diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-27 10:05:51 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-27 10:05:51 +0000 |
commit | 5d1646d90e1f2cceb9f0828f4b28318cd0ec7744 (patch) | |
tree | a94efe259b9009378be6d90eb30d2b019d95c194 /tools/perf/pmu-events/arch/x86/jaketown | |
parent | Initial commit. (diff) | |
download | linux-5d1646d90e1f2cceb9f0828f4b28318cd0ec7744.tar.xz linux-5d1646d90e1f2cceb9f0828f4b28318cd0ec7744.zip |
Adding upstream version 5.10.209.upstream/5.10.209upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/jaketown')
12 files changed, 4423 insertions, 0 deletions
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/cache.json b/tools/perf/pmu-events/arch/x86/jaketown/cache.json new file mode 100644 index 000000000..52dc6ef40 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/cache.json @@ -0,0 +1,1290 @@ +[ + { + "PEBS": "1", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x11", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops that miss the STLB.", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x12", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "SampleAfterValue": "100003", + "BriefDescription": "Retired store uops that miss the STLB.", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x21", + "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "SampleAfterValue": "100007", + "BriefDescription": "Retired load uops with locked access.", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x41", + "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops that split across a cacheline boundary.", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x42", + "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", + "SampleAfterValue": "100003", + "BriefDescription": "Retired store uops that split across a cacheline boundary.", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "PublicDescription": "This event counts the number of load uops retired", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x81", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "SampleAfterValue": "2000003", + "BriefDescription": "All retired load uops.", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "PublicDescription": "This event counts the number of store uops retired.", + "EventCode": "0xD0", + "Counter": "0,1,2,3", + "UMask": "0x82", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "SampleAfterValue": "2000003", + "BriefDescription": "All retired store uops.", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "SampleAfterValue": "2000003", + "BriefDescription": "Retired load uops with L1 cache hits as data sources.", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops with L2 cache hits as data sources.", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required.", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT", + "SampleAfterValue": "50021", + "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_MISS", + "SampleAfterValue": "100007", + "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xD1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD2", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a non-modified state.", + "EventCode": "0xD2", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package). Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line. In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2.", + "EventCode": "0xD2", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM", + "SampleAfterValue": "20011", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD2", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE", + "SampleAfterValue": "100003", + "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD3", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM", + "SampleAfterValue": "100007", + "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xD3", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM", + "SampleAfterValue": "100007", + "BriefDescription": "Data from remote DRAM either Snoop not needed or Snoop Miss (RspI)", + "CounterHTOff": "0,1,2,3" + }, + { + "PublicDescription": "This event counts L1D data line replacements. Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.", + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "L1D.REPLACEMENT", + "SampleAfterValue": "2000003", + "BriefDescription": "L1D data line replacements.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "L1D.ALLOCATED_IN_M", + "SampleAfterValue": "2000003", + "BriefDescription": "Allocated L1D data cache lines in M state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "L1D.EVICTION", + "SampleAfterValue": "2000003", + "BriefDescription": "L1D data cache lines in M state evicted due to replacement.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x51", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "L1D.ALL_M_REPLACEMENT", + "SampleAfterValue": "2000003", + "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x48", + "Counter": "2", + "UMask": "0x1", + "EventName": "L1D_PEND_MISS.PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "L1D miss oustandings duration in cycles.", + "CounterHTOff": "2" + }, + { + "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": "0x63", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when L1D is locked.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x1", + "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": "0x4", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "SampleAfterValue": "2000003", + "BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x8", + "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": "0x8", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "SampleAfterValue": "2000003", + "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" + }, + { + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "SampleAfterValue": "100003", + "BriefDescription": "Demand Data Read requests sent to uncore.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "SampleAfterValue": "100003", + "BriefDescription": "Cacheable and noncachaeble code read requests.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "SampleAfterValue": "100003", + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB0", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "SampleAfterValue": "100003", + "BriefDescription": "Demand and prefetch data reads.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB2", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "SampleAfterValue": "2000003", + "BriefDescription": "Cases when offcore requests buffer cannot take more entries for core.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x1", + "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" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "L2_RQSTS.RFO_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that hit L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "L2_RQSTS.RFO_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that miss L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x10", + "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" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache misses when fetching instructions.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "L2_RQSTS.PF_HIT", + "SampleAfterValue": "200003", + "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x80", + "EventName": "L2_RQSTS.PF_MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x27", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "L2_STORE_LOCK_RQSTS.MISS", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that miss cache lines.