Update events from v1.01 to v1.09.
Add TMA metrics 5.01.
Bring in the event updates v1.09:
https://github.com/intel/perfmon/commit/cbc3b0dc19e8fc52c9604f1da301648ed69f012b
https://github.com/intel/perfmon/commit/28f4b24f9152a0ee1fb3435535628384ad881c22
https://github.com/intel/perfmon/commit/172900e962fdd34ddb80879f4f91add5f773ca29
https://github.com/intel/perfmon/commit/dab0308f7a27d2c644e08d63436b790a207fb22e
The TMA 5.01 addition is from (with subsequent fixes):
https://github.com/intel/perfmon/commit/1d72913b2d938781fb28f3cc3507aaec5c22d782
Co-authored-by: Caleb Biggers <caleb.biggers@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
---
.../pmu-events/arch/x86/lunarlake/cache.json | 1322 ++++-
.../arch/x86/lunarlake/floating-point.json | 484 ++
.../arch/x86/lunarlake/frontend.json | 654 ++-
.../arch/x86/lunarlake/lnl-metrics.json | 4611 +++++++++++++++++
.../pmu-events/arch/x86/lunarlake/memory.json | 262 +-
.../arch/x86/lunarlake/metricgroups.json | 150 +
.../pmu-events/arch/x86/lunarlake/other.json | 496 +-
.../arch/x86/lunarlake/pipeline.json | 2104 +++++++-
.../arch/x86/lunarlake/uncore-memory.json | 18 +
.../arch/x86/lunarlake/virtual-memory.json | 428 ++
tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
11 files changed, 10218 insertions(+), 313 deletions(-)
create mode 100644 tools/perf/pmu-events/arch/x86/lunarlake/floating-point.json
create mode 100644 tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json
create mode 100644 tools/perf/pmu-events/arch/x86/lunarlake/metricgroups.json
create mode 100644 tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
index 759714618e08..9bad6a354b2b 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
@@ -1,4 +1,255 @@
[
+ {
+ "BriefDescription": "Counts the number of request that were not accepted into the L2Q because the L2Q is FULL.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x31",
+ "EventName": "CORE_REJECT_L2Q.ANY",
+ "PublicDescription": "Counts the number of (demand and L1 prefetchers) core requests rejected by the L2Q due to a full or nearly full w condition which likely indicates back pressure from L2Q. It also counts requests that would have gone directly to the XQ, but are rejected due to a full or nearly full condition, indicating back pressure from the IDI link. The L2Q may also reject transactions from a core to insure fairness between cores, or to delay a cores dirty eviction when the address conflicts incoming external snoops. (Note that L2 prefetcher requests that are dropped are not counted by this event.)",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x51",
+ "EventName": "DL1.DIRTY_EVICTION",
+ "PublicDescription": "Counts the number of L1D cacheline (dirty) evictions caused by load misses, stores, and prefetches. Does not count evictions or dirty writebacks caused by snoops. Does not count a replacement unless a (dirty) line was written back.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cache lines replaced in L0 data cache.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x51",
+ "EventName": "L1D.L0_REPLACEMENT",
+ "PublicDescription": "Counts L0 data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cachelines replaced into the L0 and L1 d-cache. Successful replacements only (not blocked) and exclude WB-miss case",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x51",
+ "EventName": "L1D.REPLACEMENT",
+ "PublicDescription": "Counts cachelines replaced into the L0 and L1 d-cache.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x5",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x49",
+ "EventName": "L1D_MISS.FB_FULL",
+ "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x49",
+ "EventName": "L1D_MISS.L2_STALLS",
+ "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of demand requests that missed L1D cache",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x49",
+ "EventName": "L1D_MISS.LOAD",
+ "PublicDescription": "Count occurrences (rising-edge) of DCACHE_PENDING sub-event0. Impl. sends per-port binary inc-bit the occupancy increases* (at FB alloc or promotion).",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of L1D misses that are outstanding",
+ "Counter": "2",
+ "EventCode": "0x48",
+ "EventName": "L1D_PENDING.LOAD",
+ "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles with L1D load Misses outstanding.",
+ "Counter": "2",
+ "CounterMask": "1",
+ "EventCode": "0x48",
+ "EventName": "L1D_PENDING.LOAD_CYCLES",
+ "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L2 cache lines filling L2",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x25",
+ "EventName": "L2_LINES_IN.ALL",
+ "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1f",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Exclusive state",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x25",
+ "EventName": "L2_LINES_IN.E",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Forward state",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x25",
+ "EventName": "L2_LINES_IN.F",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Invalid state",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x25",
+ "EventName": "L2_LINES_IN.I",
+ "PublicDescription": "Counts the number of cache lines filled into the L2 cache that are in Invalid state, does not count lines that go Invalid due to an eviction",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Modified state",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x25",
+ "EventName": "L2_LINES_IN.M",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cache lines filled into the L2 cache that are in Shared state",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x25",
+ "EventName": "L2_LINES_IN.S",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x26",
+ "EventName": "L2_LINES_OUT.NON_SILENT",
+ "PublicDescription": "Counts the number of L2 cache lines that are evicted due to an L2 cache fill. Increments on the core that brought the line in originally.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x26",
+ "EventName": "L2_LINES_OUT.NON_SILENT",
+ "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
+ "SampleAfterValue": "200003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x26",
+ "EventName": "L2_LINES_OUT.SILENT",
+ "PublicDescription": "Counts the number of L2 cache lines that are silently dropped due to an L2 cache fill. Increments on the core that brought the line in originally.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x26",
+ "EventName": "L2_LINES_OUT.SILENT",
+ "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache. These lines are typically in Shared or Exclusive state. A non-threaded event.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 cache lines that have been L2 hardware prefetched but not used by demand accesses",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x26",
+ "EventName": "L2_LINES_OUT.USELESS_HWPF",
+ "PublicDescription": "Counts the number of L2 cache lines that have been L2 hardware prefetched but not used by demand accesses. Increments on the core that brought the line in originally.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x26",
+ "EventName": "L2_LINES_OUT.USELESS_HWPF",
+ "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
+ "SampleAfterValue": "200003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 prefetches initiated by either the L2 Stream or AMP that were throttled due to Dynamic Prefetch Throttling. The throttle requestor/source could be from the uncore/SOC or the Dead Block Predictor. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x28",
+ "EventName": "L2_PREFETCHES_THROTTLED.DPT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 prefetches initiated by the L2 Stream that were throttled due to Demand Throttle Prefetcher. DTP Global Triggered with no Local Override. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x28",
+ "EventName": "L2_PREFETCHES_THROTTLED.DTP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 prefetches initiated by the L2 Stream and not throttled by DTP due to local override. These prefetches may still be throttled due to another throttler mechanism besides DTP. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x28",
+ "EventName": "L2_PREFETCHES_THROTTLED.DTP_OVERRIDE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 prefetches initiated by either the L2 Stream or AMP that were throttled due to exceeding the XQ threshold set by either XQ_THRESOLD_DTP or XQ_THRESHOLD. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x28",
+ "EventName": "L2_PREFETCHES_THROTTLED.XQ_THRESH",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of demand and prefetch transactions that the External Queue (XQ) rejects due to a full or near full condition.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x30",
+ "EventName": "L2_REJECT_XQ.ANY",
+ "PublicDescription": "Counts the number of demand and prefetch transactions that the External Queue (XQ) rejects due to a full or near full condition which likely indicates back pressure from the IDI link. The XQ may reject transactions from the L2Q (non-cacheable requests), BBL (L2 misses) and WOB (L2 write-back victims).",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of L2 Cache Accesses Counts the total number of L2 Cache Accesses - sum of hits, misses, rejects front door requests for CRd/DRd/RFO/ItoM/L2 Prefetches only, per core event",
"Counter": "0,1,2,3,4,5,6,7",
@@ -9,69 +260,672 @@
"UMask": "0x7",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES, L2_RQSTS.ANY]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.ALL",
+ "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES, L2_RQSTS.ANY]",
+ "SampleAfterValue": "200003",
+ "UMask": "0xff",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 Cache Accesses that resulted in a Hit from a front door request only (does not include rejects or recycles), per core event",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.HIT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of total L2 Cache Accesses that resulted in a Miss from a front door request only (does not include rejects or recycles), per core event",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.MISS",
+ "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
+ "SampleAfterValue": "200003",
+ "UMask": "0x3f",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of L2 Cache Accesses that miss the L2 and get BBL reject short and long rejects (includes those counted in L2_reject_XQ.any), per core event",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x24",
+ "EventName": "L2_REQUEST.REJECTS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Demand Data Read access L2 cache",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x24",
+ "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+ "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
+ "SampleAfterValue": "200003",
+ "UMask": "0xe1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES, L2_REQUEST.ALL]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x24",
+ "EventName": "L2_RQSTS.ANY",
+ "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES, L2_REQUEST.ALL]",
+ "SampleAfterValue": "200003",
+ "UMask": "0xff",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L2 cache misses when fetching instructions",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x24",
+ "EventName": "L2_RQSTS.CODE_RD_MISS",
+ "PublicDescription": "Counts L2 cache misses when fetching instructions.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x24",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Demand Data Read requests that hit L2 cache",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x24",
+ "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+ "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x41",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Demand Data Read miss L2 cache",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x24",
+ "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
+ "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x21",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_REQUEST.MISS]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x24",
+ "EventName": "L2_RQSTS.MISS",
+ "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
+ "SampleAfterValue": "200003",
+ "UMask": "0x3f",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "All accesses to L2 cache [This event is alias to L2_REQUEST.ALL,L2_RQSTS.ANY]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x24",
+ "EventName": "L2_RQSTS.REFERENCES",
+ "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL,L2_RQSTS.ANY]",
+ "SampleAfterValue": "200003",
+ "UMask": "0xff",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "RFO requests that miss L2 cache",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x24",
+ "EventName": "L2_RQSTS.RFO_MISS",
+ "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x22",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when L1D is locked",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x42",
+ "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION",
+ "PublicDescription": "This event counts the number of cycles when the L1D is locked.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x2e",
"EventName": "LONGEST_LAT_CACHE.MISS",
- "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
+ "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
"SampleAfterValue": "200003",
"UMask": "0x41",
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0x2e",
- "EventName": "LONGEST_LAT_CACHE.MISS",
- "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
- "SampleAfterValue": "100003",
- "UMask": "0x41",
- "Unit": "cpu_core"
+ "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x2e",
+ "EventName": "LONGEST_LAT_CACHE.MISS",
+ "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x41",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x2e",
+ "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+ "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x4f",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x2e",
+ "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+ "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4f",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x35",
+ "EventName": "MEM_BOUND_STALLS_IFETCH.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7f",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which hit in the L2 cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x35",
+ "EventName": "MEM_BOUND_STALLS_IFETCH.L2_HIT",
+ "PublicDescription": "Counts the number of cycles the core is stalled due to an instruction cache or Translation Lookaside Buffer (TLB) miss which hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the core is stalled due to an instruction cache or TLB miss which missed in the L2 cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x35",
+ "EventName": "MEM_BOUND_STALLS_IFETCH.L2_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7e",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to an L1 demand load miss.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x34",
+ "EventName": "MEM_BOUND_STALLS_LOAD.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7f",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which hit in the L2 cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x34",
+ "EventName": "MEM_BOUND_STALLS_LOAD.L2_HIT",
+ "PublicDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load which missed in the L2 cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x34",
+ "EventName": "MEM_BOUND_STALLS_LOAD.L2_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7e",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of unhalted cycles when the core is stalled due to a demand load miss which missed all the local caches.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x34",
+ "EventName": "MEM_BOUND_STALLS_LOAD.LLC_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x78",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of unhalted cycles when the core is stalled to a store buffer full condition",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x34",
+ "EventName": "MEM_BOUND_STALLS_LOAD.SBFULL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x80",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts all retired load instructions.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.ALL_LOADS",
+ "PublicDescription": "Counts Instructions with at least one architecturally visible load retired.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x81",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired store instructions.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.ALL_STORES",
+ "PublicDescription": "Counts all retired store instructions.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x82",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired software prefetch instructions.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.ALL_SWPF",
+ "PublicDescription": "Counts all retired software prefetch instructions.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x84",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "All retired memory instructions.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.ANY",
+ "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x87",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions with locked access.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.LOCK_LOADS",
+ "PublicDescription": "Counts retired load instructions with locked access.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x21",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions that split across a cacheline boundary.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
+ "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x41",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired store instructions that split across a cacheline boundary.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.SPLIT_STORES",
+ "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x42",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions that hit the STLB.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
+ "PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
+ "SampleAfterValue": "100003",
+ "UMask": "0x9",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired store instructions that hit the STLB.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.STLB_HIT_STORES",
+ "PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
+ "SampleAfterValue": "100003",
+ "UMask": "0xa",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions that miss the STLB.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
+ "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
+ "SampleAfterValue": "100003",
+ "UMask": "0x11",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired store instructions that miss the STLB.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
