diff options
| author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
|---|---|---|
| committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-11 08:27:49 +0000 |
| commit | ace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch) | |
| tree | b2d64bc10158fdd5497876388cd68142ca374ed3 /tools/perf/pmu-events/arch/x86/tigerlake | |
| parent | Initial commit. (diff) | |
| download | linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip | |
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/tigerlake')
12 files changed, 4103 insertions, 0 deletions
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/cache.json b/tools/perf/pmu-events/arch/x86/tigerlake/cache.json new file mode 100644 index 0000000000..c54fb65d32 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/cache.json @@ -0,0 +1,571 @@ +[ + { + "BriefDescription": "Counts the number of cache lines replaced in L1 data cache.", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", + "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", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.L2_STALL", + "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", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of L1D misses that are outstanding", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 cache lines filling L2", + "EventCode": "0xf1", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "UMask": "0x1f" + }, + { + "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.", + "EventCode": "0xf2", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "EventCode": "0xf2", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 code requests", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, + { + "BriefDescription": "Demand Data Read access L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", + "SampleAfterValue": "200003", + "UMask": "0xe1" + }, + { + "BriefDescription": "RFO requests to L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_RFO", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "SampleAfterValue": "200003", + "UMask": "0xe2" + }, + { + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "UMask": "0xc4" + }, + { + "BriefDescription": "L2 cache misses when fetching instructions", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x24" + }, + { + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc1" + }, + { + "BriefDescription": "Demand Data Read miss L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", + "SampleAfterValue": "200003", + "UMask": "0x21" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses.", + "SampleAfterValue": "200003", + "UMask": "0x3f" + }, + { + "BriefDescription": "All accesses to L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses.", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "RFO requests that hit L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc2" + }, + { + "BriefDescription": "RFO requests that miss L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x22" + }, + { + "BriefDescription": "SW prefetch requests that hit L2 cache.", + "EventCode": "0x24", + "EventName": "L2_RQSTS.SWPF_HIT", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "SampleAfterValue": "200003", + "UMask": "0xc8" + }, + { + "BriefDescription": "SW prefetch requests that miss L2 cache.", + "EventCode": "0x24", + "EventName": "L2_RQSTS.SWPF_MISS", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "SampleAfterValue": "200003", + "UMask": "0x28" + }, + { + "BriefDescription": "L2 writebacks that access L2 cache", + "EventCode": "0xf0", + "EventName": "L2_TRANS.L2_WB", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x40" + }, + { + "BriefDescription": "Cycles when L1D is locked", + "EventCode": "0x63", + "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "PublicDescription": "This event counts the number of cycles when the L1D is locked. It is a superset of the 0x1 mask (BUS_LOCK_CLOCKS.BUS_LOCK_DURATION).", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Retired load instructions.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "PEBS": "1", + "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.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "PEBS": "1", + "PublicDescription": "Counts all retired store instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x82" + }, + { + "BriefDescription": "All retired memory instructions.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ANY", + "PEBS": "1", + "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "SampleAfterValue": "1000003", + "UMask": "0x83" + }, + { + "BriefDescription": "Retired load instructions with locked access.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with locked access.", + "SampleAfterValue": "100007", + "UMask": "0x21" + }, + { + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "PEBS": "1", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x42" + }, + { + "BriefDescription": "Retired load instructions that miss the STLB.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "PEBS": "1", + "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.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "PEBS": "1", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x12" + }, + { + "BriefDescription": "Snoop hit a modified(HITM) or clean line(HIT_W_FWD) in another on-pkg core which forwarded the data back due to a retired load instruction.", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions where a cross-core snoop hit in another cores caches on this socket, the data was forwarded back to the requesting core as the data was modified (SNOOP_HITM) or the L3 did not have the data(SNOOP_HIT_WITH_FWD).", + "SampleAfterValue": "20011", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "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", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Snoop hit without forwarding in another on-pkg core due to a retired load instruction, data was supplied by the L3.", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions in which the L3 supplied the data and a cross-core snoop hit in another cores caches on this socket but that other core did not forward the data back (SNOOP_HIT_NO_FWD).", + "SampleAfterValue": "20011", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "Data_LA": "1", + "EventCode": "0xd4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PEBS": "1", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access", + "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.", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "SampleAfterValue": "100007", + "UMask": "0x40" + }, + { + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "SampleAfterValue": "200003", + "UMask": "0x8" + }, + { + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PEBS": "1", + "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", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PEBS": "1", + "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", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "SampleAfterValue": "100021", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "SampleAfterValue": "50021", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts demand data reads that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a cacheline in the L3 where a snoop hit in another cores caches, data forwarding is required as the data is modified.", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand and prefetch data reads", + "EventCode": "0xb0", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Any memory transaction that reached the SQ.", + "EventCode": "0xb0", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Demand Data Read requests sent to uncore", + "EventCode": "0xb0", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "EventCode": "0xb0", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Demand Data Read transactions pending for off-core. Highly correlated.", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Counts the number of off-core outstanding Demand Data Read transactions every cycle. A transaction is considered to be in the Off-core outstanding state between L2 cache miss and data-return to the core.