diff options
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/sapphirerapids')
11 files changed, 11690 insertions, 0 deletions
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json new file mode 100644 index 000000000..c05c741e2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json @@ -0,0 +1,1192 @@ +[ + { + "BriefDescription": "L1D.HWPF_MISS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x51", + "EventName": "L1D.HWPF_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts the number of cache lines replaced in L1 data cache.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailablability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts number of phases 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.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.L2_STALL", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.L2_STALLS", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of L1D misses that are outstanding", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 cache lines filling L2", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.ALL", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x1f" + }, + { + "BriefDescription": "L2_LINES_OUT.NON_SILENT", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "PEBScounters": "0,1,2,3", + "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", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "All accesses to L2 cache[This event is alias to L2_RQSTS.REFERENCES]", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_REQUEST.ALL", + "PEBScounters": "0,1,2,3", + "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]", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0xff" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache.[This event is alias to L2_RQSTS.MISS]", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "PEBScounters": "0,1,2,3", + "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]", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0x3f" + }, + { + "BriefDescription": "L2 code requests", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0xe4" + }, + { + "BriefDescription": "Demand Data Read access L2 cache", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0xe1" + }, + { + "BriefDescription": "Demand requests that miss L2 cache", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts demand requests that miss L2 cache.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0x27" + }, + { + "BriefDescription": "Demand requests to L2 cache", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts demand requests to L2 cache.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0xe7" + }, + { + "BriefDescription": "L2_RQSTS.ALL_HWPF", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_HWPF", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0xf0" + }, + { + "BriefDescription": "RFO requests to L2 cache", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_RFO", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0xe2" + }, + { + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0xc4" + }, + { + "BriefDescription": "L2 cache misses when fetching instructions", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0x24" + }, + { + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0xc1" + }, + { + "BriefDescription": "Demand Data Read miss L2 cache", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0x21" + }, + { + "BriefDescription": "L2_RQSTS.HWPF_MISS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.HWPF_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0x30" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache.[This event is alias to L2_REQUEST.MISS]", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PEBScounters": "0,1,2,3", + "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]", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0x3f" + }, + { + "BriefDescription": "All accesses to L2 cache[This event is alias to L2_REQUEST.ALL]", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PEBScounters": "0,1,2,3", + "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]", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0xff" + }, + { + "BriefDescription": "RFO requests that hit L2 cache", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0xc2" + }, + { + "BriefDescription": "RFO requests that miss L2 cache", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0x22" + }, + { + "BriefDescription": "SW prefetch requests that hit L2 cache.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.SWPF_HIT", + "PEBScounters": "0,1,2,3", + "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", + "Speculative": "1", + "UMask": "0xc8" + }, + { + "BriefDescription": "SW prefetch requests that miss L2 cache.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "L2_RQSTS.SWPF_MISS", + "PEBScounters": "0,1,2,3", + "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", + "Speculative": "1", + "UMask": "0x28" + }, + { + "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x41" + }, + { + "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x4f" + }, + { + "BriefDescription": "Retired load instructions.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "SampleAfterValue": "1000003", + "UMask": "0x81" + }, + { + "BriefDescription": "Retired store instructions.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts all retired store instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x82" + }, + { + "BriefDescription": "All retired memory instructions.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ANY", + "L1_Hit_Indication": "1", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "SampleAfterValue": "1000003", + "UMask": "0x83" + }, + { + "BriefDescription": "Retired load instructions with locked access.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions with locked access.", + "SampleAfterValue": "100007", + "UMask": "0x21" + }, + { + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x42" + }, + { + "BriefDescription": "Retired load instructions that miss the STLB.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x11" + }, + { + "BriefDescription": "Retired store instructions that miss the STLB.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x12" + }, + { + "BriefDescription": "Completed demand load uops that miss the L1 d-cache.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0xfd" + }, + { + "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", + "SampleAfterValue": "20011", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired load instructions with remote Intel Optane DC persistent memory as the data source where the data request missed all caches.", + "Counter": "0,1,2,3", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions with remote Intel Optane DC persistent memory as the data source and the data request missed L3.", + "SampleAfterValue": "100007", + "UMask": "0x10" + }, + { + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "SampleAfterValue": "100007", + "UMask": "0x4" + }, + { + "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.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "SampleAfterValue": "100007", + "UMask": "0x40" + }, + { + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "SampleAfterValue": "200003", + "UMask": "0x8" + }, + { + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "100021", + "UMask": "0x10" + }, + { + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "SampleAfterValue": "100021", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PEBS": "1", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "SampleAfterValue": "50021", + "UMask": "0x20" + }, + { + "BriefDescription": "Retired load instructions with local Intel Optane DC persistent memory as the data source where the data request missed all caches.", + "Counter": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.LOCAL_PMM", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts retired load instructions with local Intel Optane DC persistent memory as the data source and the data request missed L3.", + "SampleAfterValue": "1000003", + "UMask": "0x80" + }, + { + "BriefDescription": "MEM_STORE_RETIRED.L2_HIT", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x44", + "EventName": "MEM_STORE_RETIRED.L2_HIT", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired memory uops for any access", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe5", + "EventName": "MEM_UOP_RETIRED.ANY", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1008000004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x808000004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another core's 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", + "MSRValue": "0x8003C0001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1030000001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x830000001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1008000001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x808000001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1008000002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x808000002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x80082380", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F003C4477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C4477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop that hit in another core, which did not forward the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C4477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C4477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified).", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1830004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1030004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x830004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1008004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x808004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.RFO_TO_CORE.L3_HIT_M", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1F80040022", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores that hit in the L3 or were snooped from another core's caches on the same socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.STREAMING_WR.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x80080800", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_REQUESTS.ALL_REQUESTS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x80" + }, + { + "BriefDescription": "Demand and prefetch data reads", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DATA_RD", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Demand Data Read requests sent to uncore", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of PREFETCHW instructions executed.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T0", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x4" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json new file mode 100644 index 000000000..32074d455 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json @@ -0,0 +1,224 @@ +[ + { + "BriefDescription": "ARITH.FPDIV_ACTIVE", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.FPDIV_ACTIVE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all microcode FP assists.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc1", + "EventName": "ASSISTS.FP", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts all microcode Floating Point assists.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "ASSISTS.SSE_AVX_MIX", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc1", + "EventName": "ASSISTS.SSE_AVX_MIX", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.PORT_0", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.PORT_1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.PORT_5", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "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.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "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.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "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.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "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.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 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.", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 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.", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "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.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "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.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of all Scalar Half-Precision FP arithmetic instructions(1) retired - regular and complex.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.SCALAR", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR", + "SampleAfterValue": "100003", + "UMask": "0x3" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of all Vector (also called packed) Half-Precision FP arithmetic instructions(1) retired.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.VECTOR", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR", + "SampleAfterValue": "100003", + "UMask": "0x1c" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json new file mode 100644 index 000000000..ff0d47ce8 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json @@ -0,0 +1,498 @@ +[ + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x87", + "EventName": "DECODE.LCP", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "SampleAfterValue": "500009", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles the Microcode Sequencer is busy.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x87", + "EventName": "DECODE.MS_BUSY", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "500009", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "DSB-to-MITE switch true penalty cycles.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x61", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired Instructions who experienced DSB miss.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x1", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced a critical DSB miss.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x14", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L1I_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x12", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x600106", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x608006", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts 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.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "MSRValue": "0x601006", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x600206", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "MSRIndex": "0x3F7", + "MSRValue": "0x610006", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts 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.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x100206", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "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.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "MSRIndex": "0x3F7", + "MSRValue": "0x602006", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "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.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "MSRValue": "0x600406", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts 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.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "MSRValue": "0x620006", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts 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.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "MSRValue": "0x604006", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts 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.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "MSRIndex": "0x3F7", + "MSRValue": "0x600806", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "FRONTEND_RETIRED.MS_FLOWS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.MS_FLOWS", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", + "MSRIndex": "0x3F7", + "MSRValue": "0x17", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "ICACHE_DATA.STALLS", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "500009", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x83", + "EventName": "ICACHE_TAG.STALLS", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "SampleAfterValue": "200003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_ANY", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles DSB is delivering optimal number of Uops", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "6", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_OK", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles MITE is delivering any Uop", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_ANY", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles MITE is delivering optimal number of Uops", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "6", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_OK", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PEBScounters": "0,1,2,3", + "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).", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_CYCLES_ANY", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of switches from DSB or MITE to the MS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Uops delivered to IDQ while MS is busy", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x9c", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x9c", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of cycles when no uops were delivered 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.