Commit-ID: 8e355d22a8f61ce277d93ce51758b80431568481 Gitweb: https://git.kernel.org/tip/8e355d22a8f61ce277d93ce51758b80431568481 Author: Andi Kleen <a...@linux.intel.com> AuthorDate: Thu, 18 Jan 2018 04:48:12 -0800 Committer: Arnaldo Carvalho de Melo <a...@redhat.com> CommitDate: Tue, 23 Jan 2018 09:51:40 -0300
perf vendor events intel: Update Haswell events to V27 Link: https://lkml.kernel.org/r/20180118234518.ga27...@tassilo.jf.intel.com Signed-off-by: Andi Kleen <a...@linux.intel.com> --- tools/perf/pmu-events/arch/x86/haswell/cache.json | 365 ++++--- .../arch/x86/haswell/floating-point.json | 20 +- .../perf/pmu-events/arch/x86/haswell/frontend.json | 132 +-- tools/perf/pmu-events/arch/x86/haswell/memory.json | 21 + tools/perf/pmu-events/arch/x86/haswell/other.json | 20 +- .../perf/pmu-events/arch/x86/haswell/pipeline.json | 1131 ++++++++++---------- .../arch/x86/haswell/virtual-memory.json | 212 ++-- 7 files changed, 977 insertions(+), 924 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/haswell/cache.json b/tools/perf/pmu-events/arch/x86/haswell/cache.json index bfb5ebf..da4d6dd 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/cache.json +++ b/tools/perf/pmu-events/arch/x86/haswell/cache.json @@ -11,14 +11,34 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Demand data read requests that hit L2 cache.", + "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.", "EventCode": "0x24", "Counter": "0,1,2,3", - "UMask": "0x41", + "UMask": "0x22", + "EventName": "L2_RQSTS.RFO_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that miss L2 cache", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Number of instruction fetches that missed the L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache misses when fetching instructions", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Demand requests that miss L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x27", "Errata": "HSD78", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read requests that hit L2 cache", + "BriefDescription": "Demand requests that miss L2 cache", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -32,6 +52,48 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "All requests that missed L2.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x3f", + "Errata": "HSD78", + "EventName": "L2_RQSTS.MISS", + "SampleAfterValue": "200003", + "BriefDescription": "All requests that miss L2 cache", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Demand data read requests that hit L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x41", + "Errata": "HSD78", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x42", + "EventName": "L2_RQSTS.RFO_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that hit L2 cache", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Number of instruction fetches that hit the L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x44", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.", "EventCode": "0x24", "Counter": "0,1,2,3", @@ -73,6 +135,17 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Demand requests to L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xe7", + "Errata": "HSD78", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "SampleAfterValue": "200003", + "BriefDescription": "Demand requests to L2 cache", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Counts all L2 HW prefetcher requests.", "EventCode": "0x24", "Counter": "0,1,2,3", @@ -83,6 +156,17 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "All requests to L2 cache.", + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xff", + "Errata": "HSD78", + "EventName": "L2_RQSTS.REFERENCES", + "SampleAfterValue": "200003", + "BriefDescription": "All L2 requests", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Not rejected writebacks that hit L2 cache.", "EventCode": "0x27", "Counter": "0,1,2,3", @@ -124,6 +208,27 @@ }, { "EventCode": "0x48", + "Counter": "2", + "UMask": "0x1", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "CounterMask": "1", + "CounterHTOff": "2" + }, + { + "EventCode": "0x48", + "Counter": "2", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "CounterMask": "1", + "CounterHTOff": "2" + }, + { + "EventCode": "0x48", "Counter": "0,1,2,3", "UMask": "0x2", "EventName": "L1D_PEND_MISS.REQUEST_FB_FULL", @@ -133,13 +238,13 @@ }, { "EventCode": "0x48", - "Counter": "2", - "UMask": "0x1", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "L1D_PEND_MISS.FB_FULL", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with L1D load Misses outstanding.", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", "CounterMask": "1", - "CounterHTOff": "2" + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "PublicDescription": "This event counts when new data lines are brought into the L1 Data cache, which cause other lines to be evicted from the cache.", @@ -163,6 +268,28 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Errata": "HSD78, HSD62, HSD61", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Errata": "HSD78, HSD62, HSD61", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "CounterMask": "6", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Offcore outstanding Demand code Read transactions in SQ to uncore. Set Cmask=1 to count cycles.", "EventCode": "0x60", "Counter": "0,1,2,3", @@ -185,46 +312,35 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.", "EventCode": "0x60", "Counter": "0,1,2,3", - "UMask": "0x8", + "UMask": "0x4", "Errata": "HSD62, HSD61", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x60", - "Counter": "0,1,2,3", - "UMask": "0x1", - "Errata": "HSD78, HSD62, HSD61", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.", "EventCode": "0x60", "Counter": "0,1,2,3", "UMask": "0x8", "Errata": "HSD62, HSD61", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", - "CounterMask": "1", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x60", "Counter": "0,1,2,3", - "UMask": "0x4", + "UMask": "0x8", "Errata": "HSD62, HSD61", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -289,6 +405,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xB7, 0xBB", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_RESPONSE", + "SampleAfterValue": "100003", + "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.", + "CounterHTOff": "0,1,2,3" + }, + { "PEBS": "1", "EventCode": "0xD0", "Counter": "0,1,2,3", @@ -296,7 +421,7 @@ "Errata": "HSD29, HSM30", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops that miss the STLB.", + "BriefDescription": "Retired load uops that miss the STLB. (precise Event)", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, @@ -308,7 +433,7 @@ "Errata": "HSD29, HSM30", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", "SampleAfterValue": "100003", - "BriefDescription": "Retired store uops that miss the STLB.", + "BriefDescription": "Retired store uops that miss the STLB. (precise Event)", "CounterHTOff": "0,1,2,3", "Data_LA": "1", "L1_Hit_Indication": "1" @@ -321,31 +446,33 @@ "Errata": "HSD76, HSD29, HSM30", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops with locked access.", + "BriefDescription": "Retired load uops with locked access. (precise Event)", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, { "PEBS": "1", + "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.", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x41", "Errata": "HSD29, HSM30", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "SampleAfterValue": "100003", - "BriefDescription": "Retired load uops that split across a cacheline boundary.", + "BriefDescription": "Retired load uops that split across a cacheline boundary. (precise Event)", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, { "PEBS": "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.", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x42", "Errata": "HSD29, HSM30", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "SampleAfterValue": "100003", - "BriefDescription": "Retired store uops that split across a cacheline boundary.", + "BriefDescription": "Retired store uops that split across a cacheline boundary. (precise Event)", "CounterHTOff": "0,1,2,3", "Data_LA": "1", "L1_Hit_Indication": "1" @@ -358,19 +485,20 @@ "Errata": "HSD29, HSM30", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "SampleAfterValue": "2000003", - "BriefDescription": "All retired load uops.", + "BriefDescription": "All retired load uops. (precise Event)", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, { "PEBS": "1", + "PublicDescription": "This event counts all store uops retired. This is a precise event.", "EventCode": "0xD0", "Counter": "0,1,2,3", "UMask": "0x82", "Errata": "HSD29, HSM30", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "SampleAfterValue": "2000003", - "BriefDescription": "All retired store uops.", + "BriefDescription": "All retired store uops. (precise Event)", "CounterHTOff": "0,1,2,3", "Data_LA": "1", "L1_Hit_Indication": "1" @@ -401,20 +529,20 @@ }, { "PEBS": "1", - "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.", "EventCode": "0xD1", "Counter": "0,1,2,3", "UMask": "0x4", "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", "SampleAfterValue": "50021", - "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.", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, { "PEBS": "1", - "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.", "EventCode": "0xD1", "Counter": "0,1,2,3", "UMask": "0x8", @@ -427,20 +555,18 @@ }, { "PEBS": "1", - "PublicDescription": "Retired load uops missed L2. Unknown data source excluded.", "EventCode": "0xD1", "Counter": "0,1,2,3", "UMask": "0x10", "Errata": "HSD29, HSM30", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "SampleAfterValue": "50021", - "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.", + "BriefDescription": "Retired load uops with L2 cache misses as data sources.", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, { "PEBS": "1", - "PublicDescription": "Retired load uops missed L3. Excludes unknown data source .", "EventCode": "0xD1", "Counter": "0,1,2,3", "UMask": "0x20", @@ -477,25 +603,27 @@ }, { "PEBS": "1", + "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.", "EventCode": "0xD2", "Counter": "0,1,2,3", "UMask": "0x2", "Errata": "HSD29, HSD25, HSM26, HSM30", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, { "PEBS": "1", + "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.", "EventCode": "0xD2", "Counter": "0,1,2,3", "UMask": "0x4", "Errata": "HSD29, HSD25, HSM26, HSM30", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", "SampleAfterValue": "20011", - "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, @@ -513,14 +641,13 @@ }, { "PEBS": "1", - "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.", "EventCode": "0xD3", "Counter": "0,1,2,3", "UMask": "0x1", "Errata": "HSD74, HSD29, HSD25, HSM30", "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", "SampleAfterValue": "100003", - "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)", "CounterHTOff": "0,1,2,3", "Data_LA": "1" }, @@ -665,6 +792,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "", "EventCode": "0xf4", "Counter": "0,1,2,3", "UMask": "0x10", @@ -674,131 +802,7 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.", - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x42", - "EventName": "L2_RQSTS.RFO_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests that hit L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.", - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x22", - "EventName": "L2_RQSTS.RFO_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Number of instruction fetches that hit the L2 cache.", - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x44", - "EventName": "L2_RQSTS.CODE_RD_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "L2 cache hits when fetching instructions, code reads.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Number of instruction fetches that missed the L2 cache.", - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "L2_RQSTS.CODE_RD_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "L2 cache misses when fetching instructions", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Demand requests that miss L2 cache.", - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x27", - "Errata": "HSD78", - "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Demand requests that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Demand requests to L2 cache.", - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0xe7", - "Errata": "HSD78", - "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "SampleAfterValue": "200003", - "BriefDescription": "Demand requests to L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "All requests that missed L2.", - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x3f", - "Errata": "HSD78", - "EventName": "L2_RQSTS.MISS", - "SampleAfterValue": "200003", - "BriefDescription": "All requests that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "All requests to L2 cache.", - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0xff", - "Errata": "HSD78", - "EventName": "L2_RQSTS.REFERENCES", - "SampleAfterValue": "200003", - "BriefDescription": "All L2 requests", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xB7, 0xBB", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE", - "SampleAfterValue": "100003", - "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.", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0x60", - "Counter": "0,1,2,3", - "UMask": "0x1", - "Errata": "HSD78, HSD62, HSD61", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", - "CounterMask": "6", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x48", - "Counter": "2", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", - "CounterMask": "1", - "CounterHTOff": "2" - }, - { - "EventCode": "0x48", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "L1D_PEND_MISS.FB_FULL", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { + "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3f803c8fff", "Counter": "0,1,2,3", @@ -811,6 +815,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x10003c07f7", "Counter": "0,1,2,3", @@ -823,6 +828,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x04003c07f7", "Counter": "0,1,2,3", @@ -835,6 +841,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x04003c0244", "Counter": "0,1,2,3", @@ -847,6 +854,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x10003c0122", "Counter": "0,1,2,3", @@ -859,6 +867,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x04003c0122", "Counter": "0,1,2,3", @@ -871,6 +880,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x10003c0091", "Counter": "0,1,2,3", @@ -883,6 +893,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x04003c0091", "Counter": "0,1,2,3", @@ -895,6 +906,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3f803c0200", "Counter": "0,1,2,3", @@ -907,6 +919,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3f803c0100", "Counter": "0,1,2,3", @@ -919,6 +932,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3f803c0080", "Counter": "0,1,2,3", @@ -931,6 +945,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3f803c0040", "Counter": "0,1,2,3", @@ -943,6 +958,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3f803c0020", "Counter": "0,1,2,3", @@ -955,6 +971,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3f803c0010", "Counter": "0,1,2,3", @@ -967,6 +984,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x10003c0004", "Counter": "0,1,2,3", @@ -979,6 +997,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x04003c0004", "Counter": "0,1,2,3", @@ -991,6 +1010,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x10003c0002", "Counter": "0,1,2,3", @@ -1003,6 +1023,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x04003c0002", "Counter": "0,1,2,3", @@ -1015,6 +1036,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x10003c0001", "Counter": "0,1,2,3", @@ -1027,6 +1049,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x04003c0001", "Counter": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json index 1732fa4..f9843e5 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json @@ -20,6 +20,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.", + "EventCode": "0xC6", + "Counter": "0,1,2,3", + "UMask": "0x7", + "EventName": "AVX_INSTS.ALL", + "SampleAfterValue": "2000003", + "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.