diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 9056784e23f7..1040f68fee94 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -21,7 +21,7 @@ GenuineIntel-6-3E,v24,ivytown,core GenuineIntel-6-2D,v24,jaketown,core GenuineIntel-6-(57|85),v16,knightslanding,core GenuineIntel-6-BD,v1.01,lunarlake,core -GenuineIntel-6-A[AC],v1.08,meteorlake,core +GenuineIntel-6-A[AC],v1.10,meteorlake,core GenuineIntel-6-1[AEF],v4,nehalemep,core GenuineIntel-6-2E,v4,nehalemex,core GenuineIntel-6-A7,v1.02,rocketlake,core diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json index af7acb15f661..908e3c7f6d6e 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "L1D.HWPF_MISS", + "Counter": "0,1,2,3", "EventCode": "0x51", "EventName": "L1D.HWPF_MISS", "SampleAfterValue": "1000003", @@ -9,6 +10,7 @@ }, { "BriefDescription": "Counts the number of cache lines replaced in L1 data cache.", + "Counter": "0,1,2,3", "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.", @@ -18,6 +20,7 @@ }, { "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", @@ -27,6 +30,7 @@ }, { "BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x48", @@ -38,6 +42,7 @@ }, { "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.", + "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.L2_STALLS", "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", @@ -47,6 +52,7 @@ }, { "BriefDescription": "Number of L1D misses that are outstanding", + "Counter": "0,1,2,3", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the 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.", @@ -56,6 +62,7 @@ }, { "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING_CYCLES", @@ -66,6 +73,7 @@ }, { "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3", "EventCode": "0x25", "EventName": "L2_LINES_IN.ALL", "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", @@ -75,6 +83,7 @@ }, { "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.", + "Counter": "0,1,2,3", "EventCode": "0x26", "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 are in Modified state. Modified lines are written back to L3", @@ -84,6 +93,7 @@ }, { "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "Counter": "0,1,2,3", "EventCode": "0x26", "EventName": "L2_LINES_OUT.SILENT", "PublicDescription": "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 or Exclusive state. A non-threaded event.", @@ -91,8 +101,19 @@ "UMask": "0x1", "Unit": "cpu_core" }, + { + "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "SampleAfterValue": "200003", + "UMask": "0x4", + "Unit": "cpu_core" + }, { "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES]", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", @@ -102,6 +123,7 @@ }, { "BriefDescription": "All requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.HIT", "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]", @@ -111,6 +133,7 @@ }, { "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", @@ -120,6 +143,7 @@ }, { "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", "PublicDescription": "Counts the total number of L2 code requests.", @@ -129,6 +153,7 @@ }, { "BriefDescription": "Demand Data Read access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", @@ -138,6 +163,7 @@ }, { "BriefDescription": "Demand requests that miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_MISS", "PublicDescription": "Counts demand requests that miss L2 cache.", @@ -147,6 +173,7 @@ }, { "BriefDescription": "Demand requests to L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", "PublicDescription": "Counts demand requests to L2 cache.", @@ -156,6 +183,7 @@ }, { "BriefDescription": "L2_RQSTS.ALL_HWPF", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_HWPF", "SampleAfterValue": "200003", @@ -164,6 +192,7 @@ }, { "BriefDescription": "RFO requests to L2 cache", + "Counter": "0,1,2,3", "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.", @@ -173,6 +202,7 @@ }, { "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", @@ -182,6 +212,7 @@ }, { "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_MISS", "PublicDescription": "Counts L2 cache misses when fetching instructions.", @@ -191,6 +222,7 @@ }, { "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3", "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.", @@ -200,6 +232,7 @@ }, { "BriefDescription": "Demand Data Read miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", @@ -209,6 +242,7 @@ }, { "BriefDescription": "All requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HIT", "PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]", @@ -218,6 +252,7 @@ }, { "BriefDescription": "L2_RQSTS.HWPF_MISS", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.HWPF_MISS", "SampleAfterValue": "200003", @@ -226,6 +261,7 @@ }, { "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_REQUEST.MISS]", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", @@ -235,6 +271,7 @@ }, { "BriefDescription": "All accesses to L2 cache [This event is alias to L2_REQUEST.ALL]", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", @@ -244,6 +281,7 @@ }, { "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", @@ -253,6 +291,7 @@ }, { "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_MISS", "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", @@ -260,8 +299,29 @@ "UMask": "0x22", "Unit": "cpu_core" }, + { + "BriefDescription": "SW prefetch requests that hit L2 cache.", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.SWPF_HIT", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "SampleAfterValue": "200003", + "UMask": "0xc8", + "Unit": "cpu_core" + }, + { + "BriefDescription": "SW prefetch requests that miss L2 cache.", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.SWPF_MISS", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "SampleAfterValue": "200003", + "UMask": "0x28", + "Unit": "cpu_core" + }, { "BriefDescription": "L2 writebacks that access L2 cache", + "Counter": "0,1,2,3", "EventCode": "0x23", "EventName": "L2_TRANS.L2_WB", "PublicDescription": "Counts L2 writebacks that access L2 cache.", @@ -271,6 +331,7 @@ }, { "BriefDescription": "Cycles when L1D is locked", + "Counter": "0,1,2,3", "EventCode": "0x42", "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION).", @@ -280,15 +341,17 @@ }, { "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", - "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", "SampleAfterValue": "200003", "UMask": "0x41", "Unit": "cpu_atom" }, { "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", + "Counter": "0,1,2,3,4,5,6,7", "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 to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", @@ -298,15 +361,17 @@ }, { "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", - "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", "SampleAfterValue": "200003", "UMask": "0x4f", "Unit": "cpu_atom" }, { "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)", + "Counter": "0,1,2,3,4,5,6,7", "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 to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", @@ -316,6 +381,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an instruction cache or TLB miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.ALL", "SampleAfterValue": "1000003", @@ -324,6 +390,7 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.L2_HIT", "PublicDescription": "Counts the number of cycles the core is stalled due to an instruction cache or Translation Lookaside Buffer (TLB) miss which hit in the L2 cache.", @@ -333,6 +400,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which hit in the LLC.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_HIT", "SampleAfterValue": "1000003", @@ -341,6 +409,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an icache or itlb miss which missed all the caches.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x35", "EventName": "MEM_BOUND_STALLS_IFETCH.LLC_MISS", "SampleAfterValue": "1000003", @@ -349,6 +418,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an L1 demand load miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.ALL", "SampleAfterValue": "1000003", @@ -357,6 +427,7 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.L2_HIT", "PublicDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 cache.", @@ -366,6 +437,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which hit in the LLC.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.LLC_HIT", "SampleAfterValue": "1000003", @@ -374,6 +446,7 @@ }, { "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x34", "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS", "SampleAfterValue": "1000003", @@ -382,6 +455,7 @@ }, { "BriefDescription": "Retired load instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", @@ -393,6 +467,7 @@ }, { "BriefDescription": "Retired store instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", @@ -404,6 +479,7 @@ }, { "BriefDescription": "All retired memory instructions.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ANY", @@ -415,6 +491,7 @@ }, { "BriefDescription": "Retired load instructions with locked access.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.LOCK_LOADS", @@ -426,6 +503,7 @@ }, { "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", @@ -437,6 +515,7 @@ }, { "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.SPLIT_STORES", @@ -448,6 +527,7 @@ }, { "BriefDescription": "Retired load instructions that hit the STLB.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS", @@ -459,6 +539,7 @@ }, { "BriefDescription": "Retired store instructions that hit the STLB.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES", @@ -470,6 +551,7 @@ }, { "BriefDescription": "Retired load instructions that miss the STLB.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", @@ -481,6 +563,7 @@ }, { "BriefDescription": "Retired store instructions that miss the STLB.