diff options
| author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
|---|---|---|
| committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
| commit | ace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch) | |
| tree | b2d64bc10158fdd5497876388cd68142ca374ed3 /tools/perf/pmu-events/arch/x86/haswell | |
| parent | Initial commit. (diff) | |
| download | linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip | |
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/haswell')
12 files changed, 4481 insertions, 0 deletions
diff --git a/tools/perf/pmu-events/arch/x86/haswell/cache.json b/tools/perf/pmu-events/arch/x86/haswell/cache.json new file mode 100644 index 0000000000..0831f14b3c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/cache.json @@ -0,0 +1,832 @@ +[ + { + "BriefDescription": "L1D data line replacements", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "This event counts when new data lines are brought into the L1 Data cache, which cause other lines to be evicted from the cache.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "L1D miss outstanding duration in cycles", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Increments the number of outstanding L1D misses every cycle. Set Cmask = 1 and Edge =1 to count occurrences.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch. HWP are e.", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.REQUEST_FB_FULL", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Not rejected writebacks that hit L2 cache", + "EventCode": "0x27", + "EventName": "L2_DEMAND_RQSTS.WB_HIT", + "PublicDescription": "Not rejected writebacks that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x50" + }, + { + "BriefDescription": "L2 cache lines filling L2", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.ALL", + "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.", + "SampleAfterValue": "100003", + "UMask": "0x7" + }, + { + "BriefDescription": "L2 cache lines in E state filling L2", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.E", + "PublicDescription": "L2 cache lines in E state filling L2.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "L2 cache lines in I state filling L2", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.I", + "PublicDescription": "L2 cache lines in I state filling L2.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 cache lines in S state filling L2", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.S", + "PublicDescription": "L2 cache lines in S state filling L2.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Clean L2 cache lines evicted by demand", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.DEMAND_CLEAN", + "PublicDescription": "Clean L2 cache lines evicted by demand.", + "SampleAfterValue": "100003", + "UMask": "0x5" + }, + { + "BriefDescription": "Dirty L2 cache lines evicted by demand", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.DEMAND_DIRTY", + "PublicDescription": "Dirty L2 cache lines evicted by demand.", + "SampleAfterValue": "100003", + "UMask": "0x6" + }, + { + "BriefDescription": "L2 code requests", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts all L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, + { + "BriefDescription": "Demand Data Read requests", + "Errata": "HSD78, HSM80", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts any demand and L1 HW prefetch data load requests to L2.", + "SampleAfterValue": "200003", + "UMask": "0xe1" + }, + { + "BriefDescription": "Demand requests that miss L2 cache", + "Errata": "HSD78, HSM80", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", + "PublicDescription": "Demand requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x27" + }, + { + "BriefDescription": "Demand requests to L2 cache", + "Errata": "HSD78, HSM80", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "PublicDescription": "Demand requests to L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xe7" + }, + { + "BriefDescription": "Requests from L2 hardware prefetchers", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_PF", + "PublicDescription": "Counts all L2 HW prefetcher requests.", + "SampleAfterValue": "200003", + "UMask": "0xf8" + }, + { + "BriefDescription": "RFO requests to L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_RFO", + "PublicDescription": "Counts all L2 store RFO requests.", + "SampleAfterValue": "200003", + "UMask": "0xe2" + }, + { + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Number of instruction fetches that hit the L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc4" + }, + { + "BriefDescription": "L2 cache misses when fetching instructions", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Number of instruction fetches that missed the L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x24" + }, + { + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Errata": "HSD78, HSM80", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", + "SampleAfterValue": "200003", + "UMask": "0xc1" + }, + { + "BriefDescription": "Demand Data Read miss L2, no rejects", + "Errata": "HSD78, HSM80", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Demand data read requests that missed L2, no rejects.", + "SampleAfterValue": "200003", + "UMask": "0x21" + }, + { + "BriefDescription": "L2 prefetch requests that hit L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.L2_PF_HIT", + "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.", + "SampleAfterValue": "200003", + "UMask": "0xd0" + }, + { + "BriefDescription": "L2 prefetch requests that miss L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.L2_PF_MISS", + "PublicDescription": "Counts all L2 HW prefetcher requests that missed L2.", + "SampleAfterValue": "200003", + "UMask": "0x30" + }, + { + "BriefDescription": "All requests that miss L2 cache", + "Errata": "HSD78, HSM80", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "All requests that missed L2.", + "SampleAfterValue": "200003", + "UMask": "0x3f" + }, + { + "BriefDescription": "All L2 requests", + "Errata": "HSD78, HSM80", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "All requests to L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "RFO requests that hit L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc2" + }, + { + "BriefDescription": "RFO requests that miss L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x22" + }, + { + "BriefDescription": "L2 or L3 HW prefetches that access L2 cache", + "EventCode": "0xf0", + "EventName": "L2_TRANS.ALL_PF", + "PublicDescription": "Any MLC or L3 HW prefetch accessing L2, including rejects.", + "SampleAfterValue": "200003", + "UMask": "0x8" + }, + { + "BriefDescription": "Transactions accessing L2 pipe", + "EventCode": "0xf0", + "EventName": "L2_TRANS.ALL_REQUESTS", + "PublicDescription": "Transactions accessing L2 pipe.", + "SampleAfterValue": "200003", + "UMask": "0x80" + }, + { + "BriefDescription": "L2 cache accesses when fetching instructions", + "EventCode": "0xf0", + "EventName": "L2_TRANS.CODE_RD", + "PublicDescription": "L2 cache accesses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "Demand Data Read requests that access L2 cache", + "EventCode": "0xf0", + "EventName": "L2_TRANS.DEMAND_DATA_RD", + "PublicDescription": "Demand data read requests that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "L1D writebacks that access L2 cache", + "EventCode": "0xf0", + "EventName": "L2_TRANS.L1D_WB", + "PublicDescription": "L1D writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x10" + }, + { + "BriefDescription": "L2 fill requests that access L2 cache", + "EventCode": "0xf0", + "EventName": "L2_TRANS.L2_FILL", + "PublicDescription": "L2 fill requests that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x20" + }, + { + "BriefDescription": "L2 writebacks that access L2 cache", + "EventCode": "0xf0", + "EventName": "L2_TRANS.L2_WB", + "PublicDescription": "L2 writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x40" + }, + { + "BriefDescription": "RFO requests that access L2 cache", + "EventCode": "0xf0", + "EventName": "L2_TRANS.RFO", + "PublicDescription": "RFO requests that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when L1D is locked", + "EventCode": "0x63", + "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "PublicDescription": "Cycles in which the L1D is locked.