diff options
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/ivytown')
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/cache.json | 1260 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/floating-point.json | 169 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/frontend.json | 315 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json | 847 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/memory.json | 503 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/other.json | 44 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/pipeline.json | 1272 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json | 3391 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json | 1767 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json | 1812 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/uncore-other.json | 2398 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json | 687 | ||||
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/virtual-memory.json | 198 |
13 files changed, 14663 insertions, 0 deletions
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/cache.json b/tools/perf/pmu-events/arch/x86/ivytown/cache.json new file mode 100644 index 000000000..d95b98c83 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/cache.json @@ -0,0 +1,1260 @@ +[ + { + "BriefDescription": "L1D data line replacements", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts the number of lines brought into the L1 data cache.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PublicDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "L1D miss outstanding duration in cycles", + "Counter": "2", + "CounterHTOff": "2", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Increments the number of outstanding L1D misses every cycle. Set Cmask = 1 and Edge =1 to count occurrences.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "2", + "CounterHTOff": "2", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core", + "Counter": "2", + "CounterHTOff": "2", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "PublicDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "L2_L1D_WB_RQSTS.ALL", + "SampleAfterValue": "200003", + "UMask": "0xf" + }, + { + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "L2_L1D_WB_RQSTS.HIT_E", + "PublicDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "L2_L1D_WB_RQSTS.HIT_M", + "PublicDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.", + "SampleAfterValue": "200003", + "UMask": "0x8" + }, + { + "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "L2_L1D_WB_RQSTS.MISS", + "PublicDescription": "Not rejected writebacks that missed LLC.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "L2 cache lines filling L2.", + "SampleAfterValue": "100003", + "UMask": "0x7" + }, + { + "BriefDescription": "L2 cache lines in E state filling L2", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.E", + "PublicDescription": "L2 cache lines in E state filling L2.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "L2 cache lines in I state filling L2", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.I", + "PublicDescription": "L2 cache lines in I state filling L2.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 cache lines in S state filling L2", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.S", + "PublicDescription": "L2 cache lines in S state filling L2.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Clean L2 cache lines evicted by demand", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.DEMAND_CLEAN", + "PublicDescription": "Clean L2 cache lines evicted by demand.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Dirty L2 cache lines evicted by demand", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.DEMAND_DIRTY", + "PublicDescription": "Dirty L2 cache lines evicted by demand.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Dirty L2 cache lines filling the L2", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.DIRTY_ALL", + "PublicDescription": "Dirty L2 cache lines filling the L2.", + "SampleAfterValue": "100003", + "UMask": "0xa" + }, + { + "BriefDescription": "Clean L2 cache lines evicted by L2 prefetch", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.PF_CLEAN", + "PublicDescription": "Clean L2 cache lines evicted by the MLC prefetcher.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Dirty L2 cache lines evicted by L2 prefetch", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.PF_DIRTY", + "PublicDescription": "Dirty L2 cache lines evicted by the MLC prefetcher.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "L2 code requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts all L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0x30" + }, + { + "BriefDescription": "Demand Data Read requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts any demand and L1 HW prefetch data load requests to L2.", + "SampleAfterValue": "200003", + "UMask": "0x3" + }, + { + "BriefDescription": "Requests from L2 hardware prefetchers", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_PF", + "PublicDescription": "Counts all L2 HW prefetcher requests.", + "SampleAfterValue": "200003", + "UMask": "0xc0" + }, + { + "BriefDescription": "RFO requests to L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_RFO", + "PublicDescription": "Counts all L2 store RFO requests.", + "SampleAfterValue": "200003", + "UMask": "0xc" + }, + { + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Number of instruction fetches that hit the L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x10" + }, + { + "BriefDescription": "L2 cache misses when fetching instructions", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Number of instruction fetches that missed the L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x20" + }, + { + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Demand Data Read requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.PF_HIT", + "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.", + "SampleAfterValue": "200003", + "UMask": "0x40" + }, + { + "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.PF_MISS", + "PublicDescription": "Counts all L2 HW prefetcher requests that missed L2.", + "SampleAfterValue": "200003", + "UMask": "0x80" + }, + { + "BriefDescription": "RFO requests that hit L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "RFO requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "RFO requests that miss L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the number of store RFO requests that miss the L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x8" + }, + { + "BriefDescription": "RFOs that access cache lines in any state", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x27", + "EventName": "L2_STORE_LOCK_RQSTS.ALL", + "PublicDescription": "RFOs that access cache lines in any state.", + "SampleAfterValue": "200003", + "UMask": "0xf" + }, + { + "BriefDescription": "RFOs that hit cache lines in M state", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x27", + "EventName": "L2_STORE_LOCK_RQSTS.HIT_M", + "PublicDescription": "RFOs that hit cache lines in M state.", + "SampleAfterValue": "200003", + "UMask": "0x8" + }, + { + "BriefDescription": "RFOs that miss cache lines", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x27", + "EventName": "L2_STORE_LOCK_RQSTS.MISS", + "PublicDescription": "RFOs that miss cache lines.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 or LLC HW prefetches that access L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.ALL_PF", + "PublicDescription": "Any MLC or LLC HW prefetch accessing L2, including rejects.", + "SampleAfterValue": "200003", + "UMask": "0x8" + }, + { + "BriefDescription": "Transactions accessing L2 pipe", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.ALL_REQUESTS", + "PublicDescription": "Transactions accessing L2 pipe.", + "SampleAfterValue": "200003", + "UMask": "0x80" + }, + { + "BriefDescription": "L2 cache accesses when fetching instructions", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.CODE_RD", + "PublicDescription": "L2 cache accesses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "Demand Data Read requests that access L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.DEMAND_DATA_RD", + "PublicDescription": "Demand Data Read requests that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "L1D writebacks that access L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.L1D_WB", + "PublicDescription": "L1D writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x10" + }, + { + "BriefDescription": "L2 fill requests that access L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.L2_FILL", + "PublicDescription": "L2 fill requests that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x20" + }, + { + "BriefDescription": "L2 writebacks that access L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.L2_WB", + "PublicDescription": "L2 writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x40" + }, + { + "BriefDescription": "RFO requests that access L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.RFO", + "PublicDescription": "RFO requests that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when L1D is locked", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x63", + "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION", + "PublicDescription": "Cycles in which the L1D is locked.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Core-originated cacheable demand requests missed LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "This event counts each cache miss condition for references to the last level cache.", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Core-originated cacheable demand requests that refer to LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "This event counts requests originating from the core that reference a cache line in the last level cache.", + "SampleAfterValue": "100003", + "UMask": "0x4f" + }, + { + "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT", + "PEBS": "1", + "SampleAfterValue": "20011", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM", + "PEBS": "1", + "SampleAfterValue": "20011", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "SampleAfterValue": "20011", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Retired load uops whose data source was local DRAM (Snoop not needed, Snoop Miss, or Snoop Hit data not forwarded).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM", + "SampleAfterValue": "100007", + "UMask": "0x3" + }, + { + "BriefDescription": "Retired load uops whose data source was remote DRAM (Snoop not needed, Snoop Miss, or Snoop Hit data not forwarded).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM", + "SampleAfterValue": "100007", + "UMask": "0xc" + }, + { + "BriefDescription": "Data forwarded from remote cache.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD", + "SampleAfterValue": "100007", + "UMask": "0x20" + }, + { + "BriefDescription": "Remote cache HITM.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM", + "SampleAfterValue": "100007", + "UMask": "0x10" + }, + { + "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Retired load uops with L1 cache hits as data sources.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load uops which data sources following L1 data-cache miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Retired load uops with L2 cache hits as data sources.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired load uops with L2 cache misses as data sources.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", + "PEBS": "1", + "SampleAfterValue": "50021", + "UMask": "0x10" + }, + { + "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT", + "PEBS": "1", + "SampleAfterValue": "50021", + "UMask": "0x4" + }, + { + "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_MISS", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x20" + }, + { + "BriefDescription": "All retired load uops. (Precise Event)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x81" + }, + { + "BriefDescription": "All retired store uops. (Precise Event)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x82" + }, + { + "BriefDescription": "Retired load uops with locked access. (Precise Event)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x21" + }, + { + "BriefDescription": "Retired load uops that split across a cacheline boundary. (Precise Event)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x42" + }, + { + "BriefDescription": "Retired load uops that miss the STLB. (Precise Event)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x11" + }, + { + "BriefDescription": "Retired store uops that miss the STLB. (Precise Event)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xD0", + "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x12" + }, + { + "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "PublicDescription": "Data read requests sent to uncore (demand and prefetch).", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cacheable and noncacheable code read requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Demand code read requests sent to uncore.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Demand Data Read requests sent to uncore", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Demand data read requests sent to uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Demand RFO read requests sent to uncore, including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cases when offcore requests buffer cannot take more entries for core", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB2", + "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "PublicDescription": "Cases when offcore requests buffer cannot take more entries for core.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Offcore outstanding cacheable data read transactions in SQ to uncore. Set Cmask=1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Offcore outstanding code reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Offcore outstanding Demand Code Read transactions in SQ to uncore. Set Cmask=1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Offcore outstanding Demand Data Read transactions in SQ to uncore. Set Cmask=1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "PublicDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding RFO store transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Offcore outstanding RFO store transactions in SQ to uncore. Set Cmask=1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003c0091", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003c0091", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1003c0091", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand & prefetch data reads that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2003c0091", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch data reads that hit the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3f803c0090", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003c0090", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003c0090", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1003c0090", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch data reads that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2003c0090", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3f803c03f7", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003c03f7", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003c03f7", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1003c03f7", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2003c03f7", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all writebacks from the core to the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10008", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that hit in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3f803c0004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data reads that hit in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3f803c0001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003c0001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003c0001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1003c0001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit in the LLC and sibling core snoop returned a clean response", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2003c0001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data writes (RFOs) that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003c0002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts L2 hints sent to LLC to keep a line from being evicted out of the core caches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.LRU_HINTS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x803c8000", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts miscellaneous accesses that include port i/o, MMIO and uncacheable memory accesses", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.PORTIO_MMIO_UC", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x23ffc08000", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) code reads that hit in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3f803c0040", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3f803c0010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003c0010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003c0010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1003c0010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2003c0010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3f803c0200", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3f803c0080", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003c0080", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003c0080", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1003c0080", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that hit in the LLC and the snoops sent to sibling cores return clean response", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2003c0080", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.SPLIT_LOCK_UC_LOCK.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10400", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts non-temporal stores", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10800", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Split locks in SQ", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF4", + "EventName": "SQ_MISC.SPLIT_LOCK", + "SampleAfterValue": "100003", + "UMask": "0x10" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/floating-point.json b/tools/perf/pmu-events/arch/x86/ivytown/floating-point.json new file mode 100644 index 000000000..88891cba5 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/floating-point.json @@ -0,0 +1,169 @@ +[ + { + "BriefDescription": "Cycles with any input/output SSE or FP assist", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.ANY", + "PublicDescription": "Cycles with any input/output SSE* or FP assists.", + "SampleAfterValue": "100003", + "UMask": "0x1e" + }, + { + "BriefDescription": "Number of SIMD FP assists due to input values", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.SIMD_INPUT", + "PublicDescription": "Number of SIMD FP assists due to input values.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of SIMD FP assists due to Output values", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.SIMD_OUTPUT", + "PublicDescription": "Number of SIMD FP assists due to output values.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of X87 assists due to input value.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.X87_INPUT", + "PublicDescription": "Number of X87 FP assists due to input values.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of X87 assists due to output value.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.X87_OUTPUT", + "PublicDescription": "Number of X87 FP assists due to output values.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of SSE* or AVX-128 FP Computational packed double-precision uops issued this cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x10", + "EventName": "FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE", + "PublicDescription": "Number of SSE* or AVX-128 FP Computational packed double-precision uops issued this cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of SSE* or AVX-128 FP Computational packed single-precision uops issued this cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x10", + "EventName": "FP_COMP_OPS_EXE.SSE_PACKED_SINGLE", + "PublicDescription": "Number of SSE* or AVX-128 FP Computational packed single-precision uops issued this cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of SSE* or AVX-128 FP Computational scalar double-precision uops issued this cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x10", + "EventName": "FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE", + "PublicDescription": "Counts number of SSE* or AVX-128 double precision FP scalar uops executed.", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of SSE* or AVX-128 FP Computational scalar single-precision uops issued this cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x10", + "EventName": "FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE", + "PublicDescription": "Number of SSE* or AVX-128 FP Computational scalar single-precision uops issued this cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULs and IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x10", + "EventName": "FP_COMP_OPS_EXE.X87", + "PublicDescription": "Counts number of X87 uops executed.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of SIMD Move Elimination candidate uops that were eliminated.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x58", + "EventName": "MOVE_ELIMINATION.SIMD_ELIMINATED", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of SIMD Move Elimination candidate uops that were not eliminated.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x58", + "EventName": "MOVE_ELIMINATION.SIMD_NOT_ELIMINATED", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.AVX_STORE", + "PublicDescription": "Number of assists associated with 256-bit AVX store operations.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.AVX_TO_SSE", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.SSE_TO_AVX", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "number of AVX-256 Computational FP double precision uops issued this cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x11", + "EventName": "SIMD_FP_256.PACKED_DOUBLE", + "PublicDescription": "Counts 256-bit packed double-precision floating-point instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "number of GSSE-256 Computational FP single precision uops issued this cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x11", + "EventName": "SIMD_FP_256.PACKED_SINGLE", + "PublicDescription": "Counts 256-bit packed single-precision floating-point instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/frontend.json b/tools/perf/pmu-events/arch/x86/ivytown/frontend.json new file mode 100644 index 000000000..0a295c4e0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/frontend.json @@ -0,0 +1,315 @@ +[ + { + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xE6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Number of front end re-steers due to BPU misprediction.", + "SampleAfterValue": "100003", + "UMask": "0x1f" + }, + { + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.COUNT", + "PublicDescription": "Number of DSB to MITE switches.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Cycles DSB to MITE switches caused delay.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAC", + "EventName": "DSB_FILL.EXCEED_DSB_LINES", + "PublicDescription": "DSB Fill encountered > 3 DSB lines.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.HIT", + "PublicDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where a code-fetch stalled due to L1 instruction-cache miss or an iTLB miss", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.IFETCH_STALL", + "PublicDescription": "Cycles where a code-fetch stalled due to L1 instruction-cache miss or an iTLB miss.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Instruction cache, streaming buffer and victim cache misses", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE.MISSES", + "PublicDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Misses. Includes UC accesses.", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "PublicDescription": "Counts cycles DSB is delivered four uops. Set Cmask = 4.", + "SampleAfterValue": "2000003", + "UMask": "0x18" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "PublicDescription": "Counts cycles DSB is delivered at least one uops. Set Cmask = 1.", + "SampleAfterValue": "2000003", + "UMask": "0x18" + }, + { + "BriefDescription": "Cycles MITE is delivering 4 Uops", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "PublicDescription": "Counts cycles MITE is delivered four uops. Set Cmask = 4.", + "SampleAfterValue": "2000003", + "UMask": "0x24" + }, + { + "BriefDescription": "Cycles MITE is delivering any Uop", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "PublicDescription": "Counts cycles MITE is delivered at least one uops. Set Cmask = 1.", + "SampleAfterValue": "2000003", + "UMask": "0x24" + }, + { + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES", + "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Increment each cycle. # of uops delivered to IDQ from DSB path. Set Cmask = 1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Instruction Decode Queue (IDQ) empty cycles", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0x79", + "EventName": "IDQ.EMPTY", + "PublicDescription": "Counts cycles the IDQ is empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MITE_ALL_UOPS", + "PublicDescription": "Number of uops delivered to IDQ from any path.", + "SampleAfterValue": "2000003", + "UMask": "0x3c" + }, + { + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES", + "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MITE path. Set Cmask = 1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_CYCLES", + "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_DSB_CYCLES", + "PublicDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_DSB_OCCUR", + "PublicDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_DSB_UOPS", + "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MS by either DSB or MITE. Set Cmask = 1 to count cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Count issue pipeline slots where no uop was delivered from the front end to the back end when there is no back-end stall.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "4", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "3", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "2", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json new file mode 100644 index 000000000..99a45c8d8 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -0,0 +1,847 @@ +[ + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", + "MetricGroup": "PGO;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / SLOTS", + "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "MetricExpr": "ICACHE.IFETCH_STALL / CLKS - tma_itlb_misses", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / CLKS", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / CLKS", + "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_dsb_switches", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / CLKS", + "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_lcp", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * IDQ.MS_SWITCHES / CLKS", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", + "MetricName": "tma_ms_switches", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_bandwidth", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ((INT_MISC.RECOVERY_CYCLES_ANY / 2) if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricExpr": "(BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_branch_mispredicts", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_machine_clears", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if (IPC > 1.8) else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if (tma_fetch_latency > 0.1) else RESOURCE_STALLS.SB)) * tma_backend_bound", + "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / CLKS, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / CLKS", + "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", + "MetricGroup": "TopdownL4;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricExpr": "(MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / CLKS", + "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "13 * LD_BLOCKS.NO_SR / CLKS", + "MetricGroup": "TopdownL4;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CLKS", + "MetricGroup": "TopdownL4;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "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 does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / CLKS", + "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / CLKS", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "(MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / CLKS", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricExpr": "43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / CLKS", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_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": "41 * (MEM_LOAD_UOPS_RETIRED.LLC_HIT * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / CLKS", + "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "((OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2) if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricExpr": "(1 - (MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS))) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / CLKS", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", + "MetricName": "tma_mem_bandwidth", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", + "MetricName": "tma_mem_latency", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricExpr": "200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / CLKS", + "MetricGroup": "Server;TopdownL5;tma_mem_latency_group", + "MetricName": "tma_local_dram", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricExpr": "310 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / CLKS", + "MetricGroup": "Server;Snoop;TopdownL5;tma_mem_latency_group", + "MetricName": "tma_remote_dram", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", + "MetricExpr": "(200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD * (1 + mem_load_uops_retired.hit_lfb / ((MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS) + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / CLKS", + "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_mem_latency_group", + "MetricName": "tma_remote_cache", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / CLKS", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "((L2_RQSTS.RFO_HIT * 9 * (1 - (MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES))) + (1 - (MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES)) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", + "MetricName": "tma_store_latency", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / CLKS", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / CORE_CLKS", + "MetricGroup": "TopdownL4;tma_store_bound_group", + "MetricName": "tma_split_stores", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(7 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / CLKS", + "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / CORE_CLKS", + "MetricGroup": "TopdownL3;tma_core_bound_group", + "MetricName": "tma_divider", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if (IPC > 1.8) else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if (tma_fetch_latency > 0.1) else RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / CLKS", + "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@) / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - RS_EVENTS.EMPTY_CYCLES if (tma_fetch_latency > 0.1) else 0) / CORE_CLKS", + "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / CORE_CLKS", + "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", + "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", + "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * CORE_CLKS)", + "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED_PORT.PORT_0", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", + "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", + "MetricName": "tma_port_0", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED_PORT.PORT_1", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", + "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", + "MetricName": "tma_port_1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU) Sample with: UOPS_DISPATCHED.PORT_5", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", + "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", + "MetricName": "tma_port_5", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", + "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_2", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", + "MetricGroup": "TopdownL6;tma_load_op_utilization_group", + "MetricName": "tma_port_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_3", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", + "MetricGroup": "TopdownL6;tma_load_op_utilization_group", + "MetricName": "tma_port_3", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", + "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data) Sample with: UOPS_DISPATCHED_PORT.PORT_4", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", + "MetricGroup": "TopdownL6;tma_store_op_utilization_group", + "MetricName": "tma_port_4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS * FP_COMP_OPS_EXE.