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", @@ -492,6 +575,7 @@ }, { "BriefDescription": "Completed demand load uops that miss the L1 d-cache.", + "Counter": "0,1,2,3", "EventCode": "0x43", "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", @@ -501,6 +585,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", @@ -510,30 +595,9 @@ "UMask": "0x4", "Unit": "cpu_core" }, - { - "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", - "Data_LA": "1", - "EventCode": "0xd2", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", - "PEBS": "1", - "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", - "SampleAfterValue": "20011", - "UMask": "0x2", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3", - "Data_LA": "1", - "EventCode": "0xd2", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PEBS": "1", - "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", - "SampleAfterValue": "20011", - "UMask": "0x4", - "Unit": "cpu_core" - }, { "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", @@ -545,6 +609,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", @@ -556,6 +621,7 @@ }, { "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd2", "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", @@ -567,6 +633,7 @@ }, { "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", @@ -578,6 +645,7 @@ }, { "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd4", "EventName": "MEM_LOAD_MISC_RETIRED.UC", @@ -589,6 +657,7 @@ }, { "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.FB_HIT", @@ -600,6 +669,7 @@ }, { "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_HIT", @@ -611,6 +681,7 @@ }, { "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L1_MISS", @@ -622,6 +693,7 @@ }, { "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_HIT", @@ -633,6 +705,7 @@ }, { "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L2_MISS", @@ -644,6 +717,7 @@ }, { "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_HIT", @@ -655,6 +729,7 @@ }, { "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Counter": "0,1,2,3", "Data_LA": "1", "EventCode": "0xd1", "EventName": "MEM_LOAD_RETIRED.L3_MISS", @@ -666,69 +741,70 @@ }, { "BriefDescription": "Counts the number of load ops retired that miss the L3 cache and hit in DRAM", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd4", "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LOCAL_DRAM", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of load ops retired that hit the L1 data cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x1", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of load ops retired that miss in the L1 data cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x40", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of load ops retired that hit in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of load ops retired that miss in the L2 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x80", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of load ops retired that hit in the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x1c", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of loads that hit in a write combining buffer (WCB), excluding the first load that caused the WCB to allocate.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xd1", "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x20", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x04", "EventName": "MEM_SCHEDULER_BLOCK.ALL", "SampleAfterValue": "20003", @@ -737,6 +813,7 @@ }, { "BriefDescription": "Counts the number of cycles that uops are blocked due to a load buffer full condition.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x04", "EventName": "MEM_SCHEDULER_BLOCK.LD_BUF", "SampleAfterValue": "20003", @@ -745,6 +822,7 @@ }, { "BriefDescription": "Counts the number of cycles that uops are blocked due to an RSV full condition.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x04", "EventName": "MEM_SCHEDULER_BLOCK.RSV", "SampleAfterValue": "20003", @@ -753,6 +831,7 @@ }, { "BriefDescription": "Counts the number of cycles that uops are blocked due to a store buffer full condition.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x04", "EventName": "MEM_SCHEDULER_BLOCK.ST_BUF", "SampleAfterValue": "20003", @@ -761,6 +840,7 @@ }, { "BriefDescription": "MEM_STORE_RETIRED.L2_HIT", + "Counter": "0,1,2,3", "EventCode": "0x44", "EventName": "MEM_STORE_RETIRED.L2_HIT", "SampleAfterValue": "200003", @@ -769,196 +849,197 @@ }, { "BriefDescription": "Counts the number of load ops retired.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x81", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of store ops retired.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x82", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", "MSRIndex": "0x3F6", "MSRValue": "0x400", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", "MSRIndex": "0x3F6", "MSRValue": "0x800", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Counter": "0,1", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x5", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of load uops retired that performed one or more locks", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x21", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of memory uops retired that were splits.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x43", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of retired split load uops.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x41", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of retired split store uops.", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x42", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", + "Counter": "0,1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xd0", "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", - "PEBS": "2", "SampleAfterValue": "1000003", "UMask": "0x6", "Unit": "cpu_atom" }, { "BriefDescription": "Retired memory uops for any access", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe5", "EventName": "MEM_UOP_RETIRED.ANY", "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", @@ -968,6 +1049,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", "MSRIndex": "0x1a6,0x1a7", @@ -978,6 +1060,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", @@ -988,6 +1071,7 @@ }, { "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", @@ -998,6 +1082,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -1008,6 +1093,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -1018,6 +1104,7 @@ }, { "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -1028,6 +1115,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_HIT", "MSRIndex": "0x1a6,0x1a7", @@ -1038,6 +1126,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", @@ -1048,6 +1137,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", "MSRIndex": "0x1a6,0x1a7", @@ -1058,6 +1148,7 @@ }, { "BriefDescription": "Any memory transaction that reached the SQ.", + "Counter": "0,1,2,3", "EventCode": "0x21", "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..", @@ -1067,6 +1158,7 @@ }, { "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.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.", @@ -1076,6 +1168,7 @@ }, { "BriefDescription": "Cacheable and Non-Cacheable code read requests", + "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.", @@ -1085,6 +1178,7 @@ }, { "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3", "EventCode": "0x21", "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.", @@ -1094,6 +1188,7 @@ }, { "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", @@ -1103,6 +1198,7 @@ }, { "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", @@ -1113,6 +1209,7 @@ }, { "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", @@ -1123,6 +1220,7 @@ }, { "BriefDescription": "Cycles where at least 1 outstanding demand data read request is pending.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", @@ -1132,6 +1230,7 @@ }, { "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", @@ -1142,6 +1241,7 @@ }, { "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", "SampleAfterValue": "1000003", @@ -1150,6 +1250,7 @@ }, { "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", + "Counter": "0,1,2,3", "EventCode": "0x20", "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.", @@ -1159,6 +1260,7 @@ }, { "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.", + "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", @@ -1166,17 +1268,9 @@ "UMask": "0x1", "Unit": "cpu_core" }, - { - "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", - "CounterMask": "6", - "EventCode": "0x20", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", - "SampleAfterValue": "2000003", - "UMask": "0x1", - "Unit": "cpu_core" - }, { "BriefDescription": "Store Read transactions pending for off-core. Highly correlated.", + "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.", @@ -1186,6 +1280,7 @@ }, { "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "Counter": "0,1,2,3", "EventCode": "0x2c", "EventName": "SQ_MISC.BUS_LOCK", "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", @@ -1193,8 +1288,18 @@ "UMask": "0x10", "Unit": "cpu_core" }, + { + "BriefDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.ANY", + "SampleAfterValue": "100003", + "UMask": "0xf", + "Unit": "cpu_core" + }, { "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.NTA", "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", @@ -1204,6 +1309,7 @@ }, { "BriefDescription": "Number of PREFETCHW instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", "PublicDescription": "Counts the number of PREFETCHW instructions executed.", @@ -1213,6 +1319,7 @@ }, { "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T0", "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", @@ -1222,6 +1329,7 @@ }, { "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "Counter": "0,1,2,3", "EventCode": "0x40", "EventName": "SW_PREFETCH_ACCESS.T1_T2", "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", @@ -1231,6 +1339,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to an icache miss", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.ICACHE", "SampleAfterValue": "1000003", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json index 30e604d2120f..28dc5e06ee31 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/floating-point.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of cycles when any of the floating point dividers are active.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xcd", "EventName": "ARITH.FPDIV_ACTIVE", @@ -10,6 +11,7 @@ }, { "BriefDescription": "This event counts the cycles the floating point divider is busy.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.FPDIV_ACTIVE", @@ -19,6 +21,7 @@ }, { "BriefDescription": "Counts all microcode FP assists.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.FP", "PublicDescription": "Counts all microcode Floating Point assists.", @@ -28,6 +31,7 @@ }, { "BriefDescription": "ASSISTS.SSE_AVX_MIX", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.SSE_AVX_MIX", "SampleAfterValue": "1000003", @@ -36,6 +40,7 @@ }, { "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_0", "SampleAfterValue": "2000003", @@ -44,6 +49,7 @@ }, { "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_1", "SampleAfterValue": "2000003", @@ -52,6 +58,7 @@ }, { "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.PORT_5", "SampleAfterValue": "2000003", @@ -60,6 +67,7 @@ }, { "BriefDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V0", "SampleAfterValue": "2000003", @@ -68,6 +76,7 @@ }, { "BriefDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V1", "SampleAfterValue": "2000003", @@ -76,6 +85,7 @@ }, { "BriefDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb3", "EventName": "FP_ARITH_DISPATCHED.V2", "SampleAfterValue": "2000003", @@ -84,6 +94,7 @@ }, { "BriefDescription": "Counts 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 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "PublicDescription": "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 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", @@ -93,6 +104,7 @@ }, { "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": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", "PublicDescription": "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 HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", @@ -102,6 +114,7 @@ }, { "BriefDescription": "Counts 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 HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "PublicDescription": "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 HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", @@ -111,6 +124,7 @@ }, { "BriefDescription": "Counts 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 HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "PublicDescription": "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 HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", @@ -120,6 +134,7 @@ }, { "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD 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. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", @@ -129,6 +144,7 @@ }, { "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", @@ -138,6 +154,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", @@ -147,6 +164,7 @@ }, { "BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", @@ -156,6 +174,7 @@ }, { "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.VECTOR", "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", @@ -165,53 +184,108 @@ }, { "BriefDescription": "Counts the number of all types of floating point operations per uop with all default weighting", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc8", "EventName": "FP_FLOPS_RETIRED.ALL", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x3", "Unit": "cpu_atom" }, { "BriefDescription": "This event is deprecated. [This event is alias to FP_FLOPS_RETIRED.FP64]", + "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", "EventCode": "0xc8", "EventName": "FP_FLOPS_RETIRED.DP", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of floating point operations that produce 32 bit single precision results [This event is alias to FP_FLOPS_RETIRED.SP]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc8", "EventName": "FP_FLOPS_RETIRED.FP32", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of floating point operations that produce 64 bit double precision results [This event is alias to FP_FLOPS_RETIRED.DP]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc8", "EventName": "FP_FLOPS_RETIRED.FP64", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" }, { "BriefDescription": "This event is deprecated. [This event is alias to FP_FLOPS_RETIRED.FP32]", + "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", "EventCode": "0xc8", "EventName": "FP_FLOPS_RETIRED.SP", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_atom" }, + { + "BriefDescription": "Counts the total number of floating point retired instructions.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit single precision floating point. This may be SSE or AVX.128 operations.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.128B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit double precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.256B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x20", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 32bit single precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.32B_SP", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 64 bit double precision floating point.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_INST_RETIRED.64B_DP", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of uops executed on floating point and vector integer store data port.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "FP_VINT_UOPS_EXECUTED.STD", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, { "BriefDescription": "Counts the number of floating point operations retired that required microcode assist.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.FP_ASSIST", "PublicDescription": "Counts the number of floating point operations retired that required microcode assist, which is not a reflection of the number of FP operations, instructions or uops.", @@ -221,9 +295,9 @@ }, { "BriefDescription": "Counts the number of floating point divide uops retired (x87 and sse, including x87 sqrt).", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.FPDIV", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_atom" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json index f3b7b211afb5..b6c52f7385fc 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the total number of BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe6", "EventName": "BACLEARS.ANY", "PublicDescription": "Counts the total number of BACLEARS, which occur when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", @@ -10,6 +11,7 @@ }, { "BriefDescription": "Clears due to Unknown Branches.", + "Counter": "0,1,2,3", "EventCode": "0x60", "EventName": "BACLEARS.ANY", "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", @@ -19,6 +21,7 @@ }, { "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.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.", @@ -28,6 +31,7 @@ }, { "BriefDescription": "Cycles the Microcode Sequencer is busy.", + "Counter": "0,1,2,3", "EventCode": "0x87", "EventName": "DECODE.MS_BUSY", "SampleAfterValue": "500009", @@ -36,6 +40,7 @@ }, { "BriefDescription": "DSB-to-MITE switch true penalty cycles.", + "Counter": "0,1,2,3", "EventCode": "0x61", "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", @@ -43,16 +48,9 @@ "UMask": "0x2", "Unit": "cpu_core" }, - { - "BriefDescription": "DSB_FILL.FB_STALL_OT", - "EventCode": "0x62", - "EventName": "DSB_FILL.FB_STALL_OT", - "SampleAfterValue": "1000003", - "UMask": "0x10", - "Unit": "cpu_core" - }, { "BriefDescription": "Retired ANT branches", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.ANY_ANT", "MSRIndex": "0x3F7", @@ -65,6 +63,7 @@ }, { "BriefDescription": "Retired Instructions who experienced DSB miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", "MSRIndex": "0x3F7", @@ -77,6 +76,7 @@ }, { "BriefDescription": "Retired Instructions who experienced a critical DSB miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.DSB_MISS", "MSRIndex": "0x3F7", @@ -89,15 +89,16 @@ }, { "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.ITLB_MISS", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x10", "Unit": "cpu_atom" }, { "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.ITLB_MISS", "MSRIndex": "0x3F7", @@ -110,6 +111,7 @@ }, { "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", @@ -122,6 +124,7 @@ }, { "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.L2_MISS", "MSRIndex": "0x3F7", @@ -134,6 +137,7 @@ }, { "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", @@ -146,6 +150,7 @@ }, { "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": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", "MSRIndex": "0x3F7", @@ -158,6 +163,7 @@ }, { "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": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", @@ -170,6 +176,7 @@ }, { "BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", @@ -182,6 +189,7 @@ }, { "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": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", @@ -194,6 +202,7 @@ }, { "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": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", @@ -206,6 +215,7 @@ }, { "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": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", @@ -218,6 +228,7 @@ }, { "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": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", @@ -230,6 +241,7 @@ }, { "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": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", @@ -242,6 +254,7 @@ }, { "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": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", @@ -254,6 +267,7 @@ }, { "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": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", @@ -266,6 +280,7 @@ }, { "BriefDescription": "Mispredicted Retired ANT branches", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.MISP_ANT", "MSRIndex": "0x3F7", @@ -278,6 +293,7 @@ }, { "BriefDescription": "FRONTEND_RETIRED.MS_FLOWS", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.MS_FLOWS", "MSRIndex": "0x3F7", @@ -289,6 +305,7 @@ }, { "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", @@ -301,6 +318,7 @@ }, { "BriefDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc6", "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", "MSRIndex": "0x3F7", @@ -312,6 +330,7 @@ }, { "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x80", "EventName": "ICACHE.ACCESSES", "SampleAfterValue": "200003", @@ -320,6 +339,7 @@ }, { "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x80", "EventName": "ICACHE.MISSES", "SampleAfterValue": "200003", @@ -328,6 +348,7 @@ }, { "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "Counter": "0,1,2,3", "EventCode": "0x80", "EventName": "ICACHE_DATA.STALLS", "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", @@ -337,6 +358,7 @@ }, { "BriefDescription": "ICACHE_DATA.STALL_PERIODS", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x80", @@ -345,17 +367,9 @@ "UMask": "0x4", "Unit": "cpu_core" }, - { - "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", - "EventCode": "0x83", - "EventName": "ICACHE_TAG.HIT", - "PublicDescription": "Counts instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.", - "SampleAfterValue": "200003", - "UMask": "0x1", - "Unit": "cpu_core" - }, { "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "Counter": "0,1,2,3", "EventCode": "0x83", "EventName": "ICACHE_TAG.STALLS", "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", @@ -365,6 +379,7 @@ }, { "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_ANY", @@ -375,6 +390,7 @@ }, { "BriefDescription": "Cycles DSB is delivering optimal number of Uops", + "Counter": "0,1,2,3", "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES_OK", @@ -385,6 +401,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", "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.", @@ -394,6 +411,7 @@ }, { "BriefDescription": "Cycles MITE is delivering any Uop", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_ANY", @@ -404,6 +422,7 @@ }, { "BriefDescription": "Cycles MITE is delivering optimal number of Uops", + "Counter": "0,1,2,3", "CounterMask": "6", "EventCode": "0x79", "EventName": "IDQ.MITE_CYCLES_OK", @@ -414,6 +433,7 @@ }, { "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MITE_UOPS", "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", @@ -423,6 +443,7 @@ }, { "BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES_ANY", @@ -433,6 +454,7 @@ }, { "BriefDescription": "Number of switches from DSB or MITE to the MS", + "Counter": "0,1,2,3", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79", @@ -444,6 +466,7 @@ }, { "BriefDescription": "Uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", @@ -452,16 +475,18 @@ "Unit": "cpu_core" }, { - "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", + "BriefDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" }, { "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", @@ -472,6 +497,7 @@ }, { "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", @@ -483,6 +509,7 @@ }, { "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled", + "Counter": "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 by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", @@ -492,6 +519,7 @@ }, { "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", @@ -502,6 +530,7 @@ }, { "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json index 617d0e255fd5..b464a8ab32ca 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", "CounterMask": "2", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", @@ -10,6 +11,7 @@ }, { "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", "CounterMask": "6", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", @@ -19,6 +21,7 @@ }, { "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block, on a load that retires.