diff options
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/skylakex')
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/cache.json | 1675 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/floating-point.json | 85 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/frontend.json | 516 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/memory.json | 1403 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/other.json | 116 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/pipeline.json | 959 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json | 408 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json | 162 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json | 1720 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json | 284 |
10 files changed, 7328 insertions, 0 deletions
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json new file mode 100644 index 000000000..e750a2197 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json @@ -0,0 +1,1675 @@ +[ + { + "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts all demand code reads that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.PF_MISS", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x38" + }, + { + "BriefDescription": "Demand requests that miss L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", + "PublicDescription": "Demand requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x27" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "SampleAfterValue": "50021", + "UMask": "0x4" + }, + { + "BriefDescription": "L2 writebacks that access L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.L2_WB", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x40" + }, + { + "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "UMask": "0x1f" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "SampleAfterValue": "100007", + "UMask": "0x20" + }, + { + "BriefDescription": "All retired store instructions.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x82" + }, + { + "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.SILENT", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch data reads that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core-originated cacheable demand requests missed L3", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL057", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_PF", + "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", + "SampleAfterValue": "200003", + "UMask": "0xf8" + }, + { + "BriefDescription": "Retired load instructions whose data sources was remote HITM", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "PEBS": "1", + "PublicDescription": "Retired load instructions whose data sources was remote HITM.", + "SampleAfterValue": "100007", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts all prefetch data reads that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x22" + }, + { + "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped.", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "All requests that miss L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "All requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x3f" + }, + { + "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, + { + "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", + "PEBS": "1", + "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from remote dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x24" + }, + { + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Demand requests to L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "PublicDescription": "Demand requests to L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xe7" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core-originated cacheable demand requests that refer to L3", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL057", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x4f" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions that miss the STLB.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x11" + }, + { + "BriefDescription": "Counts demand data reads that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "L1D data line replacements", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "SampleAfterValue": "100007", + "UMask": "0x40" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.USELESS_PREF", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.PF_HIT", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xd8" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand Data Read miss L2, no rejects", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", + "SampleAfterValue": "200003", + "UMask": "0x21" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "All retired load instructions.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x81" + }, + { + "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "SampleAfterValue": "20011", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand Data Read requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", + "SampleAfterValue": "200003", + "UMask": "0xe1" + }, + { + "BriefDescription": "All L2 requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "All L2 requests.", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of cache line split locks sent to uncore.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF4", + "EventName": "SQ_MISC.SPLIT_LOCK", + "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "UMask": "0xc4" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PEBS": "1", + "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc2" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "L1D miss outstandings duration in cycles", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "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": "Retired load instructions which data sources were HitM responses from shared L3", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", + "SampleAfterValue": "20011", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x42" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Any memory transaction that reached the SQ.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Cacheable and noncachaeble code read requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "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.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch RFOs that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions with locked access.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x21" + }, + { + "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB2", + "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch RFOs that have any response type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired store instructions that miss the STLB.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x12" + }, + { + "BriefDescription": "RFO requests to L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_RFO", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "SampleAfterValue": "200003", + "UMask": "0xe2" + }, + { + "BriefDescription": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PEBS": "1", + "PublicDescription": "Retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "50021", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json new file mode 100644 index 000000000..e197cde15 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json @@ -0,0 +1,85 @@ +[ + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT14 RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 16 calculations per element.