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x27", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "L2_STORE_LOCK_RQSTS.HIT_E", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that hit cache lines in E state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x27", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "L2_STORE_LOCK_RQSTS.HIT_M", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that hit cache lines in M state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x27", + "Counter": "0,1,2,3", + "UMask": "0xf", + "EventName": "L2_STORE_LOCK_RQSTS.ALL", + "SampleAfterValue": "200003", + "BriefDescription": "RFOs that access cache lines in any state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "L2_L1D_WB_RQSTS.MISS", + "SampleAfterValue": "200003", + "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "L2_L1D_WB_RQSTS.HIT_S", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "L2_L1D_WB_RQSTS.HIT_E", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "L2_L1D_WB_RQSTS.HIT_M", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x28", + "Counter": "0,1,2,3", + "UMask": "0xf", + "EventName": "L2_L1D_WB_RQSTS.ALL", + "SampleAfterValue": "200003", + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF0", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "L2_TRANS.DEMAND_DATA_RD", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests that access L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF0", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "L2_TRANS.RFO", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests that access L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF0", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "L2_TRANS.CODE_RD", + "SampleAfterValue": "200003", + "BriefDescription": "L2 cache accesses when fetching instructions.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF0", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "L2_TRANS.ALL_PF", + "SampleAfterValue": "200003", + "BriefDescription": "L2 or LLC HW prefetches that access L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF0", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "L2_TRANS.L1D_WB", + "SampleAfterValue": "200003", + "BriefDescription": "L1D writebacks that access L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF0", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "L2_TRANS.L2_FILL", + "SampleAfterValue": "200003", + "BriefDescription": "L2 fill requests that access L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF0", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "L2_TRANS.L2_WB", + "SampleAfterValue": "200003", + "BriefDescription": "L2 writebacks that access L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF0", + "Counter": "0,1,2,3", + "UMask": "0x80", + "EventName": "L2_TRANS.ALL_REQUESTS", + "SampleAfterValue": "200003", + "BriefDescription": "Transactions accessing L2 pipe.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "L2_LINES_IN.I", + "SampleAfterValue": "100003", + "BriefDescription": "L2 cache lines in I state filling L2.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "L2_LINES_IN.S", + "SampleAfterValue": "100003", + "BriefDescription": "L2 cache lines in S state filling L2.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF1", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "L2_LINES_IN.E", + "SampleAfterValue": "100003", + "BriefDescription": "L2 cache lines in E state filling L2.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts the number of L2 cache lines brought into the L2 cache. Lines are filled into the L2 cache when there was an L2 miss.", + "EventCode": "0xF1", + "Counter": "0,1,2,3", + "UMask": "0x7", + "EventName": "L2_LINES_IN.ALL", + "SampleAfterValue": "100003", + "BriefDescription": "L2 cache lines filling L2.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "L2_LINES_OUT.DEMAND_CLEAN", + "SampleAfterValue": "100003", + "BriefDescription": "Clean L2 cache lines evicted by demand.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "L2_LINES_OUT.DEMAND_DIRTY", + "SampleAfterValue": "100003", + "BriefDescription": "Dirty L2 cache lines evicted by demand.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "L2_LINES_OUT.PF_CLEAN", + "SampleAfterValue": "100003", + "BriefDescription": "Clean L2 cache lines evicted by L2 prefetch.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "L2_LINES_OUT.PF_DIRTY", + "SampleAfterValue": "100003", + "BriefDescription": "Dirty L2 cache lines evicted by L2 prefetch.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF2", + "Counter": "0,1,2,3", + "UMask": "0xa", + "EventName": "L2_LINES_OUT.DIRTY_ALL", + "SampleAfterValue": "100003", + "BriefDescription": "Dirty L2 cache lines filling the L2.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x2E", + "Counter": "0,1,2,3", + "UMask": "0x41", + "EventName": "LONGEST_LAT_CACHE.MISS", + "SampleAfterValue": "100003", + "BriefDescription": "Core-originated cacheable demand requests missed LLC.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x2E", + "Counter": "0,1,2,3", + "UMask": "0x4f", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "SampleAfterValue": "100003", + "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xF4", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "SQ_MISC.SPLIT_LOCK", + "SampleAfterValue": "100003", + "BriefDescription": "Split locks in SQ.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x3", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "SampleAfterValue": "200003", + "BriefDescription": "Demand Data Read requests.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xc", + "EventName": "L2_RQSTS.ALL_RFO", + "SampleAfterValue": "200003", + "BriefDescription": "RFO requests to L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0x30", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "SampleAfterValue": "200003", + "BriefDescription": "L2 code requests.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x24", + "Counter": "0,1,2,3", + "UMask": "0xc0", + "EventName": "L2_RQSTS.ALL_PF", + "SampleAfterValue": "200003", + "BriefDescription": "Requests from L2 hardware prefetchers.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xBF", + "Counter": "0,1,2,3", + "UMask": "0x5", + "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES", + "SampleAfterValue": "100003", + "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "SampleAfterValue": "2000003", + "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" + }, + { + "EventCode": "0x60", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6", + "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" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x4003c0091", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10003c0091", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1003c0091", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2003c0091", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and sibling core snoop returned a clean response", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3f803c0090", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all prefetch data reads that hit the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x4003c0090", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10003c0090", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1003c0090", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2003c0090", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch data reads that hit in the LLC and sibling core snoop returned a clean response", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3f803c03f7", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x4003c03f7", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10003c03f7", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1003c03f7", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2003c03f7", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and sibling core snoop returned a clean response", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10008", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all writebacks from the core to the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3f803c0004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand code reads that hit in the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3f803c0001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data reads that hit in the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x4003c0001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10003c0001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1003c0001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2003c0001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that hit in the LLC and sibling core snoop returned a clean response", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x803c8000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.OTHER.LRU_HINTS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts L2 hints sent to LLC to keep a line from being evicted out of the core caches", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x23ffc08000", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.OTHER.PORTIO_MMIO_UC", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts miscellaneous accesses that include port i/o, MMIO and uncacheable memory accesses", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3f803c0040", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all prefetch (that bring data to L2) code reads that hit in the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3f803c0010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x4003c0010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10003c0010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1003c0010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2003c0010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3f803c0200", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3f803c0080", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x4003c0080", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10003c0080", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x1003c0080", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x2003c0080", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10400", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.SPLIT_LOCK_UC_LOCK.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x10800", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts non-temporal stores", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00010008", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00010001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand data reads", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00010002", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand rfo's", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00010004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand code reads", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00010008", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x000105B3", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand & prefetch data reads", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x00010122", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand & prefetch prefetch RFOs", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x000107F7", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_READS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all data/code/rfo references (demand & prefetch)", + "CounterHTOff": "0,1,2,3" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/jaketown/floating-point.json b/tools/perf/pmu-events/arch/x86/jaketown/floating-point.json new file mode 100644 index 000000000..982eda487 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/floating-point.json @@ -0,0 +1,138 @@ +[ + { + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "OTHER_ASSISTS.AVX_STORE", + "SampleAfterValue": "100003", + "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "OTHER_ASSISTS.AVX_TO_SSE", + "SampleAfterValue": "100003", + "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "OTHER_ASSISTS.SSE_TO_AVX", + "SampleAfterValue": "100003", + "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "FP_ASSIST.X87_OUTPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of X87 assists due to output value.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "FP_ASSIST.X87_INPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of X87 assists due to input value.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "FP_ASSIST.SIMD_OUTPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of SIMD FP assists due to Output values.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "FP_ASSIST.SIMD_INPUT", + "SampleAfterValue": "100003", + "BriefDescription": "Number of SIMD FP assists due to input values.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x10", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "FP_COMP_OPS_EXE.X87", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULsand IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x10", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE* or AVX-128 FP Computational packed double-precision uops issued this cycle.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x10", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE* or AVX-128 FP Computational scalar single-precision uops issued this cycle.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x10", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "FP_COMP_OPS_EXE.SSE_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE* or AVX-128 FP Computational packed single-precision uops issued this cycle.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x10", + "Counter": "0,1,2,3", + "UMask": "0x80", + "EventName": "FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of SSE* or AVX-128 FP Computational scalar double-precision uops issued this cycle.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x11", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "SIMD_FP_256.PACKED_SINGLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of GSSE-256 Computational FP single precision uops issued this cycle.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x11", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "SIMD_FP_256.PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of AVX-256 Computational FP double precision uops issued this cycle.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCA", + "Counter": "0,1,2,3", + "UMask": "0x1e", + "EventName": "FP_ASSIST.ANY", + "SampleAfterValue": "100003", + "BriefDescription": "Cycles with any input/output SSE or FP assist.