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x05", "EventName": "LD_HEAD.ANY_AT_RET", "SampleAfterValue": "1000003", @@ -27,6 +30,7 @@ }, { "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a core bound stall including a store address match, a DTLB miss or a page walk that detains the load from retiring.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x05", "EventName": "LD_HEAD.L1_BOUND_AT_RET", "SampleAfterValue": "1000003", @@ -35,6 +39,7 @@ }, { "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DL1 miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x05", "EventName": "LD_HEAD.L1_MISS_AT_RET", "SampleAfterValue": "1000003", @@ -43,6 +48,7 @@ }, { "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x05", "EventName": "LD_HEAD.OTHER_AT_RET", "PublicDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases such as pipeline conflicts, fences, etc.", @@ -52,6 +58,7 @@ }, { "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a pagewalk.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x05", "EventName": "LD_HEAD.PGWALK_AT_RET", "SampleAfterValue": "1000003", @@ -60,6 +67,7 @@ }, { "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a store address match.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x05", "EventName": "LD_HEAD.ST_ADDR_AT_RET", "SampleAfterValue": "1000003", @@ -68,6 +76,7 @@ }, { "BriefDescription": "Counts the number of machine clears due to memory ordering caused by a snoop from an external agent. Does not count internally generated machine clears such as those due to memory disambiguation.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", "SampleAfterValue": "20003", @@ -76,6 +85,7 @@ }, { "BriefDescription": "Number of machine clears due to memory ordering conflicts.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", @@ -85,6 +95,7 @@ }, { "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", "CounterMask": "2", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", @@ -94,6 +105,7 @@ }, { "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", "CounterMask": "3", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", @@ -103,6 +115,7 @@ }, { "BriefDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding.", + "Counter": "0,1,2,3", "CounterMask": "5", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", @@ -113,6 +126,7 @@ }, { "BriefDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding.", + "Counter": "0,1,2,3", "CounterMask": "9", "EventCode": "0x47", "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", @@ -121,24 +135,9 @@ "UMask": "0x9", "Unit": "cpu_core" }, - { - "BriefDescription": "MEMORY_ORDERING.MD_NUKE", - "EventCode": "0x09", - "EventName": "MEMORY_ORDERING.MD_NUKE", - "SampleAfterValue": "100003", - "UMask": "0x1", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Counts the number of memory ordering machine clears due to memory renaming.", - "EventCode": "0x09", - "EventName": "MEMORY_ORDERING.MRN_NUKE", - "SampleAfterValue": "100003", - "UMask": "0x2", - "Unit": "cpu_core" - }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.", + "Counter": "1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", @@ -152,6 +151,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "Counter": "1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", @@ -165,6 +165,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "Counter": "1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", @@ -178,6 +179,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.", + "Counter": "1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", @@ -191,6 +193,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "Counter": "1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", @@ -204,6 +207,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "Counter": "1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", @@ -217,6 +221,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "Counter": "1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", @@ -230,6 +235,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "Counter": "1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", @@ -243,6 +249,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "Counter": "1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", @@ -256,6 +263,7 @@ }, { "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "Counter": "1,2,3,4,5,6,7", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", @@ -269,6 +277,7 @@ }, { "BriefDescription": "Retired memory store access operations. A PDist event for PEBS Store Latency Facility.", + "Counter": "0", "Data_LA": "1", "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", @@ -280,24 +289,25 @@ }, { "BriefDescription": "Counts misaligned loads that are 4K page splits.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x13", "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_atom" }, { "BriefDescription": "Counts misaligned stores that are 4K page splits.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x13", "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x4", "Unit": "cpu_atom" }, { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -308,6 +318,7 @@ }, { "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -318,6 +329,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -328,6 +340,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -338,6 +351,7 @@ }, { "BriefDescription": "Counts demand data read requests that miss the L3 cache.", + "Counter": "0,1,2,3", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", "SampleAfterValue": "100003", @@ -346,6 +360,7 @@ }, { "BriefDescription": "Cycles where data return is pending for a Demand Data Read request who miss L3 cache.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", @@ -356,21 +371,12 @@ }, { "BriefDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.", + "Counter": "0,1,2,3", "EventCode": "0x20", "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_core" - }, - { - "BriefDescription": "Cycles where the core is waiting on at least 6 outstanding demand data read requests known to have missed the L3 cache.", - "CounterMask": "6", - "EventCode": "0x20", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", - "PublicDescription": "Cycles where the core is waiting on at least 6 outstanding demand data read requests known to have missed the L3 cache. Note that this event does not capture all elapsed cycles while the requests are outstanding - only cycles from when the requests were known to have missed the L3 cache.", - "SampleAfterValue": "2000003", - "UMask": "0x10", - "Unit": "cpu_core" } ] diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json index 0bc2cb2eabb3..53d23d8decc6 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "ASSISTS.PAGE_FAULT", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.PAGE_FAULT", "SampleAfterValue": "1000003", @@ -9,16 +10,17 @@ }, { "BriefDescription": "This event is deprecated. [This event is alias to MISC_RETIRED.LBR_INSERTS]", + "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", "EventCode": "0xe4", "EventName": "LBR_INSERTS.ANY", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" }, { "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -29,6 +31,7 @@ }, { "BriefDescription": "Counts demand data reads that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -39,6 +42,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -49,6 +53,7 @@ }, { "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -59,6 +64,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -69,6 +75,7 @@ }, { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -79,6 +86,7 @@ }, { "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -89,6 +97,7 @@ }, { "BriefDescription": "Counts streaming stores that have any type of response.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xB7", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -99,6 +108,7 @@ }, { "BriefDescription": "Counts streaming stores that have any type of response.", + "Counter": "0,1,2,3", "EventCode": "0x2A,0x2B", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -109,6 +119,7 @@ }, { "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY", "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", @@ -118,6 +129,7 @@ }, { "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0xa5", @@ -129,7 +141,8 @@ "Unit": "cpu_core" }, { - "BriefDescription": "RS.EMPTY_RESOURCE", + "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa5", "EventName": "RS.EMPTY_RESOURCE", "SampleAfterValue": "1000003", @@ -138,6 +151,7 @@ }, { "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x75", "EventName": "SERIALIZATION.C01_MS_SCB", "SampleAfterValue": "200003", @@ -146,6 +160,7 @@ }, { "BriefDescription": "Cycles the uncore cannot take further requests", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json index 5ff4a7a32250..bc806c7330f4 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of cycles when any of the dividers are active.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xcd", "EventName": "ARITH.DIV_ACTIVE", @@ -10,6 +11,7 @@ }, { "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.DIV_ACTIVE", @@ -20,6 +22,7 @@ }, { "BriefDescription": "This event counts the cycles the integer divider is busy.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", @@ -29,6 +32,7 @@ }, { "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc1", "EventName": "ASSISTS.ANY", "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", @@ -38,15 +42,16 @@ }, { "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", "SampleAfterValue": "200003", "Unit": "cpu_atom" }, { "BriefDescription": "All branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", "PEBS": "1", @@ -56,15 +61,16 @@ }, { "BriefDescription": "Counts the number of retired JCC (Jump on Conditional Code) branch instructions retired, includes both taken and not taken branches.