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Store Read transactions pending for off-core. Highly correlated.", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "EventCode": "0xf4", + "EventName": "SQ_MISC.BUS_LOCK", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles the superQ cannot take any more entries.", + "EventCode": "0xf4", + "EventName": "SQ_MISC.SQ_FULL", + "PublicDescription": "Counts the cycles for which the thread is active and the superQ cannot take any more entries.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of PREFETCHW instructions executed.", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.T0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x4" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json b/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json new file mode 100644 index 0000000000..63b5b56d1e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json @@ -0,0 +1,105 @@ +[ + { + "BriefDescription": "Counts all microcode FP assists.", + "EventCode": "0xc1", + "EventName": "ASSISTS.FP", + "PublicDescription": "Counts all microcode Floating Point assists.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "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.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "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.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "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.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "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.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x18" + }, + { + "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.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", + "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.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", + "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": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 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 single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 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": "0x60" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "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.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "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.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "1000003", + "UMask": "0xfc" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json b/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json new file mode 100644 index 0000000000..d7b972452c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json @@ -0,0 +1,377 @@ +[ + { + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "EventCode": "0xe6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to ILD_STALL.LCP]", + "EventCode": "0x87", + "EventName": "DECODE.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to ILD_STALL.LCP]", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, + { + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE transitions count.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xab", + "EventName": "DSB2MITE_SWITCHES.COUNT", + "PublicDescription": "Counts the number of Decode Stream Buffer (DSB a.k.a. Uop Cache)-to-MITE speculative transitions.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "DSB-to-MITE switch true penalty cycles.", + "EventCode": "0xab", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired Instructions who experienced DSB miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x1", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced a critical DSB miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PEBS": "1", + "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", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x14", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L1I_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x12", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x500106", + "PEBS": "1", + "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", + "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.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x508006", + "PEBS": "1", + "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", + "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.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "MSRValue": "0x501006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x500206", + "PEBS": "1", + "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", + "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.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "MSRIndex": "0x3F7", + "MSRValue": "0x510006", + "PEBS": "1", + "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", + "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.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x100206", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "SampleAfterValue": "100007", + "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.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "MSRIndex": "0x3F7", + "MSRValue": "0x502006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "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.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "MSRValue": "0x500406", + "PEBS": "1", + "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", + "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.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "MSRValue": "0x520006", + "PEBS": "1", + "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", + "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.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "MSRValue": "0x504006", + "PEBS": "1", + "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", + "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.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "MSRIndex": "0x3F7", + "MSRValue": "0x500806", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_DATA.STALLS]", + "EventCode": "0x80", + "EventName": "ICACHE_16B.IFDATA_STALL", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_DATA.STALLS]", + "SampleAfterValue": "500009", + "UMask": "0x4" + }, + { + "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_HIT", + "PublicDescription": "Counts instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_MISS", + "PublicDescription": "Counts instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity. Accounts for both cacheable and uncacheable accesses.", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_STALL", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_16B.IFDATA_STALL]", + "EventCode": "0x80", + "EventName": "ICACHE_DATA.STALLS", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_16B.IFDATA_STALL]", + "SampleAfterValue": "500009", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]", + "EventCode": "0x83", + "EventName": "ICACHE_TAG.STALLS", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_ANY", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles DSB is delivering optimal number of Uops", + "CounterMask": "5", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_OK", + "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", + "UMask": "0x8" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles MITE is delivering any Uop", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_ANY", + "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", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles MITE is delivering optimal number of Uops", + "CounterMask": "5", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_OK", + "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", + "UMask": "0x4" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_CYCLES_ANY", + "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", + "UMask": "0x30" + }, + { + "BriefDescription": "Number of switches from DSB or MITE to the MS", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "100003", + "UMask": "0x30" + }, + { + "BriefDescription": "Uops delivered to IDQ while MS is