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/jaketown/frontend.json b/tools/perf/pmu-events/arch/x86/jaketown/frontend.json new file mode 100644 index 000000000..1b7b1dd36 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/frontend.json @@ -0,0 +1,305 @@ +[ + { + "EventCode": "0x80", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "ICACHE.HIT", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.", + "EventCode": "0x80", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "ICACHE.MISSES", + "SampleAfterValue": "200003", + "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "IDQ.EMPTY", + "SampleAfterValue": "2000003", + "BriefDescription": "Instruction Decode Queue (IDQ) empty cycles.", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "IDQ.MITE_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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" + }, + { + "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" + }, + { + "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" + }, + { + "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. See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more information.", + "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" + }, + { + "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled. In the ideal case 4 uops can be delivered each cycle. The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them. This event is used in determining the front-end bound category of the top-down pipeline slots characterization.", + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "CounterMask": "3", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xAB", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "DSB2MITE_SWITCHES.COUNT", + "SampleAfterValue": "2000003", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline. It excludes cycles when the back-end cannot accept new micro-ops. The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.", + "EventCode": "0xAB", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xAC", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "DSB_FILL.OTHER_CANCEL", + "SampleAfterValue": "2000003", + "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xAC", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "DSB_FILL.EXCEED_DSB_LINES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "IDQ.MITE_CYCLES", + "SampleAfterValue": "2000003", + "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" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "IDQ.DSB_CYCLES", + "SampleAfterValue": "2000003", + "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" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "IDQ.MS_DSB_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) 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": "0x10", + "EdgeDetect": "1", + "EventName": "IDQ.MS_DSB_OCCUR", + "SampleAfterValue": "2000003", + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "CounterMask": "2", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x9C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x9C", + "Invert": "1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_GE_1_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when 1 or more uops were delivered to the by the front end.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x18", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x18", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x24", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles MITE is delivering 4 Uops.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x24", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles MITE is delivering any Uop.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xAC", + "Counter": "0,1,2,3", + "UMask": "0xa", + "EventName": "DSB_FILL.ALL_CANCEL", + "SampleAfterValue": "2000003", + "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x9C", + "Invert": "1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x79", + "Counter": "0,1,2,3", + "UMask": "0x3c", + "EventName": "IDQ.MITE_ALL_UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.", + "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" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json new file mode 100644 index 000000000..dbb33e00b --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -0,0 +1,232 @@ +[ + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound." + }, + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example." + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound." + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. " + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Retire", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )", + "MetricGroup": "PGO;IcMiss", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )", + "MetricGroup": "DSB;Fetch_BW", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core)", + "MetricExpr": "4 * cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core)", + "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricGroup": "SMT", + "MetricName": "CoreIPC_SMT" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", + "MetricGroup": "Pipeline", + "MetricName": "ILP" + }, + { + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time", + "MetricGroup": "Memory_BW", + "MetricName": "DRAM_BW_Use" + }, + { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cbox_0@event\\=0x0@", + "MetricGroup": "", + "MetricName": "Socket_CLKS" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/memory.json b/tools/perf/pmu-events/arch/x86/jaketown/memory.json new file mode 100644 index 000000000..27e636428 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/memory.json @@ -0,0 +1,422 @@ +[ + { + "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from memory disambiguation, external snoops, or cross SMT-HW-thread snoop (stores) hitting load buffers. Machine clears can have a significant performance impact if they are happening frequently.", + "EventCode": "0xC3", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "SampleAfterValue": "100003", + "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "2", + "EventCode": "0xCD", + "MSRValue": "0x4", + "Counter": "3", + "UMask": "0x1", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "SampleAfterValue": "100003", + "BriefDescription": "Loads with latency value being above 4 .", + "TakenAlone": "1", + "CounterHTOff": "3" + }, + { + "PEBS": "2", + "EventCode": "0xCD", + "MSRValue": "0x8", + "Counter": "3", + "UMask": "0x1", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "SampleAfterValue": "50021", + "BriefDescription": "Loads with latency value being above 8.", + "TakenAlone": "1", + "CounterHTOff": "3" + }, + { + "PEBS": "2", + "EventCode": "0xCD", + "MSRValue": "0x10", + "Counter": "3", + "UMask": "0x1", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "SampleAfterValue": "20011", + "BriefDescription": "Loads with latency value being above 16.", + "TakenAlone": "1", + "CounterHTOff": "3" + }, + { + "PEBS": "2", + "EventCode": "0xCD", + "MSRValue": "0x20", + "Counter": "3", + "UMask": "0x1", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "SampleAfterValue": "100007", + "BriefDescription": "Loads with latency value being above 32.", + "TakenAlone": "1", + "CounterHTOff": "3" + }, + { + "PEBS": "2", + "EventCode": "0xCD", + "MSRValue": "0x40", + "Counter": "3", + "UMask": "0x1", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "SampleAfterValue": "2003", + "BriefDescription": "Loads with latency value being above 64.", + "TakenAlone": "1", + "CounterHTOff": "3" + }, + { + "PEBS": "2", + "EventCode": "0xCD", + "MSRValue": "0x80", + "Counter": "3", + "UMask": "0x1", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "SampleAfterValue": "1009", + "BriefDescription": "Loads with latency value being above 128.", + "TakenAlone": "1", + "CounterHTOff": "3" + }, + { + "PEBS": "2", + "EventCode": "0xCD", + "MSRValue": "0x100", + "Counter": "3", + "UMask": "0x1", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "SampleAfterValue": "503", + "BriefDescription": "Loads with latency value being above 256.", + "TakenAlone": "1", + "CounterHTOff": "3" + }, + { + "PEBS": "2", + "EventCode": "0xCD", + "MSRValue": "0x200", + "Counter": "3", + "UMask": "0x1", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "SampleAfterValue": "101", + "BriefDescription": "Loads with latency value being above 512.", + "TakenAlone": "1", + "CounterHTOff": "3" + }, + { + "PEBS": "2", + "EventCode": "0xCD", + "Counter": "3", + "UMask": "0x2", + "EventName": "MEM_TRANS_RETIRED.PRECISE_STORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Sample stores and collect precise store operation via PEBS record. PMC3 only. (Precise Event - PEBS).", + "PRECISE_STORE": "1", + "TakenAlone": "1", + "CounterHTOff": "3" + }, + { + "EventCode": "0x05", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "MISALIGN_MEM_REF.LOADS", + "SampleAfterValue": "2000003", + "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x05", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "MISALIGN_MEM_REF.STORES", + "SampleAfterValue": "2000003", + "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3fffc20004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand code reads that miss the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x600400004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand code reads that miss the LLC and the data returned from local dram", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x67f800004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand code reads that miss the LLC and the data returned from remote dram", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x87f820004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand code reads that miss the LLC and the data forwarded from remote cache", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x107fc00004", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all demand code reads that miss the LLC the data is found in M state in remote cache and forwarded from there", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x67fc00001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that miss the LLC and the data returned from remote & local dram", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3fffc20001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that miss in the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x600400001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that miss the LLC and the data returned from local dram", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x67f800001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that miss the LLC and the data returned from remote dram", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x87f820001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that miss the LLC and the data forwarded from remote cache", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x107fc00001", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts demand data reads that miss the LLC the data is found in M state in remote cache and forwarded from there", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3fffc20040", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all prefetch (that bring data to L2) code reads that miss the LLC and the data returned from remote & local dram", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x67fc00010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data returned from remote & local dram", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3fffc20010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x600400010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data returned from local dram", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x67f800010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data returned from remote dram", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x87f820010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data forwarded from remote cache", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x107fc00010", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC the data is found in M state in remote cache and forwarded from there", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3fffc20200", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the LLC", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3fffc20080", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x600400077", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_DEMAND_MLC_PREF_READS.LLC_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "Counts all local dram accesses for all demand and L2 prefetches. LLC prefetches are excluded.", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x3FFFC20077", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_DEMAND_MLC_PREF_READS.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts all LLC misses for all demand and L2 prefetches. LLC prefetches are excluded.", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xB7, 0xBB", + "MSRValue": "0x187FC20077", + "Counter": "0,1,2,3", + "UMask": "0x1", + "Offcore": "1", + "EventName": "OFFCORE_RESPONSE.ALL_DEMAND_MLC_PREF_READS.LLC_MISS.REMOTE_HITM_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts all remote cache-to-cache transfers (includes HITM and HIT-Forward) for all demand and L2 prefetches. LLC prefetches are excluded.", + "CounterHTOff": "0,1,2,3" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/jaketown/other.json b/tools/perf/pmu-events/arch/x86/jaketown/other.json new file mode 100644 index 000000000..64b195b82 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/other.json @@ -0,0 +1,58 @@ +[ + { + "EventCode": "0x17", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "INSTS_WRITTEN_TO_IQ.INSTS", + "SampleAfterValue": "2000003", + "BriefDescription": "Valid instructions written to IQ per cycle.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "CPL_CYCLES.RING0", + "SampleAfterValue": "2000003", + "BriefDescription": "Unhalted core cycles when the thread is in ring 0.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EdgeDetect": "1", + "EventName": "CPL_CYCLES.RING0_TRANS", + "SampleAfterValue": "100007", + "BriefDescription": "Number of intervals between processor halts while thread is in ring 0.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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": "0x4E", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "HW_PRE_REQ.DL1_MISS", + "SampleAfterValue": "2000003", + "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x63", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json new file mode 100644 index 000000000..783a5b4a6 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json @@ -0,0 +1,1216 @@ +[ + { + "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.", + "Counter": "Fixed counter 1", + "UMask": "0x1", + "EventName": "INST_RETIRED.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Instructions retired from execution.", + "CounterHTOff": "Fixed counter 1" + }, + { + "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "Counter": "Fixed counter 2", + "UMask": "0x2", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "SampleAfterValue": "2000003", + "BriefDescription": "Core cycles when the thread is not in halt state.", + "CounterHTOff": "Fixed counter 2" + }, + { + "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. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "Counter": "Fixed counter 3", + "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" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0x41", + "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Not taken macro-conditional branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0x81", + "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired macro-conditional branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0x82", + "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0x84", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0x90", + "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired direct near calls.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0xa0", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired indirect calls.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0xc1", + "EventName": "BR_INST_EXEC.ALL_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired macro-conditional branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0xc2", + "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0xc4", + "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0xc8", + "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired indirect return branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x88", + "Counter": "0,1,2,3", + "UMask": "0xd0", + "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired direct near calls.