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Number of X87 FP assists due to output values.", "EventCode": "0xCA", "Counter": "0,1,2,3", @@ -69,15 +79,5 @@ "BriefDescription": "Cycles with any input/output SSE or FP assist", "CounterMask": "1", "CounterHTOff": "0,1,2,3" - }, - { - "PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.", - "EventCode": "0xC6", - "Counter": "0,1,2,3", - "UMask": "0x7", - "EventName": "AVX_INSTS.ALL", - "SampleAfterValue": "2000003", - "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.", - "CounterHTOff": "0,1,2,3,4,5,6,7" } ] \ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/haswell/frontend.json b/tools/perf/pmu-events/arch/x86/haswell/frontend.json index 57a1ce4..c0a5bed 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/frontend.json +++ b/tools/perf/pmu-events/arch/x86/haswell/frontend.json @@ -21,74 +21,43 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.", "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "IDQ.DSB_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "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.", - "EventCode": "0x79", - "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "IDQ.MS_DSB_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.", - "EventCode": "0x79", - "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "IDQ.MS_MITE_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "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.", - "EventCode": "0x79", - "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "IDQ.MS_UOPS", + "UMask": "0x4", + "EventName": "IDQ.MITE_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", + "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "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.", + "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.", "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "IDQ.MS_CYCLES", + "UMask": "0x8", + "EventName": "IDQ.DSB_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterMask": "1", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "IDQ.MITE_CYCLES", + "UMask": "0x8", + "EventName": "IDQ.DSB_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "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.", "EventCode": "0x79", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "IDQ.DSB_CYCLES", + "UMask": "0x10", + "EventName": "IDQ.MS_DSB_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", - "CounterMask": "1", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -135,6 +104,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "IDQ.MS_MITE_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Counts cycles MITE is delivered four uops. Set Cmask = 4.", "EventCode": "0x79", "Counter": "0,1,2,3", @@ -157,6 +136,38 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "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.", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x30", + "EventName": "IDQ.MS_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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.", + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x30", + "EventName": "IDQ.MS_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x30", + "EdgeDetect": "1", + "EventName": "IDQ.MS_SWITCHES", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Number of uops delivered to IDQ from any path.", "EventCode": "0x79", "Counter": "0,1,2,3", @@ -195,6 +206,15 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x80", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "ICACHE.IFDATA_STALL", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "This event count the number of undelivered (unallocated) uops from the Front-end to the Resource Allocation Table (RAT) while the Back-end of the processor is not stalled. The Front-end can allocate up to 4 uops per cycle so this event can increment 0-4 times per cycle depending on the number of unallocated uops. This event is counted on a per-core basis.", "EventCode": "0x9C", "Counter": "0,1,2,3", @@ -270,25 +290,5 @@ "SampleAfterValue": "2000003", "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x79", - "Counter": "0,1,2,3", - "UMask": "0x30", - "EdgeDetect": "1", - "EventName": "IDQ.MS_SWITCHES", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x80", - "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "ICACHE.IFDATA_STALL", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.", - "CounterHTOff": "0,1,2,3,4,5,6,7" } ] \ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/haswell/memory.json b/tools/perf/pmu-events/arch/x86/haswell/memory.json index aab981b..e5f9fa6 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/memory.json +++ b/tools/perf/pmu-events/arch/x86/haswell/memory.json @@ -401,6 +401,7 @@ "CounterHTOff": "3" }, { + "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc08fff", "Counter": "0,1,2,3", @@ -413,6 +414,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x01004007f7", "Counter": "0,1,2,3", @@ -425,6 +427,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc007f7", "Counter": "0,1,2,3", @@ -437,6 +440,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400244", "Counter": "0,1,2,3", @@ -449,6 +453,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00244", "Counter": "0,1,2,3", @@ -461,6 +466,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400122", "Counter": "0,1,2,3", @@ -473,6 +479,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00122", "Counter": "0,1,2,3", @@ -485,6 +492,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400091", "Counter": "0,1,2,3", @@ -497,6 +505,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00091", "Counter": "0,1,2,3", @@ -509,6 +518,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00200", "Counter": "0,1,2,3", @@ -521,6 +531,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00100", "Counter": "0,1,2,3", @@ -533,6 +544,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00080", "Counter": "0,1,2,3", @@ -545,6 +557,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00040", "Counter": "0,1,2,3", @@ -557,6 +570,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00020", "Counter": "0,1,2,3", @@ -569,6 +583,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00010", "Counter": "0,1,2,3", @@ -581,6 +596,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400004", "Counter": "0,1,2,3", @@ -593,6 +609,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00004", "Counter": "0,1,2,3", @@ -605,6 +622,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400002", "Counter": "0,1,2,3", @@ -617,6 +635,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00002", "Counter": "0,1,2,3", @@ -629,6 +648,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x0100400001", "Counter": "0,1,2,3", @@ -641,6 +661,7 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "EventCode": "0xB7, 0xBB", "MSRValue": "0x3fffc00001", "Counter": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/haswell/other.json b/tools/perf/pmu-events/arch/x86/haswell/other.json index 85d6a14..8a4d898 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/other.json +++ b/tools/perf/pmu-events/arch/x86/haswell/other.json @@ -10,16 +10,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.", - "EventCode": "0x5C", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "CPL_CYCLES.RING123", - "SampleAfterValue": "2000003", - "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "EventCode": "0x5C", "Counter": "0,1,2,3", "UMask": "0x1", @@ -31,6 +21,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.", + "EventCode": "0x5C", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "CPL_CYCLES.RING123", + "SampleAfterValue": "2000003", + "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.", "EventCode": "0x63", "Counter": "0,1,2,3", diff --git a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json index 0099848..a4dcfce 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json @@ -2,33 +2,43 @@ { "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. INST_RETIRED.ANY is counted by a designated fixed counter, leaving the programmable counters available for other events. Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", "EventCode": "0x00", - "Counter": "Fixed counter 1", + "Counter": "Fixed counter 0", "UMask": "0x1", "Errata": "HSD140, HSD143", "EventName": "INST_RETIRED.ANY", "SampleAfterValue": "2000003", "BriefDescription": "Instructions retired from execution.", - "CounterHTOff": "Fixed counter 1" + "CounterHTOff": "Fixed counter 0" }, { "PublicDescription": "This event counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.", "EventCode": "0x00", - "Counter": "Fixed counter 2", + "Counter": "Fixed counter 1", "UMask": "0x2", "EventName": "CPU_CLK_UNHALTED.THREAD", "SampleAfterValue": "2000003", "BriefDescription": "Core cycles when the thread is not in halt state.", - "CounterHTOff": "Fixed counter 2" + "CounterHTOff": "Fixed counter 1" + }, + { + "EventCode": "0x00", + "Counter": "Fixed counter 1", + "UMask": "0x2", + "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "CounterHTOff": "Fixed counter 1" }, { "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state.", "EventCode": "0x00", - "Counter": "Fixed counter 3", + "Counter": "Fixed counter 2", "UMask": "0x3", "EventName": "CPU_CLK_UNHALTED.REF_TSC", "SampleAfterValue": "2000003", "BriefDescription": "Reference cycles when the core is not in halt state.", - "CounterHTOff": "Fixed counter 3" + "CounterHTOff": "Fixed counter 2" }, { "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. The penalty for blocked store forwarding is that the load must wait for the store to write its value to the cache before it can be issued.", @@ -67,7 +77,19 @@ "UMask": "0x3", "EventName": "INT_MISC.RECOVERY_CYCLES", "SampleAfterValue": "2000003", - "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)", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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).", + "EventCode": "0x0D", + "Counter": "0,1,2,3", + "UMask": "0x3", + "AnyThread": "1", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "SampleAfterValue": "2000003", + "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)", "CounterMask": "1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, @@ -82,6 +104,29 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x0E", + "Invert": "1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x0E", + "Invert": "1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" + }, + { "PublicDescription": "Number of flags-merge uops allocated. Such uops add delay.", "EventCode": "0x0E", "Counter": "0,1,2,3", @@ -112,35 +157,32 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0E", - "Invert": "1", + "EventCode": "0x14", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_ISSUED.STALL_CYCLES", + "UMask": "0x2", + "EventName": "ARITH.DIVIDER_UOPS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Any uop executed by the Divider. (This includes all divide uops, sqrt, ...)", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x0E", - "Invert": "1", + "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.", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES", + "UMask": "0x0", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "Thread cycles when thread is not in halt state", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0x14", + "EventCode": "0x3C", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "ARITH.DIVIDER_UOPS", + "UMask": "0x0", + "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Any uop executed by the Divider. (This includes all divide uops, sqrt, ...)", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -154,6 +196,38 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "EventCode": "0x3C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)", + "EventCode": "0x3C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "EventCode": "0x3C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0x3c", "Counter": "0,1,2,3", "UMask": "0x2", @@ -163,6 +237,15 @@ "CounterHTOff": "0,1,2,3" }, { + "EventCode": "0x3C", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "2000003", + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Non-SW-prefetch load dispatches that hit fill buffer allocated for S/W prefetch.", "EventCode": "0x4c", "Counter": "0,1,2,3", @@ -233,6 +316,18 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0x5E", + "Invert": "1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EdgeDetect": "1", + "EventName": "RS_EVENTS.EMPTY_END", + "SampleAfterValue": "200003", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "This event counts cycles where the decoder is stalled on an instruction with a length changing prefix (LCP).", "EventCode": "0x87", "Counter": "0,1,2,3", @@ -409,6 +504,15 @@ { "EventCode": "0x89", "Counter": "0,1,2,3", + "UMask": "0xa0", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", + "Counter": "0,1,2,3", "UMask": "0xc1", "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL", "SampleAfterValue": "200003", @@ -445,136 +549,282 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles which a uop is dispatched on port 1 in this thread.", + "PublicDescription": "Cycles per core when uops are exectuted in port 0.", "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED_PORT.PORT_1", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 1", + "BriefDescription": "Cycles per core when uops are executed in port 0.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles which a uop is dispatched on port 2 in this thread.", "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "UOPS_EXECUTED_PORT.PORT_2", + "UMask": "0x1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 2", + "BriefDescription": "Cycles per thread when uops are executed in port 0.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles which a uop is dispatched on port 3 in this thread.", + "PublicDescription": "Cycles which a uop is dispatched on port 1 in this thread.", "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "UOPS_EXECUTED_PORT.PORT_3", + "UMask": "0x2", + "EventName": "UOPS_EXECUTED_PORT.PORT_1", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 3", + "BriefDescription": "Cycles per thread when uops are executed in port 1", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles which a uop is dispatched on port 4 in this thread.", + "PublicDescription": "Cycles per core when uops are exectuted in port 1.", "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "UOPS_EXECUTED_PORT.PORT_4", + "UMask": "0x2", + "AnyThread": "1", + "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 4", + "BriefDescription": "Cycles per core when uops are executed in port 1.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles which a uop is dispatched on port 5 in this thread.", "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "UOPS_EXECUTED_PORT.PORT_5", + "UMask": "0x2", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 5", + "BriefDescription": "Cycles per thread when uops are executed in port 1.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles which a uop is dispatched on port 6 in this thread.", + "PublicDescription": "Cycles which a uop is dispatched on port 2 in this thread.", "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "UOPS_EXECUTED_PORT.PORT_6", + "UMask": "0x4", + "EventName": "UOPS_EXECUTED_PORT.PORT_2", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 6", + "BriefDescription": "Cycles per thread when uops are executed in port 2", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles which a uop is dispatched on port 7 in this thread.", "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "UOPS_EXECUTED_PORT.PORT_7", + "UMask": "0x4", + "AnyThread": "1", + "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 7", + "BriefDescription": "Cycles per core when uops are dispatched to port 2.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles allocation is stalled due to resource related reason.", - "EventCode": "0xA2", + "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x1", - "Errata": "HSD135", - "EventName": "RESOURCE_STALLS.ANY", + "UMask": "0x4", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", "SampleAfterValue": "2000003", - "BriefDescription": "Resource-related stall cycles", + "BriefDescription": "Cycles per thread when uops are executed in port 2.