busy", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "SampleAfterValue": "100003", + "UMask": "0x30" + }, + { + "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled", + "EventCode": "0x9c", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled", + "CounterMask": "5", + "EventCode": "0x9c", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "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", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled", + "CounterMask": "1", + "EventCode": "0x9c", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "Invert": "1", + "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", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/memory.json b/tools/perf/pmu-events/arch/x86/tigerlake/memory.json new file mode 100644 index 0000000000..8848fcbcc3 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/memory.json @@ -0,0 +1,218 @@ +[ + { + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "CounterMask": "6", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x6" + }, + { + "BriefDescription": "Number of machine clears due to memory ordering conflicts.", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "1009", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "20011", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "503", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "101", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "2003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "50021", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand Data Read requests who miss L3 cache", + "EventCode": "0xb0", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Demand Data Read requests who miss L3 cache.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of times an RTM execution aborted.", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED", + "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)", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "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)", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "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", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "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", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "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", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Counts the number of times RTM commit succeeded.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an RTM execution started.", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed inside a transactional region", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC2", + "PublicDescription": "Counts Unfriendly TSX abort triggered by a vzeroupper instruction.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an instruction execution caused the transactional nest count supported to be exceeded", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC3", + "PublicDescription": "Counts Unfriendly TSX abort triggered by a nest count that is too deep.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_READ", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/tigerlake/metricgroups.json new file mode 100644 index 0000000000..a151ba9ccc --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/metricgroups.json @@ -0,0 +1,113 @@ +{ + "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BigFoot": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet", + "TopdownL1": "Metrics for top-down breakdown at level 1", + "TopdownL2": "Metrics for top-down breakdown at level 2", + "TopdownL3": "Metrics for top-down breakdown at level 3", + "TopdownL4": "Metrics for top-down breakdown at level 4", + "TopdownL5": "Metrics for top-down breakdown at level 5", + "TopdownL6": "Metrics for top-down breakdown at level 6", + "tma_L1_group": "Metrics for top-down breakdown at level 1", + "tma_L2_group": "Metrics for top-down breakdown at level 2", + "tma_L3_group": "Metrics for top-down breakdown at level 3", + "tma_L4_group": "Metrics for top-down breakdown at level 4", + "tma_L5_group": "Metrics for top-down breakdown at level 5", + "tma_L6_group": "Metrics for top-down breakdown at level 6", + "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category", + "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category", + "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category", + "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category", + "tma_core_bound_group": "Metrics contributing to tma_core_bound category", + "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category", + "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category", + "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category", + "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category", + "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category", + "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category", + "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category", + "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category", + "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category", + "tma_issue2P": "Metrics related by the issue $issue2P", + "tma_issueBC": "Metrics related by the issue $issueBC", + "tma_issueBM": "Metrics related by the issue $issueBM", + "tma_issueBW": "Metrics related by the issue $issueBW", + "tma_issueD0": "Metrics related by the issue $issueD0", + "tma_issueFB": "Metrics related by the issue $issueFB", + "tma_issueFL": "Metrics related by the issue $issueFL", + "tma_issueL1": "Metrics related by the issue $issueL1", + "tma_issueLat": "Metrics related by the issue $issueLat", + "tma_issueMC": "Metrics related by the issue $issueMC", + "tma_issueMS": "Metrics related by the issue $issueMS", + "tma_issueMV": "Metrics related by the issue $issueMV", + "tma_issueRFO": "Metrics related by the issue $issueRFO", + "tma_issueSL": "Metrics related by the issue $issueSL", + "tma_issueSO": "Metrics related by the issue $issueSO", + "tma_issueSmSt": "Metrics related by the issue $issueSmSt", + "tma_issueSpSt": "Metrics related by the issue $issueSpSt", + "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn", + "tma_issueTLB": "Metrics related by the issue $issueTLB", + "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category", + "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category", + "tma_light_operations_group": "Metrics contributing to tma_light_operations category", + "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category", + "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category", + "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category", + "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category", + "tma_mite_group": "Metrics contributing to tma_mite category", + "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category", + "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category", + "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category", + "tma_retiring_group": "Metrics contributing to tma_retiring category", + "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category", + "tma_store_bound_group": "Metrics contributing to tma_store_bound category", + "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category" +} diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/other.json b/tools/perf/pmu-events/arch/x86/tigerlake/other.json new file mode 100644 index 0000000000..55f3048bcf --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/other.json @@ -0,0 +1,35 @@ +[ + { + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.", + "EventCode": "0x28", + "EventName": "CORE_POWER.LVL0_TURBO_LICENSE", + "PublicDescription": "Counts Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes.", + "SampleAfterValue": "200003", + "UMask": "0x7" + }, + { + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX2 turbo schedule.", + "EventCode": "0x28", + "EventName": "CORE_POWER.LVL1_TURBO_LICENSE", + "PublicDescription": "Counts Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "UMask": "0x18" + }, + { + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", + "EventCode": "0x28", + "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchtecture). This includes high current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts streaming stores that have any type of response.", + "EventCode": "0xB7, 0xBB", + "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10800", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json new file mode 100644 index 0000000000..541bf1dd16 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json @@ -0,0 +1,809 @@ +[ + { + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.", + "CounterMask": "1", + "EventCode": "0x14", + "EventName": "ARITH.DIVIDER_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "SampleAfterValue": "1000003", + "UMask": "0x9" + }, + { + "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", + "EventCode": "0xc1", + "EventName": "ASSISTS.ANY", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware Examples include AD (page Access Dirty), FP and AVX related assists.", + "SampleAfterValue": "100003", + "UMask": "0x7" + }, + { + "BriefDescription": "All branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts all branch instructions retired.