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Core-originated cacheable demand requests missed L3", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "This event counts each cache miss condition for references to the last level cache.", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Core-originated cacheable demand requests that refer to L3", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "This event counts requests originating from the core that reference a cache line in the last level cache.", + "SampleAfterValue": "100003", + "UMask": "0x4f" + }, + { + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "Data_LA": "1", + "Errata": "HSD29, HSD25, HSM26, HSM30", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", + "PEBS": "1", + "SampleAfterValue": "20011", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.", + "Data_LA": "1", + "Errata": "HSD29, HSD25, HSM26, HSM30", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", + "PEBS": "1", + "SampleAfterValue": "20011", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Data_LA": "1", + "Errata": "HSD29, HSD25, HSM26, HSM30", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "SampleAfterValue": "20011", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required.", + "Data_LA": "1", + "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)", + "Data_LA": "1", + "Errata": "HSD74, HSD29, HSD25, HSM30", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", + "PEBS": "1", + "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "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.", + "Data_LA": "1", + "Errata": "HSM30", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Retired load uops with L1 cache hits as data sources.", + "Data_LA": "1", + "Errata": "HSD29, HSM30", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load uops misses in L1 cache as data sources.", + "Data_LA": "1", + "Errata": "HSM30", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "PEBS": "1", + "PublicDescription": "Retired load uops missed L1 cache as data sources.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Retired load uops with L2 cache hits as data sources.", + "Data_LA": "1", + "Errata": "HSD76, HSD29, HSM30", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.", + "Data_LA": "1", + "Errata": "HSD29, HSM30", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "PEBS": "1", + "PublicDescription": "Retired load uops missed L2. Unknown data source excluded.", + "SampleAfterValue": "50021", + "UMask": "0x10" + }, + { + "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.", + "Data_LA": "1", + "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", + "PEBS": "1", + "PublicDescription": "Retired load uops with L3 cache hits as data sources.", + "SampleAfterValue": "50021", + "UMask": "0x4" + }, + { + "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", + "Data_LA": "1", + "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L3_MISS", + "PEBS": "1", + "PublicDescription": "Retired load uops missed L3. Excludes unknown data source .", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Retired load uops.", + "Data_LA": "1", + "Errata": "HSD29, HSM30", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "PEBS": "1", + "PublicDescription": "Counts all retired load uops. This event accounts for SW prefetch uops of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "SampleAfterValue": "2000003", + "UMask": "0x81" + }, + { + "BriefDescription": "Retired store uops.", + "Data_LA": "1", + "Errata": "HSD29, HSM30", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "PEBS": "1", + "PublicDescription": "Counts all retired store uops.", + "SampleAfterValue": "2000003", + "UMask": "0x82" + }, + { + "BriefDescription": "Retired load uops with locked access.", + "Data_LA": "1", + "Errata": "HSD76, HSD29, HSM30", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x21" + }, + { + "BriefDescription": "Retired load uops that split across a cacheline boundary.", + "Data_LA": "1", + "Errata": "HSD29, HSM30", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Retired store uops that split across a cacheline boundary.", + "Data_LA": "1", + "Errata": "HSD29, HSM30", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x42" + }, + { + "BriefDescription": "Retired load uops that miss the STLB.", + "Data_LA": "1", + "Errata": "HSD29, HSM30", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x11" + }, + { + "BriefDescription": "Retired store uops that miss the STLB.", + "Data_LA": "1", + "Errata": "HSD29, HSM30", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x12" + }, + { + "BriefDescription": "Demand and prefetch data reads", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "PublicDescription": "Data read requests sent to uncore (demand and prefetch).", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cacheable and noncacheable code read requests", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Demand code read requests sent to uncore.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Demand Data Read requests sent to uncore", + "Errata": "HSD78, HSM80", + "EventCode": "0xb0", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Demand data read requests sent to uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Demand RFO read requests sent to uncore, including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", + "EventCode": "0xb2", + "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "Errata": "HSD62, HSD61, HSM63", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1", + "Errata": "HSD62, HSD61, HSM63", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1", + "Errata": "HSD78, HSD62, HSD61, HSM63, HSM80", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", + "CounterMask": "1", + "Errata": "HSD62, HSD61, HSM63", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Errata": "HSD62, HSD61, HSM63", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Offcore outstanding Demand code Read transactions in SQ to uncore. Set Cmask=1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "Errata": "HSD78, HSD62, HSD61, HSM63, HSM80", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Offcore outstanding demand data read transactions in SQ to uncore. Set Cmask=1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "CounterMask": "6", + "Errata": "HSD78, HSD62, HSD61, HSM63, HSM80", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore", + "Errata": "HSD62, HSD61, HSM63", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Offcore outstanding RFO store transactions in SQ to uncore. Set Cmask=1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0244", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0091", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0091", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C07F7", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C07F7", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all requests hit in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C8FFF", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0122", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0122", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0040", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0010", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0020", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0200", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0080", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0100", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Split locks in SQ", + "EventCode": "0xf4", + "EventName": "SQ_MISC.SPLIT_LOCK", + "SampleAfterValue": "100003", + "UMask": "0x10" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json new file mode 100644 index 0000000000..8fcc10f74a --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json @@ -0,0 +1,83 @@ +[ + { + "BriefDescription": "Approximate counts of AVX & AVX2 256-bit instructions, including non-arithmetic instructions, loads, and stores. May count non-AVX instructions that employ 256-bit operations, including (but not necessarily limited to) rep string instructions that use 256-bit loads and stores for optimized performance, XSAVE* and XRSTOR*, and operations that transition the x87 FPU data registers between x87 and MMX.", + "EventCode": "0xC6", + "EventName": "AVX_INSTS.ALL", + "PublicDescription": "Note that a whole rep string only counts AVX_INST.ALL once.", + "SampleAfterValue": "2000003", + "UMask": "0x7" + }, + { + "BriefDescription": "Cycles with any input/output SSE or FP assist", + "CounterMask": "1", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.ANY", + "PublicDescription": "Cycles with any input/output SSE* or FP assists.", + "SampleAfterValue": "100003", + "UMask": "0x1e" + }, + { + "BriefDescription": "Number of SIMD FP assists due to input values", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.SIMD_INPUT", + "PublicDescription": "Number of SIMD FP assists due to input values.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of SIMD FP assists due to Output values", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.SIMD_OUTPUT", + "PublicDescription": "Number of SIMD FP assists due to output values.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of X87 assists due to input value.", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.X87_INPUT", + "PublicDescription": "Number of X87 FP assists due to input values.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of X87 assists due to output value.", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.X87_OUTPUT", + "PublicDescription": "Number of X87 FP assists due to output values.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.", + "EventCode": "0x58", + "EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED", + "PublicDescription": "Number of SIMD move elimination candidate uops that were eliminated.