEARS.COUNT", + "CounterMask": "1", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xC3", "UMask": "0x4", "BriefDescription": "Self-modifying code (SMC) detected.", @@ -794,12 +1186,21 @@ }, { "EventCode": "0xC4", + "UMask": "0x0", + "BriefDescription": "All (macro) branch instructions retired.", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Branch instructions at retirement.", + "SampleAfterValue": "400009", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", "UMask": "0x1", "BriefDescription": "Conditional branch instructions retired.", "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.CONDITIONAL", - "PublicDescription": "Counts the number of conditional branch instructions retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -815,13 +1216,23 @@ }, { "EventCode": "0xC4", - "UMask": "0x0", + "UMask": "0x2", + "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).", + "PEBS": "1", + "Counter": "0,1,2,3", + "EventName": "BR_INST_RETIRED.NEAR_CALL_R3", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "UMask": "0x4", "BriefDescription": "All (macro) branch instructions retired.", + "PEBS": "2", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Branch instructions at retirement.", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xC4", @@ -830,7 +1241,6 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PublicDescription": "Counts the number of near return instructions retired.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -851,7 +1261,6 @@ "PEBS": "1", "Counter": "0,1,2,3", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PublicDescription": "Number of near taken branches retired.", "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -866,14 +1275,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xC4", - "UMask": "0x4", - "BriefDescription": "All (macro) branch instructions retired.", - "PEBS": "2", + "EventCode": "0xC5", + "UMask": "0x0", + "BriefDescription": "All mispredicted macro branch instructions retired.", "Counter": "0,1,2,3", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Mispredicted branch instructions at retirement.", "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0xC5", @@ -887,18 +1296,8 @@ }, { "EventCode": "0xC5", - "UMask": "0x0", - "BriefDescription": "All mispredicted macro branch instructions retired.", - "Counter": "0,1,2,3", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PublicDescription": "Mispredicted branch instructions at retirement.", - "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xC5", "UMask": "0x4", - "BriefDescription": "Mispredicted macro branch instructions retired. ", + "BriefDescription": "Mispredicted macro branch instructions retired.", "PEBS": "2", "Counter": "0,1,2,3", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", @@ -907,423 +1306,33 @@ "CounterHTOff": "0,1,2,3" }, { - "EventCode": "0xCC", + "EventCode": "0xC5", "UMask": "0x20", - "BriefDescription": "Count cases of saving new LBR", - "Counter": "0,1,2,3", - "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", - "PublicDescription": "Count cases of saving new LBR records by hardware.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "UMask": "0x0", - "BriefDescription": "Thread cycles when thread is not in halt state", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "PublicDescription": "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.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x89", - "UMask": "0xa0", - "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", - "Counter": "0,1,2,3", - "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x1", - "BriefDescription": "Cycles per core when uops are exectuted in port 0.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x2", - "BriefDescription": "Cycles per core when uops are exectuted in port 1.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x4", - "BriefDescription": "Cycles per core when uops are dispatched to port 2.", + "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.", + "PEBS": "1", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "400009", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", - "UMask": "0x8", - "BriefDescription": "Cycles per core when uops are dispatched to port 3.", + "EventCode": "0xCC", + "UMask": "0x20", + "BriefDescription": "Count cases of saving new LBR", "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE", - "AnyThread": "1", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "PublicDescription": "Count cases of saving new LBR records by hardware.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", - "UMask": "0x10", - "BriefDescription": "Cycles per core when uops are exectuted in port 4.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x20", - "BriefDescription": "Cycles per core when uops are exectuted in port 5.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x40", - "BriefDescription": "Cycles per core when uops are exectuted in port 6.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x80", - "BriefDescription": "Cycles per core when uops are dispatched to port 7.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xC5", - "UMask": "0x20", - "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.", - "PEBS": "1", - "Counter": "0,1,2,3", - "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PublicDescription": "Number of near branch instructions retired that were taken but mispredicted.", - "SampleAfterValue": "400009", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 1 uop was executed per-thread", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", - "CounterMask": "1", - "Errata": "HSD144, HSD30, HSM31", - "PublicDescription": "This events counts the cycles where at least one uop was executed. It is counted per thread.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 2 uops were executed per-thread", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", - "CounterMask": "2", - "Errata": "HSD144, HSD30, HSM31", - "PublicDescription": "This events counts the cycles where at least two uop were executed. It is counted per thread.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 3 uops were executed per-thread", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", - "CounterMask": "3", - "Errata": "HSD144, HSD30, HSM31", - "PublicDescription": "This events counts the cycles where at least three uop were executed. It is counted per thread.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xB1", - "UMask": "0x1", - "BriefDescription": "Cycles where at least 4 uops were executed per-thread.