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Conditional branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND", + "PEBS": "1", + "PublicDescription": "Counts conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x11" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PEBS": "1", + "PublicDescription": "Counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" + }, + { + "BriefDescription": "Taken conditional branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN", + "PEBS": "1", + "PublicDescription": "Counts taken conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Far branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PEBS": "1", + "PublicDescription": "Counts far branch instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x40" + }, + { + "BriefDescription": "Indirect near branch instructions retired (excluding returns)", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT", + "PEBS": "1", + "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.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x2" + }, + { + "BriefDescription": "Return instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PEBS": "1", + "PublicDescription": "Counts return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "Taken branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "Counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "All mispredicted branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "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": "50021" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND", + "PEBS": "1", + "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "SampleAfterValue": "50021", + "UMask": "0x11" + }, + { + "BriefDescription": "Mispredicted non-taken conditional branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN", + "PEBS": "1", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "SampleAfterValue": "50021", + "UMask": "0x10" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "PEBS": "1", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "SampleAfterValue": "50021", + "UMask": "0x1" + }, + { + "BriefDescription": "All miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "PEBS": "1", + "PublicDescription": "Counts all miss-predicted indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).", + "SampleAfterValue": "50021", + "UMask": "0x80" + }, + { + "BriefDescription": "Mispredicted indirect CALL instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "PEBS": "1", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "SampleAfterValue": "50021", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "SampleAfterValue": "50021", + "UMask": "0x20" + }, + { + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET", + "PEBS": "1", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "SampleAfterValue": "50021", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycle counts are evenly distributed between active threads in the Core.", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", + "SampleAfterValue": "25003", + "UMask": "0x2" + }, + { + "BriefDescription": "Core crystal clock cycles. Cycle counts are evenly distributed between active threads in the Core.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the 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", + "UMask": "0x3" + }, + { + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "PublicDescription": "Counts core crystal clock cycles when the thread is unhalted.", + "SampleAfterValue": "25003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core cycles when the thread is not in halt state", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Thread cycles when thread is not in halt state", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "CounterMask": "8", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "CounterMask": "1", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "CounterMask": "16", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "CounterMask": "12", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "SampleAfterValue": "1000003", + "UMask": "0xc" + }, + { + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "CounterMask": "5", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "CounterMask": "20", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", + "SampleAfterValue": "1000003", + "UMask": "0x14" + }, + { + "BriefDescription": "Total execution stalls.", + "CounterMask": "4", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles when the memory subsystem has an outstanding load. Increments by 4 for every such cycle.", + "CounterMask": "5", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "PublicDescription": "Counts cycles when the memory subsystem has an outstanding load. Increments by 4 for every such cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x21" + }, + { + "BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.", + "CounterMask": "2", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "SampleAfterValue": "1000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Cycles no uop executed while RS was not empty, the SB was not full and there was no outstanding load.", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", + "SampleAfterValue": "1000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to DECODE.LCP]", + "EventCode": "0x87", + "EventName": "ILD_STALL.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to DECODE.LCP]", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, + { + "BriefDescription": "Instruction decoders utilized in a cycle", + "EventCode": "0x55", + "EventName": "INST_DECODED.DECODERS", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", + "EventName": "INST_RETIRED.ANY", + "PEBS": "1", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "PEBS": "1", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Retired NOP instructions.", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.NOP", + "PEBS": "1", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Precise instruction retired event with a reduced effect of PEBS shadow in IP distribution", + "EventName": "INST_RETIRED.PREC_DIST", + "PEBS": "1", + "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.", + "CounterMask": "1", + "EventCode": "0x0d", + "EventName": "INT_MISC.ALL_RECOVERY_CYCLES", + "PublicDescription": "Counts cycles the Backend cluster is recovering after a miss-speculation or a Store Buffer or Load Buffer drain stall.", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x0d", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "EventCode": "0x0d", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "SampleAfterValue": "500009", + "UMask": "0x80" + }, + { + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread", + "EventCode": "0x0d", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, + { + "BriefDescription": "TMA slots where uops got dropped", + "EventCode": "0x0d", + "EventName": "INT_MISC.UOP_DROPPING", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "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", + "UMask": "0x8" + }, + { + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "EventCode": "0x07", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", + "EventCode": "0x4c", + "EventName": "LOAD_HIT_PREFETCH.SWPF", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "1", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_ACTIVE", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.", + "CounterMask": "5", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_OK", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of Uops delivered by the LSD.", + "EventCode": "0xa8", + "EventName": "LSD.UOPS", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of machine clears (nukes) of any type.