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x7e", "Unit": "cpu_atom" }, { "BriefDescription": "Conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND", "PEBS": "1", @@ -75,6 +81,7 @@ }, { "BriefDescription": "Not taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_NTAKEN", "PEBS": "1", @@ -85,15 +92,16 @@ }, { "BriefDescription": "Counts the number of taken JCC (Jump on Conditional Code) branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfe", "Unit": "cpu_atom" }, { "BriefDescription": "Taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.COND_TAKEN", "PEBS": "1", @@ -104,15 +112,16 @@ }, { "BriefDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and interrupt call and return.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xbf", "Unit": "cpu_atom" }, { "BriefDescription": "Far branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "PEBS": "1", @@ -123,15 +132,16 @@ }, { "BriefDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xeb", "Unit": "cpu_atom" }, { "BriefDescription": "Indirect near branch instructions retired (excluding returns)", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT", "PEBS": "1", @@ -142,34 +152,35 @@ }, { "BriefDescription": "Counts the number of near indirect CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.INDIRECT_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" }, { "BriefDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT_CALL", + "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.IND_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of near CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf9", "Unit": "cpu_atom" }, { "BriefDescription": "Direct and indirect near call instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_CALL", "PEBS": "1", @@ -180,15 +191,16 @@ }, { "BriefDescription": "Counts the number of near RET branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf7", "Unit": "cpu_atom" }, { "BriefDescription": "Return instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", "PEBS": "1", @@ -199,6 +211,7 @@ }, { "BriefDescription": "Taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", "PEBS": "1", @@ -209,15 +222,16 @@ }, { "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "PEBS": "1", "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", "SampleAfterValue": "200003", "Unit": "cpu_atom" }, { "BriefDescription": "All mispredicted branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", "PEBS": "1", @@ -227,6 +241,7 @@ }, { "BriefDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST", "PEBS": "1", @@ -236,15 +251,16 @@ }, { "BriefDescription": "Counts the number of mispredicted JCC (Jump on Conditional Code) branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x7e", "Unit": "cpu_atom" }, { "BriefDescription": "Mispredicted conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND", "PEBS": "1", @@ -255,6 +271,7 @@ }, { "BriefDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_COST", "PEBS": "1", @@ -264,6 +281,7 @@ }, { "BriefDescription": "Mispredicted non-taken conditional branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN", "PEBS": "1", @@ -274,6 +292,7 @@ }, { "BriefDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST", "PEBS": "1", @@ -283,15 +302,16 @@ }, { "BriefDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfe", "Unit": "cpu_atom" }, { "BriefDescription": "number of branch instructions retired that were mispredicted and taken.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", "PEBS": "1", @@ -302,6 +322,7 @@ }, { "BriefDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST", "PEBS": "1", @@ -311,15 +332,16 @@ }, { "BriefDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xeb", "Unit": "cpu_atom" }, { "BriefDescription": "Miss-predicted near indirect branch instructions retired (excluding returns)", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT", "PEBS": "1", @@ -330,15 +352,16 @@ }, { "BriefDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xfb", "Unit": "cpu_atom" }, { "BriefDescription": "Mispredicted indirect CALL retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", "PEBS": "1", @@ -349,6 +372,7 @@ }, { "BriefDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST", "PEBS": "1", @@ -358,6 +382,7 @@ }, { "BriefDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.INDIRECT_COST", "PEBS": "1", @@ -367,15 +392,16 @@ }, { "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0x80", "Unit": "cpu_atom" }, { "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", "PEBS": "1", @@ -386,6 +412,7 @@ }, { "BriefDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST", "PEBS": "1", @@ -395,6 +422,7 @@ }, { "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET", "PEBS": "1", @@ -405,15 +433,16 @@ }, { "BriefDescription": "Counts the number of mispredicted near RET branch instructions retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RETURN", - "PEBS": "1", "SampleAfterValue": "200003", "UMask": "0xf7", "Unit": "cpu_atom" }, { "BriefDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.RET_COST", "PEBS": "1", @@ -423,6 +452,7 @@ }, { "BriefDescription": "Core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C01", "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", @@ -432,6 +462,7 @@ }, { "BriefDescription": "Core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C02", "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", @@ -441,6 +472,7 @@ }, { "BriefDescription": "Core clocks when the thread is in the C0.1 or C0.2 or running a PAUSE in C0 ACPI state.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.C0_WAIT", "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", @@ -450,6 +482,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.CORE", "SampleAfterValue": "2000003", "UMask": "0x2", @@ -457,6 +490,7 @@ }, { "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.CORE_P", "SampleAfterValue": "2000003", @@ -464,6 +498,7 @@ }, { "BriefDescription": "Cycle counts are evenly distributed between active threads in the Core.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", @@ -473,6 +508,7 @@ }, { "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", @@ -482,6 +518,7 @@ }, { "BriefDescription": "CPU_CLK_UNHALTED.PAUSE", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xec", "EventName": "CPU_CLK_UNHALTED.PAUSE", "SampleAfterValue": "2000003", @@ -490,6 +527,7 @@ }, { "BriefDescription": "CPU_CLK_UNHALTED.PAUSE_INST", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0xec", @@ -500,6 +538,7 @@ }, { "BriefDescription": "Core crystal clock cycles. Cycle counts are evenly distributed between active threads in the Core.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", @@ -509,6 +548,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles", + "Counter": "Fixed counter 2", "EventName": "CPU_CLK_UNHALTED.REF_TSC", "SampleAfterValue": "2000003", "UMask": "0x3", @@ -516,6 +556,7 @@ }, { "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "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. It is counted on a dedicated fixed counter, leaving the eight 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", @@ -524,6 +565,7 @@ }, { "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.", @@ -533,6 +575,7 @@ }, { "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", "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. 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.", @@ -542,6 +585,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "Counter": "Fixed counter 1", "EventName": "CPU_CLK_UNHALTED.THREAD", "SampleAfterValue": "2000003", "UMask": "0x2", @@ -549,6 +593,7 @@ }, { "BriefDescription": "Core cycles when the thread is not in halt state", + "Counter": "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 eight programmable counters available for other events.", "SampleAfterValue": "2000003", @@ -557,6 +602,7 @@ }, { "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", "SampleAfterValue": "2000003", @@ -564,6 +610,7 @@ }, { "BriefDescription": "Thread cycles when thread is not in halt state", + "Counter": "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.", @@ -572,6 +619,7 @@ }, { "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", "CounterMask": "8", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", @@ -581,6 +629,7 @@ }, { "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", @@ -590,6 +639,7 @@ }, { "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "16", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", @@ -599,6 +649,7 @@ }, { "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", "CounterMask": "12", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", @@ -608,6 +659,7 @@ }, { "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", "CounterMask": "5", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", @@ -617,6 +669,7 @@ }, { "BriefDescription": "Total execution stalls.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "4", "EventCode": "0xa3", "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", @@ -626,6 +679,7 @@ }, { "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "Counter": "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.", @@ -633,8 +687,18 @@ "UMask": "0x2", "Unit": "cpu_core" }, + { + "BriefDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL", + "SampleAfterValue": "2000003", + "UMask": "0xc", + "Unit": "cpu_core" + }, { "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "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.", @@ -644,6 +708,7 @@ }, { "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "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.", @@ -653,6 +718,7 @@ }, { "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "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.", @@ -662,6 +728,7 @@ }, { "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "5", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", @@ -671,6 +738,7 @@ }, { "BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "2", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", @@ -681,6 +749,7 @@ }, { "BriefDescription": "Cycles no uop executed while RS was not empty, the SB was not full and there was no outstanding load.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa6", "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", @@ -690,6 +759,7 @@ }, { "BriefDescription": "Instruction decoders utilized in a cycle", + "Counter": "0,1,2,3", "EventCode": "0x75", "EventName": "INST_DECODED.DECODERS", "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", @@ -699,6 +769,7 @@ }, { "BriefDescription": "Fixed Counter: Counts the number of instructions retired", + "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", "PEBS": "1", "SampleAfterValue": "2000003", @@ -707,6 +778,7 @@ }, { "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", + "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.ANY", "PEBS": "1", "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", @@ -716,14 +788,15 @@ }, { "BriefDescription": "Counts the number of instructions retired", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", - "PEBS": "1", "SampleAfterValue": "2000003", "Unit": "cpu_atom" }, { "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", "PEBS": "1", @@ -733,6 +806,7 @@ }, { "BriefDescription": "INST_RETIRED.MACRO_FUSED", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.MACRO_FUSED", "PEBS": "1", @@ -742,6 +816,7 @@ }, { "BriefDescription": "Retired NOP instructions.