+ "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
+ "SampleAfterValue": "100003",
+ "UMask": "0x12",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd2",
+ "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
+ "PublicDescription": "Counts retired load instructions whose data sources were a cross-core Snoop hits and forwards data from an in on-package core cache (induced by NI$)",
+ "SampleAfterValue": "20011",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd2",
+ "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM",
+ "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3, Hit-with-FWD is normally excluded.",
+ "SampleAfterValue": "20011",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd2",
+ "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
+ "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
+ "SampleAfterValue": "20011",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd2",
+ "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD",
+ "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
+ "SampleAfterValue": "20011",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions which data source is memory side cache.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd3",
+ "EventName": "MEM_LOAD_L3_MISS_RETIRED.MEMSIDE_CACHE",
+ "SampleAfterValue": "100007",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd4",
+ "EventName": "MEM_LOAD_MISC_RETIRED.UC",
+ "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
+ "SampleAfterValue": "100007",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_RETIRED.FB_HIT",
+ "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x40",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions with L1 cache hits as data sources",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_RETIRED.L1_HIT",
+ "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts retired load instructions with at least one uop that hit in the Level 1 of the L1 data cache.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_RETIRED.L1_HIT_L1",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions missed L1 cache as data sources",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_RETIRED.L1_MISS",
+ "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions with L2 cache hits as data sources",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_RETIRED.L2_HIT",
+ "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions missed L2 cache as data sources",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_RETIRED.L2_MISS",
+ "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
+ "SampleAfterValue": "100021",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions with L3 cache hits as data sources",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_RETIRED.L3_HIT",
+ "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
+ "SampleAfterValue": "100021",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired load instructions missed L3 cache as data sources",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_RETIRED.L3_MISS",
+ "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
+ "SampleAfterValue": "50021",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Deprecated": "1",
+ "EventCode": "0xd3",
+ "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event MEM_LOAD_UOPS_LLC_MISS_RETIRED.MEMSIDE_CACHE",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Deprecated": "1",
+ "EventCode": "0xd3",
+ "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.MEMSIDE_CACHE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of load ops retired that miss the L2 cache, missed the Memory Side Cache and hit in DRAM",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd3",
+ "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of load ops retired that miss the LLC cache and hit in the Memory Side Cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd3",
+ "EventName": "MEM_LOAD_UOPS_LLC_MISS_RETIRED.MEMSIDE_CACHE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of load ops retired that hit the L1 data cache",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of load ops retired that miss in the L1 data cache",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of load ops retired that hit in the L2 cache",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+ "PublicDescription": "Counts the number of load ops retired that hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of load ops retired that miss in the L2 cache",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x80",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of loads that hit in a write combining buffer (WCB), excluding the first load that caused the WCB to allocate.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xd1",
+ "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that uops are blocked for any of the following reasons: load buffer, store buffer or RSV full.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x04",
+ "EventName": "MEM_SCHEDULER_BLOCK.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that uops are blocked due to load buffer full",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x04",
+ "EventName": "MEM_SCHEDULER_BLOCK.LD_BUF",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that uops are blocked due to RSV full",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x04",
+ "EventName": "MEM_SCHEDULER_BLOCK.RSV",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
},
{
- "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.",
+ "BriefDescription": "Counts the number of cycles that uops are blocked due to store buffer full",
"Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0x2e",
- "EventName": "LONGEST_LAT_CACHE.REFERENCE",
- "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
- "SampleAfterValue": "200003",
- "UMask": "0x4f",
+ "EventCode": "0x04",
+ "EventName": "MEM_SCHEDULER_BLOCK.ST_BUF",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)",
+ "BriefDescription": "MEM_STORE_RETIRED.L2_HIT",
"Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0x2e",
- "EventName": "LONGEST_LAT_CACHE.REFERENCE",
- "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
- "SampleAfterValue": "100003",
- "UMask": "0x4f",
+ "EventCode": "0x44",
+ "EventName": "MEM_STORE_RETIRED.L2_HIT",
+ "SampleAfterValue": "200003",
+ "UMask": "0x1",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Retired load instructions.",
- "Counter": "0,1,2,3",
- "Data_LA": "1",
- "EventCode": "0xd0",
- "EventName": "MEM_INST_RETIRED.ALL_LOADS",
- "PEBS": "1",
- "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
- "SampleAfterValue": "1000003",
- "UMask": "0x81",
+ "BriefDescription": "Number of cache-lines required by retired stores whose Data Source is: Memory Side Cache",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x44",
+ "EventName": "MEM_STORE_RETIRED.MEMSIDE_CACHE",
+ "SampleAfterValue": "100021",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Retired store instructions.",
- "Counter": "0,1,2,3",
+ "BriefDescription": "Counts the number of memory uops retired. A single uop that performs both a load AND a store will be counted as 1, not 2 (e.g. ADD [mem], CONST)",
+ "Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xd0",
- "EventName": "MEM_INST_RETIRED.ALL_STORES",
- "PEBS": "1",
- "PublicDescription": "Counts all retired store instructions.",
- "SampleAfterValue": "1000003",
- "UMask": "0x82",
- "Unit": "cpu_core"
+ "EventName": "MEM_UOPS_RETIRED.ALL",
+ "SampleAfterValue": "200003",
+ "UMask": "0x83",
+ "Unit": "cpu_atom"
},
{
"BriefDescription": "Counts the number of load uops retired.",
@@ -79,7 +933,6 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x81",
"Unit": "cpu_atom"
@@ -90,24 +943,10 @@
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.ALL_STORES",
- "PEBS": "1",
"SampleAfterValue": "200003",
"UMask": "0x82",
"Unit": "cpu_atom"
},
- {
- "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
- "Counter": "0,1,2,3,4,5,6,7",
- "Data_LA": "1",
- "EventCode": "0xd0",
- "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024",
- "MSRIndex": "0x3F6",
- "MSRValue": "0x400",
- "PEBS": "2",
- "SampleAfterValue": "200003",
- "UMask": "0x5",
- "Unit": "cpu_atom"
- },
{
"BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
"Counter": "0,1,2,3,4,5,6,7",
@@ -116,7 +955,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
- "PEBS": "2",
"SampleAfterValue": "200003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -129,20 +967,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
- "PEBS": "2",
- "SampleAfterValue": "200003",
- "UMask": "0x5",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled",
- "Counter": "0,1,2,3,4,5,6,7",
- "Data_LA": "1",
- "EventCode": "0xd0",
- "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048",
- "MSRIndex": "0x3F6",
- "MSRValue": "0x800",
- "PEBS": "2",
"SampleAfterValue": "200003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -155,7 +979,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
- "PEBS": "2",
"SampleAfterValue": "200003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -168,7 +991,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
- "PEBS": "2",
"SampleAfterValue": "200003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -181,7 +1003,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
- "PEBS": "2",
"SampleAfterValue": "200003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -194,7 +1015,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
- "PEBS": "2",
"SampleAfterValue": "200003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -207,7 +1027,6 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
- "PEBS": "2",
"SampleAfterValue": "200003",
"UMask": "0x5",
"Unit": "cpu_atom"
@@ -220,20 +1039,373 @@
"EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
- "PEBS": "2",
"SampleAfterValue": "200003",
"UMask": "0x5",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of load uops retired that performed one or more locks",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x21",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of memory renamed load uops retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.MRN_LOADS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x9",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of memory renamed store uops retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.MRN_STORES",
+ "SampleAfterValue": "200003",
+ "UMask": "0xa",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of memory uops retired that were splits.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.SPLIT",
+ "SampleAfterValue": "200003",
+ "UMask": "0x43",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retired split load uops.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x41",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retired split store uops.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
+ "SampleAfterValue": "200003",
+ "UMask": "0x42",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of memory uops retired that missed in the second level TLB.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.STLB_MISS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x13",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of load ops retired that filled the STLB - includes those in DTLB_LOAD_MISSES submasks",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x11",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of store ops retired (store STLB miss)",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+ "SampleAfterValue": "200003",
+ "UMask": "0x12",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES",
"Counter": "0,1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
- "PEBS": "2",
"SampleAfterValue": "200003",
"UMask": "0x6",
"Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Retired memory uops for any access",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe5",
+ "EventName": "MEM_UOP_RETIRED.ANY",
+ "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xf",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by mem side cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.MEMSIDE_CACHE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x11F80000004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x40001E00001",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x20001E00001",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts demand data reads that were supplied by mem side cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_DATA_RD.MEMSIDE_CACHE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x11F80000001",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop hit in another cores caches, data forwarding is required as the data is modified.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x40001E00002",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Any memory transaction that reached the SQ.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x21",
+ "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
+ "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
+ "SampleAfterValue": "100003",
+ "UMask": "0x80",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Demand and prefetch data reads",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x21",
+ "EventName": "OFFCORE_REQUESTS.DATA_RD",
+ "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cacheable and Non-Cacheable code read requests",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x21",
+ "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
+ "PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Demand Data Read requests sent to uncore",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x21",
+ "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
+ "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x21",
+ "EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
+ "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+ "Counter": "0,1,2,3",
+ "CounterMask": "1",
+ "EventCode": "0x20",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+ "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.",
+ "Counter": "0,1,2,3",
+ "CounterMask": "1",
+ "EventCode": "0x20",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD",
+ "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles where at least 1 outstanding demand data read request is pending.",
+ "Counter": "0,1,2,3",
+ "CounterMask": "1",
+ "EventCode": "0x20",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.",
+ "Counter": "0,1,2,3",
+ "CounterMask": "1",
+ "EventCode": "0x20",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+ "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x20",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x20",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD",
+ "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x20",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
+ "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Store Read transactions pending for off-core. Highly correlated.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x20",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
+ "PublicDescription": "Counts the number of off-core outstanding read-for-ownership (RFO) store transactions every cycle. An RFO transaction is considered to be in the Off-core outstanding state between L2 cache miss and transaction completion.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x2c",
+ "EventName": "SQ_MISC.BUS_LOCK",
+ "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x40",
+ "EventName": "SW_PREFETCH_ACCESS.ANY",
+ "SampleAfterValue": "100003",
+ "UMask": "0xf",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of PREFETCHNTA instructions executed.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x40",
+ "EventName": "SW_PREFETCH_ACCESS.NTA",
+ "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of PREFETCHW instructions executed.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x40",
+ "EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
+ "PublicDescription": "Counts the number of PREFETCHW instructions executed.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of PREFETCHT0 instructions executed.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x40",
+ "EventName": "SW_PREFETCH_ACCESS.T0",
+ "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x40",
+ "EventName": "SW_PREFETCH_ACCESS.T1_T2",
+ "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to an icache miss",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.ICACHE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/floating-point.json b/tools/perf/pmu-events/arch/x86/lunarlake/floating-point.json
new file mode 100644
index 000000000000..26eceb52a437
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/floating-point.json
@@ -0,0 +1,484 @@
+[
+ {
+ "BriefDescription": "Counts the number of cycles when any of the floating point dividers are active.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "CounterMask": "1",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.FPDIV_ACTIVE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Cycles when floating-point divide unit is busy executing divide or square root operations.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0xb0",
+ "EventName": "ARITH.FPDIV_ACTIVE",
+ "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for floating-point operations only.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of active floating point dividers per cycle in the loop stage.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.FPDIV_OCCUPANCY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of floating point divider uops executed per cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.FPDIV_UOPS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts all microcode FP assists.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc1",
+ "EventName": "ASSISTS.FP",
+ "PublicDescription": "Counts all microcode Floating Point assists.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "ASSISTS.SSE_AVX_MIX",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc1",
+ "EventName": "ASSISTS.SSE_AVX_MIX",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of FP-arith-uops dispatched on 1st VEC port (port 0). FP-arith-uops are of type ADD*/SUB*/MUL/FMA*/DPP.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb3",
+ "EventName": "FP_ARITH_DISPATCHED.V0",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of FP-arith-uops dispatched on 2nd VEC port (port 1)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb3",
+ "EventName": "FP_ARITH_DISPATCHED.V1",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of FP-arith-uops dispatched on 3rd VEC port (port 5)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb3",