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE) / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", + "MetricName": "tma_fp_scalar", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", + "MetricName": "tma_fp_vector", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", + "MetricExpr": "tma_microcode_sequencer", + "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY) * IDQ.MS_UOPS / SLOTS", + "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", + "MetricName": "tma_microcode_sequencer", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / SLOTS", + "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / CLKS", + "MetricGroup": "Ret;Summary", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "UPI" + }, + { + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "UpTB" + }, + { + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / IPC", + "MetricGroup": "Mem;Pipeline", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * CORE_CLKS", + "MetricGroup": "tma_L1_group", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "Execute_per_Issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + }, + { + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", + "MetricGroup": "Ret;SMT;tma_L1_group", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(1 * (FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / CORE_CLKS", + "MetricGroup": "Flops;Ret", + "MetricName": "FLOPc" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / ((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "ILP" + }, + { + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "((CPU_CLK_UNHALTED.THREAD / 2) * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK)) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2) if #SMT_on else CLKS", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "IpLoad" + }, + { + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "IpStore" + }, + { + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "IpBranch" + }, + { + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "IpCall" + }, + { + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", + "MetricName": "IpTB" + }, + { + "BriefDescription": "Branch instructions per taken branch. ", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "BpTkBranch" + }, + { + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "1 / (tma_fp_scalar + tma_fp_vector)", + "MetricGroup": "Flops;InsType", + "MetricName": "IpArith", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + }, + { + "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;tma_L1_group", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "Retire" + }, + { + "BriefDescription": "", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "Execute" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ((IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS))", + "MetricGroup": "DSB;Fed;FetchBW", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "IpMispredict" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "MLP" + }, + { + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "L1MPKI" + }, + { + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "L2MPKI" + }, + { + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "L3MPKI" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_NMI_WATCHDOG", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / CORE_CLKS", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L1D_Cache_Fill_BW" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L2_Cache_Fill_BW" + }, + { + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L3_Cache_Fill_BW" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "L1D_Cache_Fill_BW", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L1D_Cache_Fill_BW_1T" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "L2_Cache_Fill_BW", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L2_Cache_Fill_BW_1T" + }, + { + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "L3_Cache_Fill_BW", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "L3_Cache_Fill_BW_1T" + }, + { + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "L3_Cache_Access_BW_1T" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "HPC;Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "Turbo_Utilization * msr@tsc@ / 1000000000 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "Average_Frequency" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "((1 * (FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1000000000) / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "GFLOPs", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0", + "MetricGroup": "SMT", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "Kernel_CPI" + }, + { + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "(64 * (uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@) / 1000000000) / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC", + "MetricName": "DRAM_BW_Use" + }, + { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cbox_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "Socket_CLKS" + }, + { + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "IpFarBranch" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + }, + { + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1000000000", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/memory.json b/tools/perf/pmu-events/arch/x86/ivytown/memory.json new file mode 100644 index 000000000..99b71e43a --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/memory.json @@ -0,0 +1,503 @@ +[ + { + "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Loads with latency value being above 128", + "Counter": "3", + "CounterHTOff": "3", + "EventCode": "0xCD", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "PublicDescription": "Loads with latency value being above 128.", + "SampleAfterValue": "1009", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Loads with latency value being above 16", + "Counter": "3", + "CounterHTOff": "3", + "EventCode": "0xCD", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "PublicDescription": "Loads with latency value being above 16.", + "SampleAfterValue": "20011", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Loads with latency value being above 256", + "Counter": "3", + "CounterHTOff": "3", + "EventCode": "0xCD", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "PublicDescription": "Loads with latency value being above 256.", + "SampleAfterValue": "503", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Loads with latency value being above 32", + "Counter": "3", + "CounterHTOff": "3", + "EventCode": "0xCD", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "PublicDescription": "Loads with latency value being above 32.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Loads with latency value being above 4", + "Counter": "3", + "CounterHTOff": "3", + "EventCode": "0xCD", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "PublicDescription": "Loads with latency value being above 4.", + "SampleAfterValue": "100003", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Loads with latency value being above 512", + "Counter": "3", + "CounterHTOff": "3", + "EventCode": "0xCD", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "PublicDescription": "Loads with latency value being above 512.", + "SampleAfterValue": "101", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Loads with latency value being above 64", + "Counter": "3", + "CounterHTOff": "3", + "EventCode": "0xCD", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "PublicDescription": "Loads with latency value being above 64.", + "SampleAfterValue": "2003", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Loads with latency value being above 8", + "Counter": "3", + "CounterHTOff": "3", + "EventCode": "0xCD", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "PublicDescription": "Loads with latency value being above 8.", + "SampleAfterValue": "50021", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Sample stores and collect precise store operation via PEBS record. PMC3 only.", + "Counter": "3", + "CounterHTOff": "3", + "EventCode": "0xCD", + "EventName": "MEM_TRANS_RETIRED.PRECISE_STORE", + "PEBS": "2", + "PRECISE_STORE": "1", + "SampleAfterValue": "2000003", + "TakenAlone": "1", + "UMask": "0x2" + }, + { + "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "MISALIGN_MEM_REF.LOADS", + "PublicDescription": "Speculative cache-line split load uops dispatched to L1D.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x05", + "EventName": "MISALIGN_MEM_REF.STORES", + "PublicDescription": "Speculative cache-line split Store-address uops dispatched to L1D.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts all demand & prefetch code reads that miss the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3fffc00244", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch code reads that miss the LLC and the data returned from remote dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x67f800244", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch code reads that miss the LLC and the data forwarded from remote cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x87f800244", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand & prefetch data reads that hits the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3fffc20091", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3fffc203f7", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the LLC and the data returned from local dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x6004003f7", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the LLC the data is found in M state in remote cache and forwarded from there", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x107fc003f7", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the LLC and the data forwarded from remote cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x87f8203f7", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that miss the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3fffc20004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that miss the LLC and the data returned from local dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x600400004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that miss the LLC and the data returned from remote dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x67f800004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that miss the LLC the data is found in M state in remote cache and forwarded from there", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x107fc00004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand code reads that miss the LLC and the data forwarded from remote cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x87f820004", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss the LLC and the data returned from remote & local dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x67fc00001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3fffc20001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss the LLC and the data returned from local dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x600400001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss the LLC and the data returned from remote dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x67f800001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss the LLC the data is found in M state in remote cache and forwarded from there", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x107fc00001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that miss the LLC and the data forwarded from remote cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x87f820001", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all demand data writes (RFOs) that miss the LLC and the data is found in M state in remote cache and forwarded from there.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x107fc20002", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to L2) code reads that miss the LLC and the data returned from remote & local dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3fffc20040", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data returned from remote & local dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x67fc00010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3fffc20010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data returned from local dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x600400010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data returned from remote dram", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x67f800010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC the data is found in M state in remote cache and forwarded from there", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x107fc00010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the LLC and the data forwarded from remote cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x87f820010", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3fffc20200", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts prefetch (that bring data to LLC only) data reads that miss in the LLC", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_MISS.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3fffc20080", + "Offcore": "1", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/other.json b/tools/perf/pmu-events/arch/x86/ivytown/other.json new file mode 100644 index 000000000..2d6252179 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/other.json @@ -0,0 +1,44 @@ +[ + { + "BriefDescription": "Unhalted core cycles when the thread is in ring 0", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5C", + "EventName": "CPL_CYCLES.RING0", + "PublicDescription": "Unhalted core cycles when the thread is in ring 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of intervals between processor halts while thread is in ring 0", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x5C", + "EventName": "CPL_CYCLES.RING0_TRANS", + "PublicDescription": "Number of intervals between processor halts while thread is in ring 0.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Unhalted core cycles when thread is in rings 1, 2, or 3", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5C", + "EventName": "CPL_CYCLES.RING123", + "PublicDescription": "Unhalted core cycles when the thread is not in ring 0.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when L1 and L2 are locked due to UC or split lock", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x63", + "EventName": "LOCK_CYCLES.SPLIT_LOCK_UC_LOCK_DURATION", + "PublicDescription": "Cycles in which the L1D and L2 are locked, due to a UC lock or split lock.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json new file mode 100644 index 000000000..d89d3f8db --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json @@ -0,0 +1,1272 @@ +[ + { + "BriefDescription": "Divide operations executed", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x14", + "EventName": "ARITH.FPU_DIV", + "PublicDescription": "Divide operations executed.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles when divider is busy executing divide operations", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x14", + "EventName": "ARITH.FPU_DIV_ACTIVE", + "PublicDescription": "Cycles that the divider is active, includes INT and FP. Set 'edge =1, cmask=1' to count the number of divides.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Speculative and retired branches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_BRANCHES", + "PublicDescription": "Counts all near executed branches (not necessarily retired).", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "Speculative and retired macro-conditional branches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_CONDITIONAL", + "PublicDescription": "Speculative and retired macro-conditional branches.", + "SampleAfterValue": "200003", + "UMask": "0xc1" + }, + { + "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP", + "PublicDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.", + "SampleAfterValue": "200003", + "UMask": "0xc2" + }, + { + "BriefDescription": "Speculative and retired direct near calls", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL", + "PublicDescription": "Speculative and retired direct near calls.", + "SampleAfterValue": "200003", + "UMask": "0xd0" + }, + { + "BriefDescription": "Speculative and retired indirect branches excluding calls and returns", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", + "PublicDescription": "Speculative and retired indirect branches excluding calls and returns.", + "SampleAfterValue": "200003", + "UMask": "0xc4" + }, + { + "BriefDescription": "Speculative and retired indirect return branches.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN", + "SampleAfterValue": "200003", + "UMask": "0xc8" + }, + { + "BriefDescription": "Not taken macro-conditional branches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL", + "PublicDescription": "Not taken macro-conditional branches.", + "SampleAfterValue": "200003", + "UMask": "0x41" + }, + { + "BriefDescription": "Taken speculative and retired macro-conditional branches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL", + "PublicDescription": "Taken speculative and retired macro-conditional branches.", + "SampleAfterValue": "200003", + "UMask": "0x81" + }, + { + "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP", + "PublicDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.", + "SampleAfterValue": "200003", + "UMask": "0x82" + }, + { + "BriefDescription": "Taken speculative and retired direct near calls", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL", + "PublicDescription": "Taken speculative and retired direct near calls.", + "SampleAfterValue": "200003", + "UMask": "0x90" + }, + { + "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", + "PublicDescription": "Taken speculative and retired indirect branches excluding calls and returns.", + "SampleAfterValue": "200003", + "UMask": "0x84" + }, + { + "BriefDescription": "Taken speculative and retired indirect calls", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "PublicDescription": "Taken speculative and retired indirect calls.", + "SampleAfterValue": "200003", + "UMask": "0xa0" + }, + { + "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x88", + "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN", + "PublicDescription": "Taken speculative and retired indirect branches with return mnemonic.", + "SampleAfterValue": "200003", + "UMask": "0x88" + }, + { + "BriefDescription": "All (macro) branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Branch instructions at retirement.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "All (macro) branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "SampleAfterValue": "400009", + "UMask": "0x4" + }, + { + "BriefDescription": "Conditional branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "PEBS": "1", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Far branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PublicDescription": "Number of far branches retired.", + "SampleAfterValue": "100007", + "UMask": "0x40" + }, + { + "BriefDescription": "Direct and indirect near call instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x2" + }, + { + "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_CALL_R3", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x2" + }, + { + "BriefDescription": "Return instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "Taken branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "PublicDescription": "Counts the number of not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" + }, + { + "BriefDescription": "Speculative and retired mispredicted macro conditional branches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.ALL_BRANCHES", + "PublicDescription": "Counts all near executed branches (not necessarily retired).", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "Speculative and retired mispredicted macro conditional branches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL", + "PublicDescription": "Speculative and retired mispredicted macro conditional branches.", + "SampleAfterValue": "200003", + "UMask": "0xc1" + }, + { + "BriefDescription": "Mispredicted indirect branches excluding calls and returns", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET", + "PublicDescription": "Mispredicted indirect branches excluding calls and returns.", + "SampleAfterValue": "200003", + "UMask": "0xc4" + }, + { + "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL", + "PublicDescription": "Not taken speculative and retired mispredicted macro conditional branches.", + "SampleAfterValue": "200003", + "UMask": "0x41" + }, + { + "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL", + "PublicDescription": "Taken speculative and retired mispredicted macro conditional branches.", + "SampleAfterValue": "200003", + "UMask": "0x81" + }, + { + "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET", + "PublicDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.", + "SampleAfterValue": "200003", + "UMask": "0x84" + }, + { + "BriefDescription": "Taken speculative and retired mispredicted indirect calls", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL", + "PublicDescription": "Taken speculative and retired mispredicted indirect calls.", + "SampleAfterValue": "200003", + "UMask": "0xa0" + }, + { + "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR", + "PublicDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.", + "SampleAfterValue": "200003", + "UMask": "0x88" + }, + { + "BriefDescription": "All mispredicted macro branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Mispredicted branch instructions at retirement.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Mispredicted macro branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "SampleAfterValue": "400009", + "UMask": "0x4" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "PEBS": "1", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "PublicDescription": "Increments at the frequency of XCLK (100 MHz) when not halted.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted. (counts at 100 MHz rate)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "Fixed counter 2", + "CounterHTOff": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "PublicDescription": "Reference cycles when the thread is unhalted. (counts at 100 MHz rate)", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted. (counts at 100 MHz rate)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core cycles when the thread is not in halt state.", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Thread cycles when thread is not in halt state", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "Counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.", + "SampleAfterValue": "2000003" + }, + { + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "Counter": "2", + "CounterHTOff": "2", + "CounterMask": "8", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles with pending L1 cache miss loads.", + "Counter": "2", + "CounterHTOff": "2", + "CounterMask": "8", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING", + "PublicDescription": "Cycles with pending L1 cache miss loads. Set AnyThread to count per core.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles while L2 cache miss load* is outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with pending L2 cache miss loads.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING", + "PublicDescription": "Cycles with pending L2 miss loads. Set AnyThread to count per core.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with pending memory loads.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "2", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_LDM_PENDING", + "PublicDescription": "Cycles with pending memory loads. Set AnyThread to count per core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "2", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "This event increments by 1 for every cycle where there was no execute for this thread.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "4", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_NO_EXECUTE", + "PublicDescription": "Total execution stalls.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "Counter": "2", + "CounterHTOff": "2", + "CounterMask": "12", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "SampleAfterValue": "2000003", + "UMask": "0xc" + }, + { + "BriefDescription": "Execution stalls due to L1 data cache misses", + "Counter": "2", + "CounterHTOff": "2", + "CounterMask": "12", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING", + "PublicDescription": "Execution stalls due to L1 data cache miss loads. Set Cmask=0CH.", + "SampleAfterValue": "2000003", + "UMask": "0xc" + }, + { + "BriefDescription": "Execution stalls while L2 cache miss load* is outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "5", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Execution stalls due to L2 cache misses.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "5", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING", + "PublicDescription": "Number of loads missed L2.", + "SampleAfterValue": "2000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Execution stalls due to memory subsystem.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "6", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_LDM_PENDING", + "SampleAfterValue": "2000003", + "UMask": "0x6" + }, + { + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "6", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x6" + }, + { + "BriefDescription": "Total execution stalls.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "4", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Stall cycles because IQ is full", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x87", + "EventName": "ILD_STALL.IQ_FULL", + "PublicDescription": "Stall cycles due to IQ is full.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x87", + "EventName": "ILD_STALL.LCP", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Instructions retired from execution.", + "Counter": "Fixed counter 0", + "CounterHTOff": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.ANY_P", + "PublicDescription": "Number of instructions at retirement.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", + "Counter": "1", + "CounterHTOff": "1", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.PREC_DIST", + "PEBS": "2", + "PublicDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc.)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "AnyThread": "1", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Number of occurrences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc.)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_STALLS_COUNT", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "False dependencies in MOB due to partial compare on address", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x07", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "PublicDescription": "False dependencies in MOB due to partial compare on address.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4C", + "EventName": "LOAD_HIT_PRE.HW_PF", + "PublicDescription": "Non-SW-prefetch load dispatches that hit fill buffer allocated for H/W prefetch.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4C", + "EventName": "LOAD_HIT_PRE.SW_PF", + "PublicDescription": "Non-SW-prefetch load dispatches that hit fill buffer allocated for S/W prefetch.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_4_UOPS", + "PublicDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_ACTIVE", + "PublicDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of Uops delivered by the LSD.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA8", + "EventName": "LSD.UOPS", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of machine clears (nukes) of any type.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.COUNT", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.MASKMOV", + "PublicDescription": "Counts the number of executed AVX masked load operations that refer to an illegal address range with the mask bits set to 0.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Self-modifying code (SMC) detected.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Number of self-modifying-code machine clears detected.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of integer Move Elimination candidate uops that were eliminated.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x58", + "EventName": "MOVE_ELIMINATION.INT_ELIMINATED", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of integer Move Elimination candidate uops that were not eliminated.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x58", + "EventName": "MOVE_ELIMINATION.INT_NOT_ELIMINATED", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Resource-related stall cycles", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.ANY", + "PublicDescription": "Cycles Allocation is stalled due to Resource Related reason.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles stalled due to re-order buffer full.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.ROB", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles stalled due to no eligible RS entry available.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.RS", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Cycles stalled due to no store buffers available (not including draining form sync).", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Count cases of saving new LBR", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "PublicDescription": "Count cases of saving new LBR records by hardware.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "PublicDescription": "Cycles the RS is empty for the thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_END", + "Invert": "1", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles per thread when uops are dispatched to port 0", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "PublicDescription": "Cycles which a Uop is dispatched on port 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are dispatched to port 0", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE", + "PublicDescription": "Cycles per core when uops are dispatched to port 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles per thread when uops are dispatched to port 1", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1", + "PublicDescription": "Cycles which a Uop is dispatched on port 1.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are dispatched to port 1", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE", + "PublicDescription": "Cycles per core when uops are dispatched to port 1.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "PublicDescription": "Cycles which a Uop is dispatched on port 2.", + "SampleAfterValue": "2000003", + "UMask": "0xc" + }, + { + "AnyThread": "1", + "BriefDescription": "Uops dispatched to port 2, loads and stores per core (speculative and retired).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE", + "SampleAfterValue": "2000003", + "UMask": "0xc" + }, + { + "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "PublicDescription": "Cycles which a Uop is dispatched on port 3.", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE", + "PublicDescription": "Cycles per core when load or STA uops are dispatched to port 3.", + "SampleAfterValue": "2000003", + "UMask": "0x30" + }, + { + "BriefDescription": "Cycles per thread when uops are dispatched to port 4", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "PublicDescription": "Cycles which a Uop is dispatched on port 4.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are dispatched to port 4", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE", + "PublicDescription": "Cycles per core when uops are dispatched to port 4.