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", + "Counter": "0,1,2,3", + "UMask": "0x41", + "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", + "Counter": "0,1,2,3", + "UMask": "0x81", + "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", + "Counter": "0,1,2,3", + "UMask": "0x84", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", + "Counter": "0,1,2,3", + "UMask": "0x88", + "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", + "Counter": "0,1,2,3", + "UMask": "0x90", + "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Taken speculative and retired mispredicted direct near calls.", + "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": "0x89", + "Counter": "0,1,2,3", + "UMask": "0xc1", + "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", + "Counter": "0,1,2,3", + "UMask": "0xc4", + "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "BriefDescription": "Mispredicted indirect branches excluding calls and returns.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", + "Counter": "0,1,2,3", + "UMask": "0xd0", + "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired mispredicted direct near calls.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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": "0xA8", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "LSD.UOPS", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of Uops delivered by the LSD.", + "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": "0x87", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "ILD_STALL.LCP", + "SampleAfterValue": "2000003", + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x87", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "ILD_STALL.IQ_FULL", + "SampleAfterValue": "2000003", + "BriefDescription": "Stall cycles because IQ is full.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0D", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "INT_MISC.RAT_STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x59", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP", + "SampleAfterValue": "2000003", + "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.", + "EventCode": "0x59", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "PARTIAL_RAT_STALLS.SLOW_LEA_WINDOW", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with at least one slow LEA uop being allocated.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x59", + "Counter": "0,1,2,3", + "UMask": "0x80", + "EventName": "PARTIAL_RAT_STALLS.MUL_SINGLE_UOP", + "SampleAfterValue": "2000003", + "BriefDescription": "Multiply packed/scalar single precision uops allocated.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "Counter": "0,1,2,3", + "UMask": "0x1", + "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": "0x2", + "EventName": "RESOURCE_STALLS.LB", + "SampleAfterValue": "2000003", + "BriefDescription": "Counts the cycles of stall due to lack of load buffers.", + "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" + }, + { + "EventCode": "0xA2", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "RESOURCE_STALLS.SB", + "SampleAfterValue": "2000003", + "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" + }, + { + "EventCode": "0x5B", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "RESOURCE_STALLS2.BOB_FULL", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Allocator is stalled if BOB is full and new branch needs it.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.", + "EventCode": "0x0E", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "UOPS_ISSUED.ANY", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).", + "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" + }, + { + "EventCode": "0x5E", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xCC", + "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": "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", + "UMask": "0x4", + "EventName": "MACHINE_CLEARS.SMC", + "SampleAfterValue": "100003", + "BriefDescription": "Self-modifying code (SMC) detected.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.", + "EventCode": "0xC3", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "MACHINE_CLEARS.MASKMOV", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC0", + "Counter": "0,1,2,3", + "UMask": "0x0", + "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": "1", + "PublicDescription": "This event counts the number of micro-ops retired.", + "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" + }, + { + "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 micro-ops or 4 instructions could retire each cycle. This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization.", + "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": "0xC2", + "Invert": "1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles without actually retired uops.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC2", + "Invert": "1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with less than 10 actually retired uops.", + "CounterMask": "10", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xC4", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "SampleAfterValue": "400009", + "BriefDescription": "Conditional branch instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "1", + "EventCode": "0xC4", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "SampleAfterValue": "100007", + "BriefDescription": "Direct and indirect near call instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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", + "EventCode": "0xC4", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "SampleAfterValue": "100007", + "BriefDescription": "Return instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Not taken branch instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "1", + "EventCode": "0xC4", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Taken branch instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC4", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "SampleAfterValue": "100007", + "BriefDescription": "Far branch instructions retired.", + "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. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" + }, + { + "PEBS": "1", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "1", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "BR_MISP_RETIRED.NEAR_CALL", + "SampleAfterValue": "100007", + "BriefDescription": "Direct and indirect mispredicted near call instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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": "1", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "BR_MISP_RETIRED.NOT_TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted not taken branch instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "1", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "BR_MISP_RETIRED.TAKEN", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted taken branch instructions retired.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "2", + "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)", + "EventCode": "0xC5", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "SampleAfterValue": "400009", + "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xC1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED", + "SampleAfterValue": "100003", + "BriefDescription": "Retired instructions experiencing ITLB misses.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x14", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "ARITH.FPU_DIV_ACTIVE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when divider is busy executing divide operations.