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.", + "EventCode": "0x58", + "EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED", + "PublicDescription": "Number of SIMD move elimination candidate uops that were not eliminated.", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "Errata": "HSD56, HSM57", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.AVX_TO_SSE", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "Errata": "HSD56, HSM57", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.SSE_TO_AVX", + "SampleAfterValue": "100003", + "UMask": "0x10" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/frontend.json b/tools/perf/pmu-events/arch/x86/haswell/frontend.json new file mode 100644 index 0000000000..73d6d681df --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/frontend.json @@ -0,0 +1,246 @@ +[ + { + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "EventCode": "0xe6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Number of front end re-steers due to BPU misprediction.", + "SampleAfterValue": "100003", + "UMask": "0x1f" + }, + { + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.", + "EventCode": "0x80", + "EventName": "ICACHE.HIT", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.", + "EventCode": "0x80", + "EventName": "ICACHE.IFDATA_STALL", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction-cache miss.", + "EventCode": "0x80", + "EventName": "ICACHE.IFETCH_STALL", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes Uncacheable accesses.", + "EventCode": "0x80", + "EventName": "ICACHE.MISSES", + "PublicDescription": "This event counts Instruction Cache (ICACHE) misses.", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "PublicDescription": "Counts cycles DSB is delivered four uops. Set Cmask = 4.", + "SampleAfterValue": "2000003", + "UMask": "0x18" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "PublicDescription": "Counts cycles DSB is delivered at least one uops. Set Cmask = 1.", + "SampleAfterValue": "2000003", + "UMask": "0x18" + }, + { + "BriefDescription": "Cycles MITE is delivering 4 Uops", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "PublicDescription": "Counts cycles MITE is delivered four uops. Set Cmask = 4.", + "SampleAfterValue": "2000003", + "UMask": "0x24" + }, + { + "BriefDescription": "Cycles MITE is delivering any Uop", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "PublicDescription": "Counts cycles MITE is delivered at least one uop. Set Cmask = 1.", + "SampleAfterValue": "2000003", + "UMask": "0x24" + }, + { + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Instruction Decode Queue (IDQ) empty cycles", + "Errata": "HSD135", + "EventCode": "0x79", + "EventName": "IDQ.EMPTY", + "PublicDescription": "Counts cycles the IDQ is empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "EventCode": "0x79", + "EventName": "IDQ.MITE_ALL_UOPS", + "PublicDescription": "Number of uops delivered to IDQ from any path.", + "SampleAfterValue": "2000003", + "UMask": "0x3c" + }, + { + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MITE path. Set Cmask = 1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_CYCLES", + "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the Front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_DSB_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_DSB_OCCUR", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "EventCode": "0x79", + "EventName": "IDQ.MS_DSB_UOPS", + "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "EventCode": "0x79", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "This event counts uops delivered by the Front-end with the assistance of the microcode sequencer. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance.", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", + "Errata": "HSD135", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "This event count the number of undelivered (unallocated) uops from the Front-end to the Resource Allocation Table (RAT) while the Back-end of the processor is not stalled. The Front-end can allocate up to 4 uops per cycle so this event can increment 0-4 times per cycle depending on the number of unallocated uops. This event is counted on a per-core basis.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "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", + "Errata": "HSD135", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "This event counts the number cycles during which the Front-end allocated exactly zero uops to the Resource Allocation Table (RAT) while the Back-end of the processor is not stalled. This event is counted on a per-core basis.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", + "CounterMask": "1", + "Errata": "HSD135", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "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", + "Errata": "HSD135", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "CounterMask": "2", + "Errata": "HSD135", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "CounterMask": "1", + "Errata": "HSD135", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json new file mode 100644 index 0000000000..79d89c2636 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -0,0 +1,965 @@ +[ + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" + }, + { + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" + }, + { + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_thread_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_thread_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", + "ScaleUnit": "100%" + }, + { + "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", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", + "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.", + "ScaleUnit": "100%" + }, + { + "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_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_thread_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", + "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.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_thread_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_thread_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_core_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_thread_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_thread_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE / tma_info_thread_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_memory_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_thread_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_thread_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_thread_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", + "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-operations (uops). Ideally the Frontend can issue Pipeline_Width 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.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_thread_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_inst_mix_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + }, + { + "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) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_core_clks" + }, + { + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_core_coreipc" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_core_ilp" + }, + { + "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;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" + }, + { + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_inst_mix_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" + }, + { + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" + }, + { + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" + }, + { + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" + }, + { + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" + }, + { + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_lcp" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l1mpki" + }, + { + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_memory_l2mpki" + }, + { + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + }, + { + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" + }, + { + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" + }, + { + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_load_l2_mlp" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_core_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" + }, + { + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average number of parallel requests to external memory", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_parallel_requests", + "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" + }, + { + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_request_latency" + }, + { + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_system_smt_2t_utilization" + }, + { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_socket_clks" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" + }, + { + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 6" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_thread_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_thread_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_thread_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_thread_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_thread_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_thread_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_sq_full", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_thread_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_3", + "MetricThreshold": "tma_port_3 