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x9c", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "Invert": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered 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.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json new file mode 100644 index 000000000..6e761b628 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json @@ -0,0 +1,436 @@ +[ + { + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "6", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x6" + }, + { + "BriefDescription": "Number of machine clears due to memory ordering conflicts.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "2", + "EventCode": "0x47", + "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "3", + "EventCode": "0x47", + "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x3" + }, + { + "BriefDescription": "MEMORY_ACTIVITY.STALLS_L2_MISS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "5", + "EventCode": "0x47", + "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x5" + }, + { + "BriefDescription": "MEMORY_ACTIVITY.STALLS_L3_MISS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "9", + "EventCode": "0x47", + "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x9" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "CollectPEBSRecord": "2", + "Counter": "1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "PEBScounters": "1,2,3,4,5,6,7", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "1009", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "CollectPEBSRecord": "2", + "Counter": "1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "PEBScounters": "1,2,3,4,5,6,7", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "20011", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "CollectPEBSRecord": "2", + "Counter": "1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "PEBScounters": "1,2,3,4,5,6,7", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "503", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "CollectPEBSRecord": "2", + "Counter": "1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "PEBScounters": "1,2,3,4,5,6,7", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "CollectPEBSRecord": "2", + "Counter": "1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "PEBScounters": "1,2,3,4,5,6,7", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100003", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "CollectPEBSRecord": "2", + "Counter": "1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "PEBScounters": "1,2,3,4,5,6,7", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "101", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "CollectPEBSRecord": "2", + "Counter": "1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "PEBScounters": "1,2,3,4,5,6,7", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "2003", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "CollectPEBSRecord": "2", + "Counter": "1,2,3,4,5,6,7", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "PEBScounters": "1,2,3,4,5,6,7", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "50021", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired memory store access operations. A PDist event for PEBS Store Latency Facility.", + "CollectPEBSRecord": "2", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", + "PEBS": "2", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FC00002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that missed the local socket's L1, L2, and L3 caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x94002380", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.L3_MISS_LOCAL", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x84002380", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FC04477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F04C04477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster. It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x70CC04477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores that missed the local socket's L1, L2, and L3 caches.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.STREAMING_WR.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x94000800", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x84000800", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an RTM execution aborted.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of times RTM abort was triggered.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of times an RTM execution successfully committed", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.COMMIT", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of times RTM commit succeeded.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an RTM execution started.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.START", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_READ", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x80" + }, + { + "BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json new file mode 100644 index 000000000..95dbef8ae --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json @@ -0,0 +1,428 @@ +[ + { + "BriefDescription": "ASSISTS.PAGE_FAULT", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc1", + "EventName": "ASSISTS.PAGE_FAULT", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb7", + "EventName": "EXE.AMX_BUSY", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "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", + "MSRValue": "0x10001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "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", + "MSRValue": "0x73C000001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730000001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703000001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads 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", + "MSRValue": "0x3F3FFC0002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L1D.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10400", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L2.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10070", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x12380", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x90002380", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10808", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC4477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x70C004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM accesses that are controlled by the close or distant SNC Cluster.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x700C04477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F33004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x733004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by PMM attached to another socket.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_PMM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x703004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708004477", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "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", + "MSRValue": "0x10800", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", + "Counter": "0,1,2,3", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.WRITE_ESTIMATE.MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0xFBFF80822", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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)", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x7" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x7" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS_EMPTY.COUNT", + "Invert": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x7" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa5", + "EventName": "RS_EMPTY.CYCLES", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x7" + }, + { + "BriefDescription": "XQ.FULL_CYCLES", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x2d", + "EventName": "XQ.FULL_CYCLES", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json new file mode 100644 index 000000000..b2f0d9393 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json @@ -0,0 +1,1372 @@ +[ + { + "BriefDescription": "AMX_OPS_RETIRED.BF16", + "EventCode": "0xce", + "EventName": "AMX_OPS_RETIRED.BF16", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "AMX_OPS_RETIRED.INT8", + "EventCode": "0xce", + "EventName": "AMX_OPS_RETIRED.INT8", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.DIVIDER_ACTIVE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x9" + }, + { + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.DIV_ACTIVE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x9" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.FP_DIVIDER_ACTIVE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "This event counts the cycles the integer divider is busy.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb0", + "EventName": "ARITH.IDIV_ACTIVE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.INT_DIVIDER_ACTIVE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc1", + "EventName": "ASSISTS.ANY", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x1b" + }, + { + "BriefDescription": "All branch instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts all branch instructions retired.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Conditional branch instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x11" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" + }, + { + "BriefDescription": "Taken conditional branch instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts taken conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Far branch instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts far branch instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x40" + }, + { + "BriefDescription": "Indirect near branch instructions retired (excluding returns)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Direct and indirect near call instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x2" + }, + { + "BriefDescription": "Return instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "Taken branch instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "All mispredicted branch instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x11" + }, + { + "BriefDescription": "Mispredicted non-taken conditional branch instructions retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "SampleAfterValue": "400009", + "UMask": "0x10" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Miss-predicted near indirect branch instructions retired (excluding returns)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Mispredicted indirect CALL retired.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "SampleAfterValue": "400009", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET", + "PEBS": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C01", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C02", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 or C0.2 or running a PAUSE in C0 ACPI state.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C0_WAIT", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x70" + }, + { + "BriefDescription": "Cycle counts are evenly distributed between active threads in the Core.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", + "SampleAfterValue": "25003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "CPU_CLK_UNHALTED.PAUSE", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x40" + }, + { + "BriefDescription": "CPU_CLK_UNHALTED.PAUSE_INST", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x40" + }, + { + "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", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "CollectPEBSRecord": "2", + "Counter": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PEBScounters": "34", + "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", + "Speculative": "1", + "UMask": "0x3" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Core cycles when the thread is not in halt state", + "CollectPEBSRecord": "2", + "Counter": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PEBScounters": "33", + "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", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Thread cycles when thread is not in halt state", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003", + "Speculative": "1" + }, + { + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "8", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "16", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "12", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0xc" + }, + { + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "5", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x5" + }, + { + "BriefDescription": "Total execution stalls.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "5", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x21" + }, + { + "BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x40" + }, + { + "BriefDescription": "Cycles no uop executed while RS was not empty, the SB was not full and there was no outstanding load.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x80" + }, + { + "BriefDescription": "Instruction decoders utilized in a cycle", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x75", + "EventName": "INST_DECODED.DECODERS", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", + "CollectPEBSRecord": "2", + "Counter": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "PEBS": "1", + "PEBScounters": "32", + "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.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "PEBS": "1", + "PEBScounters": "1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "INST_RETIRED.MACRO_FUSED", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.MACRO_FUSED", + "PEBScounters": "1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Retired NOP instructions.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.NOP", + "PEBScounters": "1,2,3,4,5,6,7", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Precise instruction retired with PEBS precise-distribution", + "CollectPEBSRecord": "2", + "Counter": "Fixed counter 0", + "EventName": "INST_RETIRED.PREC_DIST", + "PEBS": "1", + "PEBScounters": "32", + "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.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "INST_RETIRED.REP_ITERATION", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.REP_ITERATION", + "PEBScounters": "1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "SampleAfterValue": "500009", + "Speculative": "1", + "UMask": "0x80" + }, + { + "BriefDescription": "INT_MISC.MBA_STALLS", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xad", + "EventName": "INT_MISC.MBA_STALLS", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xad", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "SampleAfterValue": "500009", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "INT_MISC.UNKNOWN_BRANCH_CYCLES", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xad", + "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", + "MSRIndex": "0x3F7", + "MSRValue": "0x7", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "Speculative": "1", + "TakenAlone": "1", + "UMask": "0x40" + }, + { + "BriefDescription": "TMA slots where uops got dropped", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xad", + "EventName": "INT_MISC.UOP_DROPPING", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "INT_VEC_RETIRED.128BIT", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.128BIT", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "UMask": "0x13" + }, + { + "BriefDescription": "INT_VEC_RETIRED.256BIT", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.256BIT", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "UMask": "0xac" + }, + { + "BriefDescription": "integer ADD, SUB, SAD 128-bit vector instructions.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.ADD_128", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "BriefDescription": "integer ADD, SUB, SAD 256-bit vector instructions.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.ADD_256", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", + "SampleAfterValue": "1000003", + "UMask": "0xc" + }, + { + "BriefDescription": "INT_VEC_RETIRED.MUL_256", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.MUL_256", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "UMask": "0x80" + }, + { + "BriefDescription": "INT_VEC_RETIRED.SHUFFLES", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.SHUFFLES", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "UMask": "0x40" + }, + { + "BriefDescription": "INT_VEC_RETIRED.VNNI_128", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.VNNI_128", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "INT_VEC_RETIRED.VNNI_256", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.VNNI_256", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "UMask": "0x20" + }, + { + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x88" + }, + { + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x82" + }, + { + "BriefDescription": "Counts the number of demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x4c", + "EventName": "LOAD_HIT_PREFETCH.SWPF", + "PEBScounters": "0,1,2,3", + "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", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_ACTIVE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_OK", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of Uops delivered by the LSD.