+ "EventName": "FP_ARITH_DISPATCHED.V2",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of FP-arith-uops dispatched on 4th VEC port",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb3",
+ "EventName": "FP_ARITH_DISPATCHED.V3",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Deprecated": "1",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Deprecated": "1",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
+ "SampleAfterValue": "100003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.256B_PACKED_DOUBLE",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Deprecated": "1",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
+ "SampleAfterValue": "100003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Deprecated": "1",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
+ "SampleAfterValue": "100003",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.4_FLOPS",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Deprecated": "1",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
+ "SampleAfterValue": "100003",
+ "UMask": "0x18",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Deprecated": "1",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR_DOUBLE",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Deprecated": "1",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.SCALAR_SINGLE",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Deprecated": "1",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. Refer to new event FP_ARITH_OPS_RETIRED.VECTOR",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Deprecated": "1",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3c",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "FP_ARITH_INST_RETIRED.VECTOR_128B [This event is alias to FP_ARITH_OPS_RETIRED.VECTOR_128B]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.VECTOR_128B",
+ "SampleAfterValue": "100003",
+ "UMask": "0xc",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "FP_ARITH_INST_RETIRED.VECTOR_256B [This event is alias to FP_ARITH_OPS_RETIRED.VECTOR_256B]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_INST_RETIRED.VECTOR_256B",
+ "SampleAfterValue": "100003",
+ "UMask": "0x30",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.128B_PACKED_DOUBLE",
+ "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.128B_PACKED_SINGLE",
+ "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.256B_PACKED_DOUBLE",
+ "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.256B_PACKED_SINGLE",
+ "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.4_FLOPS",
+ "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x18",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.SCALAR",
+ "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.SCALAR_DOUBLE",
+ "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.SCALAR_SINGLE",
+ "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of any Vector retired FP arithmetic instructions",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.VECTOR",
+ "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3c",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "FP_ARITH_OPS_RETIRED.VECTOR_128B [This event is alias to FP_ARITH_INST_RETIRED.VECTOR_128B]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.VECTOR_128B",
+ "SampleAfterValue": "100003",
+ "UMask": "0xc",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "FP_ARITH_OPS_RETIRED.VECTOR_256B [This event is alias to FP_ARITH_INST_RETIRED.VECTOR_256B]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc7",
+ "EventName": "FP_ARITH_OPS_RETIRED.VECTOR_256B",
+ "SampleAfterValue": "100003",
+ "UMask": "0x30",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of all types of floating point operations per uop with all default weighting",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc8",
+ "EventName": "FP_FLOPS_RETIRED.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of floating point operations that produce 32 bit single precision results",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc8",
+ "EventName": "FP_FLOPS_RETIRED.FP32",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of floating point operations that produce 64 bit double precision results",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc8",
+ "EventName": "FP_FLOPS_RETIRED.FP64",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit double precision floating point. This may be SSE or AVX.128 operations.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc7",
+ "EventName": "FP_INST_RETIRED.128B_DP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retired instructions whose sources are a packed 128 bit single precision floating point. This may be SSE or AVX.128 operations.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc7",
+ "EventName": "FP_INST_RETIRED.128B_SP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit double precision floating point.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc7",
+ "EventName": "FP_INST_RETIRED.256B_DP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retired instructions whose sources are a packed 256 bit single precision floating point.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc7",
+ "EventName": "FP_INST_RETIRED.256B_SP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 32bit single precision floating point",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc7",
+ "EventName": "FP_INST_RETIRED.32B_SP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retired instructions whose sources are a scalar 64 bit double precision floating point",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc7",
+ "EventName": "FP_INST_RETIRED.64B_DP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the total number of floating point retired instructions.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc7",
+ "EventName": "FP_INST_RETIRED.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3f",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on all floating point ports.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb2",
+ "EventName": "FP_VINT_UOPS_EXECUTED.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1f",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 0.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb2",
+ "EventName": "FP_VINT_UOPS_EXECUTED.P0",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 1.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb2",
+ "EventName": "FP_VINT_UOPS_EXECUTED.P1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 2.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb2",
+ "EventName": "FP_VINT_UOPS_EXECUTED.P2",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 3.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb2",
+ "EventName": "FP_VINT_UOPS_EXECUTED.P3",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on floating point and vector integer port 0, 1, 2, 3.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb2",
+ "EventName": "FP_VINT_UOPS_EXECUTED.PRIMARY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1e",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on floating point and vector integer store data port.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb2",
+ "EventName": "FP_VINT_UOPS_EXECUTED.STD",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of floating point operations retired that required microcode assist.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.FP_ASSIST",
+ "PublicDescription": "Counts the number of floating point operations retired that required microcode assist, which is not a reflection of the number of FP operations, instructions or uops.",
+ "SampleAfterValue": "20003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of floating point divide uops retired (x87 and sse, including x87 sqrt)",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.FPDIV",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json
index 0327bece0f94..07bd38a1904e 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json
@@ -1,4 +1,446 @@
[
+ {
+ "BriefDescription": "Counts the total number of BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe6",
+ "EventName": "BACLEARS.ANY",
+ "PublicDescription": "Counts the total number of BACLEARS, which occur when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Clears due to Unknown Branches.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x60",
+ "EventName": "BACLEARS.ANY",
+ "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of BACLEARS due to a conditional jump.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe6",
+ "EventName": "BACLEARS.COND",
+ "SampleAfterValue": "200003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of BACLEARS due to an indirect branch.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe6",
+ "EventName": "BACLEARS.INDIRECT",
+ "SampleAfterValue": "200003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of BACLEARS due to a return branch.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe6",
+ "EventName": "BACLEARS.RETURN",
+ "SampleAfterValue": "200003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of BACLEARS due to a direct, unconditional jump.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe6",
+ "EventName": "BACLEARS.UNCOND",
+ "SampleAfterValue": "200003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x87",
+ "EventName": "DECODE.LCP",
+ "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
+ "SampleAfterValue": "500009",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles the Microcode Sequencer is busy.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x87",
+ "EventName": "DECODE.MS_BUSY",
+ "SampleAfterValue": "500009",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of times a decode restriction reduces the decode throughput due to wrong instruction length prediction.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe9",
+ "EventName": "DECODE_RESTRICTION.PREDECODE_WRONG",
+ "SampleAfterValue": "200003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "DSB-to-MITE switch true penalty cycles.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x61",
+ "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
+ "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of instructions retired that were tagged with having preceded with frontend bound behavior",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.ALL",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Retired ANT branches",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.ANY_ANT",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x9",
+ "PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired Instructions who experienced DSB miss.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x1",
+ "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of instruction retired that are tagged after a branch instruction causes bubbles/empty issue slots due to a baclear",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.BRANCH_DETECT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of instruction retired that are tagged after a branch instruction causes bubbles /empty issue slots due to a btclear",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.BRANCH_RESTEER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of instructions retired that were tagged following an ms flow due to the bubble/wasted issue slot from exiting long ms flow",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.CISC",
+ "PublicDescription": "Counts the number of instructions retired that were tagged following an ms flow due to the bubble/wasted issue slot from exiting long ms flow",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of instructions retired that were tagged every cycle the decoder is unable to send 4 uops",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.DECODE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Retired Instructions who experienced a critical DSB miss.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.DSB_MISS",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x11",
+ "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to icache miss",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.ICACHE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.ITLB_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Retired Instructions who experienced iTLB true miss.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.ITLB_MISS",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x14",
+ "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.L1I_MISS",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x12",
+ "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.L2_MISS",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x13",
+ "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x608006",
+ "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x601006",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x600206",
+ "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x610006",
+ "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x100206",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x602006",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x600406",
+ "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x620006",
+ "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x604006",
+ "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x600806",
+ "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Mispredicted Retired ANT branches",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.MISP_ANT",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x9",
+ "PublicDescription": "ANT retired branches that got just mispredicted",
+ "SampleAfterValue": "100007",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts flows delivered by the Microcode Sequencer",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.MS_FLOWS",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x8",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of instruction retired tagged after a wasted issue slot if none of the previous events occurred",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.OTHER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x80",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of instruction retired that are tagged after a branch instruction causes bubbles/empty issue slots due to a predecode wrong",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.PREDECODE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.STLB_MISS",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x15",
+ "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired instructions that caused clears due to being Unknown Branches.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x17",
+ "PublicDescription": "Number retired branch instructions that caused the front-end to be resteered when it finds the instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L2 cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc9",
+ "EventName": "FRONTEND_RETIRED_SOURCE.ICACHE_L2_HIT",
+ "PublicDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to Instruction L1 cache miss, that hit in the L2 cache. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that hit in the second level TLB.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc9",
+ "EventName": "FRONTEND_RETIRED_SOURCE.ITLB_STLB_HIT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of instructions retired that were tagged because empty issue slots were seen before the uop due to ITLB miss that also missed the second level TLB.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc9",
+ "EventName": "FRONTEND_RETIRED_SOURCE.ITLB_STLB_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -8,6 +450,15 @@
"UMask": "0x3",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are present.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x80",
+ "EventName": "ICACHE.HIT",
+ "SampleAfterValue": "200003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -",
"Counter": "0,1,2,3,4,5,6,7",
@@ -18,13 +469,212 @@
"Unit": "cpu_atom"
},
{
- "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.",
+ "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x80",
+ "EventName": "ICACHE_DATA.STALLS",
+ "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
+ "SampleAfterValue": "500009",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "ICACHE_DATA.STALL_PERIODS",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EdgeDetect": "1",
+ "EventCode": "0x80",
+ "EventName": "ICACHE_DATA.STALL_PERIODS",
+ "SampleAfterValue": "500009",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x83",
+ "EventName": "ICACHE_TAG.STALLS",
+ "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0x79",
+ "EventName": "IDQ.DSB_CYCLES_ANY",
+ "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles DSB is delivering optimal number of Uops",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "8",
+ "EventCode": "0x79",
+ "EventName": "IDQ.DSB_CYCLES_OK",
+ "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x79",
+ "EventName": "IDQ.DSB_UOPS",
+ "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles MITE is delivering any Uop",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0x79",
+ "EventName": "IDQ.MITE_CYCLES_ANY",
+ "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles MITE is delivering optimal number of Uops",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "8",
+ "EventCode": "0x79",
+ "EventName": "IDQ.MITE_CYCLES_OK",
+ "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x79",
+ "EventName": "IDQ.MITE_UOPS",
+ "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0x79",
+ "EventName": "IDQ.MS_CYCLES_ANY",
+ "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of switches from DSB or MITE to the MS",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EdgeDetect": "1",
+ "EventCode": "0x79",
+ "EventName": "IDQ.MS_SWITCHES",
+ "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x79",
+ "EventName": "IDQ.MS_UOPS",
+ "PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.CORE",
- "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+ "PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event is deprecated. [This event is alias to IDQ_BUBBLES.STARVATION_CYCLES]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "8",
+ "Deprecated": "1",
+ "EventCode": "0x9c",
+ "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0x9c",
+ "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
+ "Invert": "1",
+ "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when no uops are delivered by the IDQ for 2 or more cycles when backend of the machine is not stalled - normally indicating a Fetch Latency issue",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x9c",
+ "EventName": "IDQ_BUBBLES.FETCH_LATENCY",
+ "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls for 2 or more cycles - normally indicating a Fetch Latency issue.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "8",