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", + "MetricExpr": "tma_store_op_utilization", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", + "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricName": "tma_port_7", + "MetricThreshold": "tma_port_7 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address). Sample with: UOPS_DISPATCHED_PORT.PORT_7", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_thread_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_thread_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", + "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 Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_thread_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "INST_RETIRED.X87 * tma_info_thread_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "ScaleUnit": "100%" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/memory.json b/tools/perf/pmu-events/arch/x86/haswell/memory.json new file mode 100644 index 0000000000..2fc25e22a4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/memory.json @@ -0,0 +1,514 @@ +[ + { + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", + "EventCode": "0xc8", + "EventName": "HLE_RETIRED.ABORTED", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", + "EventCode": "0xc8", + "EventName": "HLE_RETIRED.ABORTED_MISC1", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to uncommon conditions.", + "EventCode": "0xc8", + "EventName": "HLE_RETIRED.ABORTED_MISC2", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions.", + "EventCode": "0xc8", + "EventName": "HLE_RETIRED.ABORTED_MISC3", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type.", + "Errata": "HSD65", + "EventCode": "0xc8", + "EventName": "HLE_RETIRED.ABORTED_MISC4", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to none of the previous 4 categories (e.g. interrupts)", + "EventCode": "0xc8", + "EventName": "HLE_RETIRED.ABORTED_MISC5", + "PublicDescription": "Number of times an HLE execution aborted due to none of the previous 4 categories (e.g. interrupts).", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of times an HLE execution successfully committed.", + "EventCode": "0xc8", + "EventName": "HLE_RETIRED.COMMIT", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an HLE execution started.", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.START", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "This event counts the number of memory ordering machine clears detected. Memory ordering machine clears can result from memory address aliasing or snoops from another hardware thread or core to data inflight in the pipeline. Machine clears can have a significant performance impact if they are happening frequently.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Randomly selected loads with latency value being above 128.", + "Data_LA": "1", + "Errata": "HSD76, HSD25, HSM26", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "SampleAfterValue": "1009", + "UMask": "0x1" + }, + { + "BriefDescription": "Randomly selected loads with latency value being above 16.", + "Data_LA": "1", + "Errata": "HSD76, HSD25, HSM26", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "SampleAfterValue": "20011", + "UMask": "0x1" + }, + { + "BriefDescription": "Randomly selected loads with latency value being above 256.", + "Data_LA": "1", + "Errata": "HSD76, HSD25, HSM26", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "SampleAfterValue": "503", + "UMask": "0x1" + }, + { + "BriefDescription": "Randomly selected loads with latency value being above 32.", + "Data_LA": "1", + "Errata": "HSD76, HSD25, HSM26", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Randomly selected loads with latency value being above 4.", + "Data_LA": "1", + "Errata": "HSD76, HSD25, HSM26", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Randomly selected loads with latency value being above 512.", + "Data_LA": "1", + "Errata": "HSD76, HSD25, HSM26", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "SampleAfterValue": "101", + "UMask": "0x1" + }, + { + "BriefDescription": "Randomly selected loads with latency value being above 64.", + "Data_LA": "1", + "Errata": "HSD76, HSD25, HSM26", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "SampleAfterValue": "2003", + "UMask": "0x1" + }, + { + "BriefDescription": "Randomly selected loads with latency value being above 8.", + "Data_LA": "1", + "Errata": "HSD76, HSD25, HSM26", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "SampleAfterValue": "50021", + "UMask": "0x1" + }, + { + "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache", + "EventCode": "0x05", + "EventName": "MISALIGN_MEM_REF.LOADS", + "PublicDescription": "Speculative cache-line split load uops dispatched to L1D.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache", + "EventCode": "0x05", + "EventName": "MISALIGN_MEM_REF.STORES", + "PublicDescription": "Speculative cache-line split store-address uops dispatched to L1D.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts all demand & prefetch code reads miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00244", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400244", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00091", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400091", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC007F7", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "miss the L3 and the data is returned from local dram", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1004007F7", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all requests miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC08FFF", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00122", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400122", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x100400002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00040", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00010", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00020", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00200", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00080", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFFC00100", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MISC1", + "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g., read/write capacity and conflicts).", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MISC2", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MISC3", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type.", + "Errata": "HSD65", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MISC4", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MISC5", + "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of times an RTM execution successfully committed.", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.COMMIT", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an RTM execution started.", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.START", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region.", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC2", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded.", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC3", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC4", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC5", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional writes.", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address.", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer.", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer.", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", + "EventCode": "0x54", + "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", + "SampleAfterValue": "2000003", + "UMask": "0x40" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/metricgroups.json b/tools/perf/pmu-events/arch/x86/haswell/metricgroups.json new file mode 100644 index 0000000000..f6a0258e32 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/metricgroups.json @@ -0,0 +1,107 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/haswell/other.json b/tools/perf/pmu-events/arch/x86/haswell/other.json new file mode 100644 index 0000000000..2395ebf112 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/other.json @@ -0,0 +1,35 @@ +[ + { + "BriefDescription": "Unhalted core cycles when the thread is in ring 0", + "EventCode": "0x5C", + "EventName": "CPL_CYCLES.RING0", + "PublicDescription": "Unhalted core cycles when the thread is in ring 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of intervals between processor halts while thread is in ring 0.