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.NOP", "PEBS": "1", @@ -752,6 +827,7 @@ }, { "BriefDescription": "Precise instruction retired with PEBS precise-distribution", + "Counter": "Fixed counter 0", "EventName": "INST_RETIRED.PREC_DIST", "PEBS": "1", "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", @@ -761,6 +837,7 @@ }, { "BriefDescription": "Iterations of Repeat string retired instructions.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", "PEBS": "1", @@ -769,18 +846,9 @@ "UMask": "0x8", "Unit": "cpu_core" }, - { - "BriefDescription": "Cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.", - "CounterMask": "1", - "EventCode": "0xad", - "EventName": "INT_MISC.ALL_RECOVERY_CYCLES", - "PublicDescription": "Counts cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.", - "SampleAfterValue": "2000003", - "UMask": "0x3", - "Unit": "cpu_core" - }, { "BriefDescription": "Clears speculative count", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0xad", @@ -792,6 +860,7 @@ }, { "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", @@ -799,17 +868,9 @@ "UMask": "0x80", "Unit": "cpu_core" }, - { - "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread", - "EventCode": "0xad", - "EventName": "INT_MISC.RAT_STALLS", - "PublicDescription": "This event counts the number of cycles during which Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the current thread. This also includes the cycles during which the Allocator is serving another thread.", - "SampleAfterValue": "1000003", - "UMask": "0x8", - "Unit": "cpu_core" - }, { "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.RECOVERY_CYCLES", "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", @@ -819,6 +880,7 @@ }, { "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", @@ -829,6 +891,7 @@ }, { "BriefDescription": "TMA slots where uops got dropped", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xad", "EventName": "INT_MISC.UOP_DROPPING", "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", @@ -838,6 +901,7 @@ }, { "BriefDescription": "INT_VEC_RETIRED.128BIT", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.128BIT", "SampleAfterValue": "1000003", @@ -846,6 +910,7 @@ }, { "BriefDescription": "INT_VEC_RETIRED.256BIT", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.256BIT", "SampleAfterValue": "1000003", @@ -854,6 +919,7 @@ }, { "BriefDescription": "integer ADD, SUB, SAD 128-bit vector instructions.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_128", "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", @@ -863,6 +929,7 @@ }, { "BriefDescription": "integer ADD, SUB, SAD 256-bit vector instructions.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.ADD_256", "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", @@ -872,6 +939,7 @@ }, { "BriefDescription": "INT_VEC_RETIRED.MUL_256", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.MUL_256", "SampleAfterValue": "1000003", @@ -880,6 +948,7 @@ }, { "BriefDescription": "INT_VEC_RETIRED.SHUFFLES", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.SHUFFLES", "SampleAfterValue": "1000003", @@ -888,6 +957,7 @@ }, { "BriefDescription": "INT_VEC_RETIRED.VNNI_128", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_128", "SampleAfterValue": "1000003", @@ -896,6 +966,7 @@ }, { "BriefDescription": "INT_VEC_RETIRED.VNNI_256", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe7", "EventName": "INT_VEC_RETIRED.VNNI_256", "SampleAfterValue": "1000003", @@ -904,15 +975,16 @@ }, { "BriefDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x4", "Unit": "cpu_atom" }, { "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "Counter": "0,1,2,3", "EventCode": "0x03", "EventName": "LD_BLOCKS.ADDRESS_ALIAS", "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", @@ -922,15 +994,16 @@ }, { "BriefDescription": "Counts the number of retired loads that are blocked because its address exactly matches an older store whose data is not ready.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x03", "EventName": "LD_BLOCKS.DATA_UNKNOWN", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" }, { "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", "EventCode": "0x03", "EventName": "LD_BLOCKS.NO_SR", "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", @@ -940,15 +1013,16 @@ }, { "BriefDescription": "Counts the number of retired loads that are blocked because its address partially overlapped with an older store.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_atom" }, { "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", + "Counter": "0,1,2,3", "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.", @@ -956,8 +1030,19 @@ "UMask": "0x82", "Unit": "cpu_core" }, + { + "BriefDescription": "Counts the number of demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", + "Counter": "0,1,2,3", + "EventCode": "0x4c", + "EventName": "LOAD_HIT_PREFETCH.SWPF", + "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", + "Unit": "cpu_core" + }, { "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xa8", "EventName": "LSD.CYCLES_ACTIVE", @@ -968,6 +1053,7 @@ }, { "BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "6", "EventCode": "0xa8", "EventName": "LSD.CYCLES_OK", @@ -978,6 +1064,7 @@ }, { "BriefDescription": "Number of Uops delivered by the LSD.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa8", "EventName": "LSD.UOPS", "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", @@ -985,8 +1072,17 @@ "UMask": "0x1", "Unit": "cpu_core" }, + { + "BriefDescription": "Counts the total number of machine clears for any reason including, but not limited to, memory ordering, memory disambiguation, SMC, and FP assist.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.ANY", + "SampleAfterValue": "20003", + "Unit": "cpu_atom" + }, { "BriefDescription": "Number of machine clears (nukes) of any type.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0xc3", @@ -998,14 +1094,25 @@ }, { "BriefDescription": "Counts the number of machine clears due to memory ordering in which an internal load passes an older store within the same CPU.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.DISAMBIGUATION", "SampleAfterValue": "20003", "UMask": "0x8", "Unit": "cpu_atom" }, + { + "BriefDescription": "Counts the number of machines clears due to memory renaming.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MRN_NUKE", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, { "BriefDescription": "Counts the number of machine clears due to a page fault. Counts both I-Side and D-Side (Loads/Stores) page faults. A page fault occurs when either the page is not present, or an access violation occurs.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.PAGE_FAULT", "SampleAfterValue": "20003", @@ -1014,6 +1121,7 @@ }, { "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SLOW", "SampleAfterValue": "20003", @@ -1022,6 +1130,7 @@ }, { "BriefDescription": "Counts the number of machine clears due to program modifying data (self modifying code) within 1K of a recently fetched code page.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.SMC", "SampleAfterValue": "20003", @@ -1030,6 +1139,7 @@ }, { "BriefDescription": "Self-modifying code (SMC) detected.", + "Counter": "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.", @@ -1039,6 +1149,7 @@ }, { "BriefDescription": "LFENCE instructions retired", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", "PublicDescription": "number of LFENCE retired instructions", @@ -1048,15 +1159,26 @@ }, { "BriefDescription": "Counts the number of Last Branch Record (LBR) entries. Requires LBRs to be enabled and configured in IA32_LBR_CTL. [This event is alias to LBR_INSERTS.ANY]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xe4", "EventName": "MISC_RETIRED.LBR_INSERTS", - "PEBS": "1", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_atom" }, + { + "BriefDescription": "Increments whenever there is an update to the LBR array.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcc", + "EventName": "MISC_RETIRED.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": "100003", + "UMask": "0x20", + "Unit": "cpu_core" + }, { "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.SCOREBOARD", "SampleAfterValue": "100003", @@ -1065,6 +1187,7 @@ }, { "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", @@ -1074,6 +1197,7 @@ }, { "BriefDescription": "TMA slots wasted due to incorrect speculations.", + "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BAD_SPEC_SLOTS", "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", @@ -1083,6 +1207,7 @@ }, { "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions", + "Counter": "0", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", @@ -1092,6 +1217,7 @@ }, { "BriefDescription": "TOPDOWN.MEMORY_BOUND_SLOTS", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", "SampleAfterValue": "10000003", @@ -1100,6 +1226,7 @@ }, { "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", + "Counter": "Fixed counter 3", "EventName": "TOPDOWN.SLOTS", "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", "SampleAfterValue": "10000003", @@ -1108,6 +1235,7 @@ }, { "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", @@ -1117,6 +1245,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.ALL", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]", @@ -1125,6 +1254,7 @@ }, { "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]", @@ -1133,6 +1263,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Fast Nukes such as Memory Ordering Machine clears and MRN nukes", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.FASTNUKE", "SampleAfterValue": "1000003", @@ -1141,6 +1272,7 @@ }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS", "SampleAfterValue": "1000003", @@ -1149,6 +1281,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Branch Mispredict", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.MISPREDICT", "SampleAfterValue": "1000003", @@ -1157,6 +1290,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to a machine clear (nuke).", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.NUKE", "SampleAfterValue": "1000003", @@ -1165,6 +1299,7 @@ }, { "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.ALL", "SampleAfterValue": "1000003", @@ -1172,6 +1307,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to due to certain allocation restrictions", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS", "SampleAfterValue": "1000003", @@ -1180,6 +1316,7 @@ }, { "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.ALL_P", "SampleAfterValue": "1000003", @@ -1187,6 +1324,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop). This could be caused by RSV full or load/store buffer block.