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles with any input/output SSE or FP assist", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.ANY", + "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", + "SampleAfterValue": "100003", + "UMask": "0x1e" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "UMask": "0x8" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json new file mode 100644 index 000000000..cdf95bd2a --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json @@ -0,0 +1,516 @@ +[ + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE_16B.IFDATA_STALL", + "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x14", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x408006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "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", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xE6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "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", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "MSRValue": "0x401006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "BriefDescription": "Cycles MITE is delivering any Uop", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x24" + }, + { + "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_HIT", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "MSRValue": "0x404006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_STALL", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x18" + }, + { + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "MSRValue": "0x420006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "MSRIndex": "0x3F7", + "MSRValue": "0x400806", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", + "Counter": "0,1,2,3,4,5,6,7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x400106", + "PEBS": "2", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x400206", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "MSRValue": "0x400406", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles MITE is delivering 4 Uops", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x24" + }, + { + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_DSB_CYCLES", + "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "MSRIndex": "0x3F7", + "MSRValue": "0x410006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x200206", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", + "MSRIndex": "0x3F7", + "MSRValue": "0x300206", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x100206", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x18" + }, + { + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.COUNT", + "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "MSRIndex": "0x3F7", + "MSRValue": "0x402006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_MISS", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.L1I_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x12", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json new file mode 100644 index 000000000..6c3fd89d2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json @@ -0,0 +1,1403 @@ +[ + { + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "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": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch data reads that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "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", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", + "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Number of times a TSX line had a cache conflict.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "2003", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_MEM", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", + "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC5", + "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC4", + "PublicDescription": "RTM region detected inside HLE.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC3", + "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "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", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC2", + "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "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.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an RTM execution successfully committed", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Number of times RTM commit succeeded.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts prefetch RFOs that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an HLE execution successfully committed", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.COMMIT", + "PublicDescription": "Number of times HLE commit succeeded.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", + "PublicDescription": "Number of times we could not allocate Lock Buffer.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand Data Read requests who miss L3 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Demand Data Read requests who miss L3 cache.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "503", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED", + "PEBS": "1", + "PublicDescription": "Number of times RTM abort was triggered.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED", + "PEBS": "1", + "PublicDescription": "Number of times HLE abort was triggered.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "20011", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", + "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "101", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of times an RTM execution started.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL089", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", + "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "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 HLE execution started.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.START", + "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that miss in the L3.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "1009", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x083FC00491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063FC00100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x6" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100003", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "50021", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json new file mode 100644 index 000000000..f6b147ba8 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json @@ -0,0 +1,116 @@ +[ + { + "BriefDescription": "Core cycles the core was throttled due to a pending power level request.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "CORE_POWER.THROTTLE", + "PublicDescription": "Core cycles the out-of-order engine was throttled due to a pending power level request.", + "SampleAfterValue": "200003", + "UMask": "0x40" + }, + { + "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xFE", + "EventName": "IDI_MISC.WB_DOWNGRADE", + "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of PREFETCHW instructions executed.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "CORE_POWER.LVL0_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.", + "SampleAfterValue": "200003", + "UMask": "0x7" + }, + { + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "CORE_POWER.LVL1_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "UMask": "0x18" + }, + { + "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.T0", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of hardware interrupts received by the processor.