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts the number of the divide operations executed.", + "EventCode": "0x14", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EdgeDetect": "1", + "EventName": "ARITH.FPU_DIV", + "SampleAfterValue": "100003", + "BriefDescription": "Divide operations executed.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "UOPS_DISPATCHED.THREAD", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops dispatched per thread.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "UOPS_DISPATCHED.CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Uops dispatched from any thread.", + "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 dispatched to 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 dispatched to port 1.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are dispatched to port 4.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x80", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when uops are dispatched to port 5.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH", + "SampleAfterValue": "2000003", + "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.", + "CounterMask": "4", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xA3", + "Counter": "2", + "UMask": "0x2", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.", + "CounterMask": "2", + "CounterHTOff": "2" + }, + { + "EventCode": "0xA3", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA3", + "Counter": "2", + "UMask": "0x6", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.", + "CounterMask": "6", + "CounterHTOff": "2" + }, + { + "EventCode": "0xA3", + "Counter": "0,1,2,3", + "UMask": "0x5", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING", + "SampleAfterValue": "2000003", + "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.", + "CounterMask": "5", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0x4C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "LOAD_HIT_PRE.SW_PF", + "SampleAfterValue": "100003", + "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x4C", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "LOAD_HIT_PRE.HW_PF", + "SampleAfterValue": "100003", + "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x03", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "LD_BLOCKS.DATA_UNKNOWN", + "SampleAfterValue": "100003", + "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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 preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", + "EventCode": "0x03", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "SampleAfterValue": "100003", + "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x03", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "LD_BLOCKS.NO_SR", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x03", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "LD_BLOCKS.ALL_BLOCK", + "SampleAfterValue": "100003", + "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K. This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline. The enhanced address check typically has a performance penalty of 5 cycles.", + "EventCode": "0x07", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "SampleAfterValue": "100003", + "BriefDescription": "False dependencies in MOB due to partial compare.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x07", + "Counter": "0,1,2,3", + "UMask": "0x8", + "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xB6", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "AGU_BYPASS_CANCEL.COUNT", + "SampleAfterValue": "100003", + "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x3C", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "CPU_CLK_THREAD_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" + }, + { + "EventCode": "0x3C", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "2000003", + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.", + "CounterHTOff": "0,1,2,3" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per core when uops are dispatched to port 0.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x2", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per core when uops are dispatched to port 1.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x40", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per core when uops are dispatched to port 4.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x80", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per core when uops are dispatched to port 5.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0xc", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x30", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0xc", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA1", + "Counter": "0,1,2,3", + "UMask": "0x30", + "AnyThread": "1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PEBS": "2", + "EventCode": "0xC0", + "Counter": "1", + "UMask": "0x1", + "EventName": "INST_RETIRED.PREC_DIST", + "SampleAfterValue": "2000003", + "BriefDescription": "Instructions retired. (Precise Event - PEBS).", + "TakenAlone": "1", + "CounterHTOff": "1" + }, + { + "EventCode": "0x5B", + "Counter": "0,1,2,3", + "UMask": "0xf", + "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls2 control structures full for physical registers.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5B", + "Counter": "0,1,2,3", + "UMask": "0xc", + "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles with either free list is empty.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "Counter": "0,1,2,3", + "UMask": "0xe", + "EventName": "RESOURCE_STALLS.MEM_RS", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "Counter": "0,1,2,3", + "UMask": "0xf0", + "EventName": "RESOURCE_STALLS.OOO_RSRC", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x5B", + "Counter": "0,1,2,3", + "UMask": "0x4f", + "EventName": "RESOURCE_STALLS2.OOO_RSRC", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls out of order resources full.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xA2", + "Counter": "0,1,2,3", + "UMask": "0xa", + "EventName": "RESOURCE_STALLS.LB_SB", + "SampleAfterValue": "2000003", + "BriefDescription": "Resource stalls due to load or store buffers all being in use.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0D", + "Counter": "0,1,2,3", + "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...).", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel? 64 and IA-32 Architectures Optimization Reference Manual.", + "EventCode": "0x59", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x0D", + "Counter": "0,1,2,3", + "UMask": "0x3", + "EdgeDetect": "1", + "EventName": "INT_MISC.RECOVERY_STALLS_COUNT", + "SampleAfterValue": "2000003", + "BriefDescription": "Number of occurences 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...).", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "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": "0x88", + "Counter": "0,1,2,3", + "UMask": "0xff", + "EventName": "BR_INST_EXEC.ALL_BRANCHES", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x89", + "Counter": "0,1,2,3", + "UMask": "0xff", + "EventName": "BR_MISP_EXEC.ALL_BRANCHES", + "SampleAfterValue": "200003", + "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xC2", + "Invert": "1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "UOPS_RETIRED.CORE_STALL_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles without actually retired