+ "EventCode": "0x9c",
+ "EventName": "IDQ_BUBBLES.STARVATION_CYCLES",
+ "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the micro-sequencer is busy.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe7",
+ "EventName": "MS_DECODED.MS_BUSY",
+ "SampleAfterValue": "200003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of times entered into a ucode flow in the FEC. Includes inserted flows due to front-end detected faults or assists.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe7",
+ "EventName": "MS_DECODED.MS_ENTRY",
+ "SampleAfterValue": "200003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of times nanocode flow is executed.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe7",
+ "EventName": "MS_DECODED.NANO_CODE",
+ "SampleAfterValue": "200003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json b/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json
new file mode 100644
index 000000000000..6782c4e054cd
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/lnl-metrics.json
@@ -0,0 +1,4611 @@
+[
+ {
+ "BriefDescription": "C10 residency percent per package",
+ "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC",
+ "MetricGroup": "Power",
+ "MetricName": "C10_Pkg_Residency",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "C1 residency percent per core",
+ "MetricExpr": "cstate_core@c1\\-residency@ / TSC",
+ "MetricGroup": "Power",
+ "MetricName": "C1_Core_Residency",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "C2 residency percent per package",
+ "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC",
+ "MetricGroup": "Power",
+ "MetricName": "C2_Pkg_Residency",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "C3 residency percent per package",
+ "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC",
+ "MetricGroup": "Power",
+ "MetricName": "C3_Pkg_Residency",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "C6 residency percent per core",
+ "MetricExpr": "cstate_core@c6\\-residency@ / TSC",
+ "MetricGroup": "Power",
+ "MetricName": "C6_Core_Residency",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "C6 residency percent per package",
+ "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC",
+ "MetricGroup": "Power",
+ "MetricName": "C6_Pkg_Residency",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "C7 residency percent per core",
+ "MetricExpr": "cstate_core@c7\\-residency@ / TSC",
+ "MetricGroup": "Power",
+ "MetricName": "C7_Core_Residency",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "C7 residency percent per package",
+ "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC",
+ "MetricGroup": "Power",
+ "MetricName": "C7_Pkg_Residency",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "C8 residency percent per package",
+ "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC",
+ "MetricGroup": "Power",
+ "MetricName": "C8_Pkg_Residency",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "C9 residency percent per package",
+ "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC",
+ "MetricGroup": "Power",
+ "MetricName": "C9_Pkg_Residency",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "Percentage of cycles spent in System Management Interrupts.",
+ "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)",
+ "MetricGroup": "smi",
+ "MetricName": "smi_cycles",
+ "MetricThreshold": "smi_cycles > 0.1",
+ "ScaleUnit": "100%"
+ },
+ {
+ "BriefDescription": "Number of SMI interrupts.",
+ "MetricExpr": "msr@smi@",
+ "MetricGroup": "smi",
+ "MetricName": "smi_num",
+ "ScaleUnit": "1SMI#"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions",
+ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group",
+ "MetricName": "tma_allocation_restriction",
+ "MetricThreshold": "(tma_allocation_restriction >0.10) & ((tma_core_bound >0.10) & ((tma_backend_bound >0.10)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+ "MetricExpr": "UOPS_DISPATCHED.ALU / (6 * tma_info_thread_clks)",
+ "MetricGroup": "Core_Execution;TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
+ "MetricName": "tma_alu_op_utilization",
+ "MetricThreshold": "tma_alu_op_utilization > 0.4",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists",
+ "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots",
+ "MetricGroup": "BvIO;Slots_Estimated;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
+ "MetricName": "tma_assists",
+ "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+ "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+ "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots",
+ "MetricGroup": "HPC;Slots_Estimated;TopdownL5;tma_L5_group;tma_assists_group",
+ "MetricName": "tma_avx_assists",
+ "MetricThreshold": "tma_avx_assists > 0.1",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "TopdownL1;tma_L1_group",
+ "MetricName": "tma_backend_bound",
+ "MetricThreshold": "tma_backend_bound > 0.2",
+ "MetricgroupNoGroup": "TopdownL1",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricExpr": "topdown\\-bad\\-spec / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "TopdownL1;tma_L1_group",
+ "MetricName": "tma_bad_speculation",
+ "MetricThreshold": "tma_bad_speculation > 0.15",
+ "MetricgroupNoGroup": "TopdownL1",
+ "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%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+ "MetricGroup": "BigFootprint;BvBC;Default;Fed;Frontend;IcMiss;MemoryTLB;Scaled_Slots;TopdownL1;tma_L1_group",
+ "MetricName": "tma_bottleneck_big_code",
+ "MetricThreshold": "tma_bottleneck_big_code > 20",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)",
+ "MetricGroup": "BvBO;Default;Ret;Scaled_Slots;TopdownL1;tma_L1_group",
+ "MetricName": "tma_bottleneck_branching_overhead",
+ "MetricThreshold": "tma_bottleneck_branching_overhead > 5",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+ "MetricGroup": "BvMB;Default;Mem;MemoryBW;Offcore;Scaled_Slots;TopdownL1;tma_L1_group;tma_issueBW",
+ "MetricName": "tma_bottleneck_cache_memory_bandwidth",
+ "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+ "MetricGroup": "BvML;Default;Mem;MemoryLat;Offcore;Scaled_Slots;TopdownL1;tma_L1_group;tma_issueLat",
+ "MetricName": "tma_bottleneck_cache_memory_latency",
+ "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+ "MetricGroup": "BvCB;Cor;Default;Scaled_Slots;TopdownL1;tma_L1_group;tma_issueComp",
+ "MetricName": "tma_bottleneck_compute_bound_est",
+ "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+ "MetricGroup": "BvFB;Default;Fed;FetchBW;Frontend;Scaled_Slots;TopdownL1;tma_L1_group",
+ "MetricName": "tma_bottleneck_instruction_fetch_bw",
+ "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of irregular execution (e.g",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+ "MetricGroup": "Bad;BvIO;Cor;Default;Ret;Scaled_Slots;TopdownL1;tma_L1_group;tma_issueMS",
+ "MetricName": "tma_bottleneck_irregular_overhead",
+ "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+ "MetricGroup": "BvMT;Default;Mem;MemoryTLB;Offcore;Scaled_Slots;TopdownL1;tma_L1_group;tma_issueTLB",
+ "MetricName": "tma_bottleneck_memory_data_tlbs",
+ "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+ "MetricGroup": "BvMS;Default;LockCont;Mem;Offcore;Scaled_Slots;TopdownL1;tma_L1_group;tma_issueSyncxn",
+ "MetricName": "tma_bottleneck_memory_synchronization",
+ "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+ "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;Default;Scaled_Slots;TopdownL1;tma_L1_group;tma_issueBM",
+ "MetricName": "tma_bottleneck_mispredictions",
+ "MetricThreshold": "tma_bottleneck_mispredictions > 20",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)",
+ "MetricGroup": "BvOB;Cor;Default;Offcore;Scaled_Slots;TopdownL1;tma_L1_group",
+ "MetricName": "tma_bottleneck_other_bottlenecks",
+ "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+ "DefaultMetricgroupName": "TopdownL1",
+ "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+ "MetricGroup": "BvUW;Default;Ret;Scaled_Slots;TopdownL1;tma_L1_group",
+ "MetricName": "tma_bottleneck_useful_work",
+ "MetricThreshold": "tma_bottleneck_useful_work > 20",
+ "MetricgroupNoGroup": "TopdownL1;Default",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend",
+ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_DETECT@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+ "MetricName": "tma_branch_detect",
+ "MetricThreshold": "(tma_branch_detect >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+ "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
+ "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
+ "MetricName": "tma_branch_mispredicts",
+ "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
+ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.BRANCH_RESTEER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+ "MetricName": "tma_branch_resteer",
+ "MetricThreshold": "(tma_branch_resteer >0.05) & ((tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers",
+ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
+ "MetricGroup": "Clocks;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_overlap",
+ "MetricName": "tma_branch_resteers",
+ "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+ "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks",
+ "MetricGroup": "C0Wait;Clocks;TopdownL4;tma_L4_group;tma_serializing_operation_group",
+ "MetricName": "tma_c01_wait",
+ "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+ "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks",
+ "MetricGroup": "C0Wait;Clocks;TopdownL4;tma_L4_group;tma_serializing_operation_group",
+ "MetricName": "tma_c02_wait",
+ "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "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": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+ "MetricName": "tma_cisc",
+ "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+ "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears",
+ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
+ "MetricGroup": "BadSpec;Clocks;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
+ "MetricName": "tma_clears_resteers",
+ "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+ "MetricExpr": "max(0, FRONTEND_RETIRED.L1I_MISS * cpu_core@FRONTEND_RETIRED.L1I_MISS@R / tma_info_thread_clks - tma_code_l2_miss)",
+ "MetricGroup": "Clocks_Retired;FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
+ "MetricName": "tma_code_l2_hit",
+ "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+ "MetricExpr": "FRONTEND_RETIRED.L2_MISS * cpu_core@FRONTEND_RETIRED.L2_MISS@R / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Retired;FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
+ "MetricName": "tma_code_l2_miss",
+ "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
+ "MetricExpr": "max(0, FRONTEND_RETIRED.ITLB_MISS * cpu_core@FRONTEND_RETIRED.ITLB_MISS@R / tma_info_thread_clks - tma_code_stlb_miss)",
+ "MetricGroup": "Clocks_Retired;FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
+ "MetricName": "tma_code_stlb_hit",
+ "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
+ "MetricExpr": "FRONTEND_RETIRED.STLB_MISS * cpu_core@FRONTEND_RETIRED.STLB_MISS@R / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Retired;FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
+ "MetricName": "tma_code_stlb_miss",
+ "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
+ "MetricGroup": "Clocks_Estimated;FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
+ "MetricName": "tma_code_stlb_miss_2m",
+ "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
+ "MetricGroup": "Clocks_Estimated;FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
+ "MetricName": "tma_code_stlb_miss_4k",
+ "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches",
+ "MetricExpr": "BR_MISP_RETIRED.COND_NTAKEN_COST * cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@R / tma_info_thread_clks",
+ "MetricGroup": "BrMispredicts;Clocks_Retired;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_cond_nt_mispredicts",
+ "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches",
+ "MetricExpr": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST * cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@R / tma_info_thread_clks",
+ "MetricGroup": "BrMispredicts;Clocks_Retired;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_cond_tk_bwd_mispredicts",
+ "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches",
+ "MetricExpr": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST * cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@R / tma_info_thread_clks",
+ "MetricGroup": "BrMispredicts;Clocks_Retired;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_cond_tk_fwd_mispredicts",
+ "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
+ "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R else MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R, MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R else MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricGroup": "BvMS;Clocks_Estimated;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+ "MetricName": "tma_contested_accesses",
+ "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck",
+ "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)",
+ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
+ "MetricName": "tma_core_bound",
+ "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
+ "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R else MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R else MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricGroup": "BvMS;Clocks_Estimated;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+ "MetricName": "tma_data_sharing",
+ "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.",
+ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.DECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+ "MetricName": "tma_decode",
+ "MetricThreshold": "(tma_decode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
+ "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
+ "MetricGroup": "BvCB;Clocks;TopdownL3;tma_L3_group;tma_core_bound_group",
+ "MetricName": "tma_divider",
+ "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
+ "MetricExpr": "MEMORY_STALLS.MEM / tma_info_thread_clks",
+ "MetricGroup": "MemoryBound;Stalls;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
+ "MetricName": "tma_dram_bound",
+ "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
+ "MetricExpr": "(cpu@IDQ.DSB_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ + IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS) * (IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE - IDQ_BUBBLES.FETCH_LATENCY)) / tma_info_thread_clks",
+ "MetricGroup": "DSB;FetchBW;Slots_Estimated;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
+ "MetricName": "tma_dsb",
+ "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
+ "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%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines",
+ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
+ "MetricGroup": "Clocks;DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
+ "MetricName": "tma_dsb_switches",
+ "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
+ "MetricExpr": "(min(MEM_INST_RETIRED.STLB_HIT_LOADS * cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R, MEM_INST_RETIRED.STLB_HIT_LOADS * 7) if 0 < cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R else MEM_INST_RETIRED.STLB_HIT_LOADS * 7) / tma_info_thread_clks + tma_load_stlb_miss",
+ "MetricGroup": "BvMT;Clocks_Estimated;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
+ "MetricName": "tma_dtlb_load",
+ "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
+ "MetricExpr": "(min(MEM_INST_RETIRED.STLB_HIT_STORES * cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R, MEM_INST_RETIRED.STLB_HIT_STORES * 7) if 0 < cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R else MEM_INST_RETIRED.STLB_HIT_STORES * 7) / tma_info_thread_clks + tma_store_stlb_miss",
+ "MetricGroup": "BvMT;Clocks_Estimated;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
+ "MetricName": "tma_dtlb_store",
+ "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
+ "MetricExpr": "28 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks",
+ "MetricGroup": "BvMS;Clocks_Estimated;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
+ "MetricName": "tma_false_sharing",
+ "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that does not require the use of microcode, classified as a fast nuke, due to memory ordering, memory disambiguation and memory renaming",
+ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.FASTNUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
+ "MetricName": "tma_fast_nuke",
+ "MetricThreshold": "(tma_fast_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
+ "MetricExpr": "L1D_MISS.FB_FULL / tma_info_thread_clks",
+ "MetricGroup": "BvMB;Clocks_Calculated;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
+ "MetricName": "tma_fb_full",
+ "MetricThreshold": "tma_fb_full > 0.3",
+ "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues",
+ "DefaultMetricgroupName": "TopdownL2",
+ "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)",
+ "MetricGroup": "Default;FetchBW;Frontend;Slots;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
+ "MetricName": "tma_fetch_bandwidth",
+ "MetricThreshold": "tma_fetch_bandwidth > 0.2",
+ "MetricgroupNoGroup": "TopdownL2;Default",
+ "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. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
+ "DefaultMetricgroupName": "TopdownL2",
+ "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "Default;Frontend;Slots;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
+ "MetricName": "tma_fetch_latency",
+ "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricgroupNoGroup": "TopdownL2;Default",
+ "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops",
+ "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)",
+ "MetricGroup": "Slots;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0",
+ "MetricName": "tma_few_uops_instructions",
+ "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "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;Uops;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_fp_arith",
+ "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists",
+ "MetricExpr": "30 * ASSISTS.FP / tma_info_thread_slots",
+ "MetricGroup": "HPC;Slots_Estimated;TopdownL5;tma_L5_group;tma_assists_group",
+ "MetricName": "tma_fp_assists",
+ "MetricThreshold": "tma_fp_assists > 0.1",
+ "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+ "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks",
+ "MetricGroup": "Clocks;TopdownL4;tma_L4_group;tma_divider_group",
+ "MetricName": "tma_fp_divider",
+ "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired",
+ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;Flops;TopdownL4;Uops;tma_L4_group;tma_fp_arith_group;tma_issue2P",
+ "MetricName": "tma_fp_scalar",
+ "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths",
+ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;Flops;TopdownL4;Uops;tma_L4_group;tma_fp_arith_group;tma_issue2P",
+ "MetricName": "tma_fp_vector",
+ "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors",
+ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;Flops;TopdownL5;Uops;tma_L5_group;tma_fp_vector_group;tma_issue2P",
+ "MetricName": "tma_fp_vector_128b",
+ "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors",
+ "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;Flops;TopdownL5;Uops;tma_L5_group;tma_fp_vector_group;tma_issue2P",
+ "MetricName": "tma_fp_vector_256b",
+ "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "TopdownL1;tma_L1_group",
+ "MetricName": "tma_frontend_bound",
+ "MetricThreshold": "tma_frontend_bound > 0.15",
+ "MetricgroupNoGroup": "TopdownL1",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+ "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Branches;BvBO;Pipeline;Slots;TopdownL3;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_fused_instructions",
+ "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+ "DefaultMetricgroupName": "TopdownL2",
+ "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "Default;Retire;Slots;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
+ "MetricName": "tma_heavy_operations",
+ "MetricThreshold": "tma_heavy_operations > 0.1",
+ "MetricgroupNoGroup": "TopdownL2;Default",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
+ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+ "MetricName": "tma_icache_misses",
+ "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
+ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
+ "MetricName": "tma_ifetch_bandwidth",
+ "MetricThreshold": "(tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20))",
+ "MetricgroupNoGroup": "TopdownL2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend latency restrictions due to icache misses, itlb misses, branch detection, and resteer limitations.",
+ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.FRONTEND_LATENCY@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group",
+ "MetricName": "tma_ifetch_latency",
+ "MetricThreshold": "(tma_ifetch_latency >0.15) & ((tma_frontend_bound >0.20))",
+ "MetricgroupNoGroup": "TopdownL2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions",
+ "MetricExpr": "BR_MISP_RETIRED.INDIRECT_CALL_COST * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R / tma_info_thread_clks",
+ "MetricGroup": "BrMispredicts;Clocks_Retired;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_ind_call_mispredicts",
+ "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions",
+ "MetricExpr": "max((BR_MISP_RETIRED.INDIRECT_COST * cpu_core@BR_MISP_RETIRED.INDIRECT_COST@R - BR_MISP_RETIRED.INDIRECT_CALL_COST * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R) / tma_info_thread_clks, 0)",
+ "MetricGroup": "BrMispredicts;Clocks_Retired;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_ind_jump_mispredicts",
+ "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per Floating Point (FP) Operation",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_FLOPS_RETIRED.ALL@",
+ "MetricGroup": "Flops",
+ "MetricName": "tma_info_arith_inst_mix_ipflop",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic instruction",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_INST_RETIRED.ALL@",
+ "MetricGroup": "Flops",
+ "MetricName": "tma_info_arith_inst_mix_ipfparith",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@FP_INST_RETIRED.128B_DP@ + cpu_atom@FP_INST_RETIRED.128B_SP@)",
+ "MetricGroup": "Flops",
+ "MetricName": "tma_info_arith_inst_mix_ipfparith_avx128",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic AVX 256-bit instruction",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@FP_INST_RETIRED.256B_DP@ + cpu_atom@FP_INST_RETIRED.256B_SP@)",
+ "MetricGroup": "Flops",
+ "MetricName": "tma_info_arith_inst_mix_ipfparith_avx256",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_INST_RETIRED.64B_DP@",
+ "MetricGroup": "Flops",
+ "MetricName": "tma_info_arith_inst_mix_ipfparith_scalar_dp",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@FP_INST_RETIRED.32B_SP@",
+ "MetricGroup": "Flops",
+ "MetricName": "tma_info_arith_inst_mix_ipfparith_scalar_sp",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
+ "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 8 / BR_MISP_RETIRED.ALL_BRANCHES / 100",
+ "MetricGroup": "Bad;BrMispredicts;Core_Metric;tma_issueBM",
+ "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
+ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
+ "MetricGroup": "Bad;BrMispredicts;Inst_Metric",
+ "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
+ "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN_BWD",
+ "MetricGroup": "Bad;BrMispredicts",
+ "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_bwd",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN_FWD",
+ "MetricGroup": "Bad;BrMispredicts",
+ "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_fwd",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
+ "MetricGroup": "Bad;BrMispredicts;Inst_Metric",
+ "MetricName": "tma_info_bad_spec_ipmisp_indirect",
+ "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
+ "MetricGroup": "Bad;BrMispredicts;Inst_Metric",
+ "MetricName": "tma_info_bad_spec_ipmisp_ret",
+ "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500",
+ "Unit": "cpu_atom"
+ },
+ {
+ "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;Inst_Metric",
+ "MetricName": "tma_info_bad_spec_ipmispredict",
+ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)",
+ "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)",
+ "MetricGroup": "BrMispredicts;Metric",
+ "MetricName": "tma_info_bad_spec_spec_clears_ratio",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
+ "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+ "MetricGroup": "DSB;Fed;FetchBW;Scaled_Slots;tma_issueFB",
+ "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
+ "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
+ "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
+ "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+ "MetricGroup": "DSBmiss;Fed;Scaled_Slots;tma_issueFB",
+ "MetricName": "tma_info_botlnk_l2_dsb_misses",
+ "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
+ "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
+ "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+ "MetricGroup": "Fed;FetchLat;IcMiss;Scaled_Slots;tma_issueFL",
+ "MetricName": "tma_info_botlnk_l2_ic_misses",
+ "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of time that retirement is stalled due to a first level data TLB miss",
+ "MetricExpr": "100 * (cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ + cpu_atom@LD_HEAD.PGWALK_AT_RET@) / cpu_atom@CPU_CLK_UNHALTED.CORE@",
+ "MetricName": "tma_info_bottleneck_%_dtlb_miss_bound_cycles",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss",
+ "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
+ "MetricGroup": "Ifetch",
+ "MetricName": "tma_info_bottleneck_%_ifetch_miss_bound_cycles",
+ "PublicDescription": "Percentage of time that allocation and retirement is stalled by the Frontend Cluster due to an Ifetch Miss, either Icache or ITLB Miss. See Info.Ifetch_Bound",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of time that retirement is stalled due to an L1 miss",
+ "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
+ "MetricGroup": "Load_Store_Miss",
+ "MetricName": "tma_info_bottleneck_%_load_miss_bound_cycles",
+ "PublicDescription": "Percentage of time that retirement is stalled due to an L1 miss. See Info.Load_Miss_Bound",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall",
+ "MetricExpr": "100 * cpu_atom@LD_HEAD.ANY_AT_RET@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
+ "MetricGroup": "Mem_Exec",
+ "MetricName": "tma_info_bottleneck_%_mem_exec_bound_cycles",
+ "PublicDescription": "Percentage of time that retirement is stalled by the Memory Cluster due to a pipeline stall. See Info.Mem_Exec_Bound",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_INST_RETIRED.ALL_BRANCHES@",
+ "MetricName": "tma_info_br_inst_mix_ipbranch",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_INST_RETIRED.NEAR_CALL@",
+ "MetricName": "tma_info_br_inst_mix_ipcall",
+ "Unit": "cpu_atom"
+ },
+ {
+ "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": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_INST_RETIRED.FAR_BRANCH@u",
+ "MetricName": "tma_info_br_inst_mix_ipfarbranch",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / (cpu_atom@BR_MISP_RETIRED.COND@ - cpu_atom@BR_MISP_RETIRED.COND_TAKEN@)",
+ "MetricName": "tma_info_br_inst_mix_ipmisp_cond_ntaken",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.COND_TAKEN@",
+ "MetricName": "tma_info_br_inst_mix_ipmisp_cond_taken",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.INDIRECT@",
+ "MetricName": "tma_info_br_inst_mix_ipmisp_indirect",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per retired return Branch Misprediction",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.RETURN@",
+ "MetricName": "tma_info_br_inst_mix_ipmisp_ret",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per retired Branch Misprediction",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@",
+ "MetricName": "tma_info_br_inst_mix_ipmispredict",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Ratio of all branches which mispredict",
+ "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / cpu_atom@BR_INST_RETIRED.ALL_BRANCHES@",
+ "MetricName": "tma_info_br_mispredict_bound_branch_mispredict_ratio",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Ratio between Mispredicted branches and unknown branches",
+ "MetricExpr": "cpu_atom@BR_MISP_RETIRED.ALL_BRANCHES@ / cpu_atom@BACLEARS.ANY@",
+ "MetricName": "tma_info_br_mispredict_bound_branch_mispredict_to_unknown_branch_ratio",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fraction of branches that are CALL or RET",
+ "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;Branches;Fraction",
+ "MetricName": "tma_info_branches_callret",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fraction of branches that are non-taken conditionals",
+ "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;Branches;CodeGen;Fraction;PGO",
+ "MetricName": "tma_info_branches_cond_nt",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fraction of branches that are forward taken conditionals",
+ "MetricExpr": "BR_INST_RETIRED.COND_TAKEN_BWD / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;Branches;CodeGen;Fraction;PGO",
+ "MetricName": "tma_info_branches_cond_tk_bwd",
+ "MetricThreshold": "tma_info_branches_cond_tk_bwd > 0.3",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fraction of branches that are forward taken conditionals",
+ "MetricExpr": "BR_INST_RETIRED.COND_TAKEN_FWD / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;Branches;CodeGen;Fraction;PGO",
+ "MetricName": "tma_info_branches_cond_tk_fwd",
+ "MetricThreshold": "tma_info_branches_cond_tk_fwd > 0.2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
+ "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN_BWD - BR_INST_RETIRED.COND_TAKEN_FWD - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;Branches;Fraction",
+ "MetricName": "tma_info_branches_jump",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)",
+ "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk_bwd + tma_info_branches_cond_tk_fwd + tma_info_branches_callret + tma_info_branches_jump)",
+ "MetricGroup": "Bad;Branches;Fraction",
+ "MetricName": "tma_info_branches_other_branches",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of time that allocation is stalled due to load buffer full",
+ "MetricExpr": "100 * cpu_atom@MEM_SCHEDULER_BLOCK.LD_BUF@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
+ "MetricName": "tma_info_buffer_stalls_%_load_buffer_stall_cycles",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of time that allocation is stalled due to memory reservation stations full",
+ "MetricExpr": "100 * cpu_atom@MEM_SCHEDULER_BLOCK.RSV@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
+ "MetricName": "tma_info_buffer_stalls_%_mem_rsv_stall_cycles",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of time that allocation is stalled due to store buffer full",
+ "MetricExpr": "100 * cpu_atom@MEM_SCHEDULER_BLOCK.ST_BUF@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
+ "MetricName": "tma_info_buffer_stalls_%_store_buffer_stall_cycles",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Cycles Per Instruction",
+ "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@ / cpu_atom@INST_RETIRED.ANY@",
+ "MetricName": "tma_info_core_cpi",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "uops Executed per Cycle",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / tma_info_thread_clks",
+ "MetricGroup": "Metric;Power",
+ "MetricName": "tma_info_core_epc",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_thread_clks",
+ "MetricGroup": "Flops",
+ "MetricName": "tma_info_core_flopc",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
+ "MetricExpr": "(FP_ARITH_DISPATCHED.V0 + FP_ARITH_DISPATCHED.V1 + FP_ARITH_DISPATCHED.V2 + FP_ARITH_DISPATCHED.V3) / (4 * tma_info_thread_clks)",
+ "MetricGroup": "Cor;Core_Metric;Flops;HPC",
+ "MetricName": "tma_info_core_fp_arith_utilization",
+ "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+ "MetricGroup": "Backend;Cor;Metric;Pipeline;PortsUtil",
+ "MetricName": "tma_info_core_ilp",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions Per Cycle",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
+ "MetricName": "tma_info_core_ipc",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Uops Per Instruction",
+ "MetricExpr": "cpu_atom@TOPDOWN_RETIRING.ALL@ / cpu_atom@INST_RETIRED.ANY@",
+ "MetricName": "tma_info_core_upi",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY",
+ "MetricGroup": "DSB;Fed;FetchBW;Metric;tma_issueFB",
+ "MetricName": "tma_info_frontend_dsb_coverage",
+ "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 8 > 0.35",
+ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
+ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+ "MetricGroup": "DSBmiss;Metric",
+ "MetricName": "tma_info_frontend_dsb_switch_cost",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses",
+ "MetricExpr": "FRONTEND_RETIRED.ANY_DSB_MISS * cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@R / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Retired;DSBmiss;Fed;FetchLat",
+ "MetricName": "tma_info_frontend_dsb_switches_ret",
+ "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average number of Uops issued by front-end when it issued something",
+ "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+ "MetricGroup": "Fed;FetchBW;Metric",
+ "MetricName": "tma_info_frontend_fetch_upc",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average Latency for L1 instruction cache misses",
+ "MetricExpr": "ICACHE_DATA.STALLS / ICACHE_DATA.STALL_PERIODS",
+ "MetricGroup": "Fed;FetchLat;IcMiss;Metric",
+ "MetricName": "tma_info_frontend_icache_miss_latency",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
+ "MetricGroup": "DSBmiss;Fed;Inst_Metric",
+ "MetricName": "tma_info_frontend_ipdsb_miss_ret",
+ "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)",
+ "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY",
+ "MetricGroup": "Fed;Metric",
+ "MetricName": "tma_info_frontend_ipunknown_branch",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "L2 cache true code cacheline misses per kilo instruction",
+ "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "IcMiss;Metric",
+ "MetricName": "tma_info_frontend_l2mpki_code",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction",
+ "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "IcMiss;Metric",
+ "MetricName": "tma_info_frontend_l2mpki_code_all",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
+ "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY",
+ "MetricGroup": "Fed;LSD;Metric",
+ "MetricName": "tma_info_frontend_lsd_coverage",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer",
+ "MetricExpr": "FRONTEND_RETIRED.MS_FLOWS * cpu_core@FRONTEND_RETIRED.MS_FLOWS@R / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Retired;Fed;FetchLat;MicroSeq",
+ "MetricName": "tma_info_frontend_ms_latency_ret",
+ "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Taken Branches retired Per Cycle",
+ "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+ "MetricGroup": "Branches;FetchBW;Metric",
+ "MetricName": "tma_info_frontend_tbpc",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
+ "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+ "MetricGroup": "Fed;Metric",
+ "MetricName": "tma_info_frontend_unknown_branch_cost",
+ "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears",
+ "MetricExpr": "FRONTEND_RETIRED.UNKNOWN_BRANCH * cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@R / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Retired;Fed;FetchLat",
+ "MetricName": "tma_info_frontend_unknown_branches_ret",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss hits in the L2",
+ "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.L2_HIT@ / cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@",
+ "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2hit",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of ifetch miss bound stalls, where the ifetch miss doesn't hit in the L2",
+ "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_IFETCH.L2_MISS@ / cpu_atom@MEM_BOUND_STALLS_IFETCH.ALL@",
+ "MetricName": "tma_info_ifetch_miss_bound_%_ifetchmissbound_with_l2miss",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Branch instructions per taken branch",
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "MetricGroup": "Branches;Fed;Metric;PGO",
+ "MetricName": "tma_info_inst_mix_bptkbranch",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "INST_RETIRED.ANY",
+ "MetricGroup": "Count;Summary;TmaL1;TopdownL1;tma_L1_group",
+ "MetricName": "tma_info_inst_mix_instructions",
+ "MetricgroupNoGroup": "TopdownL1",
+ "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR)",
+ "MetricGroup": "Flops;InsType;Inst_Metric",
+ "MetricName": "tma_info_inst_mix_iparith",
+ "MetricThreshold": "tma_info_inst_mix_iparith < 10",
+ "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)",
+ "MetricGroup": "Flops;FpVector;InsType;Inst_Metric",
+ "MetricName": "tma_info_inst_mix_iparith_avx128",
+ "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