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Cycles per thread when uops are dispatched to port 5", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "PublicDescription": "Cycles which a Uop is dispatched on port 5.", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles per core when uops are dispatched to port 5", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE", + "PublicDescription": "Cycles per core when uops are dispatched to port 5.", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of uops executed on the core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Counts total number of uops to be executed per-core each cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "PublicDescription": "Cycles 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", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "PublicDescription": "Cycles at least 2 micro-op is 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", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "PublicDescription": "Cycles at least 3 micro-op is 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", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "PublicDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "Invert": "1", + "PublicDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Counts total number of uops to be executed per-thread each cycle. Set Cmask = 1, INV =1 to count stall cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Increments each cycle the # of Uops issued by the RAT to RS. Set Cmask = 1, Inv = 1, Any= 1to count stalled cycles of this core.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of flags-merge uops being allocated.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.FLAGS_MERGE", + "PublicDescription": "Number of flags-merge uops allocated. Such uops adds delay.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of Multiply packed/scalar single precision uops allocated", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.SINGLE_MUL", + "PublicDescription": "Number of multiply packed/scalar single precision uops allocated.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.SLOW_LEA", + "PublicDescription": "Number of slow LEA or similar uops allocated. Such uop has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired uops.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.ALL", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.CORE_STALL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retirement slots used.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "1", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 10 actually retired uops.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "10", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json new file mode 100644 index 000000000..c118ff54c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json @@ -0,0 +1,3391 @@ +[ + { + "BriefDescription": "Uncore Clocks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "Counter 0 Occupancy", + "Counter": "1,2,3", + "EventCode": "0x1f", + "EventName": "UNC_C_COUNTER0_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", + "Unit": "CBO" + }, + { + "BriefDescription": "Cache Lookups; Any Request", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:17] bits correspond to [M'FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "Cache Lookups; Data Read Request", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.DATA_READ", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:17] bits correspond to [M'FMESI] state.; Read transactions", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Cache Lookups; Lookups that Match NID", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.NID", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:17] bits correspond to [M'FMESI] state.; Qualify one of the other subevents by the Target NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", + "UMask": "0x41", + "Unit": "CBO" + }, + { + "BriefDescription": "Cache Lookups; External Snoop Request", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.REMOTE_SNOOP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:17] bits correspond to [M'FMESI] state.; Filters for only snoop requests coming from the remote socket(s) through the IPQ.", + "UMask": "0x9", + "Unit": "CBO" + }, + { + "BriefDescription": "Cache Lookups; Write Requests", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.WRITE", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:17] bits correspond to [M'FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", + "UMask": "0x5", + "Unit": "CBO" + }, + { + "BriefDescription": "Lines Victimized; Lines in E state", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.E_STATE", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Lines Victimized", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "Lines Victimized; Lines in M state", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Lines Victimized; Victimized Lines that Match NID", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.NID", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.; Qualify one of the other subevents by the Target NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", + "UMask": "0x40", + "Unit": "CBO" + }, + { + "BriefDescription": "Lines Victimized; Lines in S State", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.S_STATE", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Cbo Misc; RFO HitS", + "Counter": "0,1", + "EventCode": "0x39", + "EventName": "UNC_C_MISC.RFO_HIT_S", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.; Number of times that an RFO hit in S state. This is useful for determining if it might be good for a workload to use RspIWB instead of RspSWB.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "Cbo Misc; Silent Snoop Eviction", + "Counter": "0,1", + "EventCode": "0x39", + "EventName": "UNC_C_MISC.RSPI_WAS_FSE", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Cbo Misc", + "Counter": "0,1", + "EventCode": "0x39", + "EventName": "UNC_C_MISC.STARTED", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Cbo Misc; Write Combining Aliasing", + "Counter": "0,1", + "EventCode": "0x39", + "EventName": "UNC_C_MISC.WC_ALIASING", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "LRU Queue; LRU Age 0", + "Counter": "0,1", + "EventCode": "0x3c", + "EventName": "UNC_C_QLRU.AGE0", + "PerPkg": "1", + "PublicDescription": "How often age was set to 0", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LRU Queue; LRU Age 1", + "Counter": "0,1", + "EventCode": "0x3c", + "EventName": "UNC_C_QLRU.AGE1", + "PerPkg": "1", + "PublicDescription": "How often age was set to 1", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "LRU Queue; LRU Age 2", + "Counter": "0,1", + "EventCode": "0x3c", + "EventName": "UNC_C_QLRU.AGE2", + "PerPkg": "1", + "PublicDescription": "How often age was set to 2", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "LRU Queue; LRU Age 3", + "Counter": "0,1", + "EventCode": "0x3c", + "EventName": "UNC_C_QLRU.AGE3", + "PerPkg": "1", + "PublicDescription": "How often age was set to 3", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "LRU Queue; LRU Bits Decremented", + "Counter": "0,1", + "EventCode": "0x3c", + "EventName": "UNC_C_QLRU.LRU_DECREMENT", + "PerPkg": "1", + "PublicDescription": "How often all LRU bits were decremented by 1", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "LRU Queue; Non-0 Aged Victim", + "Counter": "0,1", + "EventCode": "0x3c", + "EventName": "UNC_C_QLRU.VICTIM_NON_ZERO", + "PerPkg": "1", + "PublicDescription": "How often we picked a victim that had a non-zero age", + "UMask": "0x20", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Counterclockwise", + "Counter": "2,3", + "EventCode": "0x1B", + "EventName": "UNC_C_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xC", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Clockwise", + "Counter": "2,3", + "EventCode": "0x1B", + "EventName": "UNC_C_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Down", + "Counter": "2,3", + "EventCode": "0x1B", + "EventName": "UNC_C_RING_AD_USED.DOWN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xCC", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Down and Even on Vring 0", + "Counter": "2,3", + "EventCode": "0x1b", + "EventName": "UNC_C_RING_AD_USED.DOWN_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Down and Odd on Vring 0", + "Counter": "2,3", + "EventCode": "0x1b", + "EventName": "UNC_C_RING_AD_USED.DOWN_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Down and Even on VRing 1", + "Counter": "2,3", + "EventCode": "0x1b", + "EventName": "UNC_C_RING_AD_USED.DOWN_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Down and Odd on VRing 1", + "Counter": "2,3", + "EventCode": "0x1b", + "EventName": "UNC_C_RING_AD_USED.DOWN_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Up", + "Counter": "2,3", + "EventCode": "0x1B", + "EventName": "UNC_C_RING_AD_USED.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x33", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Up and Even on Vring 0", + "Counter": "2,3", + "EventCode": "0x1b", + "EventName": "UNC_C_RING_AD_USED.UP_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Up and Odd on Vring 0", + "Counter": "2,3", + "EventCode": "0x1b", + "EventName": "UNC_C_RING_AD_USED.UP_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Up and Even on VRing 1", + "Counter": "2,3", + "EventCode": "0x1b", + "EventName": "UNC_C_RING_AD_USED.UP_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "AD Ring In Use; Up and Odd on VRing 1", + "Counter": "2,3", + "EventCode": "0x1b", + "EventName": "UNC_C_RING_AD_USED.UP_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Counterclockwise", + "Counter": "2,3", + "EventCode": "0x1C", + "EventName": "UNC_C_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xC", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Clockwise", + "Counter": "2,3", + "EventCode": "0x1C", + "EventName": "UNC_C_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Down", + "Counter": "2,3", + "EventCode": "0x1C", + "EventName": "UNC_C_RING_AK_USED.DOWN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xCC", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Down and Even on Vring 0", + "Counter": "2,3", + "EventCode": "0x1c", + "EventName": "UNC_C_RING_AK_USED.DOWN_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Down and Odd on Vring 0", + "Counter": "2,3", + "EventCode": "0x1c", + "EventName": "UNC_C_RING_AK_USED.DOWN_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Down and Even on VRing 1", + "Counter": "2,3", + "EventCode": "0x1c", + "EventName": "UNC_C_RING_AK_USED.DOWN_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Down and Odd on VRing 1", + "Counter": "2,3", + "EventCode": "0x1c", + "EventName": "UNC_C_RING_AK_USED.DOWN_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Up", + "Counter": "2,3", + "EventCode": "0x1C", + "EventName": "UNC_C_RING_AK_USED.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x33", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Up and Even on Vring 0", + "Counter": "2,3", + "EventCode": "0x1c", + "EventName": "UNC_C_RING_AK_USED.UP_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Up and Odd on Vring 0", + "Counter": "2,3", + "EventCode": "0x1c", + "EventName": "UNC_C_RING_AK_USED.UP_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Up and Even on VRing 1", + "Counter": "2,3", + "EventCode": "0x1c", + "EventName": "UNC_C_RING_AK_USED.UP_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "AK Ring In Use; Up and Odd on VRing 1", + "Counter": "2,3", + "EventCode": "0x1c", + "EventName": "UNC_C_RING_AK_USED.UP_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Counterclockwise", + "Counter": "2,3", + "EventCode": "0x1D", + "EventName": "UNC_C_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xC", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Clockwise", + "Counter": "2,3", + "EventCode": "0x1D", + "EventName": "UNC_C_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Down", + "Counter": "2,3", + "EventCode": "0x1D", + "EventName": "UNC_C_RING_BL_USED.DOWN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xCC", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Down and Even on Vring 0", + "Counter": "2,3", + "EventCode": "0x1d", + "EventName": "UNC_C_RING_BL_USED.DOWN_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Down and Odd on Vring 0", + "Counter": "2,3", + "EventCode": "0x1d", + "EventName": "UNC_C_RING_BL_USED.DOWN_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Down and Even on VRing 1", + "Counter": "2,3", + "EventCode": "0x1d", + "EventName": "UNC_C_RING_BL_USED.DOWN_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Down and Odd on VRing 1", + "Counter": "2,3", + "EventCode": "0x1d", + "EventName": "UNC_C_RING_BL_USED.DOWN_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Up", + "Counter": "2,3", + "EventCode": "0x1D", + "EventName": "UNC_C_RING_BL_USED.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x33", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Up and Even on Vring 0", + "Counter": "2,3", + "EventCode": "0x1d", + "EventName": "UNC_C_RING_BL_USED.UP_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Up and Odd on Vring 0", + "Counter": "2,3", + "EventCode": "0x1d", + "EventName": "UNC_C_RING_BL_USED.UP_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Up and Even on VRing 1", + "Counter": "2,3", + "EventCode": "0x1d", + "EventName": "UNC_C_RING_BL_USED.UP_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "BL Ring in Use; Up and Odd on VRing 1", + "Counter": "2,3", + "EventCode": "0x1d", + "EventName": "UNC_C_RING_BL_USED.UP_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "CBO" + }, + { + "BriefDescription": "Number of LLC responses that bounced on the Ring.", + "Counter": "0,1", + "EventCode": "0x5", + "EventName": "UNC_C_RING_BOUNCES.AD_IRQ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Number of LLC responses that bounced on the Ring.; Acknowledgements to core", + "Counter": "0,1", + "EventCode": "0x5", + "EventName": "UNC_C_RING_BOUNCES.AK", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Number of LLC responses that bounced on the Ring.: Acknowledgements to core", + "Counter": "0,1", + "EventCode": "0x5", + "EventName": "UNC_C_RING_BOUNCES.AK_CORE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Number of LLC responses that bounced on the Ring.; Data Responses to core", + "Counter": "0,1", + "EventCode": "0x5", + "EventName": "UNC_C_RING_BOUNCES.BL", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "Number of LLC responses that bounced on the Ring.: Data Responses to core", + "Counter": "0,1", + "EventCode": "0x5", + "EventName": "UNC_C_RING_BOUNCES.BL_CORE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Number of LLC responses that bounced on the Ring.; Snoops of processor's cache.", + "Counter": "0,1", + "EventCode": "0x5", + "EventName": "UNC_C_RING_BOUNCES.IV", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "Number of LLC responses that bounced on the Ring.: Snoops of processor's cache.", + "Counter": "0,1", + "EventCode": "0x5", + "EventName": "UNC_C_RING_BOUNCES.IV_CORE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "IV Ring in Use; Any", + "Counter": "2,3", + "EventCode": "0x1e", + "EventName": "UNC_C_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters any polarity", + "UMask": "0xF", + "Unit": "CBO" + }, + { + "BriefDescription": "IV Ring in Use; Down", + "Counter": "2,3", + "EventCode": "0x1e", + "EventName": "UNC_C_RING_IV_USED.DOWN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for Down polarity", + "UMask": "0xCC", + "Unit": "CBO" + }, + { + "BriefDescription": "IV Ring in Use; Up", + "Counter": "2,3", + "EventCode": "0x1e", + "EventName": "UNC_C_RING_IV_USED.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for Up polarity", + "UMask": "0x33", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Arbiter Blocking Cycles; IRQ", + "Counter": "0,1", + "EventCode": "0x12", + "EventName": "UNC_C_RxR_EXT_STARVED.IPQ", + "PerPkg": "1", + "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally startved and therefore we are blocking the IRQ.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Arbiter Blocking Cycles; IPQ", + "Counter": "0,1", + "EventCode": "0x12", + "EventName": "UNC_C_RxR_EXT_STARVED.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IRQ is externally starved and therefore we are blocking the IPQ.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Arbiter Blocking Cycles; ISMQ_BID", + "Counter": "0,1", + "EventCode": "0x12", + "EventName": "UNC_C_RxR_EXT_STARVED.ISMQ_BIDS", + "PerPkg": "1", + "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; Number of times that the ISMQ Bid.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Arbiter Blocking Cycles", + "Counter": "0,1", + "EventCode": "0x12", + "EventName": "UNC_C_RxR_EXT_STARVED.PRQ", + "PerPkg": "1", + "PublicDescription": "IRQ is blocking the ingress queue and causing the starvation.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Allocations; IPQ", + "Counter": "0,1", + "EventCode": "0x13", + "EventName": "UNC_C_RxR_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Allocations; IRQ", + "Counter": "0,1", + "EventCode": "0x13", + "EventName": "UNC_C_RxR_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Allocations; IRQ Rejected", + "Counter": "0,1", + "EventCode": "0x13", + "EventName": "UNC_C_RxR_INSERTS.IRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Allocations: IRQ Rejected", + "Counter": "0,1", + "EventCode": "0x13", + "EventName": "UNC_C_RxR_INSERTS.IRQ_REJECTED", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Allocations; VFIFO", + "Counter": "0,1", + "EventCode": "0x13", + "EventName": "UNC_C_RxR_INSERTS.VFIFO", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.; Counts the number of allocations into the IRQ Ordering FIFO. In JKT, it is necessary to keep IO requests in order. Therefore, they are allocated into an ordering FIFO that sits next to the IRQ, and must be satisfied from the FIFO in order (with respect to each other). This event, in conjunction with the Occupancy Accumulator event, can be used to calculate average lifetime in the FIFO. Transactions are allocated into the FIFO as soon as they enter the Cachebo (and the IRQ) and are deallocated from the FIFO as soon as they are deallocated from the IRQ.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Internal Starvation Cycles; IPQ", + "Counter": "0,1", + "EventCode": "0x14", + "EventName": "UNC_C_RxR_INT_STARVED.IPQ", + "PerPkg": "1", + "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the IPQ in Internal Starvation.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Internal Starvation Cycles; IRQ", + "Counter": "0,1", + "EventCode": "0x14", + "EventName": "UNC_C_RxR_INT_STARVED.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the IRQ in Internal Starvation.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Internal Starvation Cycles; ISMQ", + "Counter": "0,1", + "EventCode": "0x14", + "EventName": "UNC_C_RxR_INT_STARVED.ISMQ", + "PerPkg": "1", + "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the ISMQ in Internal Starvation.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "Probe Queue Retries; Address Conflict", + "Counter": "0,1", + "EventCode": "0x31", + "EventName": "UNC_C_RxR_IPQ_RETRY.ADDR_CONFLICT", + "PerPkg": "1", + "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject from an address conflicts. Address conflicts out of the IPQ should be rare. They will generally only occur if two different sockets are sending requests to the same address at the same time. This is a true conflict case, unlike the IPQ Address Conflict which is commonly caused by prefetching characteristics.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Probe Queue Retries; Any Reject", + "Counter": "0,1", + "EventCode": "0x31", + "EventName": "UNC_C_RxR_IPQ_RETRY.ANY", + "PerPkg": "1", + "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject. TOR rejects from the IPQ can be caused by the Egress being full or Address Conflicts.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Probe Queue Retries; No Egress Credits", + "Counter": "0,1", + "EventCode": "0x31", + "EventName": "UNC_C_RxR_IPQ_RETRY.FULL", + "PerPkg": "1", + "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject from the Egress being full. IPQ requests make use of the AD Egress for regular responses, the BL egress to forward data, and the AK egress to return credits.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Probe Queue Retries; No QPI Credits", + "Counter": "0,1", + "EventCode": "0x31", + "EventName": "UNC_C_RxR_IPQ_RETRY.QPI_CREDITS", + "PerPkg": "1", + "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Request Queue Rejects; Address Conflict", + "Counter": "0,1", + "EventCode": "0x32", + "EventName": "UNC_C_RxR_IRQ_RETRY.ADDR_CONFLICT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that a request from the IRQ was retried because of an address match in the TOR. In order to maintain coherency, requests to the same address are not allowed to pass each other up in the Cbo. Therefore, if there is an outstanding request to a given address, one cannot issue another request to that address until it is complete. This comes up most commonly with prefetches. Outstanding prefetches occasionally will not complete their memory fetch and a demand request to the same address will then sit in the IRQ and get retried until the prefetch fills the data into the LLC. Therefore, it will not be uncommon to see this case in high bandwidth streaming workloads when the LLC Prefetcher in the core is enabled.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Request Queue Rejects; Any Reject", + "Counter": "0,1", + "EventCode": "0x32", + "EventName": "UNC_C_RxR_IRQ_RETRY.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of IRQ retries that occur. Requests from the IRQ are retried if they are rejected from the TOR pipeline for a variety of reasons. Some of the most common reasons include if the Egress is full, there are no RTIDs, or there is a Physical Address match to another outstanding request.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Request Queue Rejects; No Egress Credits", + "Counter": "0,1", + "EventCode": "0x32", + "EventName": "UNC_C_RxR_IRQ_RETRY.FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that a request from the IRQ was retried because it failed to acquire an entry in the Egress. The egress is the buffer that queues up for allocating onto the ring. IRQ requests can make use of all four rings and all four Egresses. If any of the queues that a given request needs to make use of are full, the request will be retried.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Request Queue Rejects; No IIO Credits", + "Counter": "0,1", + "EventCode": "0x32", + "EventName": "UNC_C_RxR_IRQ_RETRY.IIO_CREDITS", + "PerPkg": "1", + "PublicDescription": "Number of times a request attempted to acquire the NCS/NCB credit for sending messages on BL to the IIO. There is a single credit in each CBo that is shared between the NCS and NCB message classes for sending transactions on the BL ring (such as read data) to the IIO.", + "UMask": "0x20", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Request Queue Rejects; No QPI Credits", + "Counter": "0,1", + "EventCode": "0x32", + "EventName": "UNC_C_RxR_IRQ_RETRY.QPI_CREDITS", + "PerPkg": "1", + "PublicDescription": "Number of requests rejects because of lack of QPI Ingress credits. These credits are required in order to send transactions to the QPI agent. Please see the QPI_IGR_CREDITS events for more information.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Request Queue Rejects; No RTIDs", + "Counter": "0,1", + "EventCode": "0x32", + "EventName": "UNC_C_RxR_IRQ_RETRY.RTID", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that requests from the IRQ were retried because there were no RTIDs available. RTIDs are required after a request misses the LLC and needs to send snoops and/or requests to memory. If there are no RTIDs available, requests will queue up in the IRQ and retry until one becomes available. Note that there are multiple RTID pools for the different sockets. There may be cases where the local RTIDs are all used, but requests destined for remote memory can still acquire an RTID because there are remote RTIDs available. This event does not provide any filtering for this case.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "ISMQ Retries; Any Reject", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_C_RxR_ISMQ_RETRY.ANY", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the total number of times that a request from the ISMQ retried because of a TOR reject. ISMQ requests generally will not need to retry (or at least ISMQ retries are less common than IRQ retries). ISMQ requests will retry if they are not able to acquire a needed Egress credit to get onto the ring, or for cache evictions that need to acquire an RTID. Most ISMQ requests already have an RTID, so eviction retries will be less common here.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "ISMQ Retries; No Egress Credits", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_C_RxR_ISMQ_RETRY.FULL", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the number of times that a request from the ISMQ retried because of a TOR reject caused by a lack of Egress credits. The egress is the buffer that queues up for allocating onto the ring. If any of the Egress queues that a given request needs to make use of are full, the request will be retried.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "ISMQ Retries; No IIO Credits", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_C_RxR_ISMQ_RETRY.IIO_CREDITS", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Number of times a request attempted to acquire the NCS/NCB credit for sending messages on BL to the IIO. There is a single credit in each CBo that is shared between the NCS and NCB message classes for sending transactions on the BL ring (such as read data) to the IIO.", + "UMask": "0x20", + "Unit": "CBO" + }, + { + "BriefDescription": "ISMQ Retries; No QPI Credits", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_C_RxR_ISMQ_RETRY.QPI_CREDITS", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "ISMQ Retries; No RTIDs", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_C_RxR_ISMQ_RETRY.RTID", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the number of times that a request from the ISMQ retried because of a TOR reject caused by no RTIDs. M-state cache evictions are serviced through the ISMQ, and must acquire an RTID in order to write back to memory. If no RTIDs are available, they will be retried.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "ISMQ Retries; No WB Credits", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_C_RxR_ISMQ_RETRY.WB_CREDITS", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Retries of writes to local memory due to lack of HT WB credits", + "UMask": "0x80", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Occupancy; IPQ", + "EventCode": "0x11", + "EventName": "UNC_C_RxR_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Occupancy; IRQ", + "EventCode": "0x11", + "EventName": "UNC_C_RxR_OCCUPANCY.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Occupancy; IRQ Rejected", + "EventCode": "0x11", + "EventName": "UNC_C_RxR_OCCUPANCY.IRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "IRQ Rejected", + "EventCode": "0x11", + "EventName": "UNC_C_RxR_OCCUPANCY.IRQ_REJECTED", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Ingress Occupancy; VFIFO", + "EventCode": "0x11", + "EventName": "UNC_C_RxR_OCCUPANCY.VFIFO", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.; Accumulates the number of used entries in the IRQ Ordering FIFO in each cycle. In JKT, it is necessary to keep IO requests in order. Therefore, they are allocated into an ordering FIFO that sits next to the IRQ, and must be satisfied from the FIFO in order (with respect to each other). This event, in conjunction with the Allocations event, can be used to calculate average lifetime in the FIFO. This event can be used in conjunction with the Not Empty event to calculate average queue occupancy. Transactions are allocated into the FIFO as soon as they enter the Cachebo (and the IRQ) and are deallocated from the FIFO as soon as they are deallocated from the IRQ.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; All", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Evictions", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.EVICTION", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Local Memory", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by locally HOMed memory.", + "UMask": "0x28", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Local Memory - Opcode Matched", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.LOCAL_OPCODE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", + "UMask": "0x21", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Misses to Local Memory", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.MISS_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by locally HOMed memory.", + "UMask": "0x2A", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Misses to Local Memory - Opcode Matched", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", + "UMask": "0x23", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Miss Opcode Match", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.MISS_OPCODE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Misses to Remote Memory", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.MISS_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by remote caches or remote memory.", + "UMask": "0x8A", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Misses to Remote Memory - Opcode Matched", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", + "UMask": "0x83", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; NID Matched", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.NID_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", + "UMask": "0x48", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; NID Matched Evictions", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.NID_EVICTION", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", + "UMask": "0x44", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; NID Matched Miss All", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.NID_MISS_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", + "UMask": "0x4A", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; NID and Opcode Matched Miss", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.NID_MISS_OPCODE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", + "UMask": "0x43", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; NID and Opcode Matched", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.NID_OPCODE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", + "UMask": "0x41", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; NID Matched Writebacks", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.NID_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", + "UMask": "0x50", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Opcode Match", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.OPCODE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Remote Memory", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by remote caches or remote memory.", + "UMask": "0x88", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Remote Memory - Opcode Matched", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.REMOTE_OPCODE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", + "UMask": "0x81", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Inserts; Writebacks", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; Any", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.ALL", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); All valid TOR entries. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; Evictions", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.EVICTION", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding eviction transactions in the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LOCAL", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", + "UMask": "0x28", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; Local Memory - Opcode Matched", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LOCAL_OPCODE", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", + "UMask": "0x21", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; Miss All", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding miss requests in the TOR. 