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "PublicDescription": "Cycles which a uop is dispatched on port 3 in this thread.", + "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "RESOURCE_STALLS.RS", + "UMask": "0x8", + "EventName": "UOPS_EXECUTED_PORT.PORT_3", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles stalled due to no eligible RS entry available.", + "BriefDescription": "Cycles per thread when uops are executed in port 3", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "This event counts cycles during which no instructions were allocated because no Store Buffers (SB) were available.", - "EventCode": "0xA2", + "EventCode": "0xA1", "Counter": "0,1,2,3", "UMask": "0x8", - "EventName": "RESOURCE_STALLS.SB", + "AnyThread": "1", + "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE", "SampleAfterValue": "2000003", - "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.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA2", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are executed in port 3.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Cycles which a uop is dispatched on port 4 in this thread.", + "EventCode": "0xA1", "Counter": "0,1,2,3", "UMask": "0x10", - "EventName": "RESOURCE_STALLS.ROB", + "EventName": "UOPS_EXECUTED_PORT.PORT_4", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles stalled due to re-order buffer full.", + "BriefDescription": "Cycles per thread when uops are executed in port 4", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles with pending L2 miss loads. Set Cmask=2 to count cycle.", - "EventCode": "0xA3", + "PublicDescription": "Cycles per core when uops are exectuted in port 4.", + "EventCode": "0xA1", "Counter": "0,1,2,3", - "UMask": "0x1", - "Errata": "HSD78", - "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", + "UMask": "0x10", + "AnyThread": "1", + "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with pending L2 cache miss loads.", - "CounterMask": "1", + "BriefDescription": "Cycles per core when uops are executed in port 4.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Cycles with pending L1 data cache miss loads. Set Cmask=8 to count cycle.", - "EventCode": "0xA3", - "Counter": "2", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are executed in port 4.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Cycles which a uop is dispatched on port 5 in this thread.", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "UOPS_EXECUTED_PORT.PORT_5", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are executed in port 5", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Cycles per core when uops are exectuted in port 5.", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x20", + "AnyThread": "1", + "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per core when uops are executed in port 5.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are executed in port 5.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Cycles which a uop is dispatched on port 6 in this thread.", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "UOPS_EXECUTED_PORT.PORT_6", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are executed in port 6", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Cycles per core when uops are exectuted in port 6.", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "AnyThread": "1", + "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per core when uops are executed in port 6.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "UOPS_DISPATCHED_PORT.PORT_6", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are executed in port 6.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Cycles which a uop is dispatched on port 7 in this thread.", + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x80", + "EventName": "UOPS_EXECUTED_PORT.PORT_7", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are executed in port 7", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x80", + "AnyThread": "1", + "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per core when uops are dispatched to port 7.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x80", + "EventName": "UOPS_DISPATCHED_PORT.PORT_7", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are executed in port 7.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Cycles allocation is stalled due to resource related reason.", + "EventCode": "0xA2", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Errata": "HSD135", + "EventName": "RESOURCE_STALLS.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource-related stall cycles", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "RESOURCE_STALLS.RS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles stalled due to no eligible RS entry available.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts cycles during which no instructions were allocated because no Store Buffers (SB) were available.", + "EventCode": "0xA2", + "Counter": "0,1,2,3", "UMask": "0x8", - "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", + "EventName": "RESOURCE_STALLS.SB", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with pending L1 cache miss loads.", - "CounterMask": "8", - "CounterHTOff": "2" + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "RESOURCE_STALLS.ROB", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles stalled due to re-order buffer full.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Cycles with pending L2 miss loads. Set Cmask=2 to count cycle.", + "EventCode": "0xA3", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Errata": "HSD78", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with pending L2 cache miss loads.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "PublicDescription": "Cycles with pending memory loads. Set Cmask=2 to count cycle.", @@ -594,7 +844,7 @@ "UMask": "0x4", "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE", "SampleAfterValue": "2000003", - "BriefDescription": "Total execution stalls", + "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.", "CounterMask": "4", "CounterHTOff": "0,1,2,3" }, @@ -621,6 +871,17 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Cycles with pending L1 data cache miss loads. Set Cmask=8 to count cycle.", + "EventCode": "0xA3", + "Counter": "2", + "UMask": "0x8", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with pending L1 cache miss loads.", + "CounterMask": "8", + "CounterHTOff": "2" + }, + { "PublicDescription": "Execution stalls due to L1 data cache miss loads. Set Cmask=0CH.", "EventCode": "0xA3", "Counter": "2", @@ -642,14 +903,23 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Counts total number of uops to be executed per-core each cycle.", - "EventCode": "0xB1", + "EventCode": "0xA8", "Counter": "0,1,2,3", - "UMask": "0x2", - "Errata": "HSD30, HSM31", - "EventName": "UOPS_EXECUTED.CORE", + "UMask": "0x1", + "EventName": "LSD.CYCLES_ACTIVE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of uops executed on the core.", + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA8", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "LSD.CYCLES_4_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "4", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { @@ -665,72 +935,173 @@ "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Number of instructions at retirement.", - "EventCode": "0xC0", + "PublicDescription": "This events counts the cycles where at least one uop was executed. It is counted per thread.", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0x0", - "Errata": "HSD11, HSD140", - "EventName": "INST_RETIRED.ANY_P", + "UMask": "0x1", + "Errata": "HSD144, HSD30, HSM31", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", "SampleAfterValue": "2000003", - "BriefDescription": "Number of instructions retired. General Counter - architectural event", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" }, { - "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.", - "EventCode": "0xC0", + "PublicDescription": "This events counts the cycles where at least two uop were executed. It is counted per thread.", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "INST_RETIRED.X87", - "SampleAfterValue": "2000003", - "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.