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", - "CounterMask": "4", - "Errata": "HSD144, HSD30, HSM31", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xe6", - "UMask": "0x1f", - "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "EventCode": "0xe6", + "UMask": "0x1f", + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", "Counter": "0,1,2,3", "EventName": "BACLEARS.ANY", "PublicDescription": "Number of front end re-steers due to BPU misprediction.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EdgeDetect": "1", - "EventCode": "0xC3", - "UMask": "0x1", - "BriefDescription": "Number of machine clears (nukes) of any type.", - "Counter": "0,1,2,3", - "EventName": "MACHINE_CLEARS.COUNT", - "CounterMask": "1", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA8", - "UMask": "0x1", - "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", - "Counter": "0,1,2,3", - "EventName": "LSD.CYCLES_ACTIVE", - "CounterMask": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA8", - "UMask": "0x1", - "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", - "Counter": "0,1,2,3", - "EventName": "LSD.CYCLES_4_UOPS", - "CounterMask": "4", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EdgeDetect": "1", - "Invert": "1", - "EventCode": "0x5E", - "UMask": "0x1", - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", - "Counter": "0,1,2,3", - "EventName": "RS_EVENTS.EMPTY_END", - "CounterMask": "1", - "SampleAfterValue": "200003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x1", - "BriefDescription": "Cycles per thread when uops are executed in port 0.", - "Counter": "0,1,2,3", - "EventName": "UOPS_DISPATCHED_PORT.PORT_0", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x2", - "BriefDescription": "Cycles per thread when uops are executed in port 1.", - "Counter": "0,1,2,3", - "EventName": "UOPS_DISPATCHED_PORT.PORT_1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x4", - "BriefDescription": "Cycles per thread when uops are executed in port 2.", - "Counter": "0,1,2,3", - "EventName": "UOPS_DISPATCHED_PORT.PORT_2", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x8", - "BriefDescription": "Cycles per thread when uops are executed in port 3.", - "Counter": "0,1,2,3", - "EventName": "UOPS_DISPATCHED_PORT.PORT_3", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x10", - "BriefDescription": "Cycles per thread when uops are executed in port 4.", - "Counter": "0,1,2,3", - "EventName": "UOPS_DISPATCHED_PORT.PORT_4", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x20", - "BriefDescription": "Cycles per thread when uops are executed in port 5.", - "Counter": "0,1,2,3", - "EventName": "UOPS_DISPATCHED_PORT.PORT_5", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x40", - "BriefDescription": "Cycles per thread when uops are executed in port 6.", - "Counter": "0,1,2,3", - "EventName": "UOPS_DISPATCHED_PORT.PORT_6", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "UMask": "0x80", - "BriefDescription": "Cycles per thread when uops are executed in port 7.", - "Counter": "0,1,2,3", - "EventName": "UOPS_DISPATCHED_PORT.PORT_7", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x00", - "UMask": "0x2", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "Counter": "Fixed counter 2", - "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "Fixed counter 2" - }, - { - "EventCode": "0x3C", - "UMask": "0x0", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", - "AnyThread": "1", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "UMask": "0x1", - "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", - "AnyThread": "1", - "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x0D", - "UMask": "0x3", - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke)", - "Counter": "0,1,2,3", - "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", - "AnyThread": "1", - "CounterMask": "1", - "PublicDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "UMask": "0x2", - "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "CounterMask": "1", - "Errata": "HSD30, HSM31", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "UMask": "0x2", - "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "CounterMask": "2", - "Errata": "HSD30, HSM31", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "UMask": "0x2", - "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "CounterMask": "3", - "Errata": "HSD30, HSM31", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "UMask": "0x2", - "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "CounterMask": "4", - "Errata": "HSD30, HSM31", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "Invert": "1", - "EventCode": "0xb1", - "UMask": "0x2", - "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", - "Counter": "0,1,2,3", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", - "Errata": "HSD30, HSM31", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "UMask": "0x1", - "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", - "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "UMask": "0x1", - "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "AnyThread": "1", - "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "UMask": "0x2", - "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", - "Counter": "0,1,2,3", - "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" } ] \ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/haswellx/virtual-memory.json b/tools/perf/pmu-events/arch/x86/haswellx/virtual-memory.json index 9c00f8e..168df55 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/virtual-memory.json @@ -40,6 +40,16 @@ }, { "EventCode": "0x08", + "UMask": "0xe", + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", "UMask": "0x10", "BriefDescription": "Cycles when PMH is busy with page walks", "Counter": "0,1,2,3", @@ -70,6 +80,16 @@ }, { "EventCode": "0x08", + "UMask": "0x60", + "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks", + "Counter": "0,1,2,3", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Number of cache load STLB hits. No page walk.", + "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", "UMask": "0x80", "BriefDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed", "Counter": "0,1,2,3", @@ -119,6 +139,16 @@ }, { "EventCode": "0x49", + "UMask": "0xe", + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", "UMask": "0x10", "BriefDescription": "Cycles when PMH is busy with page walks", "Counter": "0,1,2,3", @@ -149,6 +179,16 @@ }, { "EventCode": "0x49", + "UMask": "0x60", + "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks", + "Counter": "0,1,2,3", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", "UMask": "0x80", "BriefDescription": "DTLB store misses with low part of linear-to-physical address translation missed", "Counter": "0,1,2,3", @@ -207,6 +247,16 @@ }, { "EventCode": "0x85", + "UMask": "0xe", + "BriefDescription": "Misses in all ITLB levels that cause completed page walks", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Completed page walks in ITLB of any page size.