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x5C", + "EventName": "CPL_CYCLES.RING0_TRANS", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3", + "EventCode": "0x5C", + "EventName": "CPL_CYCLES.RING123", + "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock", + "EventCode": "0x63", + "EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION", + "PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json new file mode 100644 index 0000000000..540f437262 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json @@ -0,0 +1,1050 @@ +[ + { + "BriefDescription": "Any uop executed by the Divider. (This includes all divide uops, sqrt, ...)", + "EventCode": "0x14", + "EventName": "ARITH.DIVIDER_UOPS", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Speculative and retired branches", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_BRANCHES", + "PublicDescription": "Counts all near executed branches (not necessarily retired).", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "Speculative and retired macro-conditional branches.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_CONDITIONAL", + "SampleAfterValue": "200003", + "UMask": "0xc1" + }, + { + "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP", + "SampleAfterValue": "200003", + "UMask": "0xc2" + }, + { + "BriefDescription": "Speculative and retired direct near calls.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "UMask": "0xd0" + }, + { + "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "UMask": "0xc4" + }, + { + "BriefDescription": "Speculative and retired indirect return branches.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN", + "SampleAfterValue": "200003", + "UMask": "0xc8" + }, + { + "BriefDescription": "Not taken macro-conditional branches.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "UMask": "0x41" + }, + { + "BriefDescription": "Taken speculative and retired macro-conditional branches.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "UMask": "0x81" + }, + { + "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP", + "SampleAfterValue": "200003", + "UMask": "0x82" + }, + { + "BriefDescription": "Taken speculative and retired direct near calls.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "UMask": "0x90" + }, + { + "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "UMask": "0x84" + }, + { + "BriefDescription": "Taken speculative and retired indirect calls.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "UMask": "0xa0" + }, + { + "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN", + "SampleAfterValue": "200003", + "UMask": "0x88" + }, + { + "BriefDescription": "All (macro) branch instructions retired.", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Branch instructions at retirement.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "All (macro) branch instructions retired.", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "SampleAfterValue": "400009", + "UMask": "0x4" + }, + { + "BriefDescription": "Conditional branch instructions retired.", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "PEBS": "1", + "PublicDescription": "Counts the number of conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Far branch instructions retired.", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PublicDescription": "Number of far branches retired.", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Direct and indirect near call instructions retired.", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_CALL_R3", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Return instructions retired.", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PEBS": "1", + "PublicDescription": "Counts the number of near return instructions retired.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Taken branch instructions retired.", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "Number of near taken branches retired.", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "PublicDescription": "Counts the number of not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" + }, + { + "BriefDescription": "Speculative and retired mispredicted macro conditional branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.ALL_BRANCHES", + "PublicDescription": "Counts all near executed branches (not necessarily retired).", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "Speculative and retired mispredicted macro conditional branches.", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL", + "SampleAfterValue": "200003", + "UMask": "0xc1" + }, + { + "BriefDescription": "Mispredicted indirect branches excluding calls and returns.", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "UMask": "0xc4" + }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, + { + "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "UMask": "0x41" + }, + { + "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL", + "SampleAfterValue": "200003", + "UMask": "0x81" + }, + { + "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", + "SampleAfterValue": "200003", + "UMask": "0x84" + }, + { + "BriefDescription": "Taken speculative and retired mispredicted indirect calls.", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "SampleAfterValue": "200003", + "UMask": "0xa0" + }, + { + "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR", + "SampleAfterValue": "200003", + "UMask": "0x88" + }, + { + "BriefDescription": "All mispredicted macro branch instructions retired.", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Mispredicted branch instructions at retirement.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Mispredicted macro branch instructions retired.", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "PublicDescription": "This event counts all mispredicted branch instructions retired. This is a precise event.", + "SampleAfterValue": "400009", + "UMask": "0x4" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "PEBS": "1", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "Number of near branch instructions retired that were taken but mispredicted.", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "PublicDescription": "Increments at the frequency of XCLK (100 MHz) when not halted.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state.", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate)", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "PublicDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core cycles when the thread is not in halt state.", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "This event counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Thread cycles when thread is not in halt state", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "Counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.", + "SampleAfterValue": "2000003" + }, + { + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Cycles with pending L1 cache miss loads.", + "CounterMask": "8", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", + "PublicDescription": "Cycles with pending L1 data cache miss loads. Set Cmask=8 to count cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles with pending L2 cache miss loads.", + "CounterMask": "1", + "Errata": "HSD78, HSM63, HSM80", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", + "PublicDescription": "Cycles with pending L2 miss loads. Set Cmask=2 to count cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with pending memory loads.", + "CounterMask": "2", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_LDM_PENDING", + "PublicDescription": "Cycles with pending memory loads. Set Cmask=2 to count cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.", + "CounterMask": "4", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE", + "PublicDescription": "This event counts cycles during which no instructions were executed in the execution stage of the pipeline.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Execution stalls due to L1 data cache misses", + "CounterMask": "12", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING", + "PublicDescription": "Execution stalls due to L1 data cache miss loads. Set Cmask=0CH.", + "SampleAfterValue": "2000003", + "UMask": "0xc" + }, + { + "BriefDescription": "Execution stalls due to L2 cache misses.", + "CounterMask": "5", + "Errata": "HSM63, HSM80", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING", + "PublicDescription": "Number of loads missed L2.", + "SampleAfterValue": "2000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Execution stalls due to memory subsystem.", + "CounterMask": "6", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_LDM_PENDING", + "PublicDescription": "This event counts cycles during which no instructions were executed in the execution stage of the pipeline and there were memory instructions pending (waiting for data).", + "SampleAfterValue": "2000003", + "UMask": "0x6" + }, + { + "BriefDescription": "Stall cycles because IQ is full", + "EventCode": "0x87", + "EventName": "ILD_STALL.IQ_FULL", + "PublicDescription": "Stall cycles due to IQ is full.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "EventCode": "0x87", + "EventName": "ILD_STALL.LCP", + "PublicDescription": "This event counts cycles where the decoder is stalled on an instruction with a length changing prefix (LCP).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Instructions retired from execution.", + "Errata": "HSD140, HSD143", + "EventName": "INST_RETIRED.ANY", + "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. INST_RETIRED.ANY is counted by a designated fixed counter, leaving the programmable counters available for other events. Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Errata": "HSD11, HSD140", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.ANY_P", + "PublicDescription": "Number of instructions at retirement.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", + "Errata": "HSD140", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.PREC_DIST", + "PEBS": "2", + "PublicDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "FP operations retired. X87 FP operations that have no exceptions: Counts also flows that have several X87 or flows that use X87 uops in the exception handling.", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.X87", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", + "CounterMask": "1", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "This event counts the number of cycles spent waiting for a recovery after an event such as a processor nuke, JEClear, assist, hle/rtm abort etc.", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "AnyThread": "1", + "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", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "PublicDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "loads blocked by overlapping with store buffer that cannot be forwarded", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. The penalty for blocked store forwarding is that the load must wait for the store to write its value to the cache before it can be issued.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "EventCode": "0x07", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "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 which can have a performance impact.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch", + "EventCode": "0x4c", + "EventName": "LOAD_HIT_PRE.HW_PF", + "PublicDescription": "Non-SW-prefetch load dispatches that hit fill buffer allocated for H/W prefetch.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch", + "EventCode": "0x4c", + "EventName": "LOAD_HIT_PRE.SW_PF", + "PublicDescription": "Non-SW-prefetch load dispatches that hit fill buffer allocated for S/W prefetch.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "4", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_4_UOPS", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "1", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_ACTIVE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of Uops delivered by the LSD.", + "EventCode": "0xa8", + "EventName": "LSD.UOPS", + "PublicDescription": "Number of uops delivered by the LSD.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of machine clears (nukes) of any type.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.COUNT", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles there was a Nuke. Account for both thread-specific and All Thread Nukes.", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "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.", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.MASKMOV", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Self-modifying code (SMC) detected.", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.SMC", + "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.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of integer Move Elimination candidate uops that were eliminated.", + "EventCode": "0x58", + "EventName": "MOVE_ELIMINATION.INT_ELIMINATED", + "PublicDescription": "Number of integer move elimination candidate uops that were eliminated.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of integer Move Elimination candidate uops that were not eliminated.", + "EventCode": "0x58", + "EventName": "MOVE_ELIMINATION.INT_NOT_ELIMINATED", + "PublicDescription": "Number of integer move elimination candidate uops that were not eliminated.", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", + "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Resource-related stall cycles", + "Errata": "HSD135", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.ANY", + "PublicDescription": "Cycles allocation is stalled due to resource related reason.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles stalled due to re-order buffer full.", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.ROB", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles stalled due to no eligible RS entry available.", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.RS", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "This event counts cycles during which no instructions were allocated because no Store Buffers (SB) were available.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Count cases of saving new LBR", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "PublicDescription": "Count cases of saving new LBR records by hardware.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "PublicDescription": "This event counts cycles when the Reservation Station ( RS ) is empty for the thread. The RS is a structure that buffers allocated micro-ops from the Front-end. If there are many cycles when the RS is empty, it may represent an underflow of instructions delivered from the Front-end.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_END", + "Invert": "1", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 0.", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 1.", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 2.", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 3.", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 4.", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 5.", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 6.", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_6", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 7.", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_7", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of uops executed on the core.", + "Errata": "HSD30, HSM31", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Counts total number of uops to be executed per-core each cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "CounterMask": "1", + "Errata": "HSD30, HSM31", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "CounterMask": "2", + "Errata": "HSD30, HSM31", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "CounterMask": "3", + "Errata": "HSD30, HSM31", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "CounterMask": "4", + "Errata": "HSD30, HSM31", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "Errata": "HSD30, HSM31", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "CounterMask": "1", + "Errata": "HSD144, HSD30, HSM31", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "PublicDescription": "This events counts the cycles where at least one uop was executed. It is counted per thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "CounterMask": "2", + "Errata": "HSD144, HSD30, HSM31", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "PublicDescription": "This events counts the cycles where at least two uop were executed. It is counted per thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "CounterMask": "3", + "Errata": "HSD144, HSD30, HSM31", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "PublicDescription": "This events counts the cycles where at least three uop were executed. It is counted per thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread.", + "CounterMask": "4", + "Errata": "HSD144, HSD30, HSM31", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "CounterMask": "1", + "Errata": "HSD144, HSD30, HSM31", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 0", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_0", + "PublicDescription": "Cycles which a uop is dispatched on port 0 in this thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are executed in port 0.", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 1", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_1", + "PublicDescription": "Cycles which a uop is dispatched on port 1 in this thread.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are executed in port 1.", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 2", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_2", + "PublicDescription": "Cycles which a uop is dispatched on port 2 in this thread.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are dispatched to port 2.", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_2_CORE", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 3", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_3", + "PublicDescription": "Cycles which a uop is dispatched on port 3 in this thread.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are dispatched to port 3.", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_3_CORE", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 4", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_4", + "PublicDescription": "Cycles which a uop is dispatched on port 4 in this thread.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are executed in port 4.", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 5", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_5", + "PublicDescription": "Cycles which a uop is dispatched on port 5 in this thread.