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PEBS": "2", - "PublicDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution.", - "EventCode": "0xC0", - "Counter": "1", "UMask": "0x1", - "Errata": "HSD140", - "EventName": "INST_RETIRED.PREC_DIST", + "Errata": "HSD144, HSD30, HSM31", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", "SampleAfterValue": "2000003", - "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", - "CounterHTOff": "1" + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "CounterMask": "2", + "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.", - "EventCode": "0xC1", + "PublicDescription": "This events counts the cycles where at least three uop were executed. It is counted per thread.", + "EventCode": "0xB1", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", - "SampleAfterValue": "100003", - "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1", + "Errata": "HSD144, HSD30, HSM31", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "CounterMask": "3", + "CounterHTOff": "0,1,2,3" }, { - "PEBS": "1", - "PublicDescription": "Counts the number of micro-ops retired. Use Cmask=1 and invert to count active cycles or stalled cycles.", - "EventCode": "0xC2", + "EventCode": "0xB1", "Counter": "0,1,2,3", "UMask": "0x1", - "EventName": "UOPS_RETIRED.ALL", + "Errata": "HSD144, HSD30, HSM31", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", "SampleAfterValue": "2000003", - "BriefDescription": "Actually retired uops.", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "Data_LA": "1" + "BriefDescription": "Cycles where at least 4 uops were executed per-thread.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3" }, { - "PEBS": "1", - "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.", - "EventCode": "0xC2", + "PublicDescription": "Counts total number of uops to be executed per-core each cycle.", + "EventCode": "0xB1", "Counter": "0,1,2,3", "UMask": "0x2", - "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "Errata": "HSD30, HSM31", + "EventName": "UOPS_EXECUTED.CORE", "SampleAfterValue": "2000003", - "BriefDescription": "Retirement slots used.", + "BriefDescription": "Number of uops executed on the core.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xb1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "Errata": "HSD30, HSM31", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xb1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "Errata": "HSD30, HSM31", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "CounterMask": "2", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xb1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "Errata": "HSD30, HSM31", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "CounterMask": "3", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xb1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "Errata": "HSD30, HSM31", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xb1", + "Invert": "1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "Errata": "HSD30, HSM31", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Number of instructions at retirement.", + "EventCode": "0xC0", + "Counter": "0,1,2,3", + "UMask": "0x0", + "Errata": "HSD11, HSD140", + "EventName": "INST_RETIRED.ANY_P", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "2", + "PublicDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution.", + "EventCode": "0xC0", + "Counter": "1", + "UMask": "0x1", + "Errata": "HSD140", + "EventName": "INST_RETIRED.PREC_DIST", + "SampleAfterValue": "2000003", + "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", + "CounterHTOff": "1" + }, + { + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", + "EventCode": "0xC0", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "INST_RETIRED.X87", + "SampleAfterValue": "2000003", + "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.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.", + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", + "SampleAfterValue": "100003", + "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "1", + "EventCode": "0xC2", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "UOPS_RETIRED.ALL", + "SampleAfterValue": "2000003", + "BriefDescription": "Actually retired uops.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Data_LA": "1" + }, + { "EventCode": "0xC2", "Invert": "1", "Counter": "0,1,2,3", @@ -765,6 +1136,16 @@ "CounterHTOff": "0,1,2,3" }, { + "PEBS": "1", + "EventCode": "0xC2", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "SampleAfterValue": "2000003", + "BriefDescription": "Retirement slots used.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "EventCode": "0xC3", "Counter": "0,1,2,3", "UMask": "0x1", @@ -774,6 +1155,17 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "EventCode": "0xC3", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EdgeDetect": "1", + "EventName": "MACHINE_CLEARS.COUNT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of machine clears (nukes) of any type.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear. Machine clears can have a significant performance impact if they are happening frequently.", "EventCode": "0xC3", "Counter": "0,1,2,3", @@ -793,8 +1185,17 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Branch instructions at retirement.", + "EventCode": "0xC4", + "Counter": "0,1,2,3", + "UMask": "0x0", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "SampleAfterValue": "400009", + "BriefDescription": "All (macro) branch instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PEBS": "1", - "PublicDescription": "Counts the number of conditional branch instructions retired.", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x1", @@ -814,18 +1215,27 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Branch instructions at retirement.", + "PEBS": "1", "EventCode": "0xC4", "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "UMask": "0x2", + "EventName": "BR_INST_RETIRED.NEAR_CALL_R3", + "SampleAfterValue": "100003", + "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "2", + "EventCode": "0xC4", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", "SampleAfterValue": "400009", "BriefDescription": "All (macro) branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3" }, { "PEBS": "1", - "PublicDescription": "Counts the number of near return instructions retired.", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x8", @@ -846,7 +1256,6 @@ }, { "PEBS": "1", - "PublicDescription": "Number of near taken branches retired.", "EventCode": "0xC4", "Counter": "0,1,2,3", "UMask": "0x20", @@ -866,14 +1275,14 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PEBS": "2", - "EventCode": "0xC4", + "PublicDescription": "Mispredicted branch instructions at retirement.", + "EventCode": "0xC5", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "UMask": "0x0", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", "SampleAfterValue": "400009", - "BriefDescription": "All (macro) branch instructions retired.", - "CounterHTOff": "0,1,2,3" + "BriefDescription": "All mispredicted macro branch instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" }, { "PEBS": "1", @@ -886,16 +1295,6 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "PublicDescription": "Mispredicted branch instructions at retirement.", - "EventCode": "0xC5", - "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "SampleAfterValue": "400009", - "BriefDescription": "All mispredicted macro branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { "PEBS": "2", "PublicDescription": "This event counts all mispredicted branch instructions retired. This is a precise event.", "EventCode": "0xC5", @@ -903,427 +1302,37 @@ "UMask": "0x4", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted macro branch instructions retired. ", + "BriefDescription": "Mispredicted macro branch instructions retired.", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Count cases of saving new LBR records by hardware.", - "EventCode": "0xCC", + "PEBS": "1", + "EventCode": "0xC5", "Counter": "0,1,2,3", "UMask": "0x20", - "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", - "SampleAfterValue": "2000003", - "BriefDescription": "Count cases of saving new LBR", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "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.", - "EventCode": "0x3C", - "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "SampleAfterValue": "2000003", - "BriefDescription": "Thread cycles when thread is not in halt state", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x89", - "Counter": "0,1,2,3", - "UMask": "0xa0", - "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", - "SampleAfterValue": "200003", - "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are exectuted in port 0.