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", "UMask": "0x10", "BriefDescription": "Cycles when PMH is busy with page walks", "Counter": "0,1,2,3", @@ -236,6 +286,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x85", + "UMask": "0x60", + "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks", + "Counter": "0,1,2,3", + "EventName": "ITLB_MISSES.STLB_HIT", + "PublicDescription": "ITLB misses that hit STLB. No page walk.", + "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xae", "UMask": "0x1", "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", @@ -257,39 +317,43 @@ }, { "EventCode": "0xBC", - "UMask": "0x21", - "BriefDescription": "Number of ITLB page walker hits in the L1+FB", + "UMask": "0x12", + "BriefDescription": "Number of DTLB page walker hits in the L2", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.ITLB_L1", - "PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.", + "EventName": "PAGE_WALKER_LOADS.DTLB_L2", + "PublicDescription": "Number of DTLB page walker loads that hit in the L2.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x41", - "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.", + "UMask": "0x14", + "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1", + "EventName": "PAGE_WALKER_LOADS.DTLB_L3", + "Errata": "HSD25", + "PublicDescription": "Number of DTLB page walker loads that hit in the L3.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x81", - "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.", + "UMask": "0x18", + "BriefDescription": "Number of DTLB page walker hits in Memory", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1", + "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY", + "Errata": "HSD25", + "PublicDescription": "Number of DTLB page walker loads from memory.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x12", - "BriefDescription": "Number of DTLB page walker hits in the L2", + "UMask": "0x21", + "BriefDescription": "Number of ITLB page walker hits in the L1+FB", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.DTLB_L2", - "PublicDescription": "Number of DTLB page walker loads that hit in the L2.", + "EventName": "PAGE_WALKER_LOADS.ITLB_L1", + "PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -305,41 +369,41 @@ }, { "EventCode": "0xBC", - "UMask": "0x42", - "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.", + "UMask": "0x24", + "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2", + "EventName": "PAGE_WALKER_LOADS.ITLB_L3", + "Errata": "HSD25", + "PublicDescription": "Number of ITLB page walker loads that hit in the L3.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x82", - "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.", + "UMask": "0x28", + "BriefDescription": "Number of ITLB page walker hits in Memory", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2", + "EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY", + "Errata": "HSD25", + "PublicDescription": "Number of ITLB page walker loads from memory.", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x14", - "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP", + "UMask": "0x41", + "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.DTLB_L3", - "Errata": "HSD25", - "PublicDescription": "Number of DTLB page walker loads that hit in the L3.", + "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x24", - "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP", + "UMask": "0x42", + "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.ITLB_L3", - "Errata": "HSD25", - "PublicDescription": "Number of ITLB page walker loads that hit in the L3.", + "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -354,41 +418,37 @@ }, { "EventCode": "0xBC", - "UMask": "0x84", - "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.", + "UMask": "0x48", + "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3", + "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x18", - "BriefDescription": "Number of DTLB page walker hits in Memory", + "UMask": "0x81", + "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY", - "Errata": "HSD25", - "PublicDescription": "Number of DTLB page walker loads from memory.", + "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x28", - "BriefDescription": "Number of ITLB page walker hits in Memory", + "UMask": "0x82", + "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY", - "Errata": "HSD25", - "PublicDescription": "Number of ITLB page walker loads from memory.", + "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", - "UMask": "0x48", - "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.", + "UMask": "0x84", + "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.", "Counter": "0,1,2,3", - "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY", + "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3", "SampleAfterValue": "2000003", "CounterHTOff": "0,1,2,3" }, @@ -420,65 +480,5 @@ "PublicDescription": "Count number of STLB flush attempts.", "SampleAfterValue": "100003", "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x08", - "UMask": "0xe", - "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.", - "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x08", - "UMask": "0x60", - "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks", - "Counter": "0,1,2,3", - "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Number of cache load STLB hits. No page walk.", - "SampleAfterValue": "2000003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x49", - "UMask": "0xe", - "BriefDescription": "Store misses in all DTLB levels that cause completed page walks", - "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x49", - "UMask": "0x60", - "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks", - "Counter": "0,1,2,3", - "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x85", - "UMask": "0xe", - "BriefDescription": "Misses in all ITLB levels that cause completed page walks", - "Counter": "0,1,2,3", - "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Completed page walks in ITLB of any page size.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x85", - "UMask": "0x60", - "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks", - "Counter": "0,1,2,3", - "EventName": "ITLB_MISSES.STLB_HIT", - "PublicDescription": "ITLB misses that hit STLB. No page walk.", - "SampleAfterValue": "100003", - "CounterHTOff": "0,1,2,3,4,5,6,7" } ] \ No newline at end of file