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa8", + "EventName": "LSD.UOPS", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of machine clears (nukes) of any type.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.COUNT", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Self-modifying code (SMC) detected.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SMC", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "MISC2_RETIRED.LFENCE", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xe0", + "EventName": "MISC2_RETIRED.LFENCE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "400009", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Increments whenever there is an update to the LBR array.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xcc", + "EventName": "MISC_RETIRED.LBR_INSERTS", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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" + }, + { + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.SB", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.SCOREBOARD", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.", + "SampleAfterValue": "10000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "TMA slots wasted due to incorrect speculations.", + "CollectPEBSRecord": "2", + "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.", + "SampleAfterValue": "10000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions", + "CollectPEBSRecord": "2", + "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 specualtive operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "SampleAfterValue": "10000003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "TOPDOWN.MEMORY_BOUND_SLOTS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa4", + "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "10000003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", + "CollectPEBSRecord": "2", + "Counter": "Fixed counter 3", + "EventName": "TOPDOWN.SLOTS", + "PEBScounters": "35", + "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", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xa4", + "EventName": "TOPDOWN.SLOTS_P", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "10000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "UOPS_DECODED.DEC0_UOPS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x76", + "EventName": "UOPS_DECODED.DEC0_UOPS", + "PEBScounters": "0,1,2,3", + "SampleAfterValue": "1000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops executed on port 0", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_0", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of uops dispatch to execution port 0.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops executed on port 1", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of uops dispatch to execution port 1.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Uops executed on ports 2, 3 and 10", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_2_3_10", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Uops executed on ports 4 and 9", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_4_9", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "Uops executed on ports 5 and 11", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_5_11", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Uops executed on port 6", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_6", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of uops dispatch to execution port 6.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x40" + }, + { + "BriefDescription": "Uops executed on ports 7 and 8", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_7_8", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of uops executed on the core.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of uops executed from any thread.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.STALLS", + "Invert": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "Invert": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.THREAD", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of x87 uops dispatched.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.X87", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of x87 uops executed.", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "Uops that RAT issues to RS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xae", + "EventName": "UOPS_ISSUED.ANY", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "SampleAfterValue": "2000003", + "Speculative": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with retired uop(s).", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.CYCLES", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts cycles where at least one uop has retired.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired uops except the last uop of each instruction.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.HEAVY", + "PEBScounters": "0,1,2,3,4,5,6,7", + "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.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "UOPS_RETIRED.MS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "2000003", + "TakenAlone": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Retirement slots used.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.SLOTS", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "Counts the retirement slots used each cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.STALLS", + "Invert": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "PublicDescription": "This event counts cycles without actually retired uops.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "Invert": "1", + "PEBScounters": "0,1,2,3,4,5,6,7", + "SampleAfterValue": "1000003", + "UMask": "0x2" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json new file mode 100644 index 000000000..9ec42a68c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -0,0 +1,1643 @@ +[ + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / SLOTS", + "MetricGroup": "PGO;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "(topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / SLOTS)", + "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "ICACHE_DATA.STALLS / CLKS", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_TAG.STALLS / CLKS", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / CLKS + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "(tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / CLKS", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_branch_resteers_group", + "MetricName": "tma_mispredicts_resteers", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - (tma_branch_mispredicts / tma_bad_speculation)) * INT_MISC.CLEAR_RESTEER_CYCLES / CLKS", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_branch_resteers_group", + "MetricName": "tma_clears_resteers", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / CLKS", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit). Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_dsb_switches", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "DECODE.LCP / CLKS", + "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_lcp", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * IDQ.MS_SWITCHES / CLKS", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_ms_switches", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", + "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_bandwidth", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / CORE_CLKS / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / CORE_CLKS", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / CORE_CLKS / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0*SLOTS", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_branch_mispredicts", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", + "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_machine_clears", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0*SLOTS", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0*SLOTS", + "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / CLKS, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / CLKS", + "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / CLKS", + "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", + "MetricGroup": "TopdownL4;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + (MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / CLKS", + "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CLKS", + "MetricGroup": "TopdownL4;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / CLKS", + "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / CLKS", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / CLKS", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricExpr": "((25 * Average_Frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (24 * Average_Frequency) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / 2) / CLKS", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricExpr": "(24 * Average_Frequency) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD)))) * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / 2) / CLKS", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "(9 * Average_Frequency) * MEM_LOAD_RETIRED.L3_HIT * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / 2) / CLKS", + "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / CLKS", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricExpr": "((MEMORY_ACTIVITY.STALLS_L3_MISS / CLKS) - tma_pmm_bound)", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / CLKS", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", + "MetricName": "tma_mem_bandwidth", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).", + "MetricExpr": "INT_MISC.MBA_STALLS / CLKS", + "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_mem_bandwidth_group", + "MetricName": "tma_mba_stalls", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", + "MetricName": "tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricExpr": "(54.5 * Average_Frequency) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / 2) / CLKS", + "MetricGroup": "Server;TopdownL5;tma_mem_latency_group", + "MetricName": "tma_local_dram", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricExpr": "(119 * Average_Frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / 2) / CLKS", + "MetricGroup": "Server;Snoop;TopdownL5;tma_mem_latency_group", + "MetricName": "tma_remote_dram", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", + "MetricExpr": "((108 * Average_Frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (108 * Average_Frequency) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / 2) / CLKS", + "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_mem_latency_group", + "MetricName": "tma_remote_cache", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) + 10 * ((MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) + (MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) + (MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) / ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) + 10 * ((MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) + (MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) + (MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + (MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))))) * (MEMORY_ACTIVITY.STALLS_L3_MISS / CLKS)) if (1000000 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS) else 0)", + "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_pmm_bound", + "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module. ", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / CLKS", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "((MEM_STORE_RETIRED.L2_HIT * 10 * (1 - (MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES))) + (1 - (MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES)) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", + "MetricName": "tma_store_latency", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "(28 * Average_Frequency) * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / CLKS", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / CORE_CLKS", + "MetricGroup": "TopdownL4;tma_store_bound_group", + "MetricName": "tma_split_stores", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / CLKS", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_store_bound_group", + "MetricName": "tma_streaming_stores", + "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / CORE_CLKS", + "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / CORE_CLKS", + "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", + "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / CLKS", + "MetricGroup": "TopdownL3;tma_core_bound_group", + "MetricName": "tma_divider", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "(cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / CLKS if (ARITH.DIVIDER_ACTIVE < (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS)) else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / CLKS", + "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / CLKS + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / CLKS", + "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / CLKS", + "MetricGroup": "TopdownL5;tma_ports_utilized_0_group", + "MetricName": "tma_serializing_operation", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / CLKS", + "MetricGroup": "TopdownL6;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", + "MetricExpr": "13 * MISC2_RETIRED.LFENCE / CLKS", + "MetricGroup": "TopdownL6;tma_serializing_operation_group", + "MetricName": "tma_memory_fence", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", + "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / CLKS", + "MetricGroup": "TopdownL5;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the Advanced Matrix Extensions (AMX) execution engine was busy with tile (arithmetic) operations", + "MetricExpr": "EXE.AMX_BUSY / CORE_CLKS", + "MetricGroup": "Compute;HPC;Server;TopdownL5;tma_ports_utilized_0_group", + "MetricName": "tma_amx_busy", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / CLKS", + "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / CLKS", + "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / CLKS", + "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * CORE_CLKS)", + "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED.PORT_0", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / CORE_CLKS", + "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", + "MetricName": "tma_port_0", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED.PORT_1", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / CORE_CLKS", + "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", + "MetricName": "tma_port_1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU) Sample with: UOPS_DISPATCHED.PORT_6", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / CORE_CLKS", + "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", + "MetricName": "tma_port_6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3_10", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * CORE_CLKS)", + "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations Sample with: UOPS_DISPATCHED.PORT_7_8", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * CORE_CLKS)", + "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0*SLOTS", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", + "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector + tma_fp_amx", + "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * SLOTS)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", + "MetricName": "tma_fp_scalar", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * SLOTS)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", + "MetricName": "tma_fp_vector", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * SLOTS)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", + "MetricName": "tma_fp_vector_128b", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * SLOTS)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", + "MetricName": "tma_fp_vector_256b", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * SLOTS)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", + "MetricName": "tma_fp_vector_512b", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) matrix uops fraction the CPU has retired (aggregated across all supported FP datatypes in AMX engine)", + "MetricExpr": "cpu@AMX_OPS_RETIRED.BF16\\,cmask\\=1@ / (tma_retiring * SLOTS)", + "MetricGroup": "Compute;Flops;HPC;Pipeline;Server;TopdownL4;tma_fp_arith_group", + "MetricName": "tma_fp_amx", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) matrix uops fraction the CPU has retired (aggregated across all supported FP datatypes in AMX engine). Refer to AMX_Busy and GFLOPs metrics for actual AMX utilization and FP performance, resp.