+ "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)",
+ "MetricGroup": "Flops;FpVector;InsType;Inst_Metric",
+ "MetricName": "tma_info_inst_mix_iparith_avx256",
+ "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
+ "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+ "MetricGroup": "Flops;FpScalar;InsType;Inst_Metric",
+ "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
+ "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
+ "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+ "MetricGroup": "Flops;FpScalar;InsType;Inst_Metric",
+ "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
+ "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
+ "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Branches;Fed;InsType;Inst_Metric",
+ "MetricName": "tma_info_inst_mix_ipbranch",
+ "MetricThreshold": "tma_info_inst_mix_ipbranch < 8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "MetricGroup": "Branches;Fed;Inst_Metric;PGO",
+ "MetricName": "tma_info_inst_mix_ipcall",
+ "MetricThreshold": "tma_info_inst_mix_ipcall < 200",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)",
+ "MetricGroup": "Flops;InsType;Inst_Metric",
+ "MetricName": "tma_info_inst_mix_ipflop",
+ "MetricThreshold": "tma_info_inst_mix_ipflop < 10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+ "MetricGroup": "InsType;Inst_Metric",
+ "MetricName": "tma_info_inst_mix_ipload",
+ "MetricThreshold": "tma_info_inst_mix_ipload < 3",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per PAUSE (lower number means higher occurrence rate)",
+ "MetricExpr": "tma_info_inst_mix_instructions / CPU_CLK_UNHALTED.PAUSE_INST",
+ "MetricGroup": "Flops;FpVector;InsType;Inst_Metric",
+ "MetricName": "tma_info_inst_mix_ippause",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+ "MetricGroup": "InsType;Inst_Metric",
+ "MetricName": "tma_info_inst_mix_ipstore",
+ "MetricThreshold": "tma_info_inst_mix_ipstore < 8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_SWPF",
+ "MetricGroup": "Inst_Metric;Prefetches",
+ "MetricName": "tma_info_inst_mix_ipswpf",
+ "MetricThreshold": "tma_info_inst_mix_ipswpf < 100",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per taken branch",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "MetricGroup": "Branches;Fed;FetchBW;Frontend;Inst_Metric;PGO;tma_issueFB",
+ "MetricName": "tma_info_inst_mix_iptb",
+ "MetricThreshold": "tma_info_inst_mix_iptb < 8 * 2 + 1",
+ "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that hit the L2",
+ "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.L2_HIT@ / cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@",
+ "MetricGroup": "load_store_bound",
+ "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2hit",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of memory bound stalls where retirement is stalled due to an L1 miss that subsequently misses in the L2",
+ "MetricExpr": "100 * cpu_atom@MEM_BOUND_STALLS_LOAD.L2_MISS@ / cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@",
+ "MetricGroup": "load_store_bound",
+ "MetricName": "tma_info_load_miss_bound_%_loadmissbound_with_l2miss",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a pipeline block",
+ "MetricExpr": "100 * cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ / cpu_atom@CPU_CLK_UNHALTED.CORE@",
+ "MetricGroup": "load_store_bound",
+ "MetricName": "tma_info_load_store_bound_l1_bound",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement",
+ "MetricExpr": "100 * (cpu_atom@LD_HEAD.L1_BOUND_AT_RET@ + cpu_atom@MEM_BOUND_STALLS_LOAD.ALL@) / cpu_atom@CPU_CLK_UNHALTED.CORE@",
+ "MetricGroup": "load_store_bound",
+ "MetricName": "tma_info_load_store_bound_load_bound",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full",
+ "MetricExpr": "100 * (cpu_atom@MEM_SCHEDULER_BLOCK.ST_BUF@ / cpu_atom@MEM_SCHEDULER_BLOCK.ALL@) * tma_mem_scheduler",
+ "MetricGroup": "load_store_bound",
+ "MetricName": "tma_info_load_store_bound_store_bound",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to memory disambiguation",
+ "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.DISAMBIGUATION@ / cpu_atom@INST_RETIRED.ANY@",
+ "MetricName": "tma_info_machine_clear_bound_machine_clears_disamb_pki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to floating point assists",
+ "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.FP_ASSIST@ / cpu_atom@INST_RETIRED.ANY@",
+ "MetricName": "tma_info_machine_clear_bound_machine_clears_fp_assist_pki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to memory ordering",
+ "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.MEMORY_ORDERING@ / cpu_atom@INST_RETIRED.ANY@",
+ "MetricName": "tma_info_machine_clear_bound_machine_clears_monuke_pki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to memory renaming",
+ "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.MRN_NUKE@ / cpu_atom@INST_RETIRED.ANY@",
+ "MetricName": "tma_info_machine_clear_bound_machine_clears_mrn_pki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of machine clears relative to thousands of instructions retired, due to page faults",
+ "MetricExpr": "1e3 * cpu_atom@MACHINE_CLEARS.PAGE_FAULT@ / cpu_atom@INST_RETIRED.ANY@",
+ "MetricName": "tma_info_machine_clear_bound_machine_clears_page_fault_pki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of total non-speculative loads with an address aliasing block",
+ "MetricExpr": "100 * cpu_atom@LD_BLOCKS.ADDRESS_ALIAS@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@",
+ "MetricName": "tma_info_mem_exec_blocks_%_loads_with_adressaliasing",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block",
+ "MetricExpr": "100 * cpu_atom@LD_BLOCKS.DATA_UNKNOWN@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@",
+ "MetricName": "tma_info_mem_exec_blocks_%_loads_with_storefwdblk",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of Memory Execution Bound due to a first level data cache miss",
+ "MetricExpr": "100 * cpu_atom@LD_HEAD.L1_MISS_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@",
+ "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_l1miss",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of Memory Execution Bound due to other block cases, such as pipeline conflicts, fences, etc",
+ "MetricExpr": "100 * cpu_atom@LD_HEAD.OTHER_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@",
+ "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_otherpipelineblks",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of Memory Execution Bound due to a pagewalk",
+ "MetricExpr": "100 * cpu_atom@LD_HEAD.PGWALK_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@",
+ "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_pagewalk",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of Memory Execution Bound due to a second level TLB miss",
+ "MetricExpr": "100 * cpu_atom@LD_HEAD.DTLB_MISS_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@",
+ "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_stlbhit",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of Memory Execution Bound due to a store forward address match",
+ "MetricExpr": "100 * cpu_atom@LD_HEAD.ST_ADDR_AT_RET@ / cpu_atom@LD_HEAD.ANY_AT_RET@",
+ "MetricName": "tma_info_mem_exec_bound_%_loadhead_with_storefwding",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per Load",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@",
+ "MetricName": "tma_info_mem_mix_ipload",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per Store",
+ "MetricExpr": "cpu_atom@INST_RETIRED.ANY@ / cpu_atom@MEM_UOPS_RETIRED.ALL_STORES@",
+ "MetricName": "tma_info_mem_mix_ipstore",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of total non-speculative loads that perform one or more locks",
+ "MetricExpr": "100 * cpu_atom@MEM_UOPS_RETIRED.LOCK_LOADS@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@",
+ "MetricName": "tma_info_mem_mix_load_locks_ratio",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of total non-speculative loads that are splits",
+ "MetricExpr": "100 * cpu_atom@MEM_UOPS_RETIRED.SPLIT_LOADS@ / cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@",
+ "MetricName": "tma_info_mem_mix_load_splits_ratio",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Ratio of mem load uops to all uops",
+ "MetricExpr": "1e3 * cpu_atom@MEM_UOPS_RETIRED.ALL_LOADS@ / cpu_atom@TOPDOWN_RETIRING.ALL@",
+ "MetricName": "tma_info_mem_mix_memload_ratio",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
+ "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem;Metric",
+ "MetricName": "tma_info_memory_fb_hpki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time",
+ "MetricGroup": "Mem;MemoryBW;Metric",
+ "MetricName": "tma_info_memory_l1d_cache_fill_bw",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the Level 0 within L1D cache [GB / sec]",
+ "MetricExpr": "64 * L1D.L0_REPLACEMENT / 1e9 / tma_info_system_time",
+ "MetricGroup": "Mem;MemoryBW;Metric",
+ "MetricName": "tma_info_memory_l1dl0_cache_fill_bw",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem;Metric",
+ "MetricName": "tma_info_memory_l1mpki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)",
+ "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem;Metric",
+ "MetricName": "tma_info_memory_l1mpki_load",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time",
+ "MetricGroup": "Mem;MemoryBW;Metric",
+ "MetricName": "tma_info_memory_l2_cache_fill_bw",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem;Metric",
+ "MetricName": "tma_info_memory_l2hpki_all",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)",
+ "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem;Metric",
+ "MetricName": "tma_info_memory_l2hpki_load",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "Backend;CacheHits;Mem;Metric",
+ "MetricName": "tma_info_memory_l2mpki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)",
+ "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem;Metric;Offcore",
+ "MetricName": "tma_info_memory_l2mpki_all",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)",
+ "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem;Metric",
+ "MetricName": "tma_info_memory_l2mpki_load",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Offcore requests (L2 cache miss) per kilo instruction for demand RFOs",
+ "MetricExpr": "1e3 * L2_RQSTS.RFO_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "CacheMisses;Metric;Offcore",
+ "MetricName": "tma_info_memory_l2mpki_rfo",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
+ "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time",
+ "MetricGroup": "Mem;MemoryBW;Metric;Offcore",
+ "MetricName": "tma_info_memory_l3_cache_access_bw",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time",
+ "MetricGroup": "Mem;MemoryBW;Metric",
+ "MetricName": "tma_info_memory_l3_cache_fill_bw",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "Mem;Metric",
+ "MetricName": "tma_info_memory_l3mpki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average Parallel L2 cache miss data reads",
+ "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+ "MetricGroup": "Memory_BW;Metric;Offcore",
+ "MetricName": "tma_info_memory_latency_data_l2_mlp",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average Latency for L2 cache miss demand Loads",
+ "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
+ "MetricGroup": "Clocks_Latency;LockCont;Memory_Lat;Offcore",
+ "MetricName": "tma_info_memory_latency_load_l2_miss_latency",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average Parallel L2 cache miss demand Loads",
+ "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+ "MetricGroup": "Memory_BW;Metric;Offcore",
+ "MetricName": "tma_info_memory_latency_load_l2_mlp",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average Latency for L3 cache miss demand Loads",
+ "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+ "MetricGroup": "Clocks_Latency;Memory_Lat;Offcore",
+ "MetricName": "tma_info_memory_latency_load_l3_miss_latency",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
+ "MetricExpr": "L1D_PENDING.LOAD / L1D_MISS.LOAD",
+ "MetricGroup": "Clocks_Latency;Mem;MemoryBound;MemoryLat",
+ "MetricName": "tma_info_memory_load_miss_real_latency",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "\"Bus lock\" per kilo instruction",
+ "MetricExpr": "1e3 * SQ_MISC.BUS_LOCK / INST_RETIRED.ANY",
+ "MetricGroup": "Mem;Metric",
+ "MetricName": "tma_info_memory_mix_bus_lock_pki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Un-cacheable retired load per kilo instruction",
+ "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY",
+ "MetricGroup": "Mem;Metric",
+ "MetricName": "tma_info_memory_mix_uc_load_pki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss",
+ "MetricExpr": "L1D_PENDING.LOAD / L1D_PENDING.LOAD_CYCLES",
+ "MetricGroup": "Mem;MemoryBW;MemoryBound;Metric",
+ "MetricName": "tma_info_memory_mlp",
+ "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses",
+ "MetricExpr": "L2_LINES_OUT.USELESS_HWPF / (L2_LINES_OUT.SILENT + L2_LINES_OUT.NON_SILENT)",
+ "MetricGroup": "Metric;Prefetches",
+ "MetricName": "tma_info_memory_prefetches_useless_hwpf",
+ "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
+ "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
+ "MetricGroup": "Fed;MemoryTLB;Metric",
+ "MetricName": "tma_info_memory_tlb_code_stlb_mpki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads",
+ "MetricExpr": "MEM_INST_RETIRED.STLB_MISS_LOADS * cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@R / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Retired;Mem;MemoryTLB",
+ "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret",
+ "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
+ "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
+ "MetricGroup": "Mem;MemoryTLB;Metric",
+ "MetricName": "tma_info_memory_tlb_load_stlb_mpki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * tma_info_thread_clks)",
+ "MetricGroup": "Core_Metric;Mem;MemoryTLB",
+ "MetricName": "tma_info_memory_tlb_page_walks_utilization",
+ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores",
+ "MetricExpr": "MEM_INST_RETIRED.STLB_MISS_STORES * cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@R / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Retired;Mem;MemoryTLB",
+ "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret",
+ "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
+ "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
+ "MetricGroup": "Mem;MemoryTLB;Metric",
+ "MetricName": "tma_info_memory_tlb_store_stlb_mpki",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average number of uops fetched from DSB per cycle",
+ "MetricExpr": "IDQ.DSB_UOPS / IDQ.DSB_CYCLES_ANY",
+ "MetricGroup": "Fed;FetchBW;Metric",
+ "MetricName": "tma_info_pipeline_fetch_dsb",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average number of uops fetched from LSD per cycle",
+ "MetricExpr": "LSD.UOPS / LSD.CYCLES_ACTIVE",
+ "MetricGroup": "Fed;FetchBW;Metric",
+ "MetricName": "tma_info_pipeline_fetch_lsd",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average number of uops fetched from MITE per cycle",
+ "MetricExpr": "IDQ.MITE_UOPS / IDQ.MITE_CYCLES_ANY",
+ "MetricGroup": "Fed;FetchBW;Metric",
+ "MetricName": "tma_info_pipeline_fetch_mite",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions per a microcode Assist invocation",
+ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
+ "MetricGroup": "Inst_Metric;MicroSeq;Pipeline;Ret;Retire",
+ "MetricName": "tma_info_pipeline_ipassist",
+ "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+ "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
+ "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+ "MetricGroup": "Metric;Pipeline;Ret",
+ "MetricName": "tma_info_pipeline_retire",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
+ "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+ "MetricGroup": "Metric;MicroSeq;Pipeline;Ret",
+ "MetricName": "tma_info_pipeline_strings_cycles",
+ "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of time that the core is stalled due to a TPAUSE or UMWAIT instruction",
+ "MetricExpr": "100 * cpu_atom@SERIALIZATION.C01_MS_SCB@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricName": "tma_info_serialization _%_tpause_cycles",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fraction of cycles the processor is waiting yet unhalted; covering legacy PAUSE instruction, as well as C0.1 / C0.2 power-performance optimized states",
+ "MetricExpr": "CPU_CLK_UNHALTED.C0_WAIT / tma_info_thread_clks",
+ "MetricGroup": "C0Wait;Metric",
+ "MetricName": "tma_info_system_c0_wait",
+ "MetricThreshold": "tma_info_system_c0_wait > 0.05",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
+ "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
+ "MetricGroup": "Power;Summary;System_Metric",
+ "MetricName": "tma_info_system_core_frequency",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average CPU Utilization (percentage)",
+ "MetricExpr": "tma_info_system_cpus_utilized / #num_cpus_online",
+ "MetricGroup": "HPC;Metric;Summary",
+ "MetricName": "tma_info_system_cpu_utilization",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average number of utilized CPUs",
+ "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+ "MetricGroup": "Metric;Summary",
+ "MetricName": "tma_info_system_cpus_utilized",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Giga Floating Point Operations Per Second",
+ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / tma_info_system_time",
+ "MetricGroup": "Flops",
+ "MetricName": "tma_info_system_gflops",
+ "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width",
+ "Unit": "cpu_atom"
+ },
+ {
+ "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;Inst_Metric;OS",
+ "MetricName": "tma_info_system_ipfarbranch",
+ "MetricThreshold": "tma_info_system_ipfarbranch < 1000000",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+ "MetricGroup": "Metric;OS",
+ "MetricName": "tma_info_system_kernel_cpi",
+ "ScaleUnit": "1per_instr",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
+ "MetricGroup": "Summary",
+ "MetricName": "tma_info_system_kernel_utilization",
+ "MetricThreshold": "tma_info_system_kernel_utilization > 0.05",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+ "MetricGroup": "Clocks;Summary",
+ "MetricName": "tma_info_system_mux",
+ "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total package Power in Watts",
+ "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)",
+ "MetricGroup": "Power;SoC;System_Metric",
+ "MetricName": "tma_info_system_power",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Run duration time in seconds",
+ "MetricExpr": "duration_time",
+ "MetricGroup": "Seconds;Summary",
+ "MetricName": "tma_info_system_time",