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x2", - "AnyThread": "1", - "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are exectuted in port 1.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x4", - "AnyThread": "1", - "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 2.", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", + "PublicDescription": "Count cases of saving new LBR records by hardware.", + "EventCode": "0xCC", "Counter": "0,1,2,3", - "UMask": "0x8", - "AnyThread": "1", - "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE", + "UMask": "0x20", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 3.", + "BriefDescription": "Count cases of saving new LBR", "CounterHTOff": "0,1,2,3,4,5,6,7" }, { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x10", - "AnyThread": "1", - "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are exectuted in port 4.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x20", - "AnyThread": "1", - "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are exectuted in port 5.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x40", - "AnyThread": "1", - "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are exectuted in port 6.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x80", - "AnyThread": "1", - "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per core when uops are dispatched to port 7.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PEBS": "1", - "PublicDescription": "Number of near branch instructions retired that were taken but mispredicted.", - "EventCode": "0xC5", - "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "This events counts the cycles where at least one uop was executed. It is counted per thread.", - "EventCode": "0xB1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "Errata": "HSD144, HSD30, HSM31", - "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 1 uop was executed per-thread", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3" - }, - { - "PublicDescription": "This events counts the cycles where at least two uop were executed. It is counted per thread.", - "EventCode": "0xB1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "Errata": "HSD144, HSD30, HSM31", - "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 2 uops were executed per-thread", - "CounterMask": "2", - "CounterHTOff": "0,1,2,3" - }, - { - "PublicDescription": "This events counts the cycles where at least three uop were executed. It is counted per thread.", - "EventCode": "0xB1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "Errata": "HSD144, HSD30, HSM31", - "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 3 uops were executed per-thread", - "CounterMask": "3", - "CounterHTOff": "0,1,2,3" - }, - { - "EventCode": "0xB1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "Errata": "HSD144, HSD30, HSM31", - "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 4 uops were executed per-thread.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3" - }, - { - "PublicDescription": "Number of front end re-steers due to BPU misprediction.", - "EventCode": "0xe6", + "PublicDescription": "Number of front end re-steers due to BPU misprediction.", + "EventCode": "0xe6", "Counter": "0,1,2,3", "UMask": "0x1f", "EventName": "BACLEARS.ANY", "SampleAfterValue": "100003", "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.", "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xC3", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EdgeDetect": "1", - "EventName": "MACHINE_CLEARS.COUNT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of machine clears (nukes) of any type.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA8", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.CYCLES_ACTIVE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA8", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.CYCLES_4_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x5E", - "Invert": "1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EdgeDetect": "1", - "EventName": "RS_EVENTS.EMPTY_END", - "SampleAfterValue": "200003", - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_0", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 0.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_DISPATCHED_PORT.PORT_1", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 1.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "UOPS_DISPATCHED_PORT.PORT_2", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 2.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "UOPS_DISPATCHED_PORT.PORT_3", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 3.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "UOPS_DISPATCHED_PORT.PORT_4", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 4.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "UOPS_DISPATCHED_PORT.PORT_5", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 5.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "UOPS_DISPATCHED_PORT.PORT_6", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 6.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xA1", - "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "UOPS_DISPATCHED_PORT.PORT_7", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 7.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x00", - "Counter": "Fixed counter 2", - "UMask": "0x2", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "CounterHTOff": "Fixed counter 2" - }, - { - "EventCode": "0x3C", - "Counter": "0,1,2,3", - "UMask": "0x0", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", - "EventCode": "0x3C", - "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "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).", - "EventCode": "0x0D", - "Counter": "0,1,2,3", - "UMask": "0x3", - "AnyThread": "1", - "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", - "SampleAfterValue": "2000003", - "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)", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "Counter": "0,1,2,3", - "UMask": "0x2", - "Errata": "HSD30, HSM31", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "Counter": "0,1,2,3", - "UMask": "0x2", - "Errata": "HSD30, HSM31", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", - "CounterMask": "2", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "Counter": "0,1,2,3", - "UMask": "0x2", - "Errata": "HSD30, HSM31", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", - "CounterMask": "3", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "Counter": "0,1,2,3", - "UMask": "0x2", - "Errata": "HSD30, HSM31", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0xb1", - "Invert": "1", - "Counter": "0,1,2,3", - "UMask": "0x2", - "Errata": "HSD30, HSM31", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)", - "EventCode": "0x3C", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", - "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", - "EventCode": "0x3C", - "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "EventCode": "0x3C", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "SampleAfterValue": "2000003", - "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" } ] \ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json b/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json index ce80a08..777b500 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json @@ -39,6 +39,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0xe", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "SampleAfterValue": "100003", + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.", "EventCode": "0x08", "Counter": "0,1,2,3", @@ -69,6 +79,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Number of cache load STLB hits. No page walk.