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.COUNT", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Self-modifying code (SMC) detected.", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Increments whenever there is an update to the LBR array.", + "EventCode": "0xcc", + "EventName": "MISC_RETIRED.LBR_INSERTS", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of retired PAUSE instructions. This event is not supported on first SKL and KBL products.", + "EventCode": "0xcc", + "EventName": "MISC_RETIRED.PAUSE_INST", + "PublicDescription": "Counts number of retired PAUSE instructions. This event is not supported on first SKL and KBL products.", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.SCOREBOARD", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "EventCode": "0x5e", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "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 stravation periods (e.g. branch mispredictions or i-cache misses)", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x5e", + "EventName": "RS_EVENTS.EMPTY_END", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", + "PublicDescription": "Counts the number of Top-down Microarchitecture Analysis (TMA) method's slots 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", + "UMask": "0x2" + }, + { + "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by branch mispredictions. This event estimates number of operations that were issued but not retired from the speculative path as well as the out-of-order engine recovery past a branch misprediction.", + "SampleAfterValue": "10000003", + "UMask": "0x8" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", + "EventName": "TOPDOWN.SLOTS", + "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", + "SampleAfterValue": "10000003", + "UMask": "0x4" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event", + "EventCode": "0xa4", + "EventName": "TOPDOWN.SLOTS_P", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", + "SampleAfterValue": "10000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of uops decoded out of instructions exclusively fetched by decoder 0", + "EventCode": "0x56", + "EventName": "UOPS_DECODED.DEC0", + "PublicDescription": "Uops exclusively fetched by decoder 0", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of uops executed on port 0", + "EventCode": "0xa1", + "EventName": "UOPS_DISPATCHED.PORT_0", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of uops executed on port 1", + "EventCode": "0xa1", + "EventName": "UOPS_DISPATCHED.PORT_1", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of uops executed on port 2 and 3", + "EventCode": "0xa1", + "EventName": "UOPS_DISPATCHED.PORT_2_3", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 2 and 3.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of uops executed on port 4 and 9", + "EventCode": "0xa1", + "EventName": "UOPS_DISPATCHED.PORT_4_9", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 5 and 9.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of uops executed on port 5", + "EventCode": "0xa1", + "EventName": "UOPS_DISPATCHED.PORT_5", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of uops executed on port 6", + "EventCode": "0xa1", + "EventName": "UOPS_DISPATCHED.PORT_6", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of uops executed on port 7 and 8", + "EventCode": "0xa1", + "EventName": "UOPS_DISPATCHED.PORT_7_8", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to ports 7 and 8.", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of uops executed on the core.", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Counts the number of uops executed from any thread.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "CounterMask": "2", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "CounterMask": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "CounterMask": "4", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "CounterMask": "2", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "CounterMask": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "CounterMask": "4", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.THREAD", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of x87 uops dispatched.", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Uops that RAT issues to RS", + "EventCode": "0x0e", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when RAT does not issue Uops to RS for the thread", + "CounterMask": "1", + "EventCode": "0x0e", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", + "EventCode": "0x0e", + "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retirement slots used.", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.SLOTS", + "PublicDescription": "Counts the retirement slots used each cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles with less than 10 actually retired uops.", + "CounterMask": "10", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts the number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json new file mode 100644 index 0000000000..fab084e1bc --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -0,0 +1,1561 @@ +[ + { + "BriefDescription": "C10 residency percent per package", + "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C10_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C8 residency percent per package", + "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C8_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "C9 residency percent per package", + "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C9_Pkg_Residency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" + }, + { + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * ASSISTS.ANY / tma_info_thread_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_thread_slots", + "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1;Default", + "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 category represents fraction of slots wasted due to incorrect speculations", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)", + "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1;Default", + "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 where the CPU was retiring branch instructions.", + "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_branch_instructions", + "MetricThreshold": "tma_branch_instructions > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(49 * tma_info_system_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))) + 48 * tma_info_system_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "48 * tma_info_system_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) / tma_info_thread_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "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@) / tma_info_core_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35))", + "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_thread_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_thread_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks - tma_l2_bound", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_thread_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_bottleneck_memory_data_tlbs", + "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) / tma_info_core_core_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_bottleneck_memory_data_tlbs", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "54 * tma_info_system_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_thread_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_thread_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "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_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "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. Related metrics: tma_decoder0_alone", + "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", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "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 approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "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. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "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) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "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. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "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) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "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. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "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) / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_512b", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "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. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_thread_slots", + "MetricGroup": "Default;PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1;Default", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_thread_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "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": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricConstraint": "NO_GROUP_EVENTS", + "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)) * tma_info_thread_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_bad_spec_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_bottleneck_mispredictions, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200" + }, + { + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_cond_taken", + "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_taken < 200" + }, + { + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_indirect", + "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1e3" + }, + { + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmisp_ret", + "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_bad_spec_ipmispredict", + "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200" + }, + { + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_botlnk_l0_core_bound_likely", + "MetricThreshold": "tma_info_botlnk_l0_core_bound_likely > 0.5" + }, + { + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "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_lsd + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_botlnk_l2_dsb_misses", + "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_botlnk_l2_ic_misses", + "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", + "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;tma_issueBC", + "MetricName": "tma_info_bottleneck_big_code", + "MetricThreshold": "tma_info_bottleneck_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_bottleneck_branching_overhead" + }, + { + "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)) / tma_info_thread_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_bottleneck_branching_overhead", + "MetricThreshold": "tma_info_bottleneck_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_bottleneck_big_code" + }, + { + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "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)) - tma_info_bottleneck_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_bottleneck_instruction_fetch_bw", + "MetricThreshold": "tma_info_bottleneck_instruction_fetch_bw > 20" + }, + { + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_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_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_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_bottleneck_memory_bandwidth", + "MetricThreshold": "tma_info_bottleneck_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_system_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "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_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + 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_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_bottleneck_memory_data_tlbs", + "MetricThreshold": "tma_info_bottleneck_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_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_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_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_bottleneck_memory_latency", + "MetricThreshold": "tma_info_bottleneck_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "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;tma_issueBM", + "MetricName": "tma_info_bottleneck_mispredictions", + "MetricThreshold": "tma_info_bottleneck_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "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": "tma_info_branches_callret" + }, + { + "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": "tma_info_branches_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": "tma_info_branches_cond_tk" + }, + { + "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": "tma_info_branches_jump" + }, + { + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk + tma_info_branches_callret + tma_info_branches_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_branches_other_branches" + }, + { + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_core_clks" + }, + { + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_core_coreipc" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_core_flopc" + }, + { + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_core_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": "tma_info_core_ilp" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_frontend_dsb_coverage", + "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 5 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp" + }, + { + "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": "tma_info_frontend_dsb_switch_cost" + }, + { + "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": "tma_info_frontend_fetch_upc" + }, + { + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_frontend_icache_miss_latency" + }, + { + "BriefDescription": "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": "tma_info_frontend_ipdsb_miss_ret", + "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50" + }, + { + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_frontend_ipunknown_branch" + }, + { + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code" + }, + { + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_frontend_l2mpki_code_all" + }, + { + "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", + "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "Fed;LSD", + "MetricName": "tma_info_frontend_lsd_coverage" + }, + { + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_bptkbranch" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_inst_mix_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" + }, + { + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_inst_mix_iparith", + "MetricThreshold": "tma_info_inst_mix_iparith < 10", + "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 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)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_iparith_avx128", + "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10", + "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)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_iparith_avx256", + "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10", + "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)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_inst_mix_iparith_avx512", + "MetricThreshold": "tma_info_inst_mix_iparith_avx512 < 10", + "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 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": "tma_info_inst_mix_iparith_scalar_dp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10", + "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 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": "tma_info_inst_mix_iparith_scalar_sp", + "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10", + "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 Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_inst_mix_ipbranch", + "MetricThreshold": "tma_info_inst_mix_ipbranch < 8" + }, + { + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_inst_mix_ipcall", + "MetricThreshold": "tma_info_inst_mix_ipcall < 200" + }, + { + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_inst_mix_ipflop", + "MetricThreshold": "tma_info_inst_mix_ipflop < 10" + }, + { + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_inst_mix_ipload", + "MetricThreshold": "tma_info_inst_mix_ipload < 3" + }, + { + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_inst_mix_ipstore", + "MetricThreshold": "tma_info_inst_mix_ipstore < 8" + }, + { + "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": "tma_info_inst_mix_ipswpf", + "MetricThreshold": "tma_info_inst_mix_ipswpf < 100" + }, + { + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_inst_mix_iptb", + "MetricThreshold": "tma_info_inst_mix_iptb < 11", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l1d_cache_fill_bw" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l2_cache_fill_bw" + }, + { + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_core_l3_cache_access_bw" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_core_l3_cache_fill_bw" + }, + { + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_fb_hpki" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l1mpki" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l1mpki_load" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l2hpki_all" + }, + { + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l2hpki_load" + }, + { + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_memory_l2mpki" + }, + { + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_memory_l2mpki_all" + }, + { + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l2mpki_load" + }, + { + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_memory_l3mpki" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_memory_load_miss_real_latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_memory_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + }, + { + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_data_l2_mlp" + }, + { + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_memory_oro_load_l2_miss_latency" + }, + { + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_memory_oro_load_l2_mlp" + }, + { + "BriefDescription": "Average Latency for L3 cache miss demand Loads", + "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_memory_oro_load_l3_miss_latency" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l1d_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l2_cache_fill_bw_1t" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_memory_thread_l3_cache_access_bw_1t" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_memory_core_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_memory_thread_l3_cache_fill_bw_1t" + }, + { + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_memory_tlb_code_stlb_mpki" + }, + { + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_load_stlb_mpki" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * tma_info_core_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_page_walks_utilization", + "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5" + }, + { + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_memory_tlb_store_stlb_mpki" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_pipeline_execute" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_pipeline_retire" + }, + { + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_system_average_frequency" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_system_cpu_utilization" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_system_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_system_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": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_system_ipfarbranch", + "MetricThreshold": "tma_info_system_ipfarbranch < 1e6" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_cpi" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_system_kernel_utilization", + "MetricThreshold": "tma_info_system_kernel_utilization > 0.05" + }, + { + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_system_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + }, + { + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_system_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" + }, + { + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / arb@event\\=0x81\\,umask\\=0x1@", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_system_mem_request_latency" + }, + { + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", + "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_system_power_license0_utilization", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + }, + { + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", + "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_system_power_license1_utilization", + "MetricThreshold": "tma_info_system_power_license1_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + }, + { + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", + "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_system_power_license2_utilization", + "MetricThreshold": "tma_info_system_power_license2_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + }, + { + "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": "tma_info_system_smt_2t_utilization" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_system_turbo_utilization" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_thread_clks" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_thread_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_thread_cpi" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_thread_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 (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_thread_ipc" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots" + }, + { + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_thread_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_thread_slots_utilization" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "tma_retiring * tma_info_thread_slots / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_thread_uoppi", + "MetricThreshold": "tma_info_thread_uoppi > 1.05" + }, + { + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_thread_uptb", + "MetricThreshold": "tma_info_thread_uptb < 7.5" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_thread_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_thread_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_thread_clks)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_thread_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "17.5 * tma_info_system_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_bottleneck_memory_latency, tma_mem_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_thread_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * tma_info_core_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric 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_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "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 / tma_info_thread_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "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))) / tma_info_thread_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", + "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / tma_info_core_core_clks / 2", + "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_lsd", + "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "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;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_thread_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_sq_full", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_bottleneck_memory_latency, tma_l3_hit_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "tma_retiring * tma_info_thread_slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_thread_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_info_bottleneck_mispredictions", + "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) / tma_info_core_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_thread_clks", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", + "MetricName": "tma_mite_4wide", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_thread_ipc / 5 > 0.35))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", + "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "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. Related metrics: tma_ms_switches", + "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 / tma_info_thread_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", + "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", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_branch_instructions + tma_nop_instructions))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "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", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_5 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "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@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_thread_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_thread_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "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 category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "DefaultMetricgroupName": "TopdownL1", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_thread_slots", + "MetricGroup": "Default;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1;Default", + "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 cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_thread_clks", + "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric represents fraction of cycles 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. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_thread_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "tma_info_memory_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_thread_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_bottleneck_memory_bandwidth, tma_info_system_dram_bw_use, tma_mem_bandwidth", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_thread_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "(L2_RQSTS.RFO_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)) / tma_info_thread_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", + "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_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "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 / tma_info_core_core_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "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 / tma_info_thread_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", + "MetricName": "tma_streaming_stores", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often CPU was stalled due to 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. Related metrics: tma_fb_full", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "10 * BACLEARS.ANY / tma_info_thread_clks", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: BACLEARS.ANY", + "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_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "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": "Percentage of cycles in aborted transactions.", + "MetricExpr": "(max(cycles\\-t - cycles\\-ct, 0) / cycles if has_event(cycles\\-t) else 0)", + "MetricGroup": "transaction", + "MetricName": "tsx_aborted_cycles", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", + "MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_elision", + "ScaleUnit": "1cycles / elision" + }, + { + "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", + "MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_transaction", + "ScaleUnit": "1cycles / transaction" + }, + { + "BriefDescription": "Percentage of cycles within a transaction region.", + "MetricExpr": "(cycles\\-t / cycles if has_event(cycles\\-t) else 0)", + "MetricGroup": "transaction", + "MetricName": "tsx_transactional_cycles", + "ScaleUnit": "100%" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json new file mode 100644 index 0000000000..eed1b90a27 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json @@ -0,0 +1,90 @@ +[ + { + "BriefDescription": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "EventCode": "0x84", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of any coherent request at memory controller that were issued by any core.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD", + "EventCode": "0x81", + "EventName": "UNC_ARB_DAT_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_DAT_OCCUPANCY.ALL", + "EventCode": "0x85", + "EventName": "UNC_ARB_IFA_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_OCCUPANCY.RD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_REQUESTS.RD]", + "EventCode": "0x81", + "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from it's allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_OCCUPANCY.DRD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "UNC_ARB_TRK_REQUESTS.ALL", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_REQUEST.DRD]", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-memory.json new file mode 100644 index 0000000000..99fb5259fd --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-memory.json @@ -0,0 +1,50 @@ +[ + { + "BriefDescription": "Counts every read (RdCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC0_RDCAS_COUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "imc_free_running_0" + }, + { + "BriefDescription": "Counts every 64B read and write request entering the Memory Controller to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC0_TOTAL_REQCOUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "imc_free_running_0" + }, + { + "BriefDescription": "Counts every write (WrCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC0_WRCAS_COUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "imc_free_running_0" + }, + { + "BriefDescription": "Counts every read (RdCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC1_RDCAS_COUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "imc_free_running_1" + }, + { + "BriefDescription": "Counts every 64B read and write request entering the Memory Controller to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC1_TOTAL_REQCOUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "imc_free_running_1" + }, + { + "BriefDescription": "Counts every write (WrCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC1_WRCAS_COUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "imc_free_running_1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json new file mode 100644 index 0000000000..c6596ba091 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json @@ -0,0 +1,9 @@ +[ + { + "BriefDescription": "UNC_CLOCK.SOCKET", + "EventCode": "0xff", + "EventName": "UNC_CLOCK.SOCKET", + "PerPkg": "1", + "Unit": "CLOCK" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/tigerlake/virtual-memory.json new file mode 100644 index 0000000000..adb2f6b3e7 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/virtual-memory.json @@ -0,0 +1,165 @@ +[ + { + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.", + "CounterMask": "1", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 4K page.", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.", + "CounterMask": "1", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 4K page.", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.", + "CounterMask": "1", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "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", + "UMask": "0x10" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "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", + "UMask": "0x4" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "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", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "DTLB flush attempts of the thread-specific entries", + "EventCode": "0xbd", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "STLB flush attempts", + "EventCode": "0xbd", + "EventName": "TLB_FLUSH.STLB_ANY", + "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", + "SampleAfterValue": "100007", + "UMask": "0x20" + } +] |