'Miss' means the allocation requires an RTID. This generally means that the request was sent to memory or MMIO.", + "UMask": "0xA", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", + "UMask": "0x2A", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; Misses to Local Memory - Opcode Matched", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", + "UMask": "0x23", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; Miss Opcode Match", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries for miss transactions that match an opcode. This generally means that the request was sent to memory or MMIO.", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", + "UMask": "0x8A", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; Misses to Remote Memory - Opcode Matched", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE_OPCODE", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", + "UMask": "0x83", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; NID Matched", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.NID_ALL", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of NID matched outstanding requests in the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid.In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", + "UMask": "0x48", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; NID Matched Evictions", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.NID_EVICTION", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding NID matched eviction transactions in the TOR .", + "UMask": "0x44", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; NID Matched", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.NID_MISS_ALL", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss requests in the TOR that match a NID.", + "UMask": "0x4A", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; NID and Opcode Matched Miss", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.NID_MISS_OPCODE", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss requests in the TOR that match a NID and an opcode.", + "UMask": "0x43", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; NID and Opcode Matched", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.NID_OPCODE", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries that match a NID and an opcode.", + "UMask": "0x41", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; NID Matched Writebacks", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.NID_WB", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); NID matched write transactions int the TOR.", + "UMask": "0x50", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; Opcode Match", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.OPCODE", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc).", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.REMOTE", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", + "UMask": "0x88", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; Remote Memory - Opcode Matched", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.REMOTE_OPCODE", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", + "UMask": "0x81", + "Unit": "CBO" + }, + { + "BriefDescription": "TOR Occupancy; Writebacks", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.WB", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Write transactions in the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "Onto AD Ring", + "Counter": "0,1", + "EventCode": "0x4", + "EventName": "UNC_C_TxR_ADS_USED.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Onto AK Ring", + "Counter": "0,1", + "EventCode": "0x4", + "EventName": "UNC_C_TxR_ADS_USED.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Onto BL Ring", + "Counter": "0,1", + "EventCode": "0x4", + "EventName": "UNC_C_TxR_ADS_USED.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Egress Allocations; AD - Cachebo", + "Counter": "0,1", + "EventCode": "0x2", + "EventName": "UNC_C_TxR_INSERTS.AD_CACHE", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Egress Allocations; AD - Corebo", + "Counter": "0,1", + "EventCode": "0x2", + "EventName": "UNC_C_TxR_INSERTS.AD_CORE", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "Egress Allocations; AK - Cachebo", + "Counter": "0,1", + "EventCode": "0x2", + "EventName": "UNC_C_TxR_INSERTS.AK_CACHE", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Egress Allocations; AK - Corebo", + "Counter": "0,1", + "EventCode": "0x2", + "EventName": "UNC_C_TxR_INSERTS.AK_CORE", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the AK ring. This is commonly used for snoop responses coming from the core and destined for a Cachebo.", + "UMask": "0x20", + "Unit": "CBO" + }, + { + "BriefDescription": "Egress Allocations; BL - Cacheno", + "Counter": "0,1", + "EventCode": "0x2", + "EventName": "UNC_C_TxR_INSERTS.BL_CACHE", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CBO" + }, + { + "BriefDescription": "Egress Allocations; BL - Corebo", + "Counter": "0,1", + "EventCode": "0x2", + "EventName": "UNC_C_TxR_INSERTS.BL_CORE", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CBO" + }, + { + "BriefDescription": "Egress Allocations; IV - Cachebo", + "Counter": "0,1", + "EventCode": "0x2", + "EventName": "UNC_C_TxR_INSERTS.IV_CACHE", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "Injection Starvation; Onto AD Ring (to core)", + "Counter": "0,1", + "EventCode": "0x3", + "EventName": "UNC_C_TxR_STARVED.AD_CORE", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that the core AD egress spent in starvation", + "UMask": "0x10", + "Unit": "CBO" + }, + { + "BriefDescription": "Injection Starvation; Onto AK Ring", + "Counter": "0,1", + "EventCode": "0x3", + "EventName": "UNC_C_TxR_STARVED.AK_BOTH", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that both AK egresses spent in starvation", + "UMask": "0x2", + "Unit": "CBO" + }, + { + "BriefDescription": "Injection Starvation; Onto IV Ring", + "Counter": "0,1", + "EventCode": "0x3", + "EventName": "UNC_C_TxR_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that the cachebo IV egress spent in starvation", + "UMask": "0x8", + "Unit": "CBO" + }, + { + "BriefDescription": "BT Bypass", + "Counter": "0,1,2,3", + "EventCode": "0x52", + "EventName": "UNC_H_BT_BYPASS", + "PerPkg": "1", + "PublicDescription": "Number of transactions that bypass the BT (fifo) to HT", + "Unit": "HA" + }, + { + "BriefDescription": "BT Cycles Not Empty", + "Counter": "0,1,2,3", + "EventCode": "0x42", + "EventName": "UNC_H_BT_CYCLES_NE", + "PerPkg": "1", + "PublicDescription": "Cycles the Backup Tracker (BT) is not empty. The BT is the actual HOM tracker in IVT.", + "Unit": "HA" + }, + { + "BriefDescription": "BT Cycles Not Empty: Local", + "Counter": "0,1,2,3", + "EventCode": "0x42", + "EventName": "UNC_H_BT_CYCLES_NE.LOCAL", + "PerPkg": "1", + "PublicDescription": "Cycles the Backup Tracker (BT) is not empty. The BT is the actual HOM tracker in IVT.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "BT Cycles Not Empty: Remote", + "Counter": "0,1,2,3", + "EventCode": "0x42", + "EventName": "UNC_H_BT_CYCLES_NE.REMOTE", + "PerPkg": "1", + "PublicDescription": "Cycles the Backup Tracker (BT) is not empty. The BT is the actual HOM tracker in IVT.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "BT Occupancy; Local", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_H_BT_OCCUPANCY.LOCAL", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the HA BT pool in every cycle. This can be used with the not empty stat to calculate average queue occupancy or the allocations stat in order to calculate average queue latency. HA BTs are allocated as soon as a request enters the HA and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "BT Occupancy; Reads Local", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_H_BT_OCCUPANCY.READS_LOCAL", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the HA BT pool in every cycle. This can be used with the not empty stat to calculate average queue occupancy or the allocations stat in order to calculate average queue latency. HA BTs are allocated as soon as a request enters the HA and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "BT Occupancy; Reads Remote", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_H_BT_OCCUPANCY.READS_REMOTE", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the HA BT pool in every cycle. This can be used with the not empty stat to calculate average queue occupancy or the allocations stat in order to calculate average queue latency. HA BTs are allocated as soon as a request enters the HA and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "BT Occupancy; Remote", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_H_BT_OCCUPANCY.REMOTE", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the HA BT pool in every cycle. This can be used with the not empty stat to calculate average queue occupancy or the allocations stat in order to calculate average queue latency. HA BTs are allocated as soon as a request enters the HA and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "BT Occupancy; Writes Local", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_H_BT_OCCUPANCY.WRITES_LOCAL", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the HA BT pool in every cycle. This can be used with the not empty stat to calculate average queue occupancy or the allocations stat in order to calculate average queue latency. HA BTs are allocated as soon as a request enters the HA and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "BT Occupancy; Writes Remote", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_H_BT_OCCUPANCY.WRITES_REMOTE", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the HA BT pool in every cycle. This can be used with the not empty stat to calculate average queue occupancy or the allocations stat in order to calculate average queue latency. HA BTs are allocated as soon as a request enters the HA and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "BT to HT Not Issued; Incoming Data Hazard", + "Counter": "0,1,2,3", + "EventCode": "0x51", + "EventName": "UNC_H_BT_TO_HT_NOT_ISSUED.INCOMING_BL_HAZARD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the HA does not issue transaction from BT to HT.; Cycles unable to issue from BT due to incoming BL data hazard", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "BT to HT Not Issued; Incoming Snoop Hazard", + "Counter": "0,1,2,3", + "EventCode": "0x51", + "EventName": "UNC_H_BT_TO_HT_NOT_ISSUED.INCOMING_SNP_HAZARD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the HA does not issue transaction from BT to HT.; Cycles unable to issue from BT due to incoming snoop hazard", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "BT to HT Not Issued; Incoming Data Hazard", + "Counter": "0,1,2,3", + "EventCode": "0x51", + "EventName": "UNC_H_BT_TO_HT_NOT_ISSUED.RSPACKCFLT_HAZARD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the HA does not issue transaction from BT to HT.; Cycles unable to issue from BT due to incoming BL data hazard", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "BT to HT Not Issued; Incoming Data Hazard", + "Counter": "0,1,2,3", + "EventCode": "0x51", + "EventName": "UNC_H_BT_TO_HT_NOT_ISSUED.WBMDATA_HAZARD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the HA does not issue transaction from BT to HT.; Cycles unable to issue from BT due to incoming BL data hazard", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "HA to iMC Bypass; Not Taken", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_H_BYPASS_IMC.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filted by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "HA to iMC Bypass; Taken", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_H_BYPASS_IMC.TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the HA was able to bypass was attempted. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filted by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the bypass.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "uclks", + "Counter": "0,1,2,3", + "EventName": "UNC_H_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the HA. This will be slightly different than the count in the Ubox because of enable/freeze delays. The HA is on the other side of the die from the fixed Ubox uclk counter, so the drift could be somewhat larger than in units that are closer like the QPI Agent.", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict Checks; Acknowledge Conflicts", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_H_CONFLICT_CYCLES.ACKCNFLTS", + "PerPkg": "1", + "PublicDescription": "Count the number of Ackcnflts", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict Checks; Cmp Fwds", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_H_CONFLICT_CYCLES.CMP_FWDS", + "PerPkg": "1", + "PublicDescription": "Count the number of Cmp_Fwd. This will give the number of late conflicts.", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict Checks; Conflict Detected", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_H_CONFLICT_CYCLES.CONFLICT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that we are handling conflicts.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict Checks; Last in conflict chain", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_H_CONFLICT_CYCLES.LAST", + "PerPkg": "1", + "PublicDescription": "Count every last conflictor in conflict chain. Can be used to compute the average conflict chain length as (#Ackcnflts/#LastConflictor)+1. This can be used to give a feel for the conflict chain lengths while analyzing lock kernels.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Direct2Core Messages Sent", + "Counter": "0,1,2,3", + "EventCode": "0x11", + "EventName": "UNC_H_DIRECT2CORE_COUNT", + "PerPkg": "1", + "PublicDescription": "Number of Direct2Core messages sent", + "Unit": "HA" + }, + { + "BriefDescription": "Cycles when Direct2Core was Disabled", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_H_DIRECT2CORE_CYCLES_DISABLED", + "PerPkg": "1", + "PublicDescription": "Number of cycles in which Direct2Core was disabled", + "Unit": "HA" + }, + { + "BriefDescription": "Number of Reads that had Direct2Core Overridden", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_H_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Number of Reads where Direct2Core overridden", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Lat Opt Return", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_H_DIRECTORY_LAT_OPT", + "PerPkg": "1", + "PublicDescription": "Directory Latency Optimization Data Return Path Taken. When directory mode is enabled and the directory returned for a read is Dir=I, then data can be returned using a faster path if certain conditions are met (credits, free pipeline, etc).", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Lookups: Any state", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_H_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to.", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Lookups; Snoop Not Needed", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_H_DIRECTORY_LOOKUP.NO_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to.; Filters for transactions that did not have to send any snoops because the directory bit was clear.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Lookups: Snoop A", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_H_DIRECTORY_LOOKUP.SNOOP_A", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Lookups: Snoop S", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_H_DIRECTORY_LOOKUP.SNOOP_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Lookups; Snoop Needed", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_H_DIRECTORY_LOOKUP.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to.; Filters for transactions that had to send one or more snoops because the directory bit was set.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Lookups: A State", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_H_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to.", + "UMask": "0x80", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Lookups: I State", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_H_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to.", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Lookups: S State", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_H_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to.", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Updates: A2I", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_H_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "PublicDescription": "Counts the number of directory updates that were required. These result in writes to the memory controller. This can be filtered by directory sets and directory clears.", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Updates: A2S", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_H_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "PublicDescription": "Counts the number of directory updates that were required. These result in writes to the memory controller. This can be filtered by directory sets and directory clears.", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Updates; Any Directory Update", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_H_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of directory updates that were required. These result in writes to the memory controller. This can be filtered by directory sets and directory clears.", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Updates; Directory Clear", + "Counter": "0,1,2,3", + "EventCode": "0xD", + "EventName": "UNC_H_DIRECTORY_UPDATE.CLEAR", + "PerPkg": "1", + "PublicDescription": "Counts the number of directory updates that were required. These result in writes to the memory controller. This can be filtered by directory sets and directory clears.; Filter for directory clears. This occurs when snoops were sent and all returned with RspI.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Updates: I2A", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_H_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "PublicDescription": "Counts the number of directory updates that were required. These result in writes to the memory controller. This can be filtered by directory sets and directory clears.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Updates: I2S", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_H_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "PublicDescription": "Counts the number of directory updates that were required. These result in writes to the memory controller. This can be filtered by directory sets and directory clears.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Updates: S2A", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_H_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "PublicDescription": "Counts the number of directory updates that were required. These result in writes to the memory controller. This can be filtered by directory sets and directory clears.", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Updates: S2I", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_H_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "PublicDescription": "Counts the number of directory updates that were required. These result in writes to the memory controller. This can be filtered by directory sets and directory clears.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Directory Updates; Directory Set", + "Counter": "0,1,2,3", + "EventCode": "0xD", + "EventName": "UNC_H_DIRECTORY_UPDATE.SET", + "PerPkg": "1", + "PublicDescription": "Counts the number of directory updates that were required. These result in writes to the memory controller. This can be filtered by directory sets and directory clears.; Filter for directory sets. This occurs when a remote read transaction requests memory, bringing it to a remote cache.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "AD QPI Link 2 Credit Accumulator", + "Counter": "0,1,2,3", + "EventCode": "0x59", + "EventName": "UNC_H_IGR_AD_QPI2_ACCUMULATOR", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of credits available to the QPI Link 2 AD Ingress buffer.", + "Unit": "HA" + }, + { + "BriefDescription": "BL QPI Link 2 Credit Accumulator", + "Counter": "0,1,2,3", + "EventCode": "0x5a", + "EventName": "UNC_H_IGR_BL_QPI2_ACCUMULATOR", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of credits available to the QPI Link 2 BL Ingress buffer.", + "Unit": "HA" + }, + { + "BriefDescription": "AD QPI Link 2 Credit Accumulator", + "Counter": "0,1,2,3", + "EventCode": "0x59", + "EventName": "UNC_H_IGR_CREDITS_AD_QPI2", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of credits available to the QPI Link 2 AD Ingress buffer.", + "Unit": "HA" + }, + { + "BriefDescription": "BL QPI Link 2 Credit Accumulator", + "Counter": "0,1,2,3", + "EventCode": "0x5A", + "EventName": "UNC_H_IGR_CREDITS_BL_QPI2", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of credits available to the QPI Link 2 BL Ingress buffer.", + "Unit": "HA" + }, + { + "BriefDescription": "Cycles without QPI Ingress Credits; AD to QPI Link 0", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_H_IGR_NO_CREDIT_CYCLES.AD_QPI0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the HA does not have credits to send messages to the QPI Agent. This can be filtered by the different credit pools and the different links.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "Cycles without QPI Ingress Credits; AD to QPI Link 1", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_H_IGR_NO_CREDIT_CYCLES.AD_QPI1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the HA does not have credits to send messages to the QPI Agent. This can be filtered by the different credit pools and the different links.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Cycles without QPI Ingress Credits; BL to QPI Link 0", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_H_IGR_NO_CREDIT_CYCLES.BL_QPI0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the HA does not have credits to send messages to the QPI Agent. This can be filtered by the different credit pools and the different links.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Cycles without QPI Ingress Credits; BL to QPI Link 1", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_H_IGR_NO_CREDIT_CYCLES.BL_QPI1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the HA does not have credits to send messages to the QPI Agent. This can be filtered by the different credit pools and the different links.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "HA to iMC Normal Priority Reads Issued; Normal Priority", + "Counter": "0,1,2,3", + "EventCode": "0x17", + "EventName": "UNC_H_IMC_READS.NORMAL", + "PerPkg": "1", + "PublicDescription": "Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "Retry Events", + "Counter": "0,1,2,3", + "EventCode": "0x1e", + "EventName": "UNC_H_IMC_RETRY", + "PerPkg": "1", + "Unit": "HA" + }, + { + "BriefDescription": "HA to iMC Full Line Writes Issued; All Writes", + "Counter": "0,1,2,3", + "EventCode": "0x1a", + "EventName": "UNC_H_IMC_WRITES.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of full line writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0xF", + "Unit": "HA" + }, + { + "BriefDescription": "HA to iMC Full Line Writes Issued; Full Line Non-ISOCH", + "Counter": "0,1,2,3", + "EventCode": "0x1a", + "EventName": "UNC_H_IMC_WRITES.FULL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of full line writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "HA to iMC Full Line Writes Issued; ISOCH Full Line", + "Counter": "0,1,2,3", + "EventCode": "0x1a", + "EventName": "UNC_H_IMC_WRITES.FULL_ISOCH", + "PerPkg": "1", + "PublicDescription": "Counts the total number of full line writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "HA to iMC Full Line Writes Issued; Partial Non-ISOCH", + "Counter": "0,1,2,3", + "EventCode": "0x1a", + "EventName": "UNC_H_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of full line writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "HA to iMC Full Line Writes Issued; ISOCH Partial", + "Counter": "0,1,2,3", + "EventCode": "0x1a", + "EventName": "UNC_H_IMC_WRITES.PARTIAL_ISOCH", + "PerPkg": "1", + "PublicDescription": "Counts the total number of full line writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "IODC Conflicts; Any Conflict", + "Counter": "0,1,2,3", + "EventCode": "0x57", + "EventName": "UNC_H_IODC_CONFLICTS.ANY", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "IODC Conflicts; Last Conflict", + "Counter": "0,1,2,3", + "EventCode": "0x57", + "EventName": "UNC_H_IODC_CONFLICTS.LAST", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "IODC Conflicts: Remote InvItoE - Same RTID", + "Counter": "0,1,2,3", + "EventCode": "0x57", + "EventName": "UNC_H_IODC_CONFLICTS.REMOTE_INVI2E_SAME_RTID", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "IODC Conflicts: Remote (Other) - Same Addr", + "Counter": "0,1,2,3", + "EventCode": "0x57", + "EventName": "UNC_H_IODC_CONFLICTS.REMOTE_OTHER_SAME_ADDR", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "IODC Inserts", + "Counter": "0,1,2,3", + "EventCode": "0x56", + "EventName": "UNC_H_IODC_INSERTS", + "PerPkg": "1", + "PublicDescription": "IODC Allocations", + "Unit": "HA" + }, + { + "BriefDescription": "Num IODC 0 Length Writes", + "Counter": "0,1,2,3", + "EventCode": "0x58", + "EventName": "UNC_H_IODC_OLEN_WBMTOI", + "PerPkg": "1", + "PublicDescription": "Num IODC 0 Length Writebacks M to I - All of which are dropped.", + "Unit": "HA" + }, + { + "BriefDescription": "OSB Snoop Broadcast; Local InvItoE", + "Counter": "0,1,2,3", + "EventCode": "0x53", + "EventName": "UNC_H_OSB.INVITOE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "OSB Snoop Broadcast; Local Reads", + "Counter": "0,1,2,3", + "EventCode": "0x53", + "EventName": "UNC_H_OSB.READS_LOCAL", + "PerPkg": "1", + "PublicDescription": "Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "OSB Snoop Broadcast; Remote", + "Counter": "0,1,2,3", + "EventCode": "0x53", + "EventName": "UNC_H_OSB.REMOTE", + "PerPkg": "1", + "PublicDescription": "Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "OSB Early Data Return; All", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_H_OSB_EDR.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that broadcast snoop due to OSB, but found clean data in memory and was able to do early data return", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "OSB Early Data Return; Reads to Local I", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_H_OSB_EDR.READS_LOCAL_I", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that broadcast snoop due to OSB, but found clean data in memory and was able to do early data return", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "OSB Early Data Return; Reads to Local S", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_H_OSB_EDR.READS_LOCAL_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that broadcast snoop due to OSB, but found clean data in memory and was able to do early data return", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "OSB Early Data Return; Reads to Remote I", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_H_OSB_EDR.READS_REMOTE_I", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that broadcast snoop due to OSB, but found clean data in memory and was able to do early data return", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "OSB Early Data Return; Reads to Remote S", + "Counter": "0,1,2,3", + "EventCode": "0x54", + "EventName": "UNC_H_OSB_EDR.READS_REMOTE_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that broadcast snoop due to OSB, but found clean data in memory and was able to do early data return", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "Read and Write Requests; Local InvItoEs", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).; This filter includes only InvItoEs coming from the local socket.", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "Read and Write Requests; Remote InvItoEs", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).; This filter includes only InvItoEs coming from remote sockets.", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "Read and Write Requests; Reads", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).; Incoming ead requests. This is a good proxy for LLC Read Misses (including RFOs).", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "Read and Write Requests; Local Reads", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).; This filter includes only read requests coming from the local socket. This is a good proxy for LLC Read Misses (including RFOs) from the local socket.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "Read and Write Requests; Remote Reads", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).; This filter includes only read requests coming from the remote socket. This is a good proxy for LLC Read Misses (including RFOs) from the remote socket.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Read and Write Requests; Writes", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).; Incoming write requests.", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "Read and Write Requests; Local Writes", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).; This filter includes only writes coming from the local socket.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Read and Write Requests; Remote Writes", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).; This filter includes only writes coming from remote sockets.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "HA AD Ring in Use; Counterclockwise", + "Counter": "0,1,2,3", + "EventCode": "0x3E", + "EventName": "UNC_H_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xCC", + "Unit": "HA" + }, + { + "BriefDescription": "HA AD Ring in Use; Counterclockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x3e", + "EventName": "UNC_H_RING_AD_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "HA AD Ring in Use; Counterclockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x3e", + "EventName": "UNC_H_RING_AD_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "HA AD Ring in Use; Counterclockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x3e", + "EventName": "UNC_H_RING_AD_USED.CCW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "HA AD Ring in Use; Counterclockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x3e", + "EventName": "UNC_H_RING_AD_USED.CCW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "HA" + }, + { + "BriefDescription": "HA AD Ring in Use; Clockwise", + "Counter": "0,1,2,3", + "EventCode": "0x3E", + "EventName": "UNC_H_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "HA" + }, + { + "BriefDescription": "HA AD Ring in Use; Clockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x3e", + "EventName": "UNC_H_RING_AD_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "HA AD Ring in Use; Clockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x3e", + "EventName": "UNC_H_RING_AD_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "HA AD Ring in Use; Clockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x3e", + "EventName": "UNC_H_RING_AD_USED.CW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "HA AD Ring in Use; Clockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x3e", + "EventName": "UNC_H_RING_AD_USED.CW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "HA AK Ring in Use; Counterclockwise", + "Counter": "0,1,2,3", + "EventCode": "0x3F", + "EventName": "UNC_H_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xCC", + "Unit": "HA" + }, + { + "BriefDescription": "HA AK Ring in Use; Counterclockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x3f", + "EventName": "UNC_H_RING_AK_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "HA AK Ring in Use; Counterclockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x3f", + "EventName": "UNC_H_RING_AK_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "HA AK Ring in Use; Counterclockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x3f", + "EventName": "UNC_H_RING_AK_USED.CCW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "HA AK Ring in Use; Counterclockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x3f", + "EventName": "UNC_H_RING_AK_USED.CCW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "HA" + }, + { + "BriefDescription": "HA AK Ring in Use; Clockwise", + "Counter": "0,1,2,3", + "EventCode": "0x3F", + "EventName": "UNC_H_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "HA" + }, + { + "BriefDescription": "HA AK Ring in Use; Clockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x3f", + "EventName": "UNC_H_RING_AK_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "HA AK Ring in Use; Clockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x3f", + "EventName": "UNC_H_RING_AK_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "HA AK Ring in Use; Clockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x3f", + "EventName": "UNC_H_RING_AK_USED.CW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "HA AK Ring in Use; Clockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x3f", + "EventName": "UNC_H_RING_AK_USED.CW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "HA BL Ring in Use; Counterclockwise", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_H_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xCC", + "Unit": "HA" + }, + { + "BriefDescription": "HA BL Ring in Use; Counterclockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_H_RING_BL_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "HA BL Ring in Use; Counterclockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_H_RING_BL_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "HA BL Ring in Use; Counterclockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_H_RING_BL_USED.CCW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "HA BL Ring in Use; Counterclockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_H_RING_BL_USED.CCW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "HA" + }, + { + "BriefDescription": "HA BL Ring in Use; Clockwise", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_H_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "HA" + }, + { + "BriefDescription": "HA BL Ring in Use; Clockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_H_RING_BL_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "HA BL Ring in Use; Clockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_H_RING_BL_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "HA BL Ring in Use; Clockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_H_RING_BL_USED.CW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "HA BL Ring in Use; Clockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_H_RING_BL_USED.CW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "iMC RPQ Credits Empty - Regular; Channel 0", + "Counter": "0,1,2,3", + "EventCode": "0x15", + "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "iMC RPQ Credits Empty - Regular; Channel 1", + "Counter": "0,1,2,3", + "EventCode": "0x15", + "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "iMC RPQ Credits Empty - Regular; Channel 2", + "Counter": "0,1,2,3", + "EventCode": "0x15", + "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN2", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "iMC RPQ Credits Empty - Regular; Channel 3", + "Counter": "0,1,2,3", + "EventCode": "0x15", + "EventName": "UNC_H_RPQ_CYCLES_NO_REG_CREDITS.CHN3", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "iMC RPQ Credits Empty - Special; Channel 0", + "Counter": "0,1,2,3", + "EventCode": "0x16", + "EventName": "UNC_H_RPQ_CYCLES_NO_SPEC_CREDITS.CHN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no special credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the special credits. This statistic is generally not interesting for general IA workloads, but may be of interest for understanding the characteristics of systems using ISOCH. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "iMC RPQ Credits Empty - Special; Channel 1", + "Counter": "0,1,2,3", + "EventCode": "0x16", + "EventName": "UNC_H_RPQ_CYCLES_NO_SPEC_CREDITS.CHN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no special credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the special credits. This statistic is generally not interesting for general IA workloads, but may be of interest for understanding the characteristics of systems using ISOCH. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "iMC RPQ Credits Empty - Special; Channel 2", + "Counter": "0,1,2,3", + "EventCode": "0x16", + "EventName": "UNC_H_RPQ_CYCLES_NO_SPEC_CREDITS.CHN2", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no special credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the special credits. This statistic is generally not interesting for general IA workloads, but may be of interest for understanding the characteristics of systems using ISOCH. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "iMC RPQ Credits Empty - Special; Channel 3", + "Counter": "0,1,2,3", + "EventCode": "0x16", + "EventName": "UNC_H_RPQ_CYCLES_NO_SPEC_CREDITS.CHN3", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no special credits available for posting reads from the HA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's RPQ (read pending queue). This queue is broken into regular credits/buffers that are used by general reads, and special requests such as ISOCH reads. This count only tracks the special credits. This statistic is generally not interesting for general IA workloads, but may be of interest for understanding the characteristics of systems using ISOCH. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received; RSPCNFLCT*", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for snoops responses of RspConflict. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received; RspI", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPI", + "PerPkg": "1", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for snoops responses of RspI. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received; RspIFwd", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for snoop responses of RspIFwd. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received; RspS", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for snoop responses of RspS. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received; RspSFwd", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of RspSFwd. This is returned when a remote caching agent forwards data but holds on to its currently copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received; Rsp*Fwd*WB", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of Rsp*Fwd*WB. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received; Rsp*WB", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_WB", + "PerPkg": "1", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of RspIWB or RspSWB. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received Local; Other", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_H_SNP_RESP_RECV_LOCAL.OTHER", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for all other snoop responses.", + "UMask": "0x80", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspCnflct", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_H_SNP_RESP_RECV_LOCAL.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoops responses of RspConflict. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspI", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_H_SNP_RESP_RECV_LOCAL.RSPI", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoops responses of RspI. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspIFwd", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_H_SNP_RESP_RECV_LOCAL.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoop responses of RspIFwd. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspS", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_H_SNP_RESP_RECV_LOCAL.RSPS", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoop responses of RspS. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspSFwd", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_H_SNP_RESP_RECV_LOCAL.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd. This is returned when a remote caching agent forwards data but holds on to its currently copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received Local; Rsp*FWD*WB", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_H_SNP_RESP_RECV_LOCAL.RSPxFWDxWB", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of Rsp*Fwd*WB. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "Snoop Responses Received Local; Rsp*WB", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_H_SNP_RESP_RECV_LOCAL.RSPxWB", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspIWB or RspSWB. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 0; TAD Region 0", + "Counter": "0,1,2,3", + "EventCode": "0x1b", + "EventName": "UNC_H_TAD_REQUESTS_G0.REGION0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 0 to 7. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 0; TAD Region 1", + "Counter": "0,1,2,3", + "EventCode": "0x1b", + "EventName": "UNC_H_TAD_REQUESTS_G0.REGION1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 0 to 7. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 0; TAD Region 2", + "Counter": "0,1,2,3", + "EventCode": "0x1b", + "EventName": "UNC_H_TAD_REQUESTS_G0.REGION2", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 0 to 7. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 2", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 0; TAD Region 3", + "Counter": "0,1,2,3", + "EventCode": "0x1b", + "EventName": "UNC_H_TAD_REQUESTS_G0.REGION3", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 0 to 7. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 3", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 0; TAD Region 4", + "Counter": "0,1,2,3", + "EventCode": "0x1b", + "EventName": "UNC_H_TAD_REQUESTS_G0.REGION4", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 0 to 7. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 4", + "UMask": "0x10", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 0; TAD Region 5", + "Counter": "0,1,2,3", + "EventCode": "0x1b", + "EventName": "UNC_H_TAD_REQUESTS_G0.REGION5", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 0 to 7. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 5", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 0; TAD Region 6", + "Counter": "0,1,2,3", + "EventCode": "0x1b", + "EventName": "UNC_H_TAD_REQUESTS_G0.REGION6", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 0 to 7. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 6", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 0; TAD Region 7", + "Counter": "0,1,2,3", + "EventCode": "0x1b", + "EventName": "UNC_H_TAD_REQUESTS_G0.REGION7", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 0 to 7. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 7", + "UMask": "0x80", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 1; TAD Region 10", + "Counter": "0,1,2,3", + "EventCode": "0x1c", + "EventName": "UNC_H_TAD_REQUESTS_G1.REGION10", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 8 to 10. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 10", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 1; TAD Region 11", + "Counter": "0,1,2,3", + "EventCode": "0x1c", + "EventName": "UNC_H_TAD_REQUESTS_G1.REGION11", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 8 to 10. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 11", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 1; TAD Region 8", + "Counter": "0,1,2,3", + "EventCode": "0x1c", + "EventName": "UNC_H_TAD_REQUESTS_G1.REGION8", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 8 to 10. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 8", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "HA Requests to a TAD Region - Group 1; TAD Region 9", + "Counter": "0,1,2,3", + "EventCode": "0x1c", + "EventName": "UNC_H_TAD_REQUESTS_G1.REGION9", + "PerPkg": "1", + "PublicDescription": "Counts the number of HA requests to a given TAD region. There are up to 11 TAD (target address decode) regions in each home agent. All requests destined for the memory controller must first be decoded to determine which TAD region they are in. This event is filtered based on the TAD region ID, and covers regions 8 to 10. This event is useful for understanding how applications are using the memory that is spread across the different memory regions. It is particularly useful for Monroe systems that use the TAD to enable individual channels to enter self-refresh to save power.; Filters request made to TAD Region 9", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Tracker Cycles Not Empty", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_H_TRACKER_CYCLES_NE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the local HA tracker pool is not empty. This can be used with edge detect to identify the number of situations when the pool became empty. This should not be confused with RTID credit usage -- which must be tracked inside each cbo individually -- but represents the actual tracker buffer structure. In other words, this buffer could be completely empty, but there may still be credits in use by the CBos. This stat can be used in conjunction with the occupancy accumulation stat in order to calculate average queue occpancy. HA trackers are allocated as soon as a request enters the HA if an HT (Home Tracker) entry is available and is released after the snoop response and data return (or post in the case of a write) and the response is returned on the ring.", + "Unit": "HA" + }, + { + "BriefDescription": "Outbound NDR Ring Transactions; Non-data Responses", + "Counter": "0,1,2,3", + "EventCode": "0xF", + "EventName": "UNC_H_TxR_AD.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of outbound transactions on the AD ring. This can be filtered by the NDR and SNP message classes. See the filter descriptions for more details.; Filter for outbound NDR transactions sent on the AD ring. NDR stands for non-data response and is generally used for completions that do not include data. AD NDR is used for transactions to remote sockets.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Full; All", + "Counter": "0,1,2,3", + "EventCode": "0x2a", + "EventName": "UNC_H_TxR_AD_CYCLES_FULL.ALL", + "PerPkg": "1", + "PublicDescription": "AD Egress Full; Cycles full from both schedulers", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Full; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x2a", + "EventName": "UNC_H_TxR_AD_CYCLES_FULL.SCHED0", + "PerPkg": "1", + "PublicDescription": "AD Egress Full; Filter for cycles full from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Full; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x2a", + "EventName": "UNC_H_TxR_AD_CYCLES_FULL.SCHED1", + "PerPkg": "1", + "PublicDescription": "AD Egress Full; Filter for cycles full from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Not Empty; All", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_H_TxR_AD_CYCLES_NE.ALL", + "PerPkg": "1", + "PublicDescription": "AD Egress Not Empty; Cycles full from both schedulers", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Not Empty; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_H_TxR_AD_CYCLES_NE.SCHED0", + "PerPkg": "1", + "PublicDescription": "AD Egress Not Empty; Filter for cycles not empty from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Not Empty; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_H_TxR_AD_CYCLES_NE.SCHED1", + "PerPkg": "1", + "PublicDescription": "AD Egress Not Empty; Filter for cycles not empty from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Allocations; All", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_H_TxR_AD_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "AD Egress Allocations; Allocations from both schedulers", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Allocations; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_H_TxR_AD_INSERTS.SCHED0", + "PerPkg": "1", + "PublicDescription": "AD Egress Allocations; Filter for allocations from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Allocations; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_H_TxR_AD_INSERTS.SCHED1", + "PerPkg": "1", + "PublicDescription": "AD Egress Allocations; Filter for allocations from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Occupancy; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x28", + "EventName": "UNC_H_TxR_AD_OCCUPANCY.SCHED0", + "PerPkg": "1", + "PublicDescription": "AD Egress Occupancy; Filter for occupancy from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "AD Egress Occupancy; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x28", + "EventName": "UNC_H_TxR_AD_OCCUPANCY.SCHED1", + "PerPkg": "1", + "PublicDescription": "AD Egress Occupancy; Filter for occupancy from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Outbound Ring Transactions on AK: CRD Transactions to Cbo", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_H_TxR_AK.CRD_CBO", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Full; All", + "Counter": "0,1,2,3", + "EventCode": "0x32", + "EventName": "UNC_H_TxR_AK_CYCLES_FULL.ALL", + "PerPkg": "1", + "PublicDescription": "AK Egress Full; Cycles full from both schedulers", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Full; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x32", + "EventName": "UNC_H_TxR_AK_CYCLES_FULL.SCHED0", + "PerPkg": "1", + "PublicDescription": "AK Egress Full; Filter for cycles full from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Full; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x32", + "EventName": "UNC_H_TxR_AK_CYCLES_FULL.SCHED1", + "PerPkg": "1", + "PublicDescription": "AK Egress Full; Filter for cycles full from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Not Empty; All", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_H_TxR_AK_CYCLES_NE.ALL", + "PerPkg": "1", + "PublicDescription": "AK Egress Not Empty; Cycles full from both schedulers", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Not Empty; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_H_TxR_AK_CYCLES_NE.SCHED0", + "PerPkg": "1", + "PublicDescription": "AK Egress Not Empty; Filter for cycles not empty from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Not Empty; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x31", + "EventName": "UNC_H_TxR_AK_CYCLES_NE.SCHED1", + "PerPkg": "1", + "PublicDescription": "AK Egress Not Empty; Filter for cycles not empty from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Allocations; All", + "Counter": "0,1,2,3", + "EventCode": "0x2f", + "EventName": "UNC_H_TxR_AK_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "AK Egress Allocations; Allocations from both schedulers", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Allocations; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x2f", + "EventName": "UNC_H_TxR_AK_INSERTS.SCHED0", + "PerPkg": "1", + "PublicDescription": "AK Egress Allocations; Filter for allocations from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Allocations; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x2f", + "EventName": "UNC_H_TxR_AK_INSERTS.SCHED1", + "PerPkg": "1", + "PublicDescription": "AK Egress Allocations; Filter for allocations from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Occupancy; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x30", + "EventName": "UNC_H_TxR_AK_OCCUPANCY.SCHED0", + "PerPkg": "1", + "PublicDescription": "AK Egress Occupancy; Filter for occupancy from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "AK Egress Occupancy; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x30", + "EventName": "UNC_H_TxR_AK_OCCUPANCY.SCHED1", + "PerPkg": "1", + "PublicDescription": "AK Egress Occupancy; Filter for occupancy from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to Cache", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_H_TxR_BL.DRS_CACHE", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS messages sent out on the BL ring. This can be filtered by the destination.; Filter for data being sent to the cache.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to Core", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_H_TxR_BL.DRS_CORE", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS messages sent out on the BL ring. This can be filtered by the destination.; Filter for data being sent directly to the requesting core.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to QPI", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_H_TxR_BL.DRS_QPI", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS messages sent out on the BL ring. This can be filtered by the destination.; Filter for data being sent to a remote socket over QPI.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Full; All", + "Counter": "0,1,2,3", + "EventCode": "0x36", + "EventName": "UNC_H_TxR_BL_CYCLES_FULL.ALL", + "PerPkg": "1", + "PublicDescription": "BL Egress Full; Cycles full from both schedulers", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Full; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x36", + "EventName": "UNC_H_TxR_BL_CYCLES_FULL.SCHED0", + "PerPkg": "1", + "PublicDescription": "BL Egress Full; Filter for cycles full from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Full; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x36", + "EventName": "UNC_H_TxR_BL_CYCLES_FULL.SCHED1", + "PerPkg": "1", + "PublicDescription": "BL Egress Full; Filter for cycles full from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Not Empty; All", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_H_TxR_BL_CYCLES_NE.ALL", + "PerPkg": "1", + "PublicDescription": "BL Egress Not Empty; Cycles full from both schedulers", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Not Empty; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_H_TxR_BL_CYCLES_NE.SCHED0", + "PerPkg": "1", + "PublicDescription": "BL Egress Not Empty; Filter for cycles not empty from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Not Empty; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_H_TxR_BL_CYCLES_NE.SCHED1", + "PerPkg": "1", + "PublicDescription": "BL Egress Not Empty; Filter for cycles not empty from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Allocations; All", + "Counter": "0,1,2,3", + "EventCode": "0x33", + "EventName": "UNC_H_TxR_BL_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "BL Egress Allocations; Allocations from both schedulers", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Allocations; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x33", + "EventName": "UNC_H_TxR_BL_INSERTS.SCHED0", + "PerPkg": "1", + "PublicDescription": "BL Egress Allocations; Filter for allocations from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Allocations; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x33", + "EventName": "UNC_H_TxR_BL_INSERTS.SCHED1", + "PerPkg": "1", + "PublicDescription": "BL Egress Allocations; Filter for allocations from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Occupancy: All", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_H_TxR_BL_OCCUPANCY.ALL", + "PerPkg": "1", + "PublicDescription": "BL Egress Occupancy", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Occupancy; Scheduler 0", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_H_TxR_BL_OCCUPANCY.SCHED0", + "PerPkg": "1", + "PublicDescription": "BL Egress Occupancy; Filter for occupancy from scheduler bank 0", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "BL Egress Occupancy; Scheduler 1", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_H_TxR_BL_OCCUPANCY.SCHED1", + "PerPkg": "1", + "PublicDescription": "BL Egress Occupancy; Filter for occupancy from scheduler bank 1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "HA iMC CHN0 WPQ Credits Empty - Regular; Channel 0", + "Counter": "0,1,2,3", + "EventCode": "0x18", + "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "HA iMC CHN0 WPQ Credits Empty - Regular; Channel 1", + "Counter": "0,1,2,3", + "EventCode": "0x18", + "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "HA iMC CHN0 WPQ Credits Empty - Regular; Channel 2", + "Counter": "0,1,2,3", + "EventCode": "0x18", + "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN2", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "HA iMC CHN0 WPQ Credits Empty - Regular; Channel 3", + "Counter": "0,1,2,3", + "EventCode": "0x18", + "EventName": "UNC_H_WPQ_CYCLES_NO_REG_CREDITS.CHN3", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no regular credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the regular credits Common high banwidth workloads should be able to make use of all of the regular buffers, but it will be difficult (and uncommon) to make use of both the regular and special buffers at the same time. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "HA iMC CHN0 WPQ Credits Empty - Special; Channel 0", + "Counter": "0,1,2,3", + "EventCode": "0x19", + "EventName": "UNC_H_WPQ_CYCLES_NO_SPEC_CREDITS.CHN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no special credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the special credits. This statistic is generally not interesting for general IA workloads, but may be of interest for understanding the characteristics of systems using ISOCH. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 0 only.", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "HA iMC CHN0 WPQ Credits Empty - Special; Channel 1", + "Counter": "0,1,2,3", + "EventCode": "0x19", + "EventName": "UNC_H_WPQ_CYCLES_NO_SPEC_CREDITS.CHN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no special credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the special credits. This statistic is generally not interesting for general IA workloads, but may be of interest for understanding the characteristics of systems using ISOCH. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 1 only.", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "HA iMC CHN0 WPQ Credits Empty - Special; Channel 2", + "Counter": "0,1,2,3", + "EventCode": "0x19", + "EventName": "UNC_H_WPQ_CYCLES_NO_SPEC_CREDITS.CHN2", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no special credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the special credits. This statistic is generally not interesting for general IA workloads, but may be of interest for understanding the characteristics of systems using ISOCH. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 2 only.", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "HA iMC CHN0 WPQ Credits Empty - Special; Channel 3", + "Counter": "0,1,2,3", + "EventCode": "0x19", + "EventName": "UNC_H_WPQ_CYCLES_NO_SPEC_CREDITS.CHN3", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are no special credits available for posting writes from the HA into the iMC. In order to send writes into the memory controller, the HA must first acquire a credit for the iMC's WPQ (write pending queue). This queue is broken into regular credits/buffers that are used by general writes, and special requests such as ISOCH writes. This count only tracks the special credits. This statistic is generally not interesting for general IA workloads, but may be of interest for understanding the characteristics of systems using ISOCH. One can filter based on the memory controller channel. One or more channels can be tracked at a given time.; Filter for memory controller channel 3 only.", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json new file mode 100644 index 000000000..10ea4afef --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json @@ -0,0 +1,1767 @@ +[ + { + "BriefDescription": "Number of qfclks", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of clocks in the QPI LL. This clock runs at 1/8th the GT/s speed of the QPI link. For example, a 8GT/s link will have qfclk or 1GHz. JKT does not support dynamic link speeds, so this frequency is fixed.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Count of CTO Events", + "Counter": "0,1,2,3", + "EventCode": "0x38", + "EventName": "UNC_Q_CTO_COUNT", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of CTO (cluster trigger outs) events that were asserted across the two slots. If both slots trigger in a given cycle, the event will increment by 2. You can use edge detect to count the number of cases when both events triggered.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress Credits", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits. Had there been enough credits, the spawn would have worked as the RBT bit was set and the RBT tag matched.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and there weren't enough Egress credits. The valid bit was set.", + "UMask": "0x20", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Invalid", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits AND the RBT bit was not set, but the RBT tag matched.", + "UMask": "0x8", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss, Invalid", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match, the valid bit was not set and there weren't enough Egress credits.", + "UMask": "0x80", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match although the valid bit was set and there were enough Egress credits.", + "UMask": "0x10", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Invalid", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the route-back table (RBT) specified that the transaction should not trigger a direct2core transaction. This is common for IO transactions. There were enough Egress credits and the RBT tag matched but the valid bit was not set.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss and Invalid", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and the valid bit was not set although there were enough Egress credits.", + "UMask": "0x40", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Success", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.SUCCESS_RBT_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn was successful. There were sufficient credits, the RBT valid bit was set and there was an RBT tag match. The message was marked to spawn direct2core.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles in L1", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_Q_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a QPI link. Use edge detect to count the number of instances when the QPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles in L0p", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles in L0", + "Counter": "0,1,2,3", + "EventCode": "0xf", + "EventName": "UNC_Q_RxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Bypassed", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_Q_RxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "CRC Errors Detected; LinkInit", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_CRC_ERRORS.LINK_INIT", + "PerPkg": "1", + "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during link initialization.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "CRC Errors Detected; Normal Operations", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_CRC_ERRORS.NORMAL_OP", + "PerPkg": "1", + "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during normal operation.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN0 Credit Consumed; DRS", + "Counter": "0,1,2,3", + "EventCode": "0x1e", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.DRS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the DRS message class.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN0 Credit Consumed; HOM", + "Counter": "0,1,2,3", + "EventCode": "0x1e", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.HOM", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the HOM message class.", + "UMask": "0x8", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN0 Credit Consumed; NCB", + "Counter": "0,1,2,3", + "EventCode": "0x1e", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NCB", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCB message class.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN0 Credit Consumed; NCS", + "Counter": "0,1,2,3", + "EventCode": "0x1e", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NCS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCS message class.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN0 Credit Consumed; NDR", + "Counter": "0,1,2,3", + "EventCode": "0x1e", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NDR", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NDR message class.", + "UMask": "0x20", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN0 Credit Consumed; SNP", + "Counter": "0,1,2,3", + "EventCode": "0x1e", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.SNP", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the SNP message class.", + "UMask": "0x10", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN1 Credit Consumed; DRS", + "Counter": "0,1,2,3", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.DRS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the DRS message class.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN1 Credit Consumed; HOM", + "Counter": "0,1,2,3", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.HOM", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the HOM message class.", + "UMask": "0x8", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN1 Credit Consumed; NCB", + "Counter": "0,1,2,3", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NCB", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCB message class.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN1 Credit Consumed; NCS", + "Counter": "0,1,2,3", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NCS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCS message class.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN1 Credit Consumed; NDR", + "Counter": "0,1,2,3", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NDR", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NDR message class.", + "UMask": "0x20", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VN1 Credit Consumed; SNP", + "Counter": "0,1,2,3", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.SNP", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the SNP message class.", + "UMask": "0x10", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VNA Credit Consumed", + "Counter": "0,1,2,3", + "EventCode": "0x1d", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VNA", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_Q_RxL_CYCLES_NE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0xF", + "EventName": "UNC_Q_RxL_CYCLES_NE_DRS.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0xF", + "EventName": "UNC_Q_RxL_CYCLES_NE_DRS.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_Q_RxL_CYCLES_NE_HOM.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x12", + "EventName": "UNC_Q_RxL_CYCLES_NE_HOM.