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCB", + "EventName": "HW_INTERRUPTS.RECEIVED", + "PublicDescription": "Counts the number of hardware interruptions received by the processor.", + "SampleAfterValue": "203", + "UMask": "0x1" + }, + { + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture). This includes high current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x09", + "EventName": "MEMORY_DISAMBIGUATION.HISTORY_RESET", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xFE", + "EventName": "IDI_MISC.WB_UPGRADE", + "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.", + "SampleAfterValue": "100003", + "UMask": "0x2" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json new file mode 100644 index 000000000..3bfc6943d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json @@ -0,0 +1,959 @@ +[ + { + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.ANY_P", + "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x14", + "EventName": "ARITH.DIVIDER_ACTIVE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x07", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Far branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PEBS": "1", + "PublicDescription": "This event counts far branch instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x40" + }, + { + "BriefDescription": "Counts the number of x87 uops dispatched.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4C", + "EventName": "LOAD_HIT_PRE.SW_PF", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Mispredicted direct and indirect near call instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.", + "SampleAfterValue": "400009", + "UMask": "0x2" + }, + { + "BriefDescription": "Total execution stalls.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "5", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x5" + }, + { + "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.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.SLOW_LEA", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles with less than 10 actually retired uops.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "10", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "Invert": "1", + "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Thread cycles when thread is not in halt state", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "This is an architectural event that 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. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "SampleAfterValue": "25003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of machine clears (nukes) of any type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.COUNT", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Number of uops to be executed per-thread each cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "8", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_ACTIVE", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "SampleAfterValue": "25003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 0", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 1", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 2", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 3", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 4", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 5", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 6", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_6", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Cycles per thread when uops are executed in port 7", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_7", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "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).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", + "Counter": "1", + "CounterHTOff": "1", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.PREC_DIST", + "PEBS": "2", + "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_4_UOPS", + "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_END", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "25003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x59", + "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PublicDescription": "This event counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "Fixed counter 2", + "CounterHTOff": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "All mispredicted macro branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.ANY", + "SampleAfterValue": "100003", + "UMask": "0x3f" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of Uops delivered by the LSD.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA8", + "EventName": "LSD.UOPS", + "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "UMask": "0x2" + }, + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x87", + "EventName": "ILD_STALL.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "16", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Taken branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "This event counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "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": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core cycles when the thread is not in halt state", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "AnyThread": "1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "25003", + "UMask": "0x1" + }, + { + "BriefDescription": "Direct and indirect near call instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "This event counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.PAUSE_INST", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Resource-related stall cycles", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.ANY", + "PublicDescription": "Counts resource-related stall cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Self-modifying code (SMC) detected.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "20", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x14" + }, + { + "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.", + "Counter": "0,2,3", + "CounterHTOff": "0,2,3", + "CounterMask": "10", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.TOTAL_CYCLES_PS", + "Invert": "1", + "PEBS": "2", + "PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retirement slots used.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "Counts the retirement slots used.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Increments whenever there is an update to the LBR array.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Return instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PEBS": "1", + "PublicDescription": "This event counts return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "Instructions retired from execution.", + "Counter": "Fixed counter 0", + "CounterHTOff": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", + "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", + "SampleAfterValue": "100007" + }, + { + "BriefDescription": "All (macro) branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x4" + }, + { + "BriefDescription": "Mispredicted macro branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "PublicDescription": "This event counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" + }, + { + "BriefDescription": "Conditional branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "PEBS": "1", + "PublicDescription": "This event counts conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "PEBS": "1", + "PublicDescription": "This event counts mispredicted conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of uops executed on the core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Number of uops executed from any thread.