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_int_vector_128b + tma_int_vector_256b + tma_shuffles", + "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", + "MetricName": "tma_int_operations", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired.", + "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * SLOTS)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_int_operations_group", + "MetricName": "tma_int_vector_128b", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired.", + "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * SLOTS)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_int_operations_group", + "MetricName": "tma_int_vector_256b", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic Integer (Int) matrix uops fraction the CPU has retired (aggregated across all supported Int datatypes in AMX engine)", + "MetricExpr": "cpu@AMX_OPS_RETIRED.INT8\\,cmask\\=1@ / (tma_retiring * SLOTS)", + "MetricGroup": "Compute;HPC;IntVector;Pipeline;Server;TopdownL4;tma_int_operations_group", + "MetricName": "tma_int_amx", + "PublicDescription": "This metric approximates arithmetic Integer (Int) matrix uops fraction the CPU has retired (aggregated across all supported Int datatypes in AMX engine). Refer to AMX_Busy and TIOPs metrics for actual AMX utilization and Int performance, resp.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.", + "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * SLOTS)", + "MetricGroup": "HPC;Pipeline;TopdownL4;tma_int_operations_group", + "MetricName": "tma_shuffles", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * SLOTS)", + "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * SLOTS)", + "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", + "MetricName": "tma_fused_instructions", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", + "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.MACRO_FUSED) / (tma_retiring * SLOTS)", + "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", + "MetricName": "tma_non_fused_branches", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * SLOTS)", + "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", + "MetricName": "tma_nop_instructions", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", + "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0*SLOTS", + "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", + "MetricGroup": "TopdownL3;tma_heavy_operations_group", + "MetricName": "tma_few_uops_instructions", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.MS / SLOTS", + "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", + "MetricName": "tma_microcode_sequencer", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * cpu@ASSISTS.ANY\\,umask\\=0x1B@ / SLOTS", + "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults", + "MetricExpr": "99 * ASSISTS.PAGE_FAULT / SLOTS", + "MetricGroup": "TopdownL5;tma_assists_group", + "MetricName": "tma_page_faults", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists", + "MetricExpr": "30 * ASSISTS.FP / SLOTS", + "MetricGroup": "HPC;TopdownL5;tma_assists_group", + "MetricName": "tma_fp_assists", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called denormals).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists. ", + "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / SLOTS", + "MetricGroup": "HPC;TopdownL5;tma_assists_group", + "MetricName": "tma_avx_assists", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "Mispredictions" + }, + { + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * ((tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + (tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) ", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "Memory_Bandwidth" + }, + { + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricExpr": "100 * tma_memory_bound * ((tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + (tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + (tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)))", + "MetricGroup": "Mem;MemoryLat;Offcore", + "MetricName": "Memory_Latency" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * tma_memory_bound * ((tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + (tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound)) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores))) ", + "MetricGroup": "Mem;MemoryTLB;Offcore", + "MetricName": "Memory_Data_TLBs" + }, + { + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / SLOTS)", + "MetricGroup": "Ret", + "MetricName": "Branching_Overhead" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB", + "MetricName": "Big_Code" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - Big_Code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "Instruction_Fetch_BW" + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / CLKS", + "MetricGroup": "Ret;Summary", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "(tma_retiring * SLOTS) / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "UPI" + }, + { + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "(tma_retiring * SLOTS) / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "UpTB" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / IPC", + "MetricGroup": "Mem;Pipeline", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "tma_L1_group", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "SLOTS / (TOPDOWN.SLOTS / 2) if #SMT_on else 1", + "MetricGroup": "SMT;tma_L1_group", + "MetricName": "Slots_Utilization" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "Execute_per_Issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", + "MetricGroup": "Ret;SMT;tma_L1_group", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(1 * (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + FP_ARITH_INST_RETIRED2.SCALAR_HALF) + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16) / CORE_CLKS", + "MetricGroup": "Flops;Ret", + "MetricName": "FLOPc" + }, + { + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * CORE_CLKS)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "FP_Arith_Utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / ((UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "ILP" + }, + { + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricExpr": "(1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if SMT_2T_Utilization > 0.5 else 0", + "MetricGroup": "Cor;SMT", + "MetricName": "Core_Bound_Likely" + }, + { + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "IpLoad" + }, + { + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "IpStore" + }, + { + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "IpBranch" + }, + { + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "IpCall" + }, + { + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", + "MetricName": "IpTB" + }, + { + "BriefDescription": "Branch instructions per taken branch. ", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "BpTkBranch" + }, + { + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (1 * (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + FP_ARITH_INST_RETIRED2.SCALAR_HALF) + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16)", + "MetricGroup": "Flops;InsType", + "MetricName": "IpFLOP" + }, + { + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / ((FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + FP_ARITH_INST_RETIRED2.SCALAR) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.VECTOR))", + "MetricGroup": "Flops;InsType", + "MetricName": "IpArith", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "IpArith_Scalar_SP", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + }, + { + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "IpArith_Scalar_DP", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "IpArith_AVX128", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "IpArith_AVX256", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + }, + { + "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "IpArith_AVX512", + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + }, + { + "BriefDescription": "Instructions per FP Arithmetic AMX operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / AMX_OPS_RETIRED.BF16", + "MetricGroup": "Flops;FpVector;InsType;Server", + "MetricName": "IpArith_AMX_F16", + "PublicDescription": "Instructions per FP Arithmetic AMX operation (lower number means higher occurrence rate). Operations factored per matrices' sizes of the AMX instructions." + }, + { + "BriefDescription": "Instructions per Integer Arithmetic AMX operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / AMX_OPS_RETIRED.INT8", + "MetricGroup": "InsType;IntVector;Server", + "MetricName": "IpArith_AMX_Int8", + "PublicDescription": "Instructions per Integer Arithmetic AMX operation (lower number means higher occurrence rate). Operations factored per matrices' sizes of the AMX instructions." + }, + { + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricGroup": "Prefetches", + "MetricName": "IpSWPF" + }, + { + "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;tma_L1_group", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "(tma_retiring * SLOTS) / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "Retire" + }, + { + "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "Strings_Cycles" + }, + { + "BriefDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / cpu@ASSISTS.ANY\\,umask\\=0x1B@", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "IpAssist" + }, + { + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "Execute" + }, + { + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "Fetch_UpC" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "MetricGroup": "DSBmiss", + "MetricName": "DSB_Switch_Cost" + }, + { + "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "DSB_Misses" + }, + { + "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "IpDSB_Miss_Ret" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "IpMispredict" + }, + { + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": " (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "Branch_Misprediction_Cost" + }, + { + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "Cond_NT" + }, + { + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "Cond_TK" + }, + { + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "CallRet" + }, + { + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "Jump" + }, + { + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (Cond_NT + Cond_TK + CallRet + Jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "Other_Branches" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "MLP" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "L1MPKI" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1000 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "L1MPKI_Load" + }, + { + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "L2MPKI" + }, + { + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "L2MPKI_All" + }, + { + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "L2MPKI_Load" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1000 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "L2HPKI_All" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "L2HPKI_Load" + }, + { + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "L3MPKI" + }, + { + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "FB_HPKI" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_NMI_WATCHDOG", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * CORE_CLKS)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "L3_Cache_Access_BW" + }, + { + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1000 * L2_LINES_OUT.SILENT / Instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "L2_Evictions_Silent_PKI" + }, + { + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1000 * L2_LINES_OUT.NON_SILENT / Instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "L2_Evictions_NonSilent_PKI" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "L1D_Cache_Fill_BW", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L1D_Cache_Fill_BW_1T" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "L2_Cache_Fill_BW", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L2_Cache_Fill_BW_1T" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "L3_Cache_Fill_BW", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L3_Cache_Fill_BW_1T" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "L3_Cache_Access_BW", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "L3_Cache_Access_BW_1T" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "HPC;Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "Turbo_Utilization * msr@tsc@ / 1000000000 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "Average_Frequency" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "((1 * (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + FP_ARITH_INST_RETIRED2.SCALAR_HALF) + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16) / 1000000000) / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "GFLOPs", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Tera Integer (matrix) Operations Per Second", + "MetricExpr": "(8 * AMX_OPS_RETIRED.INT8 / 1e12) / duration_time", + "MetricGroup": "Cor;HPC;IntVector;Server", + "MetricName": "TIOPS" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0", + "MetricGroup": "SMT", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "Kernel_CPI" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "(64 * (uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@) / 1000000000) / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricName": "DRAM_BW_Use" + }, + { + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", + "MetricExpr": "1000000000 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (Socket_CLKS / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "MEM_Read_Latency" + }, + { + "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / cha@UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD\\,thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "MEM_Parallel_Reads" + }, + { + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", + "MetricExpr": "(1000000000 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@event\\=0x1@)", + "MetricGroup": "Mem;MemoryLat;Server;SoC", + "MetricName": "MEM_PMM_Read_Latency" + }, + { + "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", + "MetricExpr": " 1000000000 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@", + "MetricGroup": "Mem;MemoryLat;Server;SoC", + "MetricName": "MEM_DRAM_Read_Latency" + }, + { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricExpr": "((64 * UNC_M_PMM_RPQ_INSERTS / 1000000000) / duration_time)", + "MetricGroup": "Mem;MemoryBW;Server;SoC", + "MetricName": "PMM_Read_BW" + }, + { + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "((64 * UNC_M_PMM_WPQ_INSERTS / 1000000000) / duration_time)", + "MetricGroup": "Mem;MemoryBW;Server;SoC", + "MetricName": "PMM_Write_BW" + }, + { + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1000000000 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "IO_Write_BW" + }, + { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "uncore_cha_0@event\\=0x1@", + "MetricGroup": "SoC", + "MetricName": "Socket_CLKS" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "IpFarBranch" + }, + { + "BriefDescription": "C1 residency percent per core", + "MetricExpr": "(cstate_core@c1\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C1_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1000000000", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" + }, + { + "BriefDescription": "CPU operating frequency (in GHz)", + "MetricExpr": "(( CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ ) / 1000000000) / duration_time", + "MetricGroup": "", + "MetricName": "cpu_operating_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "loads_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", + "MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "stores_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "l1d_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions ", + "MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "l1d_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions ", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "l2_demand_data_read_hits_per_instr", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", + "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "l2_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "l2_demand_data_read_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", + "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "l2_demand_code_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "( UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA + UNC_CHA_TOR_INSERTS.IA_MISS_DRD + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF ) / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "llc_data_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "llc_code_read_mpi_demand_plus_prefetch", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) in nano seconds", + "MetricExpr": "( 1000000000 * ( UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD ) / ( UNC_CHA_CLOCKTICKS / ( source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD) * #num_packages ) ) ) * duration_time", + "MetricGroup": "", + "MetricName": "llc_demand_data_read_miss_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to local memory in nano seconds", + "MetricExpr": "( 1000000000 * ( UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL ) / ( UNC_CHA_CLOCKTICKS / ( source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL) * #num_packages ) ) ) * duration_time", + "MetricGroup": "", + "MetricName": "llc_demand_data_read_miss_latency_for_local_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to remote memory in nano seconds", + "MetricExpr": "( 1000000000 * ( UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE ) / ( UNC_CHA_CLOCKTICKS / ( source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE) * #num_packages ) ) ) * duration_time", + "MetricGroup": "", + "MetricName": "llc_demand_data_read_miss_latency_for_remote_requests", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to Intel(R) Optane(TM) Persistent Memory(PMEM) in nano seconds", + "MetricExpr": "( 1000000000 * ( UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM ) / ( UNC_CHA_CLOCKTICKS / ( source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM) * #num_packages ) ) ) * duration_time", + "MetricGroup": "", + "MetricName": "llc_demand_data_read_miss_to_pmem_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to DRAM in nano seconds", + "MetricExpr": "( 1000000000 * ( UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR ) / ( UNC_CHA_CLOCKTICKS / ( source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR) * #num_packages ) ) ) * duration_time", + "MetricGroup": "", + "MetricName": "llc_demand_data_read_miss_to_dram_latency", + "ScaleUnit": "1ns" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "itlb_2nd_level_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", + "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "itlb_2nd_level_large_page_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "dtlb_2nd_level_load_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", + "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "", + "MetricName": "dtlb_2nd_level_store_mpi", + "ScaleUnit": "1per_instr" + }, + { + "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "100 * ( UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL ) / ( UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE )", + "MetricGroup": "", + "MetricName": "numa_reads_addressed_to_local_dram", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", + "MetricExpr": "100 * ( UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE ) / ( UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE )", + "MetricGroup": "", + "MetricName": "numa_reads_addressed_to_remote_dram", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Uncore operating frequency in GHz", + "MetricExpr": "( UNC_CHA_CLOCKTICKS / ( source_count(UNC_CHA_CLOCKTICKS) * #num_packages ) / 1000000000) / duration_time", + "MetricGroup": "", + "MetricName": "uncore_frequency", + "ScaleUnit": "1GHz" + }, + { + "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", + "MetricExpr": "( UNC_UPI_TxL_FLITS.ALL_DATA * (64 / 9.0) / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "upi_data_transmit_bw", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory read bandwidth (MB/sec)", + "MetricExpr": "( UNC_M_CAS_COUNT.RD * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory write bandwidth (MB/sec)", + "MetricExpr": "( UNC_M_CAS_COUNT.WR * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "DDR memory bandwidth (MB/sec)", + "MetricExpr": "(( UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR ) * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory read bandwidth (MB/sec)", + "MetricExpr": "( UNC_M_PMM_RPQ_INSERTS * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "pmem_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory write bandwidth (MB/sec)", + "MetricExpr": "( UNC_M_PMM_WPQ_INSERTS * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "pmem_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory bandwidth (MB/sec)", + "MetricExpr": "(( UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS ) * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "pmem_memory_bandwidth_total", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", + "MetricExpr": "( UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "io_bandwidth_disk_or_network_writes", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", + "MetricExpr": "(( UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR ) * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "io_bandwidth_disk_or_network_reads", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "100 * ( IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS ) )", + "MetricGroup": "", + "MetricName": "percent_uops_delivered_from_decoded_icache", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "100 * ( IDQ.MITE_UOPS / ( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS ) )", + "MetricGroup": "", + "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", + "MetricExpr": "100 * ( IDQ.MS_UOPS / ( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS ) )", + "MetricGroup": "", + "MetricName": "percent_uops_delivered_from_microcode_sequencer", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", + "MetricExpr": "( UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "llc_miss_local_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", + "MetricExpr": "( UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "llc_miss_local_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", + "MetricExpr": "( UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "llc_miss_remote_memory_bandwidth_read", + "ScaleUnit": "1MB/s" + }, + { + "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", + "MetricExpr": "( UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1000000) / duration_time", + "MetricGroup": "", + "MetricName": "llc_miss_remote_memory_bandwidth_write", + "ScaleUnit": "1MB/s" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json new file mode 100644 index 000000000..41d7cd495 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json @@ -0,0 +1,499 @@ +[ + { + "BriefDescription": "IMC Clockticks at DCLK frequency", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "IMC Clockticks at HCLK frequency", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_M_HCLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM read CAS commands issued (does not include underfills)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_REG", + "PerPkg": "1", + "UMask": "0x00000000c1", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM underfill read CAS commands issued", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL", + "PerPkg": "1", + "UMask": "0x00000000c4", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM read CAS commands issued (including underfills)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "UMask": "0x00000000cf", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM write CAS commands issued", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "UMask": "0x00000000f0", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x10", + "EventName": "UNC_M_RPQ_INSERTS.PCH0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x10", + "EventName": "UNC_M_RPQ_INSERTS.PCH1", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x20", + "EventName": "UNC_M_WPQ_INSERTS.PCH0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x20", + "EventName": "UNC_M_WPQ_INSERTS.PCH1", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x80", + "EventName": "UNC_M_RPQ_OCCUPANCY_PCH0", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x81", + "EventName": "UNC_M_RPQ_OCCUPANCY_PCH1", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x82", + "EventName": "UNC_M_WPQ_OCCUPANCY_PCH0", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_M_WPQ_OCCUPANCY_PCH1", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.ALL_SCH0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.ALL_SCH1", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue inserts", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xe3", + "EventName": "UNC_M_PMM_RPQ_INSERTS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xe4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x03", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue inserts", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xe7", + "EventName": "UNC_M_PMM_WPQ_INSERTS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xE4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL_SCH0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xE4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL_SCH1", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Activate due to read, write, underfill, or bypass", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_M_ACT_COUNT.ALL", + "PerPkg": "1", + "UMask": "0x00000000ff", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Precharge due to read on page miss", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x0000000011", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Precharge due to write on page miss", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x0000000022", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharge due to (?)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.PGT", + "PerPkg": "1", + "UMask": "0x0000000088", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "Precharge due to read, write, underfill, or PGT", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.ALL", + "PerPkg": "1", + "UMask": "0x00000000ff", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM CAS commands issued", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.ALL", + "PerPkg": "1", + "UMask": "0x00000000ff", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_PRE_REG", + "PerPkg": "1", + "UMask": "0x00000000c2", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_PRE_UNDERFILL", + "PerPkg": "1", + "UMask": "0x00000000c8", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.WR_PRE", + "PerPkg": "1", + "UMask": "0x00000000e0", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.NO_GNT_SCH0", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.NO_GNT_SCH1", + "PerPkg": "1", + "UMask": "0x0000000008", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharge due to read", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.RD_PCH0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharge due to write", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.WR_PCH0", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.UFILL_PCH0", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Prechages from Page Table", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.PGT_PCH0", + "PerPkg": "1", + "UMask": "0x0000000008", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.RD_PCH1", + "PerPkg": "1", + "UMask": "0x0000000010", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.WR_PCH1", + "PerPkg": "1", + "UMask": "0x0000000020", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.UFILL_PCH1", + "PerPkg": "1", + "UMask": "0x0000000040", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.PGT_PCH1", + "PerPkg": "1", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.UFILL", + "PerPkg": "1", + "UMask": "0x0000000044", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM WR_CAS commands w/o auto-pre", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.WR_NONPRE", + "PerPkg": "1", + "UMask": "0x00000000D0", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 0", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.PCH0", + "PerPkg": "1", + "UMask": "0x0000000040", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.PCH1", + "PerPkg": "1", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xE0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.GNT_WAIT_SCH0", + "PerPkg": "1", + "UMask": "0x0000000010", + "UMaskExt": "0x00000000", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xE0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.GNT_WAIT_SCH1", + "PerPkg": "1", + "UMask": "0x0000000020", + "UMaskExt": "0x00000000", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json new file mode 100644 index 000000000..495ceee21 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json @@ -0,0 +1,5141 @@ +[ + { + "BriefDescription": "UPI Clockticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_UPI_CLOCKTICKS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent : All Data", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", + "PerPkg": "1", + "UMask": "0x000000000f", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "IRP Clockticks", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "IRP" + }, + { + "BriefDescription": "M2P Clockticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_M2P_CLOCKTICKS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "IIO Clockticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "PortMask": "0x0000", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part0 to Memory", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part1 to Memory", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part2 to Memory", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part3 to Memory", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "M2M Clockticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_M2M_CLOCKTICKS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "M3UPI Clockticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_M3UPI_CLOCKTICKS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Read requests from a unit on this socket", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests from a remote socket", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Write Requests from a unit on this socket", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Read and Write Requests; Writes Remote", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x0000000008", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Requests for exclusive ownership of a cache line without receiving data", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE", + "PerPkg": "1", + "UMask": "0x0000000030", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA Clockticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for CRd misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", + "PerPkg": "1", + "UMask": "0x00c80ffe01", + "UMaskExt": "0x00c80ffe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", + "PerPkg": "1", + "UMask": "0x00c817fe01", + "UMaskExt": "0x00c817fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd Pref misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF", + "PerPkg": "1", + "UMask": "0x00c897fe01", + "UMaskExt": "0x00c897fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for ItoM from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM", + "PerPkg": "1", + "UMask": "0x00cc43ff04", + "UMaskExt": "0x00cc43ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd misses from local IA targeting local memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL", + "PerPkg": "1", + "UMask": "0x00c816fe01", + "UMaskExt": "0x00c816fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd misses from local IA targeting remote memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE", + "PerPkg": "1", + "UMask": "0x00c8177e01", + "UMaskExt": "0x00c8177e", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd Pref misses from local IA targeting local memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL", + "PerPkg": "1", + "UMask": "0x00C896FE01", + "UMaskExt": "0x00C896FE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd Pref misses from local IA targeting remote memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE", + "PerPkg": "1", + "UMask": "0x00C8977E01", + "UMaskExt": "0x00C8977E", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRd misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", + "PerPkg": "1", + "UMask": "0x00c817fe01", + "UMaskExt": "0x00c817fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRd misses from local IA targeting local memory", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL", + "PerPkg": "1", + "UMask": "0x00c816fe01", + "UMaskExt": "0x00c816fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRd misses from local IA targeting remote memory", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE", + "PerPkg": "1", + "UMask": "0x00c8177e01", + "UMaskExt": "0x00c8177e", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRds issued by iA Cores targeting PMM Mem that Missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM", + "PerPkg": "1", + "UMask": "0x00c8178a01", + "UMaskExt": "0x00c8178a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRds issued by IA Cores targeting DDR Mem that Missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR", + "PerPkg": "1", + "UMask": "0x00c8178601", + "UMaskExt": "0x00c81786", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRds issued by iA Cores targeting DDR Mem that Missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR", + "PerPkg": "1", + "UMask": "0x00c8178601", + "UMaskExt": "0x00c81786", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRds issued by iA Cores targeting PMM Mem that Missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM", + "PerPkg": "1", + "UMask": "0x00c8178a01", + "UMaskExt": "0x00c8178a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for RdCur from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", + "PerPkg": "1", + "UMask": "0x00c8f3ff04", + "UMaskExt": "0x00c8f3ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for ItoMCacheNears from IO devices", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR", + "PerPkg": "1", + "UMask": "0x00cd43ff04", + "UMaskExt": "0x00cd43ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 0", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT1", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 2", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT2", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent : Data", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.DATA", + "PerPkg": "1", + "UMask": "0x0000000008", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent : LLCRD Not Empty", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.LLCRD", + "PerPkg": "1", + "UMask": "0x0000000010", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.NULL", + "PerPkg": "1", + "UMask": "0x0000000020", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent : LLCTRL", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.LLCTRL", + "PerPkg": "1", + "UMask": "0x0000000040", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent : Protocol