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are executed in port 5.", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 6", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_6", + "PublicDescription": "Cycles which a uop is dispatched on port 6 in this thread.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are executed in port 6.", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 7", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_7", + "PublicDescription": "Cycles which a uop is dispatched on port 7 in this thread.", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are dispatched to port 7.", + "EventCode": "0xA1", + "EventName": "UOPS_EXECUTED_PORT.PORT_7_CORE", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "This event counts the number of uops issued by the Front-end of the pipeline to the Back-end. This event is counted at the allocation stage and will count both retired and non-retired uops.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.", + "CounterMask": "1", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of flags-merge uops being allocated. Such uops considered perf sensitive; added by GSR u-arch.", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.FLAGS_MERGE", + "PublicDescription": "Number of flags-merge uops allocated. Such uops add delay.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of Multiply packed/scalar single precision uops allocated", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.SINGLE_MUL", + "PublicDescription": "Number of multiply packed/scalar single precision uops allocated.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.SLOW_LEA", + "PublicDescription": "Number of slow LEA or similar uops allocated. Such uop has 3 sources (for example, 2 sources + immediate) regardless of whether it is a result of LEA instruction or not.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.", + "CounterMask": "1", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Actually retired uops.", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.ALL", + "PEBS": "1", + "PublicDescription": "Counts the number of micro-ops retired. Use Cmask=1 and invert to count active cycles or stalled cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles without actually retired uops.", + "CounterMask": "1", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.CORE_STALL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retirement slots used.", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PEBS": "1", + "PublicDescription": "This event counts the number of retirement slots used each cycle. There are potentially 4 slots that can be used each cycle - meaning, 4 uops or 4 instructions could retire each cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "CounterMask": "1", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 10 actually retired uops.", + "CounterMask": "16", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswell/uncore-cache.json new file mode 100644 index 0000000000..be9a3ed1a9 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/uncore-cache.json @@ -0,0 +1,202 @@ +[ + { + "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", + "PerPkg": "1", + "UMask": "0x86", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup any request that access cache and found line in I-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", + "PerPkg": "1", + "UMask": "0x88", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup any request that access cache and found line in M-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", + "PerPkg": "1", + "UMask": "0x81", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", + "PerPkg": "1", + "UMask": "0x8f", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES", + "PerPkg": "1", + "UMask": "0x46", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I", + "PerPkg": "1", + "UMask": "0x48", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M", + "PerPkg": "1", + "UMask": "0x41", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI", + "PerPkg": "1", + "UMask": "0x4f", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", + "PerPkg": "1", + "UMask": "0x16", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup read request that access cache and found line in I-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", + "PerPkg": "1", + "UMask": "0x18", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup read request that access cache and found line in M-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", + "PerPkg": "1", + "UMask": "0x1f", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", + "PerPkg": "1", + "UMask": "0x26", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup write request that access cache and found line in I-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup write request that access cache and found line in M-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CBOX" + }, + { + "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.", + "EventCode": "0x34", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", + "PerPkg": "1", + "UMask": "0x2f", + "Unit": "CBOX" + }, + { + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.", + "EventCode": "0x22", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION", + "PerPkg": "1", + "UMask": "0x88", + "Unit": "CBOX" + }, + { + "BriefDescription": "An external snoop hits a modified line in some processor core.", + "EventCode": "0x22", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CBOX" + }, + { + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "EventCode": "0x22", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", + "PerPkg": "1", + "UMask": "0x48", + "Unit": "CBOX" + }, + { + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.", + "EventCode": "0x22", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION", + "PerPkg": "1", + "UMask": "0x84", + "Unit": "CBOX" + }, + { + "BriefDescription": "An external snoop hits a non-modified line in some processor core.", + "EventCode": "0x22", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "CBOX" + }, + { + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "EventCode": "0x22", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", + "PerPkg": "1", + "UMask": "0x44", + "Unit": "CBOX" + }, + { + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "EventCode": "0x22", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", + "PerPkg": "1", + "UMask": "0x81", + "Unit": "CBOX" + }, + { + "BriefDescription": "An external snoop misses in some processor core.", + "EventCode": "0x22", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CBOX" + }, + { + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "EventCode": "0x22", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", + "PerPkg": "1", + "UMask": "0x41", + "Unit": "CBOX" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswell/uncore-interconnect.json new file mode 100644 index 0000000000..8da28239eb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/uncore-interconnect.json @@ -0,0 +1,52 @@ +[ + { + "BriefDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory)", + "EventCode": "0x83", + "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.All", + "PerPkg": "1", + "PublicDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory).", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "EventCode": "0x84", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "CounterMask": "1", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "ARB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore-other.json b/tools/perf/pmu-events/arch/x86/haswell/uncore-other.json new file mode 100644 index 0000000000..2af92e43b2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/uncore-other.json @@ -0,0 +1,9 @@ +[ + { + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "EventCode": "0xff", + "EventName": "UNC_CLOCK.SOCKET", + "PerPkg": "1", + "Unit": "CLOCK" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json b/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json new file mode 100644 index 0000000000..87a4ec1ee7 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/virtual-memory.json @@ -0,0 +1,386 @@ +[ + { + "BriefDescription": "Load misses in all DTLB levels that cause page walks", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Misses in all TLB levels that cause a page walk of any page size.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.PDE_CACHE_MISS", + "PublicDescription": "DTLB demand load misses with low part of linear-to-physical address translation missed.", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Number of cache load STLB hits. No page walk.", + "SampleAfterValue": "2000003", + "UMask": "0x60" + }, + { + "BriefDescription": "Load misses that miss the DTLB and hit the STLB (2M)", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT_2M", + "PublicDescription": "This event counts load operations from a 2M page that miss the first DTLB level but hit the second and do not cause page walks.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Load misses that miss the DTLB and hit the STLB (4K)", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K", + "PublicDescription": "This event counts load operations from a 4K page that miss the first DTLB level but hit the second and do not cause page walks.