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "12", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "SampleAfterValue": "2000003", + "UMask": "0xc" + }, + { + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "All (macro) branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x1" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json new file mode 100644 index 000000000..0dd8b13b5 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -0,0 +1,408 @@ +[ + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "MetricGroup": "TopdownL1", + "MetricName": "Frontend_Bound", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_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." + }, + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Frontend_Bound_SMT", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_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. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "MetricGroup": "TopdownL1", + "MetricName": "Bad_Speculation", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example." + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Bad_Speculation_SMT", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_NMI_WATCHDOG", + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", + "MetricGroup": "TopdownL1", + "MetricName": "Backend_Bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound." + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Backend_Bound_SMT", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "MetricGroup": "TopdownL1", + "MetricName": "Retiring", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. " + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricGroup": "TopdownL1_SMT", + "MetricName": "Retiring_SMT", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU." + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Retire", + "MetricName": "UPI" + }, + { + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fetch_BW;PGO", + "MetricName": "IpTB" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "TopDownL1_SMT", + "MetricName": "SLOTS_SMT" + }, + { + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "Instruction_Type", + "MetricName": "IpLoad" + }, + { + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "Instruction_Type", + "MetricName": "IpStore" + }, + { + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Instruction_Type", + "MetricName": "IpBranch" + }, + { + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { + "BriefDescription": "Branch instructions per taken branch. ", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTkBranch" + }, + { + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )", + "MetricGroup": "FLOPS;FP_Arith;Instruction_Type", + "MetricName": "IpFLOP" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TopDownL1", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fetch_BW", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / cycles", + "MetricGroup": "SMT;TopDownL1", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "SMT;TopDownL1", + "MetricName": "CoreIPC_SMT" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / cycles", + "MetricGroup": "FLOPS", + "MetricName": "FLOPc" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "FLOPS_SMT", + "MetricName": "FLOPc_SMT" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 )", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)", + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "BrMispredicts", + "MetricName": "Branch_Misprediction_Cost" + }, + { + "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)", + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * ( IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - ( FRONTEND_RETIRED.LATENCY_GE_1 - FRONTEND_RETIRED.LATENCY_GE_2 ) / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) * (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "BrMispredicts_SMT", + "MetricName": "Branch_Misprediction_Cost_SMT" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "BrMispredicts", + "MetricName": "IpMispredict" + }, + { + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", + "MetricGroup": "Memory_Bound;Memory_Lat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Memory_Bound;Memory_BW", + "MetricName": "MLP" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_NMI_WATCHDOG", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", + "MetricGroup": "TLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )", + "MetricGroup": "TLB_SMT", + "MetricName": "Page_Walks_Utilization_SMT" + }, + { + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "MetricGroup": "Memory_BW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "MetricGroup": "Memory_BW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "MetricGroup": "Memory_BW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "L3_Cache_Access_BW" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "Cache_Misses", + "MetricName": "L1MPKI" + }, + { + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Cache_Misses", + "MetricName": "L2MPKI" + }, + { + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "Cache_Misses;Offcore", + "MetricName": "L2MPKI_All" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "MetricGroup": "Cache_Misses", + "MetricName": "L2HPKI_All" + }, + { + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "Cache_Misses", + "MetricName": "L3MPKI" + }, + { + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1000 * L2_LINES_OUT.SILENT / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "L2_Evictions_Silent_PKI" + }, + { + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1000 * L2_LINES_OUT.NON_SILENT / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "L2_Evictions_NonSilent_PKI" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 )", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time", + "MetricGroup": "Memory_BW;SoC", + "MetricName": "DRAM_BW_Use" + }, + { + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", + "MetricExpr": "1000000000 * ( cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433@ / cha@event\\=0x35\\,umask\\=0x21\\,config\\=0x40433@ ) / ( cha_0@event\\=0x0@ / duration_time )", + "MetricGroup": "Memory_Lat;SoC", + "MetricName": "MEM_Read_Latency" + }, + { + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricExpr": "cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433@ / cha@event\\=0x36\\,umask\\=0x21\\,config\\=0x40433\\,thresh\\=1@", + "MetricGroup": "Memory_BW;SoC", + "MetricName": "MEM_Parallel_Reads" + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "( UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3 ) * 4 / 1000000000 / duration_time", + "MetricGroup": "IO_BW;SoC;Server", + "MetricName": "IO_Write_BW" + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", + "MetricExpr": "( UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3 ) * 4 / 1000000000 / duration_time", + "MetricGroup": "IO_BW;SoC;Server", + "MetricName": "IO_Read_BW" + }, + { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cha_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "Socket_CLKS" + }, + { + "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 / 2 )", + "MetricGroup": "Branches;OS", + "MetricName": "IpFarBranch" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json new file mode 100644 index 000000000..b80b5d663 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json @@ -0,0 +1,162 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Page Activate commands sent due to a write request", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "Counts DRAM Page Activate commands sent on this channel due to a write request to the iMC (Memory Controller). Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS (Column Access Select) command.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM CAS Commands issued", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "Counts all CAS (Column Address Select) commands issued to DRAM per memory channel. CAS commands are issued to specify the address to read or write on DRAM, so this event increments for every read and write. This event counts whether AutoPrecharge (which closes the DRAM Page automatically after a read/write) is enabled or not.", + "UMask": "0xF", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM Read CAS Commands issued (does not include underfills)", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD_REG", + "PerPkg": "1", + "PublicDescription": "Counts CAS (Column Access Select) regular read commands issued to DRAM on a per channel basis. CAS commands are issued to specify the address to read or write on DRAM, and this event increments for every regular read. This event only counts regular reads and does not includes underfill reads due to partial write requests. This event counts whether AutoPrecharge (which closes the DRAM Page automatically after a read/write) is enabled or not.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Underfill Read CAS Commands issued", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL", + "PerPkg": "1", + "PublicDescription": "Counts CAS (Column Access Select) underfill read commands issued to DRAM due to a partial write, on a per channel basis. CAS commands are issued to specify the address to read or write on DRAM, and this command counts underfill reads. Partial writes must be completed by first reading in the underfill from DRAM and then merging in the partial write data before writing the full line back to DRAM. This event will generally count about the same as the number of partial writes, but may be slightly less because of partials hitting in the WPQ (due to a previous write request).", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM CAS (Column Address Strobe) Commands.; DRAM WR_CAS (w/ and w/out auto-pre) in Write Major Mode", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.WR_WMM", + "PerPkg": "1", + "PublicDescription": "Counts the total number or DRAM Write CAS commands issued on this channel while in Write-Major-Mode.", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_M_RPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of read requests allocated into the Read Pending Queue (RPQ). This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. The requests deallocate after the read CAS command has been issued to DRAM. This event counts both Isochronous and non-Isochronous requests which were issued to the RPQ.", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_M_RPQ_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries in the Read Pending Queue (RPQ) at each cycle. This can then be used to calculate both the average occupancy of the queue (in conjunction with the number of cycles not empty) and the average latency in the queue (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate from the RPQ after the CAS command has been issued to memory.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "UNC_M_WPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of writes requests allocated into the Write Pending Queue (WPQ). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (Memory Controller). The write requests deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x81", + "EventName": "UNC_M_WPQ_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happenning in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts???", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json new file mode 100644 index 000000000..d7a0270de --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json @@ -0,0 +1,1720 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "config1=0x40e33", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "config1=0x40040e33", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "config1=0x40041e33", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "config1=0x41833", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "config1=0x41a33", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x03", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0x0C", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x04", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "7.11E-06Bytes", + "UMask": "0xf", + "Unit": "UPI LL" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_READ", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "MetricName": "LLC_MISSES.PCIE_READ", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_WRITE", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 +UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "MetricName": "LLC_MISSES.PCIE_WRITE", + "PerPkg": "1", + "PortMask": "0x01", + "ScaleUnit": "4Bytes", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple Core Requests", + "Counter": "0,1,2,3", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple Eviction", + "Counter": "0,1,2,3", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", + "Counter": "0,1,2,3", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", + "Counter": "0,1,2,3", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.HA", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.TOR", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "FaST wire asserted; Horizontal", + "Counter": "0,1,2,3", + "EventCode": "0xA5", + "EventName": "UNC_CHA_FAST_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", + "Counter": "0,1,2,3", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.EX_RDS", + "PerPkg": "1", + "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*)", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", + "Counter": "0,1,2,3", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH", + "Counter": "0,1,2,3", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in E state", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in F State", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_F", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in M state", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in S State", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x04", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of times that an RFO hit in S state.", + "Counter": "0,1,2,3", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RFO_HIT_S", + "PerPkg": "1", + "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "Counter": "0,1,2,3", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; IRQ", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "Counter": "0,1,2,3", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy; IRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for E-state entries.", + "Counter": "0,1,2,3", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.E_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x02", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for M-state entries.", + "Counter": "0,1,2,3", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.M_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for S-state entries.", + "Counter": "0,1,2,3", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.S_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x04", + "Unit": "CHA" + }, + { + "BriefDescription": "RspCnflct* Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCTS", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspCnflct* Snoop Response was received. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent. This triggers conflict resolution hardware. This covers both the opcode RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RspI Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPI", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", + "UMask": "0x01", + "Unit": "CHA" + }, + { + "BriefDescription": "RspIFwd Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", + "UMask": "0x04", + "Unit": "CHA" + }, + { + "BriefDescription": "RspSFwd Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", + "UMask": "0x08", + "Unit": "CHA" + }, + { + "BriefDescription": "Rsp*Fwd*WB Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to it's home socket, and the cacheline was forwarded to the requestor socket. This snoop response is only used in >= 4 socket systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to it's home socket to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Rsp*WB Snoop Responses Received", + "Counter": "0,1,2,3", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSP_WBWB", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to it's home. This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured. This response will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Clockticks of the IIO Traffic Controller", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the 1GHz trafiic controller clock in the IIO unit.", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part1", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part2", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part3", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part1 by a different IIO unit", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part2 by a different IIO unit", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part3 by a different IIO unit", + "Counter": "2,3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part1 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part2 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part3 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part0", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part1", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part2", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part3", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part0 by a different IIO unit", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part1 by a different IIO unit", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part2 by a different IIO unit", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part3 by a different IIO unit", + "Counter": "0,1,2,3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x04", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x01", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x08", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part1 to the MMIO space of an IIO target.In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x02", + "Unit": "IIO" + }, + { + "BriefDescription": "Traffic in which the M2M to iMC Bypass was not taken", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_Egress.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts traffic in which the M2M (Mesh to Memory) to iMC (Memory Controller) bypass was not taken", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "PublicDescription": "Counts cycles when direct to core mode (which bypasses the CHA) was disabled", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to core (bypassing the CHA)", + "Counter": "0,1,2,3", + "EventCode": "0x23", + "EventName": "UNC_M2M_DIRECT2CORE_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts when messages were sent direct to core (bypassing the CHA)", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction were overridden", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Counts reads in which direct to core transactions (which would have bypassed the CHA) were overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "Counter": "0,1,2,3", + "EventCode": "0x28", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "PublicDescription": "Counts reads in which direct to Intel Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to Intel UPI was disabled", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel Ultra Path Interconnect (bypassing the CHA) was disabled", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to the Intel UPI", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts when messages were sent direct to the Intel Ultra Path Interconnect (bypassing the CHA)", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Counts when a read message that was sent direct to the Intel Ultra Path Interconnect (bypassing the CHA) was overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in Any State (A, I, S or unused)", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in the A (SnoopAll) state, indicating the cacheline is stored in another socket in any state, and we must snoop the other sockets to make sure we get the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the I (Invalid) state indicating the cacheline is not stored in another socket, and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", + "Counter": "0,1,2,3", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the S (Shared) state indicating the cacheline is either stored in another socket in the S(hared) state , and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to I", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from A (SnoopAll) to I (Invalid)", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to S", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from A (SnoopAll) to S (Shared)", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory to a new state", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to A", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from I (Invalid) to A (SnoopAll)", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to S", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from I (Invalid) to S (Shared)", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to A", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from S (Shared) to A (SnoopAll)", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to I", + "Counter": "0,1,2,3", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from from S (Shared) to I (Invalid)", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ALL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller).", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued at Normal Priority (Non-Isochronous)", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). It only counts normal priority non-isochronous reads.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Writes to iMC issued", + "Counter": "0,1,2,3", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.ALL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues writes to the iMC (Memory Controller).", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; All, regardless of priority.", + "Counter": "0,1,2,3", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.NI", + "PerPkg": "1", + "PublicDescription": "M2M Writes Issued to iMC; All, regardless of priority.