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCB.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCB.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x11", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCS.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x11", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCS.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_RxL_CYCLES_NE_NDR.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_RxL_CYCLES_NE_NDR.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_Q_RxL_CYCLES_NE_SNP.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x13", + "EventName": "UNC_Q_RxL_CYCLES_NE_SNP.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 0; Data Tx Flits", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_Q_RxL_FLITS_G0.DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits received over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 0; Idle and Null Flits", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_Q_RxL_FLITS_G0.IDLE", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generally not considered part of the QPI bandwidth.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 0; Non-Data protocol Tx Flits", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_Q_RxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits received across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 1; DRS Flits (both Header and Data)", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.DRS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", + "UMask": "0x18", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 1; DRS Data Flits", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.DRS_DATA", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", + "UMask": "0x8", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 1; DRS Header Flits", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.DRS_NONDATA", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 1; HOM Flits", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.HOM", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", + "UMask": "0x6", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 1; HOM Non-Request Flits", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.HOM_NONREQ", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 1; HOM Request Flits", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.HOM_REQ", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 1; SNP Flits", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.SNP", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent Rx Flits", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCB", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", + "UMask": "0xC", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent data Rx Flits", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCB_DATA", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent non-data Rx Flits", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCB_NONDATA", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "UMask": "0x8", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent standard Rx Flits", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AD", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AD", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AK", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AK", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_Q_RxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - DRS", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_Q_RxL_INSERTS_DRS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_Q_RxL_INSERTS_DRS.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_Q_RxL_INSERTS_DRS.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - HOM", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_Q_RxL_INSERTS_HOM", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0xC", + "EventName": "UNC_Q_RxL_INSERTS_HOM.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0xC", + "EventName": "UNC_Q_RxL_INSERTS_HOM.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCB", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_Q_RxL_INSERTS_NCB", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_Q_RxL_INSERTS_NCB.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_Q_RxL_INSERTS_NCB.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCS", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_Q_RxL_INSERTS_NCS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0xB", + "EventName": "UNC_Q_RxL_INSERTS_NCS.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0xB", + "EventName": "UNC_Q_RxL_INSERTS_NCS.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NDR", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_Q_RxL_INSERTS_NDR", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0xE", + "EventName": "UNC_Q_RxL_INSERTS_NDR.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0xE", + "EventName": "UNC_Q_RxL_INSERTS_NDR.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - SNP", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_Q_RxL_INSERTS_SNP", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0xD", + "EventName": "UNC_Q_RxL_INSERTS_SNP.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0xD", + "EventName": "UNC_Q_RxL_INSERTS_SNP.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_Q_RxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - DRS", + "Counter": "0,1,2,3", + "EventCode": "0x15", + "EventName": "UNC_Q_RxL_OCCUPANCY_DRS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - DRS; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x15", + "EventName": "UNC_Q_RxL_OCCUPANCY_DRS.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - DRS; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x15", + "EventName": "UNC_Q_RxL_OCCUPANCY_DRS.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - HOM", + "Counter": "0,1,2,3", + "EventCode": "0x18", + "EventName": "UNC_Q_RxL_OCCUPANCY_HOM", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - HOM; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x18", + "EventName": "UNC_Q_RxL_OCCUPANCY_HOM.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - HOM; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x18", + "EventName": "UNC_Q_RxL_OCCUPANCY_HOM.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - NCB", + "Counter": "0,1,2,3", + "EventCode": "0x16", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCB", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - NCB; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x16", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCB.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - NCB; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x16", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCB.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - NCS", + "Counter": "0,1,2,3", + "EventCode": "0x17", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - NCS; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x17", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCS.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - NCS; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x17", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCS.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - NDR", + "Counter": "0,1,2,3", + "EventCode": "0x1a", + "EventName": "UNC_Q_RxL_OCCUPANCY_NDR", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - NDR; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x1A", + "EventName": "UNC_Q_RxL_OCCUPANCY_NDR.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - NDR; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x1A", + "EventName": "UNC_Q_RxL_OCCUPANCY_NDR.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - SNP", + "Counter": "0,1,2,3", + "EventCode": "0x19", + "EventName": "UNC_Q_RxL_OCCUPANCY_SNP", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - SNP; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x19", + "EventName": "UNC_Q_RxL_OCCUPANCY_SNP.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "RxQ Occupancy - SNP; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x19", + "EventName": "UNC_Q_RxL_OCCUPANCY_SNP.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - HOM", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_DRS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - DRS", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_HOM", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x8", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - SNP", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NCB", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NDR", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NCS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCS", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NDR", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x20", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCB", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_SNP", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x10", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; Egress Credits", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.EGRESS_CREDITS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet because there were insufficient BGF credits. For details on a message class granularity, use the Egress Credit Occupancy events.", + "UMask": "0x40", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; GV", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.GV", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled because a GV transition (frequency transition) was taking place.", + "UMask": "0x80", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - HOM", + "Counter": "0,1,2,3", + "EventCode": "0x3a", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_DRS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - DRS", + "Counter": "0,1,2,3", + "EventCode": "0x3a", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_HOM", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x8", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - SNP", + "Counter": "0,1,2,3", + "EventCode": "0x3a", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NCB", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NDR", + "Counter": "0,1,2,3", + "EventCode": "0x3a", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NCS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCS", + "Counter": "0,1,2,3", + "EventCode": "0x3a", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NDR", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x20", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCB", + "Counter": "0,1,2,3", + "EventCode": "0x3a", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_SNP", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x10", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles in L0p", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles in L0", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_Q_TxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Tx Flit Buffer Bypassed", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_Q_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the QPI Link. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is almost full", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_Q_TxL_CRC_NO_CREDITS.ALMOST_FULL", + "PerPkg": "1", + "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is almost full, we block some but not all packets.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is full", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_Q_TxL_CRC_NO_CREDITS.FULL", + "PerPkg": "1", + "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is totally full, we are not allowed to send any packets.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Tx Flit Buffer Cycles not Empty", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_Q_TxL_CYCLES_NE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the TxQ is not empty. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G1.DRS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", + "UMask": "0x18", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G1.DRS_DATA", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", + "UMask": "0x8", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G1.DRS_NONDATA", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 1; HOM Flits", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G1.HOM", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", + "UMask": "0x6", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G1.HOM_NONREQ", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G1.HOM_REQ", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 1; SNP Flits", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G1.SNP", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent Bypass Tx Flits", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCB", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", + "UMask": "0xC", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent data Tx Flits", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCB_DATA", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent non-data Tx Flits", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCB_NONDATA", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "UMask": "0x8", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent standard Tx Flits", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AD", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AD", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AK", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AK", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Tx Flit Buffer Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_Q_TxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Tx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Tx Flit Buffer Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_Q_TxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_ACQUIRED.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_ACQUIRED.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_OCCUPANCY.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_OCCUPANCY.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x28", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_ACQUIRED.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x28", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_ACQUIRED.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_OCCUPANCY.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_OCCUPANCY.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_ACQUIRED.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x27", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_ACQUIRED.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x23", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x23", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_ACQUIRED", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_ACQUIRED.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x29", + "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_ACQUIRED.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_OCCUPANCY", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_OCCUPANCY.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_OCCUPANCY.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x2a", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x2a", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for Shared VN", + "Counter": "0,1,2,3", + "EventCode": "0x2a", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN_SHR", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x1f", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x1f", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for Shared VN", + "Counter": "0,1,2,3", + "EventCode": "0x1f", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN_SHR", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "UMask": "0x4", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x2b", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_ACQUIRED.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x2b", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_ACQUIRED.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_OCCUPANCY.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_OCCUPANCY.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x2c", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_ACQUIRED.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x2c", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_ACQUIRED.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN0", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_OCCUPANCY.VN0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN1", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_OCCUPANCY.VN1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VNA Credits Returned", + "Counter": "0,1,2,3", + "EventCode": "0x1c", + "EventName": "UNC_Q_VNA_CREDIT_RETURNS", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of VNA credits returned.", + "Unit": "QPI LL" + }, + { + "BriefDescription": "VNA Credits Pending Return - Occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x1b", + "EventName": "UNC_Q_VNA_CREDIT_RETURN_OCCUPANCY", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json new file mode 100644 index 000000000..ed60ebca3 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json @@ -0,0 +1,1812 @@ +[ + { + "BriefDescription": "DRAM Activate Count; Activate due to Write", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT.BYP", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRAM Activate commands sent on this channel. Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Activate Count; Activate due to Read", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRAM Activate commands sent on this channel. Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Activate Count; Activate due to Write", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRAM Activate commands sent on this channel. Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "ACT command issued by 2 cycle bypass", + "Counter": "0,1,2,3", + "EventCode": "0xa1", + "EventName": "UNC_M_BYP_CMDS.ACT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "CAS command issued by 2 cycle bypass", + "Counter": "0,1,2,3", + "EventCode": "0xa1", + "EventName": "UNC_M_BYP_CMDS.CAS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "PRE command issued by 2 cycle bypass", + "Counter": "0,1,2,3", + "EventCode": "0xa1", + "EventName": "UNC_M_BYP_CMDS.PRE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.; All DRAM WR_CAS (w/ and w/out auto-pre)", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands; Counts the total number of DRAM CAS commands issued on this channel.", + "UMask": "0xF", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.; All DRAM Reads (RD_CAS + Underfills)", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands; Counts the total number of DRAM Read CAS commands issued on this channel (including underfills).", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.; All DRAM RD_CAS (w/ and w/out auto-pre)", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD_REG", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands; Counts the total number or DRAM Read CAS commands issued on this channel. This includes both regular RD CAS commands as well as those with implicit Precharge. AutoPre is only used in systems that are using closed page policy. We do not filter based on major mode, as RD_CAS is not issued during WMM (with the exception of underfills).", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.; Read CAS issued in RMM", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD_RMM", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.; Underfill Read Issued", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands; Counts the number of underfill reads that are issued by the memory controller. This will generally be about the same as the number of partial writes, but may be slightly less because of partials hitting in the WPQ. While it is possible for underfills to be issed in both WMM and RMM, this event counts both.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.; Read CAS issued in WMM", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.RD_WMM", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.; All DRAM WR_CAS (both Modes)", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands; Counts the total number of DRAM Write CAS commands issued on this channel.", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.; DRAM WR_CAS (w/ and w/out auto-pre) in Read Major Mode", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.WR_RMM", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands; Counts the total number of Opportunistic DRAM Write CAS commands issued on this channel while in Read-Major-Mode.", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.; DRAM WR_CAS (w/ and w/out auto-pre) in Write Major Mode", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_M_CAS_COUNT.WR_WMM", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands; Counts the total number or DRAM Write CAS commands issued on this channel while in Write-Major-Mode.", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Clockticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_DCLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge All Commands", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_M_DRAM_PRE_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that the precharge all command was sent.", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_M_DRAM_REFRESH.HIGH", + "PerPkg": "1", + "PublicDescription": "Counts the number of refreshes issued.", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of DRAM Refreshes Issued", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_M_DRAM_REFRESH.PANIC", + "PerPkg": "1", + "PublicDescription": "Counts the number of refreshes issued.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "ECC Correctable Errors", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_M_ECC_CORRECTABLE_ERRORS", + "PerPkg": "1", + "PublicDescription": "Counts the number of ECC errors detected and corrected by the iMC on this channel. This counter is only useful with ECC DRAM devices. This count will increment one time for each correction regardless of the number of bits corrected. The iMC can correct up to 4 bit errors in independent channel mode and 8 bit errors in lockstep mode.", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles in a Major Mode; Isoch Major Mode", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_M_MAJOR_MODES.ISOCH", + "PerPkg": "1", + "PublicDescription": "Counts the total number of cycles spent in a major mode (selected by a filter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) mode.; We group these two modes together so that we can use four counters to track each of the major modes at one time. These major modes are used whenever there is an ISOCH txn in the memory controller. In these mode, only ISOCH transactions are processed.", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles in a Major Mode; Partial Major Mode", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_M_MAJOR_MODES.PARTIAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of cycles spent in a major mode (selected by a filter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) mode.; This major mode is used to drain starved underfill reads. Regular reads and writes are blocked and only underfill reads will be processed.", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles in a Major Mode; Read Major Mode", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_M_MAJOR_MODES.READ", + "PerPkg": "1", + "PublicDescription": "Counts the total number of cycles spent in a major mode (selected by a filter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) mode.; Read Major Mode is the default mode for the iMC, as reads are generally more critical to forward progress than writes.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles in a Major Mode; Write Major Mode", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_M_MAJOR_MODES.WRITE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of cycles spent in a major mode (selected by a filter) on the given channel. Major modea are channel-wide, and not a per-rank (or dimm or bank) mode.; This mode is triggered when the WPQ hits high occupancy and causes writes to be higher priority than reads. This can cause blips in the available read bandwidth in the system and temporarily increase read latencies in order to achieve better bus utilizations and higher bandwidth.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Channel DLLOFF Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x84", + "EventName": "UNC_M_POWER_CHANNEL_DLLOFF", + "PerPkg": "1", + "PublicDescription": "Number of cycles when all the ranks in the channel are in CKE Slow (DLLOFF) mode.", + "Unit": "iMC" + }, + { + "BriefDescription": "Channel PPD Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "PerPkg": "1", + "PublicDescription": "Number of cycles when all the ranks in the channel are in PPD mode. If IBT=off is enabled, then this can be used to count those cycles. If it is not enabled, then this can count the number of cycles when that could have been taken advantage of.", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x83", + "EventName": "UNC_M_POWER_CKE_CYCLES.RANK0", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x83", + "EventName": "UNC_M_POWER_CKE_CYCLES.RANK1", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x83", + "EventName": "UNC_M_POWER_CKE_CYCLES.RANK2", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x83", + "EventName": "UNC_M_POWER_CKE_CYCLES.RANK3", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x83", + "EventName": "UNC_M_POWER_CKE_CYCLES.RANK4", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x83", + "EventName": "UNC_M_POWER_CKE_CYCLES.RANK5", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x83", + "EventName": "UNC_M_POWER_CKE_CYCLES.RANK6", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x83", + "EventName": "UNC_M_POWER_CKE_CYCLES.RANK7", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "Critical Throttle Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the iMC is in critical thermal throttling. When this happens, all traffic is blocked. This should be rare unless something bad is going on in the platform. There is no filtering by rank for this event.", + "Unit": "iMC" + }, + { + "BriefDescription": "Clock-Enabled Self-Refresh", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the iMC is in self-refresh and the iMC still has a clock. This happens in some package C-states. For example, the PCU may ask the iMC to enter self-refresh even though some of the cores are still processing. One use of this is for Monroe technology. Self-refresh is required during package C3 and C6, but there is no clock in the iMC at this time, so it is not possible to count these cases.", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RANK0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.; Thermal throttling is performed per DIMM. We support 3 DIMMs per channel. This ID allows us to filter by ID.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RANK1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RANK2", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RANK3", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RANK4", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RANK5", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RANK6", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0; DIMM ID", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_M_POWER_THROTTLE_CYCLES.RANK7", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Preemption Count; Read over Read Preemption", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_M_PREEMPTION.RD_PREEMPT_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times a read in the iMC preempts another read or write. Generally reads to an open page are issued ahead of requests to closed pages. This improves the page hit rate of the system. However, high priority requests can cause pages of active requests to be closed in order to get them out. This will reduce the latency of the high-priority request at the expense of lower bandwidth and increased overall average latency.; Filter for when a read preempts another read.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Preemption Count; Read over Write Preemption", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_M_PREEMPTION.RD_PREEMPT_WR", + "PerPkg": "1", + "PublicDescription": "Counts the number of times a read in the iMC preempts another read or write. Generally reads to an open page are issued ahead of requests to closed pages. This improves the page hit rate of the system. However, high priority requests can cause pages of active requests to be closed in order to get them out. This will reduce the latency of the high-priority request at the expense of lower bandwidth and increased overall average latency.; Filter for when a read preempts a write.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.; Precharge due to bypass", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.BYP", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.; Precharge due to timer expiration", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_CLOSE", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRAM Precharge commands sent on this channel.; Counts the number of DRAM Precharge commands sent on this channel as a result of the page close counter expiring. This does not include implicit precharge commands sent in auto-precharge mode.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.; Precharges due to page miss", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRAM Precharge commands sent on this channel.; Counts the number of DRAM Precharge commands sent on this channel as a result of page misses. This does not include explicit precharge commands sent with CAS commands in Auto-Precharge mode. This does not include PRE commands sent as a result of the page close counter expiration.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.; Precharge due to read", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.; Precharge due to write", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "Read CAS issued with HIGH priority", + "Counter": "0,1,2,3", + "EventCode": "0xa0", + "EventName": "UNC_M_RD_CAS_PRIO.HIGH", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Read CAS issued with LOW priority", + "Counter": "0,1,2,3", + "EventCode": "0xa0", + "EventName": "UNC_M_RD_CAS_PRIO.LOW", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read CAS issued with MEDIUM priority", + "Counter": "0,1,2,3", + "EventCode": "0xa0", + "EventName": "UNC_M_RD_CAS_PRIO.MED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Read CAS issued with PANIC NON ISOCH priority (starved)", + "Counter": "0,1,2,3", + "EventCode": "0xa0", + "EventName": "UNC_M_RD_CAS_PRIO.PANIC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 0; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xb0", + "EventName": "UNC_M_RD_CAS_RANK0.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 0; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xb0", + "EventName": "UNC_M_RD_CAS_RANK0.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 0; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xb0", + "EventName": "UNC_M_RD_CAS_RANK0.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 0; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xb0", + "EventName": "UNC_M_RD_CAS_RANK0.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 0; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xb0", + "EventName": "UNC_M_RD_CAS_RANK0.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 0; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xb0", + "EventName": "UNC_M_RD_CAS_RANK0.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 0; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xb0", + "EventName": "UNC_M_RD_CAS_RANK0.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 0; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xb0", + "EventName": "UNC_M_RD_CAS_RANK0.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 1; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xB1", + "EventName": "UNC_M_RD_CAS_RANK1.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 1; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xB1", + "EventName": "UNC_M_RD_CAS_RANK1.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 1; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xB1", + "EventName": "UNC_M_RD_CAS_RANK1.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 1; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xB1", + "EventName": "UNC_M_RD_CAS_RANK1.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 1; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xB1", + "EventName": "UNC_M_RD_CAS_RANK1.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 1; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xB1", + "EventName": "UNC_M_RD_CAS_RANK1.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 1; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xB1", + "EventName": "UNC_M_RD_CAS_RANK1.