Header", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.PROTHDR", + "PerPkg": "1", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent : All Non Data", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", + "PerPkg": "1", + "UMask": "0x0000000097", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Sent : Idle", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.IDLE", + "PerPkg": "1", + "UMask": "0x0000000047", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "All Null Flits", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", + "PerPkg": "1", + "UMask": "0x0000000027", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : Slot 0", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : Slot 1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT1", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : Slot 2", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT2", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : Data", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.DATA", + "PerPkg": "1", + "UMask": "0x0000000008", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : LLCRD Not Empty", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.LLCRD", + "PerPkg": "1", + "UMask": "0x0000000010", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : Slot NULL or LLCRD Empty", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.NULL", + "PerPkg": "1", + "UMask": "0x0000000020", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : LLCTRL", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.LLCTRL", + "PerPkg": "1", + "UMask": "0x0000000040", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : Protocol Header", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.PROTHDR", + "PerPkg": "1", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : All Data", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", + "PerPkg": "1", + "UMask": "0x000000000f", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : All Non Data", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", + "PerPkg": "1", + "UMask": "0x0000000097", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Valid Flits Received : Idle", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.IDLE", + "PerPkg": "1", + "UMask": "0x0000000047", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Null FLITs received from any slot", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", + "PerPkg": "1", + "UMask": "0x0000000027", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "UMask": "0x000000000e", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "UMask": "0x000000010e", + "UMaskExt": "0x00000001", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "UMask": "0x000000000f", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "UMask": "0x000000010f", + "UMaskExt": "0x00000001", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "UMask": "0x000000000e", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "UMask": "0x000000010e", + "UMaskExt": "0x00000001", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "UMask": "0x000000000f", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "UMask": "0x000000010f", + "UMaskExt": "0x00000001", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Direct packet attempts : D2C", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Cycles in L1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x21", + "EventName": "UNC_UPI_L1_POWER_CYCLES", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 0", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT1", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 2", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT2", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 0", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 2", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 0", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT1", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 2", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT2", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Tx Flit Buffer Allocations", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x40", + "EventName": "UNC_UPI_TxL_INSERTS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Tx Flit Buffer Bypassed", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x41", + "EventName": "UNC_UPI_TxL_BYPASSED", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "Tx Flit Buffer Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x42", + "EventName": "UNC_UPI_TxL_OCCUPANCY", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "UPI LL" + }, + { + "BriefDescription": "FAF allocation -- sent to ADQ", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x16", + "EventName": "UNC_I_FAF_TRANSACTIONS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF - request insert from TC", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x18", + "EventName": "UNC_I_FAF_INSERTS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF occupancy", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x19", + "EventName": "UNC_I_FAF_OCCUPANCY", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Inbound (p2p + faf + cset)", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound write (fast path) requests received by the IRP", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WR_PREF", + "PerPkg": "1", + "UMask": "0x0000000008", + "UMaskExt": "0x00000000", + "Unit": "IRP" + }, + { + "BriefDescription": "CMS Clockticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_M2P_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part0 to Memory", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part1 to Memory", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part2 to Memory", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part3 to Memory", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", + "Counter": "2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", + "Counter": "2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU", + "Counter": "2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU", + "Counter": "2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "Counter": "2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "Counter": "2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "Counter": "2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "Counter": "2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "Counter": "0,1", + "CounterType": "PGMABLE", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 4", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 5", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 6", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 7", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", + "Counter": "2,3", + "CounterType": "PGMABLE", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0x00000000ff", + "UMaskExt": "0x00000000", + "Unit": "IIO" + }, + { + "BriefDescription": "AD Ingress (from CMS) : AD Ingress (from CMS) Allocations", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x02", + "EventName": "UNC_M2M_RxC_AD_INSERTS", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x03", + "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to core (bypassing the CHA)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x16", + "EventName": "UNC_M2M_DIRECT2CORE_TAKEN", + "PerPkg": "1", + "UMask": "0x07", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x17", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "UMask": "0x07", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction were overridden", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x18", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "UMask": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to the Intel UPI", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x19", + "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", + "PerPkg": "1", + "UMask": "0x07", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to Intel UPI was disabled", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x1a", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "UMask": "0x07", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x1b", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "UMask": "0x07", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x1c", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "UMask": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "UMask": "0x01", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "UMask": "0x08", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "UMask": "0x02", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "UMask": "0x04", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to I", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "UMask": "0x0320", + "UMaskExt": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to S", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "UMask": "0x0340", + "UMaskExt": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "UMask": "0x0301", + "UMaskExt": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to A", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "UMask": "0x0304", + "UMaskExt": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to S", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "UMask": "0x0302", + "UMaskExt": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to A", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "UMask": "0x0310", + "UMaskExt": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to I", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "UMask": "0x0308", + "UMaskExt": "0x03", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 0", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x32", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x0000000104", + "UMaskExt": "0x00000001", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x32", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x0000000204", + "UMaskExt": "0x00000002", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 0", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x33", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 1", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x33", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x0000000008", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - All Channels", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0x000000000a", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - All Channels", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x0000000005", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x0000000005", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": ": UPI - All Channels", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x5d", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0x000000000a", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": ": XPT - All Channels", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x5d", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x0000000005", + "UMaskExt": "0x00000000", + "Unit": "M2M" + }, + { + "BriefDescription": "FlowQ Generated Prefetch", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x29", + "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2U Sent", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x2a", + "EventName": "UNC_M3UPI_D2U_SENT", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2C Sent", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x2b", + "EventName": "UNC_M3UPI_D2C_SENT", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M3UPI CMS Clockticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_M3UPI_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "UMask": "0x0000000010", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests made into the CHA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x0000000003", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Write requests made into the CHA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0x000000000c", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.SNP", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.HA", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.TOR", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Local InvItoE", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.LOCAL_INVITOE", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Local Rd", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.LOCAL_READ", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Clockticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0xc0", + "EventName": "UNC_CHA_CMS_CLOCKTICKS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_RD", + "PerPkg": "1", + "UMask": "0x00001bc1ff", + "UMaskExt": "0x00001bc1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Snoop Requests from a Remote Socket", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNP", + "PerPkg": "1", + "UMask": "0x00001c19ff", + "UMaskExt": "0x00001c19", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All Snoops from Remote", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.SNPS_FROM_REM", + "PerPkg": "1", + "UMask": "0x00c001ff08", + "UMaskExt": "0x00c001ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL", + "PerPkg": "1", + "UMask": "0x00C001FFff", + "UMaskExt": "0x00C001FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from Local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA", + "PerPkg": "1", + "UMask": "0x00c001ff01", + "UMaskExt": "0x00c001ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from Local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", + "PerPkg": "1", + "UMask": "0x00c001fd01", + "UMaskExt": "0x00c001fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", + "PerPkg": "1", + "UMask": "0x00c80ffd01", + "UMaskExt": "0x00c80ffd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", + "PerPkg": "1", + "UMask": "0x00c817fd01", + "UMaskExt": "0x00c817fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefRFO hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFRFO", + "PerPkg": "1", + "UMask": "0x00ccc7fd01", + "UMaskExt": "0x00ccc7fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", + "PerPkg": "1", + "UMask": "0x00c807fd01", + "UMaskExt": "0x00c807fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; misses from Local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", + "PerPkg": "1", + "UMask": "0x00c001fe01", + "UMaskExt": "0x00c001fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefRFO misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO", + "PerPkg": "1", + "UMask": "0x00ccc7fe01", + "UMaskExt": "0x00ccc7fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", + "PerPkg": "1", + "UMask": "0x00c807fe01", + "UMaskExt": "0x00c807fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO", + "PerPkg": "1", + "UMask": "0x00c001ff04", + "UMaskExt": "0x00c001ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", + "PerPkg": "1", + "UMask": "0x00c001fd04", + "UMaskExt": "0x00c001fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Misses from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", + "PerPkg": "1", + "UMask": "0x00c001fe04", + "UMaskExt": "0x00c001fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; ItoM misses from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", + "PerPkg": "1", + "UMask": "0x00cc43fe04", + "UMaskExt": "0x00cc43fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", + "PerPkg": "1", + "UMask": "0x00c803fe04", + "UMaskExt": "0x00c803fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IRQ - iA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ_IA", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : SF/LLC Evictions", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.EVICT", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PRQ - IOSF", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ_IOSF", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IPQ", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IPQ", + "PerPkg": "1", + "UMask": "0x0000000008", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IRQ - Non iA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ_NON_IA", + "PerPkg": "1", + "UMask": "0x0000000010", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PRQ - Non IOSF", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ_NON_IOSF", + "PerPkg": "1", + "UMask": "0x0000000020", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RRQ", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.RRQ", + "PerPkg": "1", + "UMask": "0x0000000040", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBQ", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.WBQ", + "PerPkg": "1", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_IO", + "PerPkg": "1", + "UMask": "0x00C000FF04", + "UMaskExt": "0x00C000FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local iA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_IA", + "PerPkg": "1", + "UMask": "0x00c000ff01", + "UMaskExt": "0x00c000ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local iA and IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", + "PerPkg": "1", + "UMask": "0x00C000FF05", + "UMaskExt": "0x00C000FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All Snoops from Remote", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REM_SNPS", + "PerPkg": "1", + "UMask": "0x00C001FF08", + "UMaskExt": "0x00C001FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Remote", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REM_ALL", + "PerPkg": "1", + "UMask": "0x00C001FFC8", + "UMaskExt": "0x00C001FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Hits", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.HIT", + "PerPkg": "1", + "UMaskExt": "0x00000001", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Misses", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MISS", + "PerPkg": "1", + "UMaskExt": "0x00000002", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : MMCFG Access", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MMCFG", + "PerPkg": "1", + "UMaskExt": "0x00000020", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : MMIO Access", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MMIO", + "PerPkg": "1", + "UMaskExt": "0x00000040", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Local Targets", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOCAL_TGT", + "PerPkg": "1", + "UMaskExt": "0x00000080", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Remote Targets", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REMOTE_TGT", + "PerPkg": "1", + "UMaskExt": "0x00000100", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MATCH_OPC", + "PerPkg": "1", + "UMaskExt": "0x00000200", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PREMORPH_OPC", + "PerPkg": "1", + "UMaskExt": "0x00000400", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NonCoherent", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NONCOH", + "PerPkg": "1", + "UMaskExt": "0x01000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just ISOC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ISOC", + "PerPkg": "1", + "UMaskExt": "0x02000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD_PREF", + "PerPkg": "1", + "UMask": "0x00c88ffd01", + "UMaskExt": "0x00c88ffd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Pref hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_PREF", + "PerPkg": "1", + "UMask": "0x00c897fd01", + "UMaskExt": "0x00c897fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT", + "PerPkg": "1", + "UMask": "0x00c827fd01", + "UMaskExt": "0x00c827fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt Pref hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT_PREF", + "PerPkg": "1", + "UMask": "0x00c8a7fd01", + "UMaskExt": "0x00c8a7fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO Pref hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO_PREF", + "PerPkg": "1", + "UMask": "0x00c887fd01", + "UMaskExt": "0x00c887fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF", + "PerPkg": "1", + "UMask": "0x00c88ffe01", + "UMaskExt": "0x00c88ffe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT", + "PerPkg": "1", + "UMask": "0x00c827fe01", + "UMaskExt": "0x00c827fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt Pref misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "UMask": "0x00c8a7fe01", + "UMaskExt": "0x00c8a7fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO pref misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF", + "PerPkg": "1", + "UMask": "0x00c887fe01", + "UMaskExt": "0x00c887fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; ItoM hits from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOM", + "PerPkg": "1", + "UMask": "0x00cc43fd04", + "UMaskExt": "0x00cc43fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO hits from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_RFO", + "PerPkg": "1", + "UMask": "0x00c803fd04", + "UMaskExt": "0x00c803fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO", + "PerPkg": "1", + "UMask": "0x00c803ff04", + "UMaskExt": "0x00c803ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO pref from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", + "PerPkg": "1", + "UMask": "0x00c887ff01", + "UMaskExt": "0x00c887ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", + "PerPkg": "1", + "UMask": "0x00c807ff01", + "UMaskExt": "0x00c807ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefRFO from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO", + "PerPkg": "1", + "UMask": "0x00ccc7ff01", + "UMaskExt": "0x00ccc7ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD", + "PerPkg": "1", + "UMask": "0x00c817ff01", + "UMaskExt": "0x00c817ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Pref from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_PREF", + "PerPkg": "1", + "UMask": "0x00c897ff01", + "UMaskExt": "0x00c897ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT", + "PerPkg": "1", + "UMask": "0x00c827ff01", + "UMaskExt": "0x00c827ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt Pref from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF", + "PerPkg": "1", + "UMask": "0x00c8a7ff01", + "UMaskExt": "0x00c8a7ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD_PREF", + "PerPkg": "1", + "UMask": "0x00C88FFF01", + "UMaskExt": "0x00C88FFF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", + "PerPkg": "1", + "UMask": "0x00c80fff01", + "UMaskExt": "0x00c80fff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts RFO misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL", + "PerPkg": "1", + "UMask": "0x00c806fe01", + "UMaskExt": "0x00c806fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_REMOTE", + "PerPkg": "1", + "UMask": "0x00c8077e01", + "UMaskExt": "0x00c8077e", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO prefetch misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL", + "PerPkg": "1", + "UMask": "0x00c886fe01", + "UMaskExt": "0x00c886fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO prefetch misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_REMOTE", + "PerPkg": "1", + "UMask": "0x00c8877e01", + "UMaskExt": "0x00c8877e", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;CLFlush from Local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSH", + "PerPkg": "1", + "UMask": "0x00c8c7ff01", + "UMaskExt": "0x00c8c7ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;CLFlushOpt from Local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSHOPT", + "PerPkg": "1", + "UMask": "0x00c8d7ff01", + "UMaskExt": "0x00c8d7ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;ItoM from Local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOM", + "PerPkg": "1", + "UMask": "0x00cc47ff01", + "UMaskExt": "0x00cc47ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;SpecItoM from Local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_SPECITOM", + "PerPkg": "1", + "UMask": "0x00cc57ff01", + "UMaskExt": "0x00cc57ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All Snoops from Remote", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.SNPS_FROM_REM", + "PerPkg": "1", + "UMask": "0x00c001ff08", + "UMaskExt": "0x00c001ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x00C001FFff", + "UMaskExt": "0x00C001FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", + "PerPkg": "1", + "UMask": "0x00c001ff01", + "UMaskExt": "0x00c001ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", + "PerPkg": "1", + "UMask": "0x00c001fd01", + "UMaskExt": "0x00c001fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", + "PerPkg": "1", + "UMask": "0x00c80ffd01", + "UMaskExt": "0x00c80ffd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", + "PerPkg": "1", + "UMask": "0x00c817fd01", + "UMaskExt": "0x00c817fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefRFO hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFRFO", + "PerPkg": "1", + "UMask": "0x00ccc7fd01", + "UMaskExt": "0x00ccc7fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", + "PerPkg": "1", + "UMask": "0x00c807fd01", + "UMaskExt": "0x00c807fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from Local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", + "PerPkg": "1", + "UMask": "0x00c001fe01", + "UMaskExt": "0x00c001fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", + "PerPkg": "1", + "UMask": "0x00c80ffe01", + "UMaskExt": "0x00c80ffe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefRFO misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO", + "PerPkg": "1", + "UMask": "0x00ccc7fe01", + "UMaskExt": "0x00ccc7fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", + "PerPkg": "1", + "UMask": "0x00c807fe01", + "UMaskExt": "0x00c807fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", + "PerPkg": "1", + "UMask": "0x00c001ff04", + "UMaskExt": "0x00c001ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", + "PerPkg": "1", + "UMask": "0x00c001fd04", + "UMaskExt": "0x00c001fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", + "PerPkg": "1", + "UMask": "0x00c001fe04", + "UMaskExt": "0x00c001fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", + "PerPkg": "1", + "UMask": "0x00c803fe04", + "UMaskExt": "0x00c803fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM misses from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", + "PerPkg": "1", + "UMask": "0x00cc43fe04", + "UMaskExt": "0x00cc43fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IRQ - iA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_IA", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : SF/LLC Evictions", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PRQ - IOSF", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IPQ", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ", + "PerPkg": "1", + "UMask": "0x0000000008", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IRQ - Non iA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_NON_IA", + "PerPkg": "1", + "UMask": "0x0000000010", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PRQ - Non IOSF", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ_NON_IOSF", + "PerPkg": "1", + "UMask": "0x0000000020", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RRQ", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.RRQ", + "PerPkg": "1", + "UMask": "0x0000000040", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WBQ", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.WBQ", + "PerPkg": "1", + "UMask": "0x0000000080", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IO", + "PerPkg": "1", + "UMask": "0x00C000FF04", + "UMaskExt": "0x00C000FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local iA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IA", + "PerPkg": "1", + "UMask": "0x00C000FF01", + "UMaskExt": "0x00C000FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local iA and IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", + "PerPkg": "1", + "UMask": "0x00C000FF05", + "UMaskExt": "0x00C000FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All Snoops from Remote", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.REM_SNPS", + "PerPkg": "1", + "UMask": "0x00C001FF08", + "UMaskExt": "0x00C001FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Remote", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.REM_ALL", + "PerPkg": "1", + "UMask": "0x00C001FFC8", + "UMaskExt": "0x00C001FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Hits", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", + "PerPkg": "1", + "UMaskExt": "0x00000001", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Misses", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", + "PerPkg": "1", + "UMaskExt": "0x00000002", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : MMCFG Access", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MMCFG", + "PerPkg": "1", + "UMaskExt": "0x00000020", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : MMIO Access", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MMIO", + "PerPkg": "1", + "UMaskExt": "0x00000040", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Local Targets", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOCAL_TGT", + "PerPkg": "1", + "UMaskExt": "0x00000080", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Remote Targets", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.REMOTE_TGT", + "PerPkg": "1", + "UMaskExt": "0x00000100", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MATCH_OPC", + "PerPkg": "1", + "UMaskExt": "0x00000200", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PREMORPH_OPC", + "PerPkg": "1", + "UMaskExt": "0x00000400", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NonCoherent", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NONCOH", + "PerPkg": "1", + "UMaskExt": "0x01000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just ISOC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ISOC", + "PerPkg": "1", + "UMaskExt": "0x02000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD_PREF", + "PerPkg": "1", + "UMask": "0x00c88ffd01", + "UMaskExt": "0x00c88ffd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_PREF", + "PerPkg": "1", + "UMask": "0x00c897fd01", + "UMaskExt": "0x00c897fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT", + "PerPkg": "1", + "UMask": "0x00c827fd01", + "UMaskExt": "0x00c827fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt Pref hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT_PREF", + "PerPkg": "1", + "UMask": "0x00c8a7fd01", + "UMaskExt": "0x00c8a7fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO Pref hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO_PREF", + "PerPkg": "1", + "UMask": "0x00c887fd01", + "UMaskExt": "0x00c887fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF", + "PerPkg": "1", + "UMask": "0x00c88ffe01", + "UMaskExt": "0x00c88ffe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF", + "PerPkg": "1", + "UMask": "0x00c897fe01", + "UMaskExt": "0x00c897fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT", + "PerPkg": "1", + "UMask": "0x00c827fe01", + "UMaskExt": "0x00c827fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt Pref misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "UMask": "0x00c8a7fe01", + "UMaskExt": "0x00c8a7fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF", + "PerPkg": "1", + "UMask": "0x00c887fe01", + "UMaskExt": "0x00c887fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM hits from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOM", + "PerPkg": "1", + "UMask": "0x00cc43fd04", + "UMaskExt": "0x00cc43fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO hits from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_RFO", + "PerPkg": "1", + "UMask": "0x00c803fd04", + "UMaskExt": "0x00c803fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ItoM from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_RFO", + "PerPkg": "1", + "UMask": "0x00c803ff04", + "UMaskExt": "0x00c803ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOM", + "PerPkg": "1", + "UMask": "0x00cc43ff04", + "UMaskExt": "0x00cc43ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO", + "PerPkg": "1", + "UMask": "0x00c807ff01", + "UMaskExt": "0x00c807ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO_PREF", + "PerPkg": "1", + "UMask": "0x00c887ff01", + "UMaskExt": "0x00c887ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefRFO from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFRFO", + "PerPkg": "1", + "UMask": "0x00ccc7ff01", + "UMaskExt": "0x00ccc7ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD", + "PerPkg": "1", + "UMask": "0x00c817ff01", + "UMaskExt": "0x00c817ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", + "PerPkg": "1", + "UMask": "0x00c827ff01", + "UMaskExt": "0x00c827ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt Pref from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT_PREF", + "PerPkg": "1", + "UMask": "0x00c8a7ff01", + "UMaskExt": "0x00c8a7ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD", + "PerPkg": "1", + "UMask": "0x00c80fff01", + "UMaskExt": "0x00c80fff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD_PREF", + "PerPkg": "1", + "UMask": "0x00c88fff01", + "UMaskExt": "0x00c88fff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_PREF", + "PerPkg": "1", + "UMask": "0x00c897ff01", + "UMaskExt": "0x00c897ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL", + "PerPkg": "1", + "UMask": "0x00C896FE01", + "UMaskExt": "0x00C896FE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE", + "PerPkg": "1", + "UMask": "0x00C8977E01", + "UMaskExt": "0x00C8977E", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_LOCAL", + "PerPkg": "1", + "UMask": "0x00c806fe01", + "UMaskExt": "0x00c806fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_REMOTE", + "PerPkg": "1", + "UMask": "0x00c8077e01", + "UMaskExt": "0x00c8077e", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_LOCAL", + "PerPkg": "1", + "UMask": "0x00c886fe01", + "UMaskExt": "0x00c886fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_REMOTE", + "PerPkg": "1", + "UMask": "0x00c8877e01", + "UMaskExt": "0x00c8877e", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in E state that are victimized on a fill", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_E", + "PerPkg": "1", + "UMask": "0x0000000002", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in M state that are victimized on a fill", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_M", + "PerPkg": "1", + "UMask": "0x0000000001", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in S state that are victimized on a fill", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_S", + "PerPkg": "1", + "UMask": "0x0000000004", + "UMaskExt": "0x00000000", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR", + "PerPkg": "1", + "UMask": "0x00cd43fd04", + "UMaskExt": "0x00cd43fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR", + "PerPkg": "1", + "UMask": "0x00cd43fe04", + "UMaskExt": "0x00cd43fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRDPTE", + "PerPkg": "1", + "UMask": "0x00c837fe01", + "UMaskExt": "0x00c837fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Hit