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Partial Non-Isochronous writes to the iMC", + "Counter": "0,1,2,3", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues partial writes to the iMC (Memory Controller). It only counts normal priority non-isochronous writes.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefecth requests that got turn into a demand request", + "Counter": "0,1,2,3", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_DEMAND_PROMOTIONS", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address. Explanatory Side Note: The Prefecth queue is made of CAM (Content Addressable Memory)", + "Unit": "M2M" + }, + { + "BriefDescription": "Inserts into the Memory Controller Prefetch Queue", + "Counter": "0,1,2,3", + "EventCode": "0x57", + "EventName": "UNC_M2M_PREFCAM_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) receives a prefetch request and inserts it into its outstanding prefetch queue. Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Queue Inserts", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M2M_RxC_AD_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop). This is generally used for reads, and", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "AD Ingress (from CMS) Occupancy", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_M2M_RxC_BL_INSERTS", + "PerPkg": "1", + "PublicDescription": "BL Ingress (from CMS) Allocations", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_M2M_RxC_BL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "BL Ingress (from CMS) Occupancy", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_M2M_TxC_AD_INSERTS", + "PerPkg": "1", + "PublicDescription": "AD Egress (to CMS) Allocations", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_M2M_TxC_AD_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "AD Egress (to CMS) Occupancy", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations; All", + "Counter": "0,1,2,3", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "BL Egress (to CMS) Allocations; All", + "UMask": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy; All", + "Counter": "0,1,2,3", + "EventCode": "0x16", + "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.ALL", + "PerPkg": "1", + "PublicDescription": "BL Egress (to CMS) Occupancy; All", + "UMask": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.", + "Counter": "0,1,2", + "EventCode": "0x29", + "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", + "PerPkg": "1", + "PublicDescription": "Count cases where flow control queue that sits between the Intel Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Clocks of the Intel Ultra Path Interconnect (UPI)", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Data Response packets that go direct to core", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", + "PerPkg": "1", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to core bypassing the CHA.", + "UMask": "0x1", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Data Response packets that go direct to Intel UPI", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U", + "PerPkg": "1", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel Ultra Path Interconnect (UPI) bypassing the CHA .", + "UMask": "0x2", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Cycles Intel UPI is in L1 power mode (shutdown)", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_UPI_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the Intel Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Cycles the Rx of the Intel UPI is in L0p power mode", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the the receive side (Rx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x1", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer (Receive Queue) and passed directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x2", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot2 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x4", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid data FLITs received from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "UMask": "0x0F", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Null FLITs received from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "UMask": "0x27", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Protocol header and credit FLITs received from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) received from any of the 3 UPI slots on this UPI unit.", + "UMask": "0x97", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Cycles in which the Tx of the Intel Ultra Path Interconnect (UPI) is in L0p power mode", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FLITs that bypassed the TxL Buffer", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_UPI_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Null FLITs transmitted from any slot", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel Ulra Path Interconnect (UPI) slots on this UPI unit.", + "UMask": "0x27", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent; Data", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Idle FLITs transmitted", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Counts when the Intel Ultra Path Interconnect(UPI) transmits an idle FLIT(80 bit FLow control unITs). Every UPI cycle must be sending either data FLITs, protocol/credit FLITs or idle FLITs.", + "UMask": "0x47", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Protocol header and credit FLITs transmitted across any slot", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) transmitted across any of the 3 UPI (Ultra Path Interconnect) slots on this UPI unit.", + "UMask": "0x97", + "Unit": "UPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json new file mode 100644 index 000000000..bbeee1058 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json @@ -0,0 +1,284 @@ +[ + { + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Store misses in all DTLB levels that cause page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAE", + "EventName": "ITLB.ITLB_FLUSH", + "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "DTLB flush attempts of the thread-specific entries", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Misses at all ITLB levels that cause page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Page walk completed due to a demand data store to a 4K page", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Page walk completed due to a demand data load to a 4K page", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Load misses in all DTLB levels that cause page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4F", + "EventName": "EPT.WALK_PENDING", + "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "STLB flush attempts", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.STLB_ANY", + "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", + "SampleAfterValue": "100007", + "UMask": "0x20" + }, + { + "BriefDescription": "Page walk completed due to a demand data load to a 1G page", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Page walk completed due to a demand data store to a 1G page", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" + } +]
\ No newline at end of file |