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER", "SampleAfterValue": "1000003", @@ -1195,6 +1333,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to IEC and FPC RAT stalls - which can be due to the FIQ and IEC reservation station stall (integer, FP and SIMD scheduler not being able to accept another uop. )", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER", "SampleAfterValue": "1000003", @@ -1203,6 +1342,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to mrbl stall. A 'marble' refers to a physical register file entry, also known as the physical destination (PDST).", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.REGISTER", "SampleAfterValue": "1000003", @@ -1211,6 +1351,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to ROB full", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER", "SampleAfterValue": "1000003", @@ -1219,6 +1360,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to iq/jeu scoreboards or ms scb", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.SERIALIZATION", "SampleAfterValue": "1000003", @@ -1227,6 +1369,7 @@ }, { "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL_P]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.ALL", "SampleAfterValue": "1000003", @@ -1234,6 +1377,7 @@ }, { "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.ALL_P", "SampleAfterValue": "1000003", @@ -1241,6 +1385,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.BRANCH_DETECT", "SampleAfterValue": "1000003", @@ -1249,6 +1394,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BTClear", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.BRANCH_RESTEER", "SampleAfterValue": "1000003", @@ -1257,6 +1403,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to ms", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.CISC", "SampleAfterValue": "1000003", @@ -1265,6 +1412,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to decode stall", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.DECODE", "SampleAfterValue": "1000003", @@ -1273,6 +1421,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH", "SampleAfterValue": "1000003", @@ -1281,6 +1430,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to latency related stalls including BACLEARs, BTCLEARs, ITLB misses, and ICache misses.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY", "SampleAfterValue": "1000003", @@ -1289,6 +1439,7 @@ }, { "BriefDescription": "This event is deprecated. [This event is alias to TOPDOWN_FE_BOUND.ITLB_MISS]", + "Counter": "0,1,2,3,4,5,6,7", "Deprecated": "1", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.ITLB", @@ -1298,6 +1449,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to itlb miss [This event is alias to TOPDOWN_FE_BOUND.ITLB]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.ITLB_MISS", "SampleAfterValue": "1000003", @@ -1306,6 +1458,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend that do not categorize into any other common frontend stall", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.OTHER", "SampleAfterValue": "1000003", @@ -1314,6 +1467,7 @@ }, { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to predecode wrong", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.PREDECODE", "SampleAfterValue": "1000003", @@ -1321,23 +1475,24 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL_P]", + "BriefDescription": "Counts the number of consumed retirement slots. [This event is alias to TOPDOWN_RETIRING.ALL_P]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x72", "EventName": "TOPDOWN_RETIRING.ALL", - "PEBS": "1", "SampleAfterValue": "1000003", "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL]", + "BriefDescription": "Counts the number of consumed retirement slots. [This event is alias to TOPDOWN_RETIRING.ALL]", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x72", "EventName": "TOPDOWN_RETIRING.ALL_P", - "PEBS": "1", "SampleAfterValue": "1000003", "Unit": "cpu_atom" }, { "BriefDescription": "Number of non dec-by-all uops decoded by decoder", + "Counter": "0,1,2,3", "EventCode": "0x76", "EventName": "UOPS_DECODED.DEC0_UOPS", "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.", @@ -1347,6 +1502,7 @@ }, { "BriefDescription": "Uops executed on port 0", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_0", "PublicDescription": "Number of uops dispatch to execution port 0.", @@ -1356,6 +1512,7 @@ }, { "BriefDescription": "Uops executed on port 1", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_1", "PublicDescription": "Number of uops dispatch to execution port 1.", @@ -1365,6 +1522,7 @@ }, { "BriefDescription": "Uops executed on ports 2, 3 and 10", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_2_3_10", "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", @@ -1374,6 +1532,7 @@ }, { "BriefDescription": "Uops executed on ports 4 and 9", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_4_9", "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", @@ -1383,6 +1542,7 @@ }, { "BriefDescription": "Uops executed on ports 5 and 11", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_5_11", "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", @@ -1392,6 +1552,7 @@ }, { "BriefDescription": "Uops executed on port 6", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_6", "PublicDescription": "Number of uops dispatch to execution port 6.", @@ -1401,6 +1562,7 @@ }, { "BriefDescription": "Uops executed on ports 7 and 8", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb2", "EventName": "UOPS_DISPATCHED.PORT_7_8", "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", @@ -1410,6 +1572,7 @@ }, { "BriefDescription": "Number of uops executed on the core.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE", "PublicDescription": "Counts the number of uops executed from any thread.", @@ -1419,6 +1582,7 @@ }, { "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", @@ -1429,6 +1593,7 @@ }, { "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", @@ -1439,6 +1604,7 @@ }, { "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", @@ -1449,6 +1615,7 @@ }, { "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", @@ -1459,6 +1626,7 @@ }, { "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_1", @@ -1469,6 +1637,7 @@ }, { "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "2", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_2", @@ -1479,6 +1648,7 @@ }, { "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "3", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_3", @@ -1489,6 +1659,7 @@ }, { "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "4", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.CYCLES_GE_4", @@ -1499,6 +1670,7 @@ }, { "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.STALLS", @@ -1510,6 +1682,7 @@ }, { "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.THREAD", "SampleAfterValue": "2000003", @@ -1518,6 +1691,7 @@ }, { "BriefDescription": "Counts the number of x87 uops dispatched.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xb1", "EventName": "UOPS_EXECUTED.X87", "PublicDescription": "Counts the number of x87 uops executed.", @@ -1527,6 +1701,7 @@ }, { "BriefDescription": "Counts the number of uops issued by the front end every cycle.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x0e", "EventName": "UOPS_ISSUED.ANY", "PublicDescription": "Counts the number of uops issued by the front end every cycle. When 4-uops are requested and only 2-uops are delivered, the event counts 2. Uops_issued correlates to the number of ROB entries. If uop takes 2 ROB slots it counts as 2 uops_issued.", @@ -1535,6 +1710,7 @@ }, { "BriefDescription": "Uops that RAT issues to RS", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xae", "EventName": "UOPS_ISSUED.ANY", "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", @@ -1544,6 +1720,7 @@ }, { "BriefDescription": "UOPS_ISSUED.CYCLES", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xae", "EventName": "UOPS_ISSUED.CYCLES", @@ -1551,27 +1728,17 @@ "UMask": "0x1", "Unit": "cpu_core" }, - { - "BriefDescription": "Cycles when RAT does not issue Uops to RS for the thread", - "CounterMask": "1", - "EventCode": "0xae", - "EventName": "UOPS_ISSUED.STALLS", - "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": "1000003", - "UMask": "0x1", - "Unit": "cpu_core" - }, { "BriefDescription": "Counts the total number of uops retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.ALL", - "PEBS": "1", "SampleAfterValue": "2000003", "Unit": "cpu_atom" }, { "BriefDescription": "Cycles with retired uop(s).", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.CYCLES", @@ -1582,6 +1749,7 @@ }, { "BriefDescription": "Retired uops except the last uop of each instruction.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.HEAVY", "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", @@ -1591,24 +1759,25 @@ }, { "BriefDescription": "Counts the number of integer divide uops retired.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.IDIV", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x10", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.MS", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_atom" }, { "BriefDescription": "UOPS_RETIRED.MS", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.MS", "MSRIndex": "0x3F7", @@ -1619,6 +1788,7 @@ }, { "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", @@ -1628,6 +1798,7 @@ }, { "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.STALLS", @@ -1637,22 +1808,11 @@ "UMask": "0x2", "Unit": "cpu_core" }, - { - "BriefDescription": "Cycles with less than 10 actually retired uops.", - "CounterMask": "10", - "EventCode": "0xc2", - "EventName": "UOPS_RETIRED.TOTAL_CYCLES", - "Invert": "1", - "PublicDescription": "Counts the number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", - "SampleAfterValue": "1000003", - "UMask": "0x2", - "Unit": "cpu_core" - }, { "BriefDescription": "Counts the number of x87 uops retired, includes those in ms flows", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.X87", - "PEBS": "1", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_atom" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-cache.json index 188843be4caf..f294852dfbe6 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-cache.