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x60", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "SampleAfterValue": "2000003", + "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed.", "EventCode": "0x08", "Counter": "0,1,2,3", @@ -118,6 +138,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).", + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0xe", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "SampleAfterValue": "100003", + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB store misses.", "EventCode": "0x49", "Counter": "0,1,2,3", @@ -148,6 +178,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x60", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "SampleAfterValue": "100003", + "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "DTLB store misses with low part of linear-to-physical address translation missed.", "EventCode": "0x49", "Counter": "0,1,2,3", @@ -206,6 +246,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "Completed page walks in ITLB of any page size.", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0xe", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "SampleAfterValue": "100003", + "BriefDescription": "Misses in all ITLB levels that cause completed page walks", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by ITLB misses.", "EventCode": "0x85", "Counter": "0,1,2,3", @@ -236,6 +286,16 @@ "CounterHTOff": "0,1,2,3,4,5,6,7" }, { + "PublicDescription": "ITLB misses that hit STLB. No page walk.", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x60", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "100003", + "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { "PublicDescription": "Counts the number of ITLB flushes, includes 4k/2M/4M pages.", "EventCode": "0xae", "Counter": "0,1,2,3", @@ -256,41 +316,45 @@ "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.", + "PublicDescription": "Number of DTLB page walker loads that hit in the L2.", "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x21", - "EventName": "PAGE_WALKER_LOADS.ITLB_L1", + "UMask": "0x12", + "EventName": "PAGE_WALKER_LOADS.DTLB_L2", "SampleAfterValue": "2000003", - "BriefDescription": "Number of ITLB page walker hits in the L1+FB", + "BriefDescription": "Number of DTLB page walker hits in the L2", "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Number of DTLB page walker loads that hit in the L3.", "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1", + "UMask": "0x14", + "Errata": "HSD25", + "EventName": "PAGE_WALKER_LOADS.DTLB_L3", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.", + "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP", "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Number of DTLB page walker loads from memory.", "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x81", - "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1", + "UMask": "0x18", + "Errata": "HSD25", + "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.", + "BriefDescription": "Number of DTLB page walker hits in Memory", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Number of DTLB page walker loads that hit in the L2.", + "PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.", "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x12", - "EventName": "PAGE_WALKER_LOADS.DTLB_L2", + "UMask": "0x21", + "EventName": "PAGE_WALKER_LOADS.ITLB_L1", "SampleAfterValue": "2000003", - "BriefDescription": "Number of DTLB page walker hits in the L2", + "BriefDescription": "Number of ITLB page walker hits in the L1+FB", "CounterHTOff": "0,1,2,3" }, { @@ -304,43 +368,43 @@ "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Number of ITLB page walker loads that hit in the L3.", "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x42", - "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2", + "UMask": "0x24", + "Errata": "HSD25", + "EventName": "PAGE_WALKER_LOADS.ITLB_L3", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.", + "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP", "CounterHTOff": "0,1,2,3" }, { + "PublicDescription": "Number of ITLB page walker loads from memory.", "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x82", - "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2", + "UMask": "0x28", + "Errata": "HSD25", + "EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.", + "BriefDescription": "Number of ITLB page walker hits in Memory", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Number of DTLB page walker loads that hit in the L3.", "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x14", - "Errata": "HSD25", - "EventName": "PAGE_WALKER_LOADS.DTLB_L3", + "UMask": "0x41", + "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1", "SampleAfterValue": "2000003", - "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP", + "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Number of ITLB page walker loads that hit in the L3.", "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x24", - "Errata": "HSD25", - "EventName": "PAGE_WALKER_LOADS.ITLB_L3", + "UMask": "0x42", + "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2", "SampleAfterValue": "2000003", - "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP", + "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.", "CounterHTOff": "0,1,2,3" }, { @@ -355,41 +419,37 @@ { "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x84", - "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3", + "UMask": "0x48", + "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.", + "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Number of DTLB page walker loads from memory.", "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x18", - "Errata": "HSD25", - "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY", + "UMask": "0x81", + "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1", "SampleAfterValue": "2000003", - "BriefDescription": "Number of DTLB page walker hits in Memory", + "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.", "CounterHTOff": "0,1,2,3" }, { - "PublicDescription": "Number of ITLB page walker loads from memory.", "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x28", - "Errata": "HSD25", - "EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY", + "UMask": "0x82", + "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2", "SampleAfterValue": "2000003", - "BriefDescription": "Number of ITLB page walker hits in Memory", + "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.", "CounterHTOff": "0,1,2,3" }, { "EventCode": "0xBC", "Counter": "0,1,2,3", - "UMask": "0x48", - "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY", + "UMask": "0x84", + "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.", + "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.", "CounterHTOff": "0,1,2,3" }, { @@ -420,65 +480,5 @@ "SampleAfterValue": "100003", "BriefDescription": "STLB flush attempts", "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.", - "EventCode": "0x08", - "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "SampleAfterValue": "100003", - "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Number of cache load STLB hits. No page walk.", - "EventCode": "0x08", - "Counter": "0,1,2,3", - "UMask": "0x60", - "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "SampleAfterValue": "2000003", - "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).", - "EventCode": "0x49", - "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "SampleAfterValue": "100003", - "BriefDescription": "Store misses in all DTLB levels that cause completed page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", - "EventCode": "0x49", - "Counter": "0,1,2,3", - "UMask": "0x60", - "EventName": "DTLB_STORE_MISSES.STLB_HIT", - "SampleAfterValue": "100003", - "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Completed page walks in ITLB of any page size.", - "EventCode": "0x85", - "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "ITLB_MISSES.WALK_COMPLETED", - "SampleAfterValue": "100003", - "BriefDescription": "Misses in all ITLB levels that cause completed page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "ITLB misses that hit STLB. No page walk.", - "EventCode": "0x85", - "Counter": "0,1,2,3", - "UMask": "0x60", - "EventName": "ITLB_MISSES.STLB_HIT", - "SampleAfterValue": "100003", - "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" } ] \ No newline at end of file