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 1; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xB1", + "EventName": "UNC_M_RD_CAS_RANK1.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 2; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xB2", + "EventName": "UNC_M_RD_CAS_RANK2.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 2; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xB2", + "EventName": "UNC_M_RD_CAS_RANK2.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 2; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xB2", + "EventName": "UNC_M_RD_CAS_RANK2.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 2; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xB2", + "EventName": "UNC_M_RD_CAS_RANK2.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 2; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xB2", + "EventName": "UNC_M_RD_CAS_RANK2.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 2; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xB2", + "EventName": "UNC_M_RD_CAS_RANK2.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 2; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xB2", + "EventName": "UNC_M_RD_CAS_RANK2.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 2; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xB2", + "EventName": "UNC_M_RD_CAS_RANK2.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 3; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xB3", + "EventName": "UNC_M_RD_CAS_RANK3.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 3; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xB3", + "EventName": "UNC_M_RD_CAS_RANK3.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 3; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xB3", + "EventName": "UNC_M_RD_CAS_RANK3.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 3; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xB3", + "EventName": "UNC_M_RD_CAS_RANK3.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 3; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xB3", + "EventName": "UNC_M_RD_CAS_RANK3.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 3; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xB3", + "EventName": "UNC_M_RD_CAS_RANK3.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 3; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xB3", + "EventName": "UNC_M_RD_CAS_RANK3.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 3; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xB3", + "EventName": "UNC_M_RD_CAS_RANK3.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 4; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xB4", + "EventName": "UNC_M_RD_CAS_RANK4.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 4; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xB4", + "EventName": "UNC_M_RD_CAS_RANK4.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 4; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xB4", + "EventName": "UNC_M_RD_CAS_RANK4.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 4; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xB4", + "EventName": "UNC_M_RD_CAS_RANK4.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 4; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xB4", + "EventName": "UNC_M_RD_CAS_RANK4.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 4; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xB4", + "EventName": "UNC_M_RD_CAS_RANK4.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 4; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xB4", + "EventName": "UNC_M_RD_CAS_RANK4.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 4; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xB4", + "EventName": "UNC_M_RD_CAS_RANK4.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 5; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xB5", + "EventName": "UNC_M_RD_CAS_RANK5.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 5; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xB5", + "EventName": "UNC_M_RD_CAS_RANK5.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 5; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xB5", + "EventName": "UNC_M_RD_CAS_RANK5.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 5; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xB5", + "EventName": "UNC_M_RD_CAS_RANK5.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 5; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xB5", + "EventName": "UNC_M_RD_CAS_RANK5.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 5; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xB5", + "EventName": "UNC_M_RD_CAS_RANK5.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 5; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xB5", + "EventName": "UNC_M_RD_CAS_RANK5.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 5; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xB5", + "EventName": "UNC_M_RD_CAS_RANK5.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 6; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xB6", + "EventName": "UNC_M_RD_CAS_RANK6.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 6; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xB6", + "EventName": "UNC_M_RD_CAS_RANK6.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 6; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xB6", + "EventName": "UNC_M_RD_CAS_RANK6.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 6; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xB6", + "EventName": "UNC_M_RD_CAS_RANK6.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 6; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xB6", + "EventName": "UNC_M_RD_CAS_RANK6.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 6; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xB6", + "EventName": "UNC_M_RD_CAS_RANK6.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 6; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xB6", + "EventName": "UNC_M_RD_CAS_RANK6.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 6; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xB6", + "EventName": "UNC_M_RD_CAS_RANK6.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 7; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xB7", + "EventName": "UNC_M_RD_CAS_RANK7.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 7; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xB7", + "EventName": "UNC_M_RD_CAS_RANK7.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 7; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xB7", + "EventName": "UNC_M_RD_CAS_RANK7.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 7; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xB7", + "EventName": "UNC_M_RD_CAS_RANK7.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 7; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xB7", + "EventName": "UNC_M_RD_CAS_RANK7.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 7; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xB7", + "EventName": "UNC_M_RD_CAS_RANK7.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 7; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xB7", + "EventName": "UNC_M_RD_CAS_RANK7.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "RD_CAS Access to Rank 7; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xB7", + "EventName": "UNC_M_RD_CAS_RANK7.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Not Empty", + "Counter": "0,1,2,3", + "EventCode": "0x11", + "EventName": "UNC_M_RPQ_CYCLES_NE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Read Pending Queue is not empty. This can then be used to calculate the average occupancy (in conjunction with the Read Pending Queue Occupancy count). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This filter is to be used in conjunction with the occupancy filter so that one can correctly track the average occupancies for schedulable entries and scheduled requests.", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_M_RPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", + "Unit": "iMC" + }, + { + "BriefDescription": "VMSE MXB write buffer occupancy", + "Counter": "0,1,2,3", + "EventCode": "0x91", + "EventName": "UNC_M_VMSE_MXB_WR_OCCUPANCY", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "VMSE WR PUSH issued; VMSE write PUSH issued in RMM", + "Counter": "0,1,2,3", + "EventCode": "0x90", + "EventName": "UNC_M_VMSE_WR_PUSH.RMM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "VMSE WR PUSH issued; VMSE write PUSH issued in WMM", + "Counter": "0,1,2,3", + "EventCode": "0x90", + "EventName": "UNC_M_VMSE_WR_PUSH.WMM", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Transition from WMM to RMM because of low threshold; Transition from WMM to RMM because of starve counter", + "Counter": "0,1,2,3", + "EventCode": "0xc0", + "EventName": "UNC_M_WMM_TO_RMM.LOW_THRESH", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Transition from WMM to RMM because of low threshold", + "Counter": "0,1,2,3", + "EventCode": "0xc0", + "EventName": "UNC_M_WMM_TO_RMM.STARVE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Transition from WMM to RMM because of low threshold", + "Counter": "0,1,2,3", + "EventCode": "0xc0", + "EventName": "UNC_M_WMM_TO_RMM.VMSE_RETRY", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Full Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_M_WPQ_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the Write Pending Queue is full. When the WPQ is full, the HA will not be able to issue any additional read requests into the iMC. This count should be similar count in the HA which tracks the number of cycles that the HA has no WPQ credits, just somewhat smaller to account for the credit return overhead.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Not Empty", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_M_WPQ_CYCLES_NE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Write Pending Queue is not empty. This can then be used to calculate the average queue occupancy (in conjunction with the WPQ Occupancy Accumulation count). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "UNC_M_WPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the Write Pending Queue. This can then be used to calculate the average queuing latency (in conjunction with the WPQ occupancy count). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "Counter": "0,1,2,3", + "EventCode": "0x23", + "EventName": "UNC_M_WPQ_READ_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "UNC_M_WPQ_WRITE_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "Unit": "iMC" + }, + { + "BriefDescription": "Not getting the requested Major Mode", + "Counter": "0,1,2,3", + "EventCode": "0xc1", + "EventName": "UNC_M_WRONG_MM", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 0; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xb8", + "EventName": "UNC_M_WR_CAS_RANK0.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 0; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xb8", + "EventName": "UNC_M_WR_CAS_RANK0.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 0; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xb8", + "EventName": "UNC_M_WR_CAS_RANK0.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 0; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xb8", + "EventName": "UNC_M_WR_CAS_RANK0.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 0; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xb8", + "EventName": "UNC_M_WR_CAS_RANK0.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 0; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xb8", + "EventName": "UNC_M_WR_CAS_RANK0.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 0; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xb8", + "EventName": "UNC_M_WR_CAS_RANK0.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 0; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xb8", + "EventName": "UNC_M_WR_CAS_RANK0.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 1; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xB9", + "EventName": "UNC_M_WR_CAS_RANK1.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 1; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xB9", + "EventName": "UNC_M_WR_CAS_RANK1.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 1; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xB9", + "EventName": "UNC_M_WR_CAS_RANK1.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 1; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xB9", + "EventName": "UNC_M_WR_CAS_RANK1.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 1; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xB9", + "EventName": "UNC_M_WR_CAS_RANK1.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 1; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xB9", + "EventName": "UNC_M_WR_CAS_RANK1.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 1; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xB9", + "EventName": "UNC_M_WR_CAS_RANK1.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 1; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xB9", + "EventName": "UNC_M_WR_CAS_RANK1.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 2; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xBA", + "EventName": "UNC_M_WR_CAS_RANK2.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 2; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xBA", + "EventName": "UNC_M_WR_CAS_RANK2.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 2; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xBA", + "EventName": "UNC_M_WR_CAS_RANK2.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 2; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xBA", + "EventName": "UNC_M_WR_CAS_RANK2.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 2; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xBA", + "EventName": "UNC_M_WR_CAS_RANK2.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 2; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xBA", + "EventName": "UNC_M_WR_CAS_RANK2.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 2; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xBA", + "EventName": "UNC_M_WR_CAS_RANK2.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 2; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xBA", + "EventName": "UNC_M_WR_CAS_RANK2.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 3; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xBB", + "EventName": "UNC_M_WR_CAS_RANK3.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 3; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xBB", + "EventName": "UNC_M_WR_CAS_RANK3.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 3; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xBB", + "EventName": "UNC_M_WR_CAS_RANK3.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 3; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xBB", + "EventName": "UNC_M_WR_CAS_RANK3.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 3; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xBB", + "EventName": "UNC_M_WR_CAS_RANK3.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 3; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xBB", + "EventName": "UNC_M_WR_CAS_RANK3.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 3; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xBB", + "EventName": "UNC_M_WR_CAS_RANK3.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 3; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xBB", + "EventName": "UNC_M_WR_CAS_RANK3.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 4; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xBC", + "EventName": "UNC_M_WR_CAS_RANK4.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 4; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xBC", + "EventName": "UNC_M_WR_CAS_RANK4.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 4; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xBC", + "EventName": "UNC_M_WR_CAS_RANK4.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 4; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xBC", + "EventName": "UNC_M_WR_CAS_RANK4.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 4; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xBC", + "EventName": "UNC_M_WR_CAS_RANK4.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 4; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xBC", + "EventName": "UNC_M_WR_CAS_RANK4.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 4; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xBC", + "EventName": "UNC_M_WR_CAS_RANK4.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 4; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xBC", + "EventName": "UNC_M_WR_CAS_RANK4.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 5; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xBD", + "EventName": "UNC_M_WR_CAS_RANK5.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 5; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xBD", + "EventName": "UNC_M_WR_CAS_RANK5.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 5; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xBD", + "EventName": "UNC_M_WR_CAS_RANK5.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 5; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xBD", + "EventName": "UNC_M_WR_CAS_RANK5.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 5; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xBD", + "EventName": "UNC_M_WR_CAS_RANK5.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 5; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xBD", + "EventName": "UNC_M_WR_CAS_RANK5.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 5; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xBD", + "EventName": "UNC_M_WR_CAS_RANK5.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 5; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xBD", + "EventName": "UNC_M_WR_CAS_RANK5.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 6; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xBE", + "EventName": "UNC_M_WR_CAS_RANK6.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 6; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xBE", + "EventName": "UNC_M_WR_CAS_RANK6.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 6; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xBE", + "EventName": "UNC_M_WR_CAS_RANK6.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 6; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xBE", + "EventName": "UNC_M_WR_CAS_RANK6.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 6; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xBE", + "EventName": "UNC_M_WR_CAS_RANK6.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 6; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xBE", + "EventName": "UNC_M_WR_CAS_RANK6.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 6; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xBE", + "EventName": "UNC_M_WR_CAS_RANK6.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 6; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xBE", + "EventName": "UNC_M_WR_CAS_RANK6.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 7; Bank 0", + "Counter": "0,1,2,3", + "EventCode": "0xBF", + "EventName": "UNC_M_WR_CAS_RANK7.BANK0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 7; Bank 1", + "Counter": "0,1,2,3", + "EventCode": "0xBF", + "EventName": "UNC_M_WR_CAS_RANK7.BANK1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 7; Bank 2", + "Counter": "0,1,2,3", + "EventCode": "0xBF", + "EventName": "UNC_M_WR_CAS_RANK7.BANK2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 7; Bank 3", + "Counter": "0,1,2,3", + "EventCode": "0xBF", + "EventName": "UNC_M_WR_CAS_RANK7.BANK3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 7; Bank 4", + "Counter": "0,1,2,3", + "EventCode": "0xBF", + "EventName": "UNC_M_WR_CAS_RANK7.BANK4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 7; Bank 5", + "Counter": "0,1,2,3", + "EventCode": "0xBF", + "EventName": "UNC_M_WR_CAS_RANK7.BANK5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 7; Bank 6", + "Counter": "0,1,2,3", + "EventCode": "0xBF", + "EventName": "UNC_M_WR_CAS_RANK7.BANK6", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "WR_CAS Access to Rank 7; Bank 7", + "Counter": "0,1,2,3", + "EventCode": "0xBF", + "EventName": "UNC_M_WR_CAS_RANK7.BANK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-other.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-other.json new file mode 100644 index 000000000..6c7ddf642 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-other.json @@ -0,0 +1,2398 @@ +[ + { + "BriefDescription": "Address Match (Conflict) Count; Conflict Merges", + "Counter": "0,1", + "EventCode": "0x17", + "EventName": "UNC_I_ADDRESS_MATCH.MERGE_COUNT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.; When two requests to the same address from the same source are received back to back, it is possible to merge the two of them together.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Address Match (Conflict) Count; Conflict Stalls", + "Counter": "0,1", + "EventCode": "0x17", + "EventName": "UNC_I_ADDRESS_MATCH.STALL_COUNT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.; When it is not possible to merge two conflicting requests, a stall event occurs. This is bad for performance.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ack Pending Occupancy; Any Source", + "Counter": "0,1", + "EventCode": "0x14", + "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ack Pending Occupancy; Select Source", + "Counter": "0,1", + "EventCode": "0x14", + "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.; Tracks all requests from any source port.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Ownership Occupancy; Any Source", + "Counter": "0,1", + "EventCode": "0x13", + "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Ownership Occupancy; Select Source", + "Counter": "0,1", + "EventCode": "0x13", + "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Read Occupancy; Any Source", + "Counter": "0,1", + "EventCode": "0x10", + "EventName": "UNC_I_CACHE_READ_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Read Occupancy; Select Source", + "Counter": "0,1", + "EventCode": "0x10", + "EventName": "UNC_I_CACHE_READ_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Any Source", + "Counter": "0,1", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Select Source", + "Counter": "0,1", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Occupancy; Any Source", + "Counter": "0,1", + "EventCode": "0x11", + "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Occupancy; Select Source", + "Counter": "0,1", + "EventCode": "0x11", + "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Clocks in the IRP", + "Counter": "0,1", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of clocks in the IRP.", + "Unit": "IRP" + }, + { + "Counter": "0,1", + "EventCode": "0xb", + "EventName": "UNC_I_RxR_AK_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the AK Ingress is full. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Ingress Occupancy", + "Counter": "0,1", + "EventCode": "0xa", + "EventName": "UNC_I_RxR_AK_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "Counter": "0,1", + "EventCode": "0xc", + "EventName": "UNC_I_RxR_AK_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the AK Ingress in each cycles. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "Counter": "0,1", + "EventCode": "0x4", + "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - DRS", + "Counter": "0,1", + "EventCode": "0x1", + "EventName": "UNC_I_RxR_BL_DRS_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "Counter": "0,1", + "EventCode": "0x7", + "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "Counter": "0,1", + "EventCode": "0x5", + "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - NCB", + "Counter": "0,1", + "EventCode": "0x2", + "EventName": "UNC_I_RxR_BL_NCB_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "Counter": "0,1", + "EventCode": "0x8", + "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "Counter": "0,1", + "EventCode": "0x6", + "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - NCS", + "Counter": "0,1", + "EventCode": "0x3", + "EventName": "UNC_I_RxR_BL_NCS_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "Counter": "0,1", + "EventCode": "0x9", + "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "Tickle Count; Ownership Lost", + "Counter": "0,1", + "EventCode": "0x16", + "EventName": "UNC_I_TICKLES.LOST_OWNERSHIP", + "PerPkg": "1", + "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.; Tracks the number of requests that lost ownership as a result of a tickle. When a tickle comes in, if the request is not at the head of the queue in the switch, then that request as well as any requests behind it in the switch queue will lose ownership and have to re-acquire it later when they get to the head of the queue. This will therefore track the number of requests that lost ownership and not just the number of tickles.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Tickle Count; Data Returned", + "Counter": "0,1", + "EventCode": "0x16", + "EventName": "UNC_I_TICKLES.TOP_OF_QUEUE", + "PerPkg": "1", + "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.; Tracks the number of cases when a tickle was received but the requests was at the head of the queue in the switch. In this case, data is returned rather than releasing ownership.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count: Read Prefetches", + "Counter": "0,1", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.PD_PREFETCHES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Read Prefetches", + "Counter": "0,1", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.RD_PREFETCHES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Reads", + "Counter": "0,1", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.READS", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Writes", + "Counter": "0,1", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD Egress Credit Stalls", + "Counter": "0,1", + "EventCode": "0x18", + "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "Counter": "0,1", + "EventCode": "0x19", + "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "Counter": "0,1", + "EventCode": "0xe", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "Counter": "0,1", + "EventCode": "0xf", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "Counter": "0,1", + "EventCode": "0xd", + "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ordering Stalls", + "Counter": "0,1", + "EventCode": "0x1a", + "EventName": "UNC_I_WRITE_ORDERING_STALL_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are pending write ACK's in the switch but the switch->IRP pipeline is not utilized.", + "Unit": "IRP" + }, + { + "BriefDescription": "Number of uclks in domain", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_R2_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the R2PCIe uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the R2PCIe is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; DRS", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; NCB", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; NCS", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Failed to Acquire a Credit; DRS", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_R2_IIO_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; DRS", + "Counter": "0,1", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; NCB", + "Counter": "0,1", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; NCS", + "Counter": "0,1", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xCC", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xCC", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xCC", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Even on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd on VRing 0", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Even on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd on VRing 1", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Any", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_R2_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters any polarity", + "UMask": "0xFF", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Counterclockwise", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_R2_RING_IV_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Counterclockwise polarity", + "UMask": "0xCC", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Clockwise", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_R2_RING_IV_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Clockwise polarity", + "UMask": "0x33", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced", + "EventCode": "0x12", + "EventName": "UNC_R2_RxR_AK_BOUNCES", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced; Counterclockwise", + "EventCode": "0x12", + "EventName": "UNC_R2_RxR_AK_BOUNCES.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced; Clockwise", + "EventCode": "0x12", + "EventName": "UNC_R2_RxR_AK_BOUNCES.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCB", + "Counter": "0,1", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCS", + "Counter": "0,1", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Allocations; NCB", + "Counter": "0,1", + "EventCode": "0x11", + "EventName": "UNC_R2_RxR_INSERTS.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Allocations; NCS", + "Counter": "0,1", + "EventCode": "0x11", + "EventName": "UNC_R2_RxR_INSERTS.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; DRS", + "EventCode": "0x13", + "EventName": "UNC_R2_RxR_OCCUPANCY.DRS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given R2PCIe Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the R2PCIe Ingress Not Empty event to calculate average occupancy or the R2PCIe Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; AD", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AD Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; AK", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AK Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; BL", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; BL Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; AD", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AD Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; AK", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AK Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; BL", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; BL Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; AD CCW", + "Counter": "0,1", + "EventCode": "0x28", + "EventName": "UNC_R2_TxR_NACK_CCW.AD", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; AK CCW", + "Counter": "0,1", + "EventCode": "0x28", + "EventName": "UNC_R2_TxR_NACK_CCW.AK", + "PerPkg": "1", + "PublicDescription": "AK CounterClockwise Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; BL CCW", + "Counter": "0,1", + "EventCode": "0x28", + "EventName": "UNC_R2_TxR_NACK_CCW.BL", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CW NACK; AD CW", + "Counter": "0,1", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.AD", + "PerPkg": "1", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CW NACK; AK CW", + "Counter": "0,1", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.AK", + "PerPkg": "1", + "PublicDescription": "AK Clockwise Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CW NACK; BL CW", + "Counter": "0,1", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.BL", + "PerPkg": "1", + "PublicDescription": "BL Clockwise Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Number of uclks in domain", + "Counter": "0,1,2", + "EventCode": "0x1", + "EventName": "UNC_R3_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the QPI uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the QPI Agent is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO10", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 10", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO11", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 11", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO12", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 12", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO13", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 13", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO14", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 14&16", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO8", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 8", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO9", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 9", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO0", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 0", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO1", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO2", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 2", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO3", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 3", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO4", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 4", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO5", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 5", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO6", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 6", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO7", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 7", + "UMask": "0x80", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA0", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA0", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA1", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCB Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCS", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCS Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "Counter": "0,1", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "Counter": "0,1", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise", + "Counter": "0,1,2", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xCC", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Even on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Odd on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise", + "Counter": "0,1,2", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Even on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Odd on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise", + "Counter": "0,1,2", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xCC", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Even on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Odd on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise", + "Counter": "0,1,2", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Even on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Odd on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise", + "Counter": "0,1,2", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xCC", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Even on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Odd on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise", + "Counter": "0,1,2", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Even on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Odd on VRing 0", + "Counter": "0,1,2", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R2 IV Ring in Use; Any", + "Counter": "0,1,2", + "EventCode": "0xA", + "EventName": "UNC_R3_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters any polarity", + "UMask": "0xFF", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R2 IV Ring in Use; Counterclockwise", + "Counter": "0,1,2", + "EventCode": "0xa", + "EventName": "UNC_R3_RING_IV_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Counterclockwise polarity", + "UMask": "0xCC", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R2 IV Ring in Use; Clockwise", + "Counter": "0,1,2", + "EventCode": "0xa", + "EventName": "UNC_R3_RING_IV_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Clockwise polarity", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "AD Ingress Bypassed", + "Counter": "0,1", + "EventCode": "0x12", + "EventName": "UNC_R3_RxR_AD_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the AD Ingress was bypassed and an incoming transaction was bypassed directly across the BGF and into the qfclk domain.