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Completed page walks in any TLB of any page size due to demand load misses.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (1G)", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (2M/4M).", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Completed page walks due to demand load misses that caused 2M/4M page walks in any TLB levels.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes (4K).", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Completed page walks due to demand load misses that caused 4K page walks in any TLB levels.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when PMH is busy with page walks", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_DURATION", + "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB load misses.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Store misses in all DTLB levels that cause page walks", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Miss in all TLB levels causes a page walk of any page size (4K/2M/4M/1G).", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "DTLB store misses with low part of linear-to-physical address translation missed", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.PDE_CACHE_MISS", + "PublicDescription": "DTLB store misses with low part of linear-to-physical address translation missed.", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", + "SampleAfterValue": "100003", + "UMask": "0x60" + }, + { + "BriefDescription": "Store misses that miss the DTLB and hit the STLB (2M)", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT_2M", + "PublicDescription": "This event counts store operations from a 2M page that miss the first DTLB level but hit the second and do not cause page walks.", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Store misses that miss the DTLB and hit the STLB (4K)", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT_4K", + "PublicDescription": "This event counts store operations from a 4K page that miss the first DTLB level but hit the second and do not cause page walks.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Completed page walks due to store miss in any TLB levels of any page size (4K/2M/4M/1G).", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks. (1G)", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks (2M/4M)", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Completed page walks due to store misses in one or more TLB levels of 2M/4M page structure.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (4K)", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Completed page walks due to store misses in one or more TLB levels of 4K page structure.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when PMH is busy with page walks", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_DURATION", + "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by DTLB store misses.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycle count for an Extended Page table walk.", + "EventCode": "0x4f", + "EventName": "EPT.WALK_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", + "EventCode": "0xae", + "EventName": "ITLB.ITLB_FLUSH", + "PublicDescription": "Counts the number of ITLB flushes, includes 4k/2M/4M pages.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Misses at all ITLB levels that cause page walks", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Misses in ITLB that causes a page walk of any page size.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", + "PublicDescription": "ITLB misses that hit STLB. No page walk.", + "SampleAfterValue": "100003", + "UMask": "0x60" + }, + { + "BriefDescription": "Code misses that miss the DTLB and hit the STLB (2M)", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT_2M", + "PublicDescription": "ITLB misses that hit STLB (2M).", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Core misses that miss the DTLB and hit the STLB (4K)", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT_4K", + "PublicDescription": "ITLB misses that hit STLB (4K).", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Misses in all ITLB levels that cause completed page walks", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Completed page walks in ITLB of any page size.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Store miss in all TLB levels causes a page walk that completes. (1G)", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Completed page walks due to misses in ITLB 2M/4M page entries.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Completed page walks due to misses in ITLB 4K page entries.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when PMH is busy with page walks", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_DURATION", + "PublicDescription": "This event counts cycles when the page miss handler (PMH) is servicing page walks caused by ITLB misses.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of DTLB page walker hits in the L1+FB", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.DTLB_L1", + "PublicDescription": "Number of DTLB page walker loads that hit in the L1+FB.", + "SampleAfterValue": "2000003", + "UMask": "0x11" + }, + { + "BriefDescription": "Number of DTLB page walker hits in the L2", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.DTLB_L2", + "PublicDescription": "Number of DTLB page walker loads that hit in the L2.", + "SampleAfterValue": "2000003", + "UMask": "0x12" + }, + { + "BriefDescription": "Number of DTLB page walker hits in the L3 + XSNP", + "Errata": "HSD25", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.DTLB_L3", + "PublicDescription": "Number of DTLB page walker loads that hit in the L3.", + "SampleAfterValue": "2000003", + "UMask": "0x14" + }, + { + "BriefDescription": "Number of DTLB page walker hits in Memory", + "Errata": "HSD25", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.DTLB_MEMORY", + "PublicDescription": "Number of DTLB page walker loads from memory.", + "SampleAfterValue": "2000003", + "UMask": "0x18" + }, + { + "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L1 and FB.", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L1", + "SampleAfterValue": "2000003", + "UMask": "0x41" + }, + { + "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L2.", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L2", + "SampleAfterValue": "2000003", + "UMask": "0x42" + }, + { + "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in the L3.", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_L3", + "SampleAfterValue": "2000003", + "UMask": "0x44" + }, + { + "BriefDescription": "Counts the number of Extended Page Table walks from the DTLB that hit in memory.", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.EPT_DTLB_MEMORY", + "SampleAfterValue": "2000003", + "UMask": "0x48" + }, + { + "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L1 and FB.", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L1", + "SampleAfterValue": "2000003", + "UMask": "0x81" + }, + { + "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L2", + "SampleAfterValue": "2000003", + "UMask": "0x82" + }, + { + "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in the L2.", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_L3", + "SampleAfterValue": "2000003", + "UMask": "0x84" + }, + { + "BriefDescription": "Counts the number of Extended Page Table walks from the ITLB that hit in memory.", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.EPT_ITLB_MEMORY", + "SampleAfterValue": "2000003", + "UMask": "0x88" + }, + { + "BriefDescription": "Number of ITLB page walker hits in the L1+FB", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.ITLB_L1", + "PublicDescription": "Number of ITLB page walker loads that hit in the L1+FB.", + "SampleAfterValue": "2000003", + "UMask": "0x21" + }, + { + "BriefDescription": "Number of ITLB page walker hits in the L2", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.ITLB_L2", + "PublicDescription": "Number of ITLB page walker loads that hit in the L2.", + "SampleAfterValue": "2000003", + "UMask": "0x22" + }, + { + "BriefDescription": "Number of ITLB page walker hits in the L3 + XSNP", + "Errata": "HSD25", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.ITLB_L3", + "PublicDescription": "Number of ITLB page walker loads that hit in the L3.", + "SampleAfterValue": "2000003", + "UMask": "0x24" + }, + { + "BriefDescription": "Number of ITLB page walker hits in Memory", + "Errata": "HSD25", + "EventCode": "0xBC", + "EventName": "PAGE_WALKER_LOADS.ITLB_MEMORY", + "PublicDescription": "Number of ITLB page walker loads from memory.", + "SampleAfterValue": "2000003", + "UMask": "0x28" + }, + { + "BriefDescription": "DTLB flush attempts of the thread-specific entries", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "PublicDescription": "DTLB flush attempts of the thread-specific entries.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "STLB flush attempts", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.STLB_ANY", + "PublicDescription": "Count number of STLB flush attempts.", + "SampleAfterValue": "100003", + "UMask": "0x20" + } +] |