+ "MetricThreshold": "tma_info_system_time < 1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+ "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
+ "MetricGroup": "Power",
+ "MetricName": "tma_info_system_turbo_utilization",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "MetricGroup": "Count;Pipeline",
+ "MetricName": "tma_info_thread_clks",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
+ "MetricExpr": "1 / tma_info_thread_ipc",
+ "MetricGroup": "Mem;Metric;Pipeline",
+ "MetricName": "tma_info_thread_cpi",
+ "ScaleUnit": "1per_instr",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "The ratio of Executed- by Issued-Uops",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
+ "MetricGroup": "Cor;Metric;Pipeline",
+ "MetricName": "tma_info_thread_execute_per_issue",
+ "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
+ "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks",
+ "MetricGroup": "Metric;Ret;Summary",
+ "MetricName": "tma_info_thread_ipc",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
+ "MetricExpr": "slots",
+ "MetricGroup": "Count;TmaL1;TopdownL1;tma_L1_group",
+ "MetricName": "tma_info_thread_slots",
+ "MetricgroupNoGroup": "TopdownL1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Uops Per Instruction",
+ "MetricExpr": "tma_retiring * tma_info_thread_slots / INST_RETIRED.ANY",
+ "MetricGroup": "Metric;Pipeline;Ret;Retire",
+ "MetricName": "tma_info_thread_uoppi",
+ "MetricThreshold": "tma_info_thread_uoppi > 1.05",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Uops per taken branch",
+ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
+ "MetricGroup": "Branches;Fed;FetchBW;Metric",
+ "MetricName": "tma_info_thread_uptb",
+ "MetricThreshold": "tma_info_thread_uptb < 8 * 1.5",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of all uops which are FPDiv uops",
+ "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.FPDIV@ / cpu_atom@TOPDOWN_RETIRING.ALL@",
+ "MetricName": "tma_info_uop_mix_fpdiv_uop_ratio",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of all uops which are IDiv uops",
+ "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.IDIV@ / cpu_atom@TOPDOWN_RETIRING.ALL@",
+ "MetricName": "tma_info_uop_mix_idiv_uop_ratio",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of all uops which are microcode ops",
+ "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.MS@ / cpu_atom@TOPDOWN_RETIRING.ALL@",
+ "MetricName": "tma_info_uop_mix_microcode_uop_ratio",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Percentage of all uops which are x87 uops",
+ "MetricExpr": "100 * cpu_atom@UOPS_RETIRED.X87@ / cpu_atom@TOPDOWN_RETIRING.ALL@",
+ "MetricName": "tma_info_uop_mix_x87_uop_ratio",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+ "MetricExpr": "tma_divider - tma_fp_divider",
+ "MetricGroup": "Clocks;TopdownL4;tma_L4_group;tma_divider_group",
+ "MetricName": "tma_int_divider",
+ "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)",
+ "MetricExpr": "tma_int_vector_128b + tma_int_vector_256b",
+ "MetricGroup": "Pipeline;TopdownL3;Uops;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_int_operations",
+ "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired",
+ "MetricExpr": "INT_VEC_RETIRED.128BIT / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;Uops;tma_L4_group;tma_int_operations_group;tma_issue2P",
+ "MetricName": "tma_int_vector_128b",
+ "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired",
+ "MetricExpr": "INT_VEC_RETIRED.256BIT / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;Uops;tma_L4_group;tma_int_operations_group;tma_issue2P",
+ "MetricName": "tma_int_vector_256b",
+ "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
+ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_latency_group",
+ "MetricName": "tma_itlb_misses",
+ "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache",
+ "MetricExpr": "MEMORY_STALLS.L1 / tma_info_thread_clks",
+ "MetricGroup": "CacheHits;MemoryBound;Stalls;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
+ "MetricName": "tma_l1_bound",
+ "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D 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 L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache",
+ "MetricExpr": "(min(MEM_LOAD_RETIRED.L1_HIT_L1 * cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@R, MEM_LOAD_RETIRED.L1_HIT_L1 * 9) if 0 < cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@R else MEM_LOAD_RETIRED.L1_HIT_L1 * 9) / tma_info_thread_clks",
+ "MetricGroup": "BvML;Clocks_Retired;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
+ "MetricName": "tma_l1_latency_capacity",
+ "MetricThreshold": "tma_l1_latency_capacity > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache",
+ "MetricExpr": "4 * DEPENDENT_LOADS.ANY / tma_info_thread_clks",
+ "MetricGroup": "BvML;Clocks_Estimated;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
+ "MetricName": "tma_l1_latency_dependency",
+ "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: DEPENDENT_LOADS.ANY",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
+ "MetricExpr": "MEMORY_STALLS.L2 / tma_info_thread_clks",
+ "MetricGroup": "BvML;CacheHits;MemoryBound;Stalls;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
+ "MetricName": "tma_l2_bound",
+ "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
+ "MetricExpr": "(min(MEM_LOAD_RETIRED.L2_HIT * cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, MEM_LOAD_RETIRED.L2_HIT * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@MEM_LOAD_RETIRED.L2_HIT@R else MEM_LOAD_RETIRED.L2_HIT * (3 * tma_info_system_core_frequency)) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Retired;MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
+ "MetricName": "tma_l2_hit_latency",
+ "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+ "MetricExpr": "MEMORY_STALLS.L3 / tma_info_thread_clks",
+ "MetricGroup": "CacheHits;MemoryBound;Stalls;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
+ "MetricName": "tma_l3_bound",
+ "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
+ "MetricExpr": "(min(MEM_LOAD_RETIRED.L3_HIT * cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, MEM_LOAD_RETIRED.L3_HIT * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@MEM_LOAD_RETIRED.L3_HIT@R else MEM_LOAD_RETIRED.L3_HIT * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricGroup": "BvML;Clocks_Estimated;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group;tma_overlap",
+ "MetricName": "tma_l3_hit_latency",
+ "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)",
+ "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
+ "MetricGroup": "Clocks;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
+ "MetricName": "tma_lcp",
+ "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "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)",
+ "DefaultMetricgroupName": "TopdownL2",
+ "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
+ "MetricGroup": "Default;Retire;Slots;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
+ "MetricName": "tma_light_operations",
+ "MetricThreshold": "tma_light_operations > 0.6",
+ "MetricgroupNoGroup": "TopdownL2;Default",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code 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. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations",
+ "MetricExpr": "UOPS_DISPATCHED.LOAD / (3 * tma_info_thread_clks)",
+ "MetricGroup": "Core_Execution;TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
+ "MetricName": "tma_load_op_utilization",
+ "MetricThreshold": "tma_load_op_utilization > 0.6",
+ "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.LOAD",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)",
+ "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)",
+ "MetricGroup": "Clocks_Estimated;MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
+ "MetricName": "tma_load_stlb_hit",
+ "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk",
+ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Calculated;MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
+ "MetricName": "tma_load_stlb_miss",
+ "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+ "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "Clocks_Estimated;MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+ "MetricName": "tma_load_stlb_miss_1g",
+ "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+ "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "Clocks_Estimated;MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+ "MetricName": "tma_load_stlb_miss_2m",
+ "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+ "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "Clocks_Estimated;MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+ "MetricName": "tma_load_stlb_miss_4k",
+ "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
+ "MetricExpr": "MEM_INST_RETIRED.LOCK_LOADS * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks",
+ "MetricGroup": "Clocks;LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
+ "MetricName": "tma_lock_latency",
+ "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit",
+ "MetricExpr": "cpu@LSD.UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks",
+ "MetricGroup": "FetchBW;LSD;Slots_Estimated;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
+ "MetricName": "tma_lsd",
+ "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
+ "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears",
+ "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)",
+ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group",
+ "MetricName": "tma_machine_clears",
+ "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
+ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+ "MetricGroup": "BvMB;Clocks;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+ "MetricName": "tma_mem_bandwidth",
+ "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM)",
+ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
+ "MetricGroup": "BvML;Clocks;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
+ "MetricName": "tma_mem_latency",
+ "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops",
+ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
+ "MetricName": "tma_mem_scheduler",
+ "MetricThreshold": "(tma_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
+ "DefaultMetricgroupName": "TopdownL2",
+ "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "Backend;Default;Slots;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
+ "MetricName": "tma_memory_bound",
+ "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricgroupNoGroup": "TopdownL2;Default",
+ "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%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+ "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+ "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
+ "MetricGroup": "Clocks;TopdownL4;tma_L4_group;tma_serializing_operation_group",
+ "MetricName": "tma_memory_fence",
+ "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+ "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Pipeline;Slots;TopdownL3;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_memory_operations",
+ "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit",
+ "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots",
+ "MetricGroup": "MicroSeq;Slots;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
+ "MetricName": "tma_microcode_sequencer",
+ "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+ "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage",
+ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
+ "MetricGroup": "BadSpec;BrMispredicts;BvMP;Clocks;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
+ "MetricName": "tma_mispredicts_resteers",
+ "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)",
+ "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks + IDQ.MITE_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS) * (IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE - IDQ_BUBBLES.FETCH_LATENCY)) / tma_info_thread_clks",
+ "MetricGroup": "DSBmiss;FetchBW;Slots_Estimated;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
+ "MetricName": "tma_mite",
+ "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+ "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+ "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks",
+ "MetricGroup": "Clocks;TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
+ "MetricName": "tma_mixing_vectors",
+ "MetricThreshold": "tma_mixing_vectors > 0.05",
+ "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
+ "MetricExpr": "IDQ.MS_CYCLES_ANY / tma_info_thread_clks",
+ "MetricGroup": "MicroSeq;Slots_Estimated;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
+ "MetricName": "tma_ms",
+ "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
+ "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Estimated;FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
+ "MetricName": "tma_ms_switches",
+ "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused",
+ "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.BR_FUSED) / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Branches;BvBO;Pipeline;Slots;TopdownL3;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_non_fused_branches",
+ "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops",
+ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
+ "MetricName": "tma_non_mem_scheduler",
+ "MetricThreshold": "(tma_non_mem_scheduler >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions",
+ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "BvBO;Pipeline;Slots;TopdownL4;tma_L4_group;tma_other_light_ops_group",
+ "MetricName": "tma_nop_instructions",
+ "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear that requires the use of microcode (slow nuke)",
+ "MetricExpr": "cpu_atom@TOPDOWN_BAD_SPECULATION.NUKE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group",
+ "MetricName": "tma_nuke",
+ "MetricThreshold": "(tma_nuke >0.05) & ((tma_machine_clears >0.05) & ((tma_bad_speculation >0.15)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.",
+ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.OTHER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+ "MetricName": "tma_other_fb",
+ "MetricThreshold": "(tma_other_fb >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes",
+ "MetricExpr": "max(0, tma_light_operations - (tma_x87_use + (FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (tma_retiring * tma_info_thread_slots) + (INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128 + INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots) + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))",
+ "MetricGroup": "Pipeline;Slots;TopdownL3;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_other_light_ops",
+ "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+ "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
+ "MetricGroup": "BrMispredicts;BvIO;Slots;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_other_mispredicts",
+ "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+ "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
+ "MetricGroup": "BvIO;Machine_Clears;Slots;TopdownL3;tma_L3_group;tma_machine_clears_group",
+ "MetricName": "tma_other_nukes",
+ "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults",
+ "MetricExpr": "99 * ASSISTS.PAGE_FAULT / tma_info_thread_slots",
+ "MetricGroup": "Slots_Estimated;TopdownL5;tma_L5_group;tma_assists_group",
+ "MetricName": "tma_page_faults",
+ "MetricThreshold": "tma_page_faults > 0.05",
+ "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)",
+ "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)",
+ "MetricGroup": "Clocks;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
+ "MetricName": "tma_ports_utilization",
+ "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "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": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks",
+ "MetricGroup": "Clocks;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
+ "MetricName": "tma_ports_utilized_0",
+ "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
+ "MetricGroup": "Clocks;PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
+ "MetricName": "tma_ports_utilized_1",
+ "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "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)",
+ "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
+ "MetricGroup": "Clocks;PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
+ "MetricName": "tma_ports_utilized_2",
+ "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "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)",
+ "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
+ "MetricGroup": "BvCB;Clocks;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
+ "MetricName": "tma_ports_utilized_3m",
+ "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.",
+ "MetricExpr": "cpu_atom@TOPDOWN_FE_BOUND.PREDECODE@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_ifetch_bandwidth_group",
+ "MetricName": "tma_predecode",
+ "MetricThreshold": "(tma_predecode >0.05) & ((tma_ifetch_bandwidth >0.10) & ((tma_frontend_bound >0.20)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls)",
+ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REGISTER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
+ "MetricName": "tma_register",
+ "MetricThreshold": "(tma_register >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls)",
+ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.REORDER_BUFFER@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
+ "MetricName": "tma_reorder_buffer",
+ "MetricThreshold": "(tma_reorder_buffer >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the core is stalled due to a resource limitation",
+ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.ALL_P@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@) - tma_core_bound",
+ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group",
+ "MetricName": "tma_resource_bound",
+ "MetricThreshold": "(tma_resource_bound >0.20) & ((tma_backend_bound >0.10))",
+ "MetricgroupNoGroup": "TopdownL2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions",
+ "MetricExpr": "BR_MISP_RETIRED.RET_COST * cpu_core@BR_MISP_RETIRED.RET_COST@R / tma_info_thread_clks",
+ "MetricGroup": "BrMispredicts;Clocks_Retired;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_ret_mispredicts",
+ "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "TopdownL1;tma_L1_group",
+ "MetricName": "tma_retiring",
+ "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+ "MetricgroupNoGroup": "TopdownL1",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS)",
+ "MetricExpr": "cpu_atom@TOPDOWN_BE_BOUND.SERIALIZATION@ / (8 * cpu_atom@CPU_CLK_UNHALTED.CORE@)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group",
+ "MetricName": "tma_serialization",