uops.", + "CounterMask": "1", + "CounterHTOff": "0,1,2,3" + }, + { + "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": "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": "0x5E", + "Invert": "1", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EdgeDetect": "1", + "EventName": "RS_EVENTS.EMPTY_END", + "SampleAfterValue": "2000003", + "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" + }, + { + "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" + }, + { + "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" + }, + { + "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", + "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", + "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", + "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", + "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", + "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" + }, + { + "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/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json new file mode 100644 index 000000000..3fa61d962 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json @@ -0,0 +1,210 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ", + "Filter": "filter_opc=0x195", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_READ", + "Filter": "filter_opc=0x1e4", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x1e5", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_WRITE", + "Filter": "filter_opc=0x1e6", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL", + "Filter": "filter_opc=0x182", + "MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.", + "MetricName": "tor_occupancy.miss_all %", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json new file mode 100644 index 000000000..1b53c0e60 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json @@ -0,0 +1,48 @@ +[ + { + "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where receiving QPI link is in half-width mode", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "MetricName": "rxl0p_power_cycles %", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where transmitting QPI link is in half-width mode", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "MetricName": "txl0p_power_cycles %", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted ", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted ", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json new file mode 100644 index 000000000..8551cebeb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json @@ -0,0 +1,82 @@ +[ + { + "BriefDescription": "Memory page activates", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory page conflicts", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Occupancy counter for memory read queue", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_M_RPQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json new file mode 100644 index 000000000..8755693d8 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json @@ -0,0 +1,273 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band0_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band1_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band2_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band3_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band0_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transistioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band1_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band2_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band3_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_current_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency", + "Counter": "0,1,2,3", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", + "Filter": "filter_band0=12", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_1200mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", + "Filter": "filter_band1=20", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_2000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", + "Filter": "filter_band2=30", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_3000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", + "Filter": "filter_band3=40", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_4000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band0=12", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_1200mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band1=20", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_2000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band2=30", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_3000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band3=40", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_4000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/virtual-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/virtual-memory.json new file mode 100644 index 000000000..a654ab771 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/virtual-memory.json @@ -0,0 +1,149 @@ +[ + { + "EventCode": "0xAE", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "ITLB.ITLB_FLUSH", + "SampleAfterValue": "100007", + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x4F", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "EPT.WALK_CYCLES", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycle count for an Extended Page table walk. The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "SampleAfterValue": "100003", + "BriefDescription": "Misses at all ITLB levels that cause page walks.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x2", + "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 count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.", + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "ITLB_MISSES.WALK_DURATION", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when PMH is busy with page walks.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x85", + "Counter": "0,1,2,3", + "UMask": "0x10", + "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" + }, + { + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "SampleAfterValue": "100003", + "BriefDescription": "Load misses in all DTLB levels that cause page walks.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x2", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "SampleAfterValue": "100003", + "BriefDescription": "Load misses at 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 load misses.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "DTLB_LOAD_MISSES.WALK_DURATION", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when PMH is busy with page walks.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.", + "EventCode": "0x08", + "Counter": "0,1,2,3", + "UMask": "0x10", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "SampleAfterValue": "100003", + "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" + }, + { + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "SampleAfterValue": "100003", + "BriefDescription": "Store misses in all DTLB levels that cause page walks.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x2", + "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" + }, + { + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x4", + "EventName": "DTLB_STORE_MISSES.WALK_DURATION", + "SampleAfterValue": "2000003", + "BriefDescription": "Cycles when PMH is busy with page walks.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0x49", + "Counter": "0,1,2,3", + "UMask": "0x10", + "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" + }, + { + "EventCode": "0xBD", + "Counter": "0,1,2,3", + "UMask": "0x1", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "SampleAfterValue": "100007", + "BriefDescription": "DTLB flush attempts of the thread-specific entries.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + }, + { + "EventCode": "0xBD", + "Counter": "0,1,2,3", + "UMask": "0x20", + "EventName": "TLB_FLUSH.STLB_ANY", + "SampleAfterValue": "100007", + "BriefDescription": "STLB flush attempts.", + "CounterHTOff": "0,1,2,3,4,5,6,7" + } +]
\ No newline at end of file |