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "Number of all entries allocated. Includes also retries.", + "Counter": "0,1", "EventCode": "0x35", "EventName": "UNC_HAC_CBO_TOR_ALLOCATION.ALL", "PerPkg": "1", @@ -9,6 +10,7 @@ }, { "BriefDescription": "Asserted on coherent DRD + DRdPref allocations into the queue. Cacheable only", + "Counter": "0,1", "EventCode": "0x35", "EventName": "UNC_HAC_CBO_TOR_ALLOCATION.DRD", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json index 901d8510f90f..a2f4386a8379 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core.", + "Counter": "0", "EventCode": "0x85", "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", "PerPkg": "1", @@ -9,14 +10,17 @@ }, { "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, etc.", + "Counter": "0,1", "EventCode": "0x84", "EventName": "UNC_HAC_ARB_COH_TRK_REQUESTS.ALL", + "Experimental": "1", "PerPkg": "1", "UMask": "0x1", "Unit": "HAC_ARB" }, { "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches", + "Counter": "0,1", "EventCode": "0x81", "EventName": "UNC_HAC_ARB_REQ_TRK_REQUEST.DRD", "PerPkg": "1", @@ -25,6 +29,7 @@ }, { "BriefDescription": "Number of all CMI transactions", + "Counter": "0,1", "EventCode": "0x8A", "EventName": "UNC_HAC_ARB_TRANSACTIONS.ALL", "PerPkg": "1", @@ -33,6 +38,7 @@ }, { "BriefDescription": "Number of all CMI reads", + "Counter": "0,1", "EventCode": "0x8A", "EventName": "UNC_HAC_ARB_TRANSACTIONS.READS", "PerPkg": "1", @@ -41,6 +47,7 @@ }, { "BriefDescription": "Number of all CMI writes not including Mflush", + "Counter": "0,1", "EventCode": "0x8A", "EventName": "UNC_HAC_ARB_TRANSACTIONS.WRITES", "PerPkg": "1", @@ -49,6 +56,7 @@ }, { "BriefDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "Counter": "0,1", "EventCode": "0x81", "EventName": "UNC_HAC_ARB_TRK_REQUESTS.ALL", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json index c9d248d1042e..783a4f7fd05b 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-memory.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts every CAS read command sent from the Memory Controller 0 to DRAM (sum of all channels).", + "Counter": "0", "EventCode": "0xff", "EventName": "UNC_MC0_RDCAS_COUNT_FREERUN", "PerPkg": "1", @@ -10,6 +11,7 @@ }, { "BriefDescription": "Counts every read and write request entering the Memory Controller 0.", + "Counter": "2", "EventCode": "0xff", "EventName": "UNC_MC0_TOTAL_REQCOUNT_FREERUN", "PerPkg": "1", @@ -19,6 +21,7 @@ }, { "BriefDescription": "Counts every CAS write command sent from the Memory Controller 0 to DRAM (sum of all channels).", + "Counter": "1", "EventCode": "0xff", "EventName": "UNC_MC0_WRCAS_COUNT_FREERUN", "PerPkg": "1", @@ -28,6 +31,7 @@ }, { "BriefDescription": "Counts every CAS read command sent from the Memory Controller 1 to DRAM (sum of all channels).", + "Counter": "3", "EventCode": "0xff", "EventName": "UNC_MC1_RDCAS_COUNT_FREERUN", "PerPkg": "1", @@ -37,6 +41,7 @@ }, { "BriefDescription": "Counts every read and write request entering the Memory Controller 1.", + "Counter": "5", "EventCode": "0xff", "EventName": "UNC_MC1_TOTAL_REQCOUNT_FREERUN", "PerPkg": "1", @@ -46,6 +51,7 @@ }, { "BriefDescription": "Counts every CAS write command sent from the Memory Controller 1 to DRAM (sum of all channels).", + "Counter": "4", "EventCode": "0xff", "EventName": "UNC_MC1_WRCAS_COUNT_FREERUN", "PerPkg": "1", @@ -55,6 +61,7 @@ }, { "BriefDescription": "ACT command for a read request sent to DRAM", + "Counter": "0,1,2,3,4", "EventCode": "0x24", "EventName": "UNC_M_ACT_COUNT_RD", "PerPkg": "1", @@ -62,6 +69,7 @@ }, { "BriefDescription": "ACT command sent to DRAM", + "Counter": "0,1,2,3,4", "EventCode": "0x26", "EventName": "UNC_M_ACT_COUNT_TOTAL", "PerPkg": "1", @@ -69,6 +77,7 @@ }, { "BriefDescription": "ACT command for a write request sent to DRAM", + "Counter": "0,1,2,3,4", "EventCode": "0x25", "EventName": "UNC_M_ACT_COUNT_WR", "PerPkg": "1", @@ -76,6 +85,7 @@ }, { "BriefDescription": "Read CAS command sent to DRAM", + "Counter": "0,1,2,3,4", "EventCode": "0x22", "EventName": "UNC_M_CAS_COUNT_RD", "PerPkg": "1", @@ -83,6 +93,7 @@ }, { "BriefDescription": "Write CAS command sent to DRAM", + "Counter": "0,1,2,3,4", "EventCode": "0x23", "EventName": "UNC_M_CAS_COUNT_WR", "PerPkg": "1", @@ -90,6 +101,7 @@ }, { "BriefDescription": "PRE command sent to DRAM due to page table idle timer expiration", + "Counter": "0,1,2,3,4", "EventCode": "0x28", "EventName": "UNC_M_PRE_COUNT_IDLE", "PerPkg": "1", @@ -97,6 +109,7 @@ }, { "BriefDescription": "PRE command sent to DRAM for a read/write request", + "Counter": "0,1,2,3,4", "EventCode": "0x27", "EventName": "UNC_M_PRE_COUNT_PAGE_MISS", "PerPkg": "1", @@ -104,6 +117,7 @@ }, { "BriefDescription": "Number of bytes read from DRAM, in 32B chunks. Counter increments by 1 after receiving 32B chunk data.", + "Counter": "0,1,2,3,4", "EventCode": "0x3A", "EventName": "UNC_M_RD_DATA", "PerPkg": "1", @@ -111,6 +125,7 @@ }, { "BriefDescription": "Total number of read and write byte transfers to/from DRAM, in 32B chunks. Counter increments by 1 after sending or receiving 32B chunk data.", + "Counter": "0,1,2,3,4", "EventCode": "0x3C", "EventName": "UNC_M_TOTAL_DATA", "PerPkg": "1", @@ -118,6 +133,7 @@ }, { "BriefDescription": "Number of bytes written to DRAM, in 32B chunks. Counter increments by 1 after sending 32B chunk data.", + "Counter": "0,1,2,3,4", "EventCode": "0x3B", "EventName": "UNC_M_WR_DATA", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json index 2af92e43b28a..1ac5b5ef8094 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "FIXED", "EventCode": "0xff", "EventName": "UNC_CLOCK.SOCKET", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json index 55798e64c58a..305b96b26a4e 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json @@ -1,6 +1,7 @@ [ { "BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", "SampleAfterValue": "200003", @@ -9,6 +10,7 @@ }, { "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", @@ -18,6 +20,7 @@ }, { "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", @@ -28,6 +31,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to load DTLB misses.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", "SampleAfterValue": "200003", @@ -36,6 +40,7 @@ }, { "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", @@ -45,6 +50,7 @@ }, { "BriefDescription": "Page walks completed due to a demand data load to a 1G page.", + "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", @@ -54,6 +60,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", @@ -63,6 +70,7 @@ }, { "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.", + "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", @@ -72,6 +80,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", @@ -81,6 +90,7 @@ }, { "BriefDescription": "Page walks completed due to a demand data load to a 4K page.", + "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", @@ -90,6 +100,7 @@ }, { "BriefDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", "PublicDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.", @@ -99,6 +110,7 @@ }, { "BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.", + "Counter": "0,1,2,3", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", @@ -108,6 +120,7 @@ }, { "BriefDescription": "Counts the number of first level TLB misses but second level hits due to stores that did not start a page walk. Accounts for all pages sizes. Will result in a DTLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x49", "EventName": "DTLB_STORE_MISSES.STLB_HIT", "SampleAfterValue": "2000003", @@ -116,6 +129,7 @@ }, { "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.STLB_HIT", "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", @@ -125,6 +139,7 @@ }, { "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", @@ -135,6 +150,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 1G page.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x49", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", "SampleAfterValue": "2000003", @@ -143,6 +159,7 @@ }, { "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", @@ -152,6 +169,7 @@ }, { "BriefDescription": "Page walks completed due to a demand data store to a 1G page.", + "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", @@ -161,6 +179,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x49", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", @@ -170,6 +189,7 @@ }, { "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.", + "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", @@ -179,6 +199,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x49", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", @@ -188,6 +209,7 @@ }, { "BriefDescription": "Page walks completed due to a demand data store to a 4K page.", + "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", @@ -197,6 +219,7 @@ }, { "BriefDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x49", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", "PublicDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.", @@ -206,6 +229,7 @@ }, { "BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.", + "Counter": "0,1,2,3", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_PENDING", "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", @@ -215,6 +239,7 @@ }, { "BriefDescription": "Counts the number of page walks initiated by a instruction fetch that missed the first and second level TLBs.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x85", "EventName": "ITLB_MISSES.MISS_CAUSED_WALK", "SampleAfterValue": "1000003", @@ -223,6 +248,7 @@ }, { "BriefDescription": "Counts the number of first level TLB misses but second level hits due to an instruction fetch that did not start a page walk. Account for all pages sizes. Will result in an ITLB write from STLB.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x85", "EventName": "ITLB_MISSES.STLB_HIT", "SampleAfterValue": "2000003", @@ -231,6 +257,7 @@ }, { "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.STLB_HIT", "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", @@ -240,6 +267,7 @@ }, { "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.", + "Counter": "0,1,2,3", "CounterMask": "1", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_ACTIVE", @@ -250,6 +278,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_COMPLETED", "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", @@ -259,6 +288,7 @@ }, { "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", @@ -268,6 +298,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 2M or 4M page.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.", @@ -277,6 +308,7 @@ }, { "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", @@ -286,6 +318,7 @@ }, { "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 4K page.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.", @@ -295,6 +328,7 @@ }, { "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", @@ -304,6 +338,7 @@ }, { "BriefDescription": "Counts the number of page walks outstanding for iside in PMH every cycle.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_PENDING", "PublicDescription": "Counts the number of page walks outstanding for iside in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals. Walks could be counted by edge detecting on this event, but would count restarted suspended walks.", @@ -313,6 +348,7 @@ }, { "BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.", + "Counter": "0,1,2,3", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_PENDING", "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", @@ -322,6 +358,7 @@ }, { "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DTLB miss.", + "Counter": "0,1,2,3,4,5,6,7", "EventCode": "0x05", "EventName": "LD_HEAD.DTLB_MISS_AT_RET", "SampleAfterValue": "1000003",