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Bypassed", + "Counter": "0,1", + "EventCode": "0x12", + "EventName": "UNC_R3_RxR_BYPASSED.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the Ingress was bypassed and an incoming transaction was bypassed directly across the BGF and into the qfclk domain.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; HOM", + "Counter": "0,1", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NDR", + "Counter": "0,1", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; SNP", + "Counter": "0,1", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; DRS", + "Counter": "0,1", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; HOM", + "Counter": "0,1", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCB", + "Counter": "0,1", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCS", + "Counter": "0,1", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NDR", + "Counter": "0,1", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; SNP", + "Counter": "0,1", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; DRS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.DRS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; HOM", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.HOM", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NCB", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NCS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NDR", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NDR", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; SNP", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.SNP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AK CCW", + "Counter": "0,1", + "EventCode": "0x28", + "EventName": "UNC_R3_TxR_NACK_CCW.AD", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; BL CW", + "Counter": "0,1", + "EventCode": "0x28", + "EventName": "UNC_R3_TxR_NACK_CCW.AK", + "PerPkg": "1", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; BL CCW", + "Counter": "0,1", + "EventCode": "0x28", + "EventName": "UNC_R3_TxR_NACK_CCW.BL", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AD CW", + "Counter": "0,1", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK_CW.AD", + "PerPkg": "1", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AD CCW", + "Counter": "0,1", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK_CW.AK", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AK CW", + "Counter": "0,1", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK_CW.BL", + "PerPkg": "1", + "PublicDescription": "BL Clockwise Egress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; DRS Message Class", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; HOM Message Class", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCB Message Class", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCS Message Class", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NDR Message Class", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; SNP Message Class", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; DRS Message Class", + "Counter": "0,1", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; HOM Message Class", + "Counter": "0,1", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCB Message Class", + "Counter": "0,1", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCS Message Class", + "Counter": "0,1", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NDR Message Class", + "Counter": "0,1", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; SNP Message Class", + "Counter": "0,1", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; DRS Message Class", + "Counter": "0,1", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; HOM Message Class", + "Counter": "0,1", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCB Message Class", + "Counter": "0,1", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCS Message Class", + "Counter": "0,1", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NDR Message Class", + "Counter": "0,1", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; SNP Message Class", + "Counter": "0,1", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; DRS Message Class", + "Counter": "0,1", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; HOM Message Class", + "Counter": "0,1", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NCB Message Class", + "Counter": "0,1", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NCS Message Class", + "Counter": "0,1", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NDR Message Class", + "Counter": "0,1", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; SNP Message Class", + "Counter": "0,1", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA credit Acquisitions", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED", + "PerPkg": "1", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA credit Acquisitions; HOM Message Class", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", + "PerPkg": "1", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA credit Acquisitions; HOM Message Class", + "Counter": "0,1", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", + "PerPkg": "1", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; DRS Message Class", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; HOM Message Class", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCB Message Class", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCS Message Class", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Standard (NCS).", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NDR Message Class", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; SNP Message Class", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Cycles with no VNA credits available", + "Counter": "0,1", + "EventCode": "0x31", + "EventName": "UNC_R3_VNA_CREDIT_CYCLES_OUT", + "PerPkg": "1", + "PublicDescription": "Number of QPI uclk cycles when the transmitted has no VNA credits available and therefore cannot send any requests on this channel. Note that this does not mean that no flits can be transmitted, as those holding VN0 credits will still (potentially) be able to transmit. Generally it is the goal of the uncore that VNA credits should not run out, as this can substantially throttle back useful QPI bandwidth.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Cycles with 1 or more VNA credits in use", + "Counter": "0,1", + "EventCode": "0x32", + "EventName": "UNC_R3_VNA_CREDIT_CYCLES_USED", + "PerPkg": "1", + "PublicDescription": "Number of QPI uclk cycles with one or more VNA credits in use. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average number of used VNA credits.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VLW Received", + "Counter": "0,1", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "Counter": "0,1", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "Counter": "0,1", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "Counter": "0,1", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "Counter": "0,1", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "Counter": "0,1", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.DISABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "Counter": "0,1", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.ENABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "Counter": "0,1", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "Counter": "0,1", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "IDI Lock/SplitLock Cycles", + "Counter": "0,1", + "EventCode": "0x44", + "EventName": "UNC_U_LOCK_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of times an IDI Lock/SplitLock sequence was started", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", + "Counter": "0,1", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "PHOLD cycles. Filter from source CoreID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "Counter": "0,1", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", + "PerPkg": "1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", + "Counter": "0,1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.CMC", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Livelock", + "Counter": "0,1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; LTError", + "Counter": "0,1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LTERROR", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Monitor T0", + "Counter": "0,1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Monitor T1", + "Counter": "0,1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Other", + "Counter": "0,1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.OTHER", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; PREQ, PSMI, P2U, Thermal, PCUSMI, PMI", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Trap", + "Counter": "0,1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.TRAP", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", + "Counter": "0,1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.UMC", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x20", + "Unit": "UBOX" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json new file mode 100644 index 000000000..74c87217d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json @@ -0,0 +1,687 @@ +[ + { + "BriefDescription": "pclk Cycles", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "The PCU runs off a fixed 800 MHz clock. This event counts the number of pclk cycles measured while the counter was enabled. The pclk, like the Memory Controller's dclk, counts at a constant rate making it a good measure of actual wall time.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 0 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x70", + "EventName": "UNC_P_CORE0_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 10 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x7a", + "EventName": "UNC_P_CORE10_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 11 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x7b", + "EventName": "UNC_P_CORE11_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 12 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x7c", + "EventName": "UNC_P_CORE12_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 13 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x7d", + "EventName": "UNC_P_CORE13_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 14 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x7e", + "EventName": "UNC_P_CORE14_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 1 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x71", + "EventName": "UNC_P_CORE1_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 2 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x72", + "EventName": "UNC_P_CORE2_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 3 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x73", + "EventName": "UNC_P_CORE3_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 4 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_CORE4_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 5 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x75", + "EventName": "UNC_P_CORE5_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 6 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x76", + "EventName": "UNC_P_CORE6_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 7 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x77", + "EventName": "UNC_P_CORE7_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 8 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x78", + "EventName": "UNC_P_CORE8_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 9 C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x79", + "EventName": "UNC_P_CORE9_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions. There is one event per core.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 0", + "Counter": "0,1,2,3", + "EventCode": "0x17", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE0", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 1", + "Counter": "0,1,2,3", + "EventCode": "0x18", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE1", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 10", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE10", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 11", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE11", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 12", + "Counter": "0,1,2,3", + "EventCode": "0x23", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE12", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 13", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE13", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 14", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE14", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 2", + "Counter": "0,1,2,3", + "EventCode": "0x19", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE2", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 3", + "Counter": "0,1,2,3", + "EventCode": "0x1a", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE3", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 4", + "Counter": "0,1,2,3", + "EventCode": "0x1b", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE4", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 5", + "Counter": "0,1,2,3", + "EventCode": "0x1c", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE5", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 6", + "Counter": "0,1,2,3", + "EventCode": "0x1d", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE6", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 7", + "Counter": "0,1,2,3", + "EventCode": "0x1e", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE7", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 8", + "Counter": "0,1,2,3", + "EventCode": "0x1f", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE8", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Deep C State Rejection - Core 9", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "UNC_P_DELAYED_C_STATE_ABORT_CORE9", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Number of times that a deep C state was requested, but the delayed C state algorithm rejected the deep sleep state. In other words, a wake event occurred before the timer expired that causes a transition into the deeper C state.", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 0 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x1e", + "EventName": "UNC_P_DEMOTIONS_CORE0", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 1 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x1f", + "EventName": "UNC_P_DEMOTIONS_CORE1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 10 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x42", + "EventName": "UNC_P_DEMOTIONS_CORE10", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 11 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_P_DEMOTIONS_CORE11", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 12 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x44", + "EventName": "UNC_P_DEMOTIONS_CORE12", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 13 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x45", + "EventName": "UNC_P_DEMOTIONS_CORE13", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 14 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x46", + "EventName": "UNC_P_DEMOTIONS_CORE14", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 2 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x20", + "EventName": "UNC_P_DEMOTIONS_CORE2", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 3 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_P_DEMOTIONS_CORE3", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 4 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x22", + "EventName": "UNC_P_DEMOTIONS_CORE4", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 5 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x23", + "EventName": "UNC_P_DEMOTIONS_CORE5", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 6 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x24", + "EventName": "UNC_P_DEMOTIONS_CORE6", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 7 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x25", + "EventName": "UNC_P_DEMOTIONS_CORE7", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 8 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x40", + "EventName": "UNC_P_DEMOTIONS_CORE8", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Core 9 C State Demotions", + "Counter": "0,1,2,3", + "EventCode": "0x41", + "EventName": "UNC_P_DEMOTIONS_CORE9", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a configurable cores had a C-state demotion", + "Unit": "PCU" + }, + { + "BriefDescription": "Frequency Residency", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. One can use all four counters with this event, so it is possible to track up to 4 configurable bands. One can use edge detect in conjunction with this event to track the number of times that we transitioned into a frequency greater than or equal to the configurable frequency. One can also use inversion to track cycles when we were less than the configured frequency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Frequency Residency", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. One can use all four counters with this event, so it is possible to track up to 4 configurable bands. One can use edge detect in conjunction with this event to track the number of times that we transitioned into a frequency greater than or equal to the configurable frequency. One can also use inversion to track cycles when we were less than the configured frequency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Frequency Residency", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. One can use all four counters with this event, so it is possible to track up to 4 configurable bands. One can use edge detect in conjunction with this event to track the number of times that we transitioned into a frequency greater than or equal to the configurable frequency. One can also use inversion to track cycles when we were less than the configured frequency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Frequency Residency", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. One can use all four counters with this event, so it is possible to track up to 4 configurable bands. One can use edge detect in conjunction with this event to track the number of times that we transitioned into a frequency greater than or equal to the configurable frequency. One can also use inversion to track cycles when we were less than the configured frequency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Current Strongest Upper Limit Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when current is the upper limit on frequency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Thermal Strongest Upper Limit Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when thermal conditions are the upper limit on frequency. This is related to the THERMAL_THROTTLE CYCLES_ABOVE_TEMP event, which always counts cycles when we are above the thermal temperature. This event (STRONGEST_UPPER_LIMIT) is sampled at the output of the algorithm that determines the actual frequency, while THERMAL_THROTTLE looks at the input.", + "Unit": "PCU" + }, + { + "BriefDescription": "OS Strongest Upper Limit Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the OS is the upper limit on frequency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Power Strongest Upper Limit Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when power is the upper limit on frequency.", + "Unit": "PCU" + }, + { + "BriefDescription": "IO P Limit Strongest Lower Limit Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x61", + "EventName": "UNC_P_FREQ_MIN_IO_P_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when IO P Limit is preventing us from dropping the frequency lower. This algorithm monitors the needs to the IO subsystem on both local and remote sockets and will maintain a frequency high enough to maintain good IO BW. This is necessary for when all the IA cores on a socket are idle but a user still would like to maintain high IO Bandwidth.", + "Unit": "PCU" + }, + { + "BriefDescription": "Perf P Limit Strongest Lower Limit Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x62", + "EventName": "UNC_P_FREQ_MIN_PERF_P_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when Perf P Limit is preventing us from dropping the frequency lower. Perf P Limit is an algorithm that takes input from remote sockets when determining if a socket should drop it's frequency down. This is largely to minimize increases in snoop and remote read latencies.", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system.", + "Unit": "PCU" + }, + { + "BriefDescription": "Memory Phase Shedding Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x2f", + "EventName": "UNC_P_MEMORY_PHASE_SHEDDING_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the PCU has triggered memory phase shedding. This is a mode that can be run in the iMC physicals that saves power at the expense of additional latency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Exit Latency", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "UNC_P_PKG_C_EXIT_LATENCY", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the package is transitioning from package C2 to C3.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Exit Latency", + "Counter": "0,1,2,3", + "EventCode": "0x26", + "EventName": "UNC_P_PKG_C_EXIT_LATENCY_SEL", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the package is transitioning from package C2 to C3.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C0", + "Counter": "0,1,2,3", + "EventCode": "0x2a", + "EventName": "UNC_P_PKG_C_STATE_RESIDENCY_C0_CYCLES", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the package is in C0", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C2", + "Counter": "0,1,2,3", + "EventCode": "0x2b", + "EventName": "UNC_P_PKG_C_STATE_RESIDENCY_C2_CYCLES", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the package is in C2", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C3", + "Counter": "0,1,2,3", + "EventCode": "0x2c", + "EventName": "UNC_P_PKG_C_STATE_RESIDENCY_C3_CYCLES", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the package is in C3", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C6", + "Counter": "0,1,2,3", + "EventCode": "0x2d", + "EventName": "UNC_P_PKG_C_STATE_RESIDENCY_C6_CYCLES", + "ExtSel": "1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the package is in C6", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C-State; C0 and C1", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "PerPkg": "1", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C-State; C3", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "PerPkg": "1", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C-State; C6 and C7", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "PerPkg": "1", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "External Prochot", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip.", + "Unit": "PCU" + }, + { + "BriefDescription": "Internal Prochot", + "Counter": "0,1,2,3", + "EventCode": "0x9", + "EventName": "UNC_P_PROCHOT_INTERNAL_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that we are in Internal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", + "Unit": "PCU" + }, + { + "BriefDescription": "Total Core C State Transition Cycles", + "Counter": "0,1,2,3", + "EventCode": "0x63", + "EventName": "UNC_P_TOTAL_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of cycles spent performing core C state transitions across all cores.", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles Changing Voltage", + "Counter": "0,1,2,3", + "EventCode": "0x3", + "EventName": "UNC_P_VOLT_TRANS_CYCLES_CHANGE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the system is changing voltage. There is no filtering supported with this event. One can use it as a simple event, or use it conjunction with the occupancy events to monitor the number of cores or threads that were impacted by the transition. This event is calculated by or'ing together the increasing and decreasing events.", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles Decreasing Voltage", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_P_VOLT_TRANS_CYCLES_DECREASE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the system is decreasing voltage. There is no filtering supported with this event. One can use it as a simple event, or use it conjunction with the occupancy events to monitor the number of cores or threads that were impacted by the transition.", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles Increasing Voltage", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_P_VOLT_TRANS_CYCLES_INCREASE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the system is increasing voltage. There is no filtering supported with this event. One can use it as a simple event, or use it conjunction with the occupancy events to monitor the number of cores or threads that were impacted by the transition.", + "Unit": "PCU" + }, + { + "BriefDescription": "VR Hot", + "Counter": "0,1,2,3", + "EventCode": "0x32", + "EventName": "UNC_P_VR_HOT_CYCLES", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/virtual-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/virtual-memory.json new file mode 100644 index 000000000..6624d02ad --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/virtual-memory.json @@ -0,0 +1,198 @@ +[ + { + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.DEMAND_LD_WALK_COMPLETED", + "SampleAfterValue": "100003", + "UMask": "0x82" + }, + { + "BriefDescription": "Demand load cycles page miss handler (PMH) is busy with this walk.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.DEMAND_LD_WALK_DURATION", + "SampleAfterValue": "2000003", + "UMask": "0x84" + }, + { + "BriefDescription": "Page walk for a large page completed for Demand load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.LARGE_PAGE_WALK_COMPLETED", + "SampleAfterValue": "100003", + "UMask": "0x88" + }, + { + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes an page walk of any page size.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Misses in all TLB levels that cause a page walk of any page size from demand loads.", + "SampleAfterValue": "100003", + "UMask": "0x81" + }, + { + "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5F", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts load operations that missed 1st level DTLB but hit the 2nd level.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Demand load Miss in all translation lookaside buffer (TLB) levels causes a page walk that completes of any page size.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Misses in all TLB levels that caused page walk completed of any size by demand loads.", + "SampleAfterValue": "100003", + "UMask": "0x82" + }, + { + "BriefDescription": "Demand load cycles page miss handler (PMH) is busy with this walk.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_DURATION", + "PublicDescription": "Cycle PMH is busy with a walk due to demand loads.", + "SampleAfterValue": "2000003", + "UMask": "0x84" + }, + { + "BriefDescription": "Store misses in all DTLB levels that cause page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Miss in all TLB levels causes a page walk of any page size (4K/2M/4M/1G).", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Store misses in all DTLB levels that cause completed page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Miss in all TLB levels causes a page walk that completes of any page size (4K/2M/4M/1G).", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when PMH is busy with page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_DURATION", + "PublicDescription": "Cycles PMH is busy with this walk.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycle count for an Extended Page table walk. The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4F", + "EventName": "EPT.WALK_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAE", + "EventName": "ITLB.ITLB_FLUSH", + "PublicDescription": "Counts the number of ITLB flushes, includes 4k/2M/4M pages.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Completed page walks in ITLB due to STLB load misses for large pages", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.LARGE_PAGE_WALK_COMPLETED", + "PublicDescription": "Completed page walks in ITLB due to STLB load misses for large pages.", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Misses at all ITLB levels that cause page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Misses in all ITLB levels that cause page walks.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", + "PublicDescription": "Number of cache load STLB hits. No page walk.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Misses in all ITLB levels that cause completed page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Misses in all ITLB levels that cause completed page walks.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles when PMH is busy with page walks", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_DURATION", + "PublicDescription": "Cycle PMH is busy with a walk.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "DTLB flush attempts of the thread-specific entries", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "PublicDescription": "DTLB flush attempts of the thread-specific entries.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "STLB flush attempts", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.STLB_ANY", + "PublicDescription": "Count number of STLB flush attempts.", + "SampleAfterValue": "100007", + "UMask": "0x20" + } +] |