the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRDPTE", + "PerPkg": "1", + "UMask": "0x00c837fd01", + "UMaskExt": "0x00c837fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRDPTE", + "PerPkg": "1", + "UMask": "0x00c837ff01", + "UMaskExt": "0x00c837ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOE", + "PerPkg": "1", + "UMask": "0xcc3fff01", + "UMaskExt": "0xcc3fff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RdCur and FsRdCur hits from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR", + "PerPkg": "1", + "UMask": "0x00c8f3fd04", + "UMaskExt": "0x00c8f3fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RdCur and FsRdCur misses from local IO", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR", + "PerPkg": "1", + "UMask": "0x00c8f3fe04", + "UMaskExt": "0x00c8f3fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RdCur and FsRdCur hits from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_PCIRDCUR", + "PerPkg": "1", + "UMask": "0x00c8f3fd04", + "UMaskExt": "0x00c8f3fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR", + "PerPkg": "1", + "UMask": "0x00c8f3fe04", + "UMaskExt": "0x00c8f3fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RdCur and FsRdCur from local IO", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_PCIRDCUR", + "PerPkg": "1", + "UMask": "0x00c8f3ff04", + "UMaskExt": "0x00c8f3ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefCode hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFCODE", + "PerPkg": "1", + "UMask": "0x00cccffd01", + "UMaskExt": "0x00cccffd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefData hits from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFDATA", + "PerPkg": "1", + "UMask": "0x00ccd7fd01", + "UMaskExt": "0x00ccd7fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefData from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFDATA", + "PerPkg": "1", + "UMask": "0x00ccd7ff01", + "UMaskExt": "0x00ccd7ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefCode misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFCODE", + "PerPkg": "1", + "UMask": "0x00cccffe01", + "UMaskExt": "0x00cccffe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefData misses from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA", + "PerPkg": "1", + "UMask": "0x00ccd7fe01", + "UMaskExt": "0x00ccd7fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefCode hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFCODE", + "PerPkg": "1", + "UMask": "0x00cccffd01", + "UMaskExt": "0x00cccffd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefData hits from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFDATA", + "PerPkg": "1", + "UMask": "0x00ccd7fd01", + "UMaskExt": "0x00ccd7fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefData from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFDATA", + "PerPkg": "1", + "UMask": "0x00ccd7ff01", + "UMaskExt": "0x00ccd7ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefCode misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFCODE", + "PerPkg": "1", + "UMask": "0x00cccffe01", + "UMaskExt": "0x00cccffe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefData misses from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA", + "PerPkg": "1", + "UMask": "0x00ccd7fe01", + "UMaskExt": "0x00ccd7fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefCode from local IA", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFCODE", + "PerPkg": "1", + "UMask": "0x00cccfff01", + "UMaskExt": "0x00cccfff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefCode from local IA", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFCODE", + "PerPkg": "1", + "UMask": "0x00cccfff01", + "UMaskExt": "0x00cccfff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_PMM", + "PerPkg": "1", + "UMask": "0x00c8168a01", + "UMaskExt": "0x00c8168a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_PMM", + "PerPkg": "1", + "UMask": "0x00c8170a01", + "UMaskExt": "0x00c8170a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_DDR", + "PerPkg": "1", + "UMask": "0x00c8168601", + "UMaskExt": "0x00c81686", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_DDR", + "PerPkg": "1", + "UMask": "0x00c8170601", + "UMaskExt": "0x00c81706", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_PMM", + "PerPkg": "1", + "UMask": "0x00C8978A01", + "UMaskExt": "0x00C8978A", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_PMM", + "PerPkg": "1", + "UMask": "0x00C8968A01", + "UMaskExt": "0x00C8968A", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_PMM", + "PerPkg": "1", + "UMask": "0x00C8970A01", + "UMaskExt": "0x00C8970A", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_DDR", + "PerPkg": "1", + "UMask": "0x00C8978601", + "UMaskExt": "0x00C89786", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_DDR", + "PerPkg": "1", + "UMask": "0x00C8968601", + "UMaskExt": "0x00C89686", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_DDR", + "PerPkg": "1", + "UMask": "0x00C8970601", + "UMaskExt": "0x00C89706", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed locally", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_LOCAL", + "PerPkg": "1", + "UMask": "0x00C80EFE01", + "UMaskExt": "0x00C80EFE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed remotely", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_REMOTE", + "PerPkg": "1", + "UMask": "0x00C80F7E01", + "UMaskExt": "0x00C80F7E", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_LOCAL", + "PerPkg": "1", + "UMask": "0x00C88EFE01", + "UMaskExt": "0x00C88EFE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_REMOTE", + "PerPkg": "1", + "UMask": "0x00C88F7E01", + "UMaskExt": "0x00C88F7E", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears issued by iA Cores", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOMCACHENEAR", + "PerPkg": "1", + "UMask": "0x00CD47FF01", + "UMaskExt": "0x00CD47FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WbMtoIs issued by an iA Cores. Modified Write Backs", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOI", + "PerPkg": "1", + "UMask": "0x00cc27ff01", + "UMaskExt": "0x00cc27ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Hit LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_ITOM", + "PerPkg": "1", + "UMask": "0x00CC47FD01", + "UMaskExt": "0x00CC47FD", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Missed LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_ITOM", + "PerPkg": "1", + "UMask": "0x00CC47FE01", + "UMaskExt": "0x00CC47FE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_UCRDF", + "PerPkg": "1", + "UMask": "0x00C877DE01", + "UMaskExt": "0x00C877DE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WIL", + "PerPkg": "1", + "UMask": "0x00C87FDE01", + "UMaskExt": "0x00C87FDE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WCILF", + "PerPkg": "1", + "UMask": "0x00C867FF01", + "UMaskExt": "0x00C867FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF", + "PerPkg": "1", + "UMask": "0x00C867FE01", + "UMaskExt": "0x00C867FE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_PMM", + "PerPkg": "1", + "UMask": "0x00C8678A01", + "UMaskExt": "0x00C8678A", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_PMM", + "PerPkg": "1", + "UMask": "0x00C8668A01", + "UMaskExt": "0x00C8668A", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_PMM", + "PerPkg": "1", + "UMask": "0x00C8670A01", + "UMaskExt": "0x00C8670A", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_DDR", + "PerPkg": "1", + "UMask": "0x00C8678601", + "UMaskExt": "0x00C86786", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_DDR", + "PerPkg": "1", + "UMask": "0x00C8668601", + "UMaskExt": "0x00C86686", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_DDR", + "PerPkg": "1", + "UMask": "0x00C8670601", + "UMaskExt": "0x00C86706", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WCIL", + "PerPkg": "1", + "UMask": "0x00C86FFF01", + "UMaskExt": "0x00C86FFF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL", + "PerPkg": "1", + "UMask": "0x00C86FFE01", + "UMaskExt": "0x00C86FFE", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_PMM", + "PerPkg": "1", + "UMask": "0x00C86F8A01", + "UMaskExt": "0x00C86F8A", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_PMM", + "PerPkg": "1", + "UMask": "0x00C86E8A01", + "UMaskExt": "0x00C86E8A", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_PMM", + "PerPkg": "1", + "UMask": "0x00C86F0A01", + "UMaskExt": "0x00C86F0A", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_DDR", + "PerPkg": "1", + "UMask": "0x00C86F8601", + "UMaskExt": "0x00C86F86", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_DDR", + "PerPkg": "1", + "UMask": "0x00C86E8601", + "UMaskExt": "0x00C86E86", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_DDR", + "PerPkg": "1", + "UMask": "0x00C86F0601", + "UMaskExt": "0x00C86F06", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WbMtoIs issued by IO Devices", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_WBMTOI", + "PerPkg": "1", + "UMask": "0x00CC23FF04", + "UMaskExt": "0x00CC23FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CLFlushes issued by IO Devices", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_CLFLUSH", + "PerPkg": "1", + "UMask": "0x00C8C3FF04", + "UMaskExt": "0x00C8C3FF", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_PMM", + "PerPkg": "1", + "UMask": "0x00c8168a01", + "UMaskExt": "0x00c8168a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_PMM", + "PerPkg": "1", + "UMask": "0x00c8170a01", + "UMaskExt": "0x00c8170a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_DDR", + "PerPkg": "1", + "UMask": "0x00c8168601", + "UMaskExt": "0x00c81686", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_DDR", + "PerPkg": "1", + "UMask": "0x00c8170601", + "UMaskExt": "0x00c81706", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_PMM", + "PerPkg": "1", + "UMask": "0x00c8978a01", + "UMaskExt": "0x00c8978a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_PMM", + "PerPkg": "1", + "UMask": "0x00c8968a01", + "UMaskExt": "0x00c8968a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_PMM", + "PerPkg": "1", + "UMask": "0x00c8970a01", + "UMaskExt": "0x00c8970a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_DDR", + "PerPkg": "1", + "UMask": "0x00c8978601", + "UMaskExt": "0x00c89786", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_DDR", + "PerPkg": "1", + "UMask": "0x00c8968601", + "UMaskExt": "0x00c89686", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_DDR", + "PerPkg": "1", + "UMask": "0x00c8970601", + "UMaskExt": "0x00c89706", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_LOCAL", + "PerPkg": "1", + "UMask": "0x00c80efe01", + "UMaskExt": "0x00c80efe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_REMOTE", + "PerPkg": "1", + "UMask": "0x00c80f7e01", + "UMaskExt": "0x00c80f7e", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_LOCAL", + "PerPkg": "1", + "UMask": "0x00c88efe01", + "UMaskExt": "0x00c88efe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_REMOTE", + "PerPkg": "1", + "UMask": "0x00c88f7e01", + "UMaskExt": "0x00c88f7e", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushes issued by iA Cores", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSH", + "PerPkg": "1", + "UMask": "0x00c8c7ff01", + "UMaskExt": "0x00c8c7ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSHOPT", + "PerPkg": "1", + "UMask": "0x00c8d7ff01", + "UMaskExt": "0x00c8d7ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOMCACHENEAR", + "PerPkg": "1", + "UMask": "0x00cd47ff01", + "UMaskExt": "0x00cd47ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : SpecItoMs issued by iA Cores", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_SPECITOM", + "PerPkg": "1", + "UMask": "0x00cc57ff01", + "UMaskExt": "0x00cc57ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WbMtoIs issued by iA Cores", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WBMTOI", + "PerPkg": "1", + "UMask": "0x00cc27ff01", + "UMaskExt": "0x00cc27ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOM", + "PerPkg": "1", + "UMask": "0x00cc47ff01", + "UMaskExt": "0x00cc47ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_ITOM", + "PerPkg": "1", + "UMask": "0x00cc47fd01", + "UMaskExt": "0x00cc47fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_ITOM", + "PerPkg": "1", + "UMask": "0x00cc47fe01", + "UMaskExt": "0x00cc47fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_UCRDF", + "PerPkg": "1", + "UMask": "0x00c877de01", + "UMaskExt": "0x00c877de", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WIL", + "PerPkg": "1", + "UMask": "0x00c87fde01", + "UMaskExt": "0x00c87fde", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCILF", + "PerPkg": "1", + "UMask": "0x00c867ff01", + "UMaskExt": "0x00c867ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF", + "PerPkg": "1", + "UMask": "0x00c867fe01", + "UMaskExt": "0x00c867fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_PMM", + "PerPkg": "1", + "UMask": "0x00c8678a01", + "UMaskExt": "0x00c8678a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_PMM", + "PerPkg": "1", + "UMask": "0x00c8668a01", + "UMaskExt": "0x00c8668a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_PMM", + "PerPkg": "1", + "UMask": "0x00c8670a01", + "UMaskExt": "0x00c8670a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_DDR", + "PerPkg": "1", + "UMask": "0x00c8678601", + "UMaskExt": "0x00c86786", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_DDR", + "PerPkg": "1", + "UMask": "0x00c8668601", + "UMaskExt": "0x00c86686", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_DDR", + "PerPkg": "1", + "UMask": "0x00c8670601", + "UMaskExt": "0x00c86706", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCIL", + "PerPkg": "1", + "UMask": "0x00c86fff01", + "UMaskExt": "0x00c86fff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL", + "PerPkg": "1", + "UMask": "0x00c86ffe01", + "UMaskExt": "0x00c86ffe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_PMM", + "PerPkg": "1", + "UMask": "0x00c86f8a01", + "UMaskExt": "0x00c86f8a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_PMM", + "PerPkg": "1", + "UMask": "0x00c86e8a01", + "UMaskExt": "0x00c86e8a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_PMM", + "PerPkg": "1", + "UMask": "0x00c86f0a01", + "UMaskExt": "0x00c86f0a", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_DDR", + "PerPkg": "1", + "UMask": "0x00c86f8601", + "UMaskExt": "0x00c86f86", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_DDR", + "PerPkg": "1", + "UMask": "0x00c86e8601", + "UMaskExt": "0x00c86e86", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_DDR", + "PerPkg": "1", + "UMask": "0x00c86f0601", + "UMaskExt": "0x00c86f06", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WbMtoIs issued by IO Devices", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_WBMTOI", + "PerPkg": "1", + "UMask": "0x00cc23ff04", + "UMaskExt": "0x00cc23ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushes issued by IO Devices", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_CLFLUSH", + "PerPkg": "1", + "UMask": "0x00c8c3ff04", + "UMaskExt": "0x00c8c3ff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOMCACHENEAR", + "PerPkg": "1", + "UMask": "0x00cd43fd04", + "UMaskExt": "0x00cd43fd", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR", + "PerPkg": "1", + "UMask": "0x00cd43fe04", + "UMaskExt": "0x00cd43fe", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PMM Access", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PMM", + "PerPkg": "1", + "UMaskExt": "0x00000008", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PMM Access", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PMM", + "PerPkg": "1", + "UMaskExt": "0x00000008", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DDR Access", + "CounterType": "PGMABLE", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.DDR", + "PerPkg": "1", + "UMaskExt": "0x00000004", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DDR Access", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.DDR", + "PerPkg": "1", + "UMaskExt": "0x00000004", + "Unit": "CHA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json new file mode 100644 index 000000000..6299afe54 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json @@ -0,0 +1,12 @@ +[ + { + "BriefDescription": "PCU PCLK Clockticks", + "Counter": "0,1,2,3", + "CounterType": "PGMABLE", + "EventCode": "0x01", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "UMaskExt": "0x00000000", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json new file mode 100644 index 000000000..f591f4fed --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/virtual-memory.json @@ -0,0 +1,245 @@ +[ + { + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0xe" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 1G page.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 4K page.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0xe" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 1G page.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x8" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 4K page.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.STLB_HIT", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x10" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0xe" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x4" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PEBScounters": "0,1,2,3", + "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.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.", + "CollectPEBSRecord": "2", + "Counter": "0,1,2,3", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PEBScounters": "0,1,2,3", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "Speculative": "1", + "UMask": "0x10" + } +] |