+ "MetricThreshold": "(tma_serialization >0.10) & ((tma_resource_bound >0.20) & ((tma_backend_bound >0.10)))",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations",
+ "MetricExpr": "(BE_STALLS.SCOREBOARD + CPU_CLK_UNHALTED.C02) / tma_info_thread_clks",
+ "MetricGroup": "BvIO;Clocks;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
+ "MetricName": "tma_serializing_operation",
+ "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: BE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer)",
+ "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "HPC;Pipeline;Slots;TopdownL4;tma_L4_group;tma_other_light_ops_group",
+ "MetricName": "tma_shuffles_256b",
+ "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
+ "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+ "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
+ "MetricGroup": "Clocks;TopdownL4;tma_L4_group;tma_serializing_operation_group",
+ "MetricName": "tma_slow_pause",
+ "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary",
+ "MetricExpr": "(min(MEM_INST_RETIRED.SPLIT_LOADS * cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R, MEM_INST_RETIRED.SPLIT_LOADS * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R else MEM_INST_RETIRED.SPLIT_LOADS * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Calculated;TopdownL4;tma_L4_group;tma_l1_bound_group",
+ "MetricName": "tma_split_loads",
+ "MetricThreshold": "tma_split_loads > 0.3",
+ "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents rate of split store accesses",
+ "MetricExpr": "(min(MEM_INST_RETIRED.SPLIT_STORES * cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R, MEM_INST_RETIRED.SPLIT_STORES) if 0 < cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R else MEM_INST_RETIRED.SPLIT_STORES) / tma_info_thread_clks",
+ "MetricGroup": "Core_Utilization;TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
+ "MetricName": "tma_split_stores",
+ "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
+ "MetricExpr": "(XQ.FULL + L1D_MISS.L2_STALLS) / tma_info_thread_clks",
+ "MetricGroup": "BvMB;Clocks;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
+ "MetricName": "tma_sq_full",
+ "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write",
+ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
+ "MetricGroup": "MemoryBound;Stalls;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
+ "MetricName": "tma_store_bound",
+ "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "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 / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Estimated;TopdownL4;tma_L4_group;tma_l1_bound_group",
+ "MetricName": "tma_store_fwd_blk",
+ "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
+ "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
+ "MetricGroup": "BvML;Clocks_Estimated;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_overlap;tma_store_bound_group",
+ "MetricName": "tma_store_latency",
+ "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations",
+ "MetricExpr": "(UOPS_DISPATCHED.STD + UOPS_DISPATCHED.STA) / (7 * tma_info_thread_clks)",
+ "MetricGroup": "Core_Execution;TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
+ "MetricName": "tma_store_op_utilization",
+ "MetricThreshold": "tma_store_op_utilization > 0.6",
+ "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.STD, UOPS_DISPATCHED.STA",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)",
+ "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)",
+ "MetricGroup": "Clocks_Estimated;MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
+ "MetricName": "tma_store_stlb_hit",
+ "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk",
+ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Calculated;MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
+ "MetricName": "tma_store_stlb_miss",
+ "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+ "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "Clocks_Estimated;MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+ "MetricName": "tma_store_stlb_miss_1g",
+ "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+ "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "Clocks_Estimated;MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+ "MetricName": "tma_store_stlb_miss_2m",
+ "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+ "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "Clocks_Estimated;MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+ "MetricName": "tma_store_stlb_miss_4k",
+ "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores",
+ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
+ "MetricGroup": "Clocks_Estimated;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
+ "MetricName": "tma_streaming_stores",
+ "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears",
+ "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
+ "MetricGroup": "BigFootprint;BvBC;Clocks;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
+ "MetricName": "tma_unknown_branches",
+ "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric serves as an approximation of legacy x87 usage",
+ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
+ "MetricGroup": "Compute;TopdownL4;Uops;tma_L4_group;tma_fp_arith_group",
+ "MetricName": "tma_x87_use",
+ "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations",
+ "MetricExpr": "UOPS_DISPATCHED.ALU / (6 * tma_info_thread_clks)",
+ "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
+ "MetricName": "tma_alu_op_utilization",
+ "MetricThreshold": "tma_alu_op_utilization > 0.4",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists",
+ "MetricExpr": "78 * ASSISTS.ANY / tma_info_thread_slots",
+ "MetricGroup": "BvIO;TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
+ "MetricName": "tma_assists",
+ "MetricThreshold": "tma_assists > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+ "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists",
+ "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_thread_slots",
+ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
+ "MetricName": "tma_avx_assists",
+ "MetricThreshold": "tma_avx_assists > 0.1",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+ "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "BvOB;TmaL1;TopdownL1;tma_L1_group",
+ "MetricName": "tma_backend_bound",
+ "MetricThreshold": "tma_backend_bound > 0.2",
+ "MetricgroupNoGroup": "TopdownL1",
+ "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+ "MetricExpr": "topdown\\-bad\\-spec / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group",
+ "MetricName": "tma_bad_speculation",
+ "MetricThreshold": "tma_bad_speculation > 0.15",
+ "MetricgroupNoGroup": "TopdownL1",
+ "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%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
+ "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches)",
+ "MetricGroup": "BigFootprint;BvBC;Fed;Frontend;IcMiss;MemoryTLB",
+ "MetricName": "tma_bottleneck_big_code",
+ "MetricThreshold": "tma_bottleneck_big_code > 20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA",
+ "MetricExpr": "100 * ((BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots)",
+ "MetricGroup": "BvBO;Ret",
+ "MetricName": "tma_bottleneck_branching_overhead",
+ "MetricThreshold": "tma_bottleneck_branching_overhead > 5",
+ "PublicDescription": "Total pipeline cost of instructions used for program control-flow - a subset of the Retiring category in TMA. Examples include function calls; loops and alignments. (A lower bound)",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_fb_full / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)))",
+ "MetricGroup": "BvMB;Mem;MemoryBW;Offcore;tma_issueBW",
+ "MetricName": "tma_bottleneck_cache_memory_bandwidth",
+ "MetricThreshold": "tma_bottleneck_cache_memory_bandwidth > 20",
+ "PublicDescription": "Total pipeline cost of external Memory- or Cache-Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_dram_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_memory_bound * tma_l2_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_dependency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_l1_latency_capacity / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_lock_latency / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_loads / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_split_stores / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_store_latency / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+ "MetricGroup": "BvML;Mem;MemoryLat;Offcore;tma_issueLat",
+ "MetricName": "tma_bottleneck_cache_memory_latency",
+ "MetricThreshold": "tma_bottleneck_cache_memory_latency > 20",
+ "PublicDescription": "Total pipeline cost of external Memory- or Cache-Latency related bottlenecks. Related metrics: tma_l3_hit_latency, tma_mem_latency",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost when the execution is compute-bound - an estimation",
+ "MetricExpr": "100 * (tma_core_bound * tma_divider / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_core_bound * (tma_ports_utilization / (tma_divider + tma_serializing_operation + tma_ports_utilization)) * (tma_ports_utilized_3m / (tma_ports_utilized_0 + tma_ports_utilized_1 + tma_ports_utilized_2 + tma_ports_utilized_3m)))",
+ "MetricGroup": "BvCB;Cor;tma_issueComp",
+ "MetricName": "tma_bottleneck_compute_bound_est",
+ "MetricThreshold": "tma_bottleneck_compute_bound_est > 20",
+ "PublicDescription": "Total pipeline cost when the execution is compute-bound - an estimation. Covers Core Bound when High ILP as well as when long-latency execution units are busy",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks (when the front-end could not sustain operations delivery to the back-end)",
+ "MetricExpr": "100 * (tma_frontend_bound - (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) - (1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms))) - tma_bottleneck_big_code",
+ "MetricGroup": "BvFB;Fed;FetchBW;Frontend",
+ "MetricName": "tma_bottleneck_instruction_fetch_bw",
+ "MetricThreshold": "tma_bottleneck_instruction_fetch_bw > 20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of irregular execution (e.g",
+ "MetricExpr": "100 * ((1 - INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.MS\\,cmask\\=0x1@) * (tma_fetch_latency * (tma_ms_switches + tma_branch_resteers * (tma_clears_resteers + tma_mispredicts_resteers * tma_other_mispredicts / tma_branch_mispredicts) / (tma_mispredicts_resteers + tma_clears_resteers + tma_unknown_branches)) / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_ms / (tma_mite + tma_dsb + tma_lsd + tma_ms)) + 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts * tma_branch_mispredicts + tma_machine_clears * tma_other_nukes / tma_other_nukes + tma_core_bound * (tma_serializing_operation + RS.EMPTY_RESOURCE / tma_info_thread_clks * tma_ports_utilized_0) / (tma_divider + tma_serializing_operation + tma_ports_utilization) + tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+ "MetricGroup": "Bad;BvIO;Cor;Ret;tma_issueMS",
+ "MetricName": "tma_bottleneck_irregular_overhead",
+ "MetricThreshold": "tma_bottleneck_irregular_overhead > 10",
+ "PublicDescription": "Total pipeline cost of irregular execution (e.g. FP-assists in HPC, Wait time with work imbalance multithreaded workloads, overhead in system services or virtualized environments). Related metrics: tma_microcode_sequencer, tma_ms_switches",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_l1_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_load / (tma_dtlb_load + tma_store_fwd_blk + tma_l1_latency_dependency + tma_l1_latency_capacity + tma_lock_latency + tma_split_loads + tma_fb_full)) + tma_memory_bound * (tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound)) * (tma_dtlb_store / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store)))",
+ "MetricGroup": "BvMT;Mem;MemoryTLB;Offcore;tma_issueTLB",
+ "MetricName": "tma_bottleneck_memory_data_tlbs",
+ "MetricThreshold": "tma_bottleneck_memory_data_tlbs > 20",
+ "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors)",
+ "MetricExpr": "100 * (tma_memory_bound * (tma_l3_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * (tma_contested_accesses + tma_data_sharing) / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full) + tma_store_bound / (tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound + tma_store_bound) * tma_false_sharing / (tma_store_latency + tma_false_sharing + tma_split_stores + tma_streaming_stores + tma_dtlb_store - tma_store_latency)) + tma_machine_clears * (1 - tma_other_nukes / tma_other_nukes))",
+ "MetricGroup": "BvMS;LockCont;Mem;Offcore;tma_issueSyncxn",
+ "MetricName": "tma_bottleneck_memory_synchronization",
+ "MetricThreshold": "tma_bottleneck_memory_synchronization > 10",
+ "PublicDescription": "Total pipeline cost of Memory Synchronization related bottlenecks (data transfers and coherency updates across processors). Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks",
+ "MetricExpr": "100 * (1 - 10 * tma_microcode_sequencer * tma_other_mispredicts / tma_branch_mispredicts) * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+ "MetricGroup": "Bad;BadSpec;BrMispredicts;BvMP;tma_issueBM",
+ "MetricName": "tma_bottleneck_mispredictions",
+ "MetricThreshold": "tma_bottleneck_mispredictions > 20",
+ "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of remaining bottlenecks in the back-end",
+ "MetricExpr": "100 - (tma_bottleneck_big_code + tma_bottleneck_instruction_fetch_bw + tma_bottleneck_mispredictions + tma_bottleneck_cache_memory_bandwidth + tma_bottleneck_cache_memory_latency + tma_bottleneck_memory_data_tlbs + tma_bottleneck_memory_synchronization + tma_bottleneck_compute_bound_est + tma_bottleneck_irregular_overhead + tma_bottleneck_branching_overhead + tma_bottleneck_useful_work)",
+ "MetricGroup": "BvOB;Cor;Offcore",
+ "MetricName": "tma_bottleneck_other_bottlenecks",
+ "MetricThreshold": "tma_bottleneck_other_bottlenecks > 20",
+ "PublicDescription": "Total pipeline cost of remaining bottlenecks in the back-end. Examples include data-dependencies (Core Bound when Low ILP) and other unlisted memory-related stalls",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of \"useful operations\" - the portion of Retiring category not covered by Branching_Overhead nor Irregular_Overhead",
+ "MetricExpr": "100 * (tma_retiring - (BR_INST_RETIRED.ALL_BRANCHES + 2 * BR_INST_RETIRED.NEAR_CALL + INST_RETIRED.NOP) / tma_info_thread_slots - tma_microcode_sequencer / (tma_microcode_sequencer + tma_few_uops_instructions) * (tma_assists / tma_microcode_sequencer) * tma_heavy_operations)",
+ "MetricGroup": "BvUW;Ret",
+ "MetricName": "tma_bottleneck_useful_work",
+ "MetricThreshold": "tma_bottleneck_useful_work > 20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction",
+ "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "BadSpec;BrMispredicts;BvMP;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM",
+ "MetricName": "tma_branch_mispredicts",
+ "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_bottleneck_mispredictions, tma_info_bad_spec_branch_misprediction_cost, tma_mispredicts_resteers",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers",
+ "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks + tma_unknown_branches",
+ "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group",
+ "MetricName": "tma_branch_resteers",
+ "MetricThreshold": "tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_l3_hit_latency, tma_store_latency",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.1 power-performance optimized state (Faster wakeup time; Smaller power savings)",
+ "MetricExpr": "CPU_CLK_UNHALTED.C01 / tma_info_thread_clks",
+ "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
+ "MetricName": "tma_c01_wait",
+ "MetricThreshold": "tma_c01_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due staying in C0.2 power-performance optimized state (Slower wakeup time; Larger power savings)",
+ "MetricExpr": "CPU_CLK_UNHALTED.C02 / tma_info_thread_clks",
+ "MetricGroup": "C0Wait;TopdownL4;tma_L4_group;tma_serializing_operation_group",
+ "MetricName": "tma_c02_wait",
+ "MetricThreshold": "tma_c02_wait > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction",
+ "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)",
+ "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group",
+ "MetricName": "tma_cisc",
+ "MetricThreshold": "tma_cisc > 0.1 & tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+ "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears",
+ "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
+ "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC",
+ "MetricName": "tma_clears_resteers",
+ "MetricThreshold": "tma_clears_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that hit in the L2 cache",
+ "MetricExpr": "max(0, FRONTEND_RETIRED.L1I_MISS * cpu_core@FRONTEND_RETIRED.L1I_MISS@R / tma_info_thread_clks - tma_code_l2_miss)",
+ "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
+ "MetricName": "tma_code_l2_hit",
+ "MetricThreshold": "tma_code_l2_hit > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU was stalled due to instruction cache misses that miss in the L2 cache",
+ "MetricExpr": "FRONTEND_RETIRED.L2_MISS * cpu_core@FRONTEND_RETIRED.L2_MISS@R / tma_info_thread_clks",
+ "MetricGroup": "FetchLat;IcMiss;Offcore;TopdownL4;tma_L4_group;tma_icache_misses_group",
+ "MetricName": "tma_code_l2_miss",
+ "MetricThreshold": "tma_code_l2_miss > 0.05 & tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
+ "MetricExpr": "max(0, FRONTEND_RETIRED.ITLB_MISS * cpu_core@FRONTEND_RETIRED.ITLB_MISS@R / tma_info_thread_clks - tma_code_stlb_miss)",
+ "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
+ "MetricName": "tma_code_stlb_hit",
+ "MetricThreshold": "tma_code_stlb_hit > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
+ "MetricExpr": "FRONTEND_RETIRED.STLB_MISS * cpu_core@FRONTEND_RETIRED.STLB_MISS@R / tma_info_thread_clks",
+ "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
+ "MetricName": "tma_code_stlb_miss",
+ "MetricThreshold": "tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for (instruction) code accesses",
+ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_2M_4M / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
+ "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
+ "MetricName": "tma_code_stlb_miss_2m",
+ "MetricThreshold": "tma_code_stlb_miss_2m > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for (instruction) code accesses",
+ "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks * ITLB_MISSES.WALK_COMPLETED_4K / (ITLB_MISSES.WALK_COMPLETED_4K + ITLB_MISSES.WALK_COMPLETED_2M_4M)",
+ "MetricGroup": "FetchLat;MemoryTLB;TopdownL5;tma_L5_group;tma_code_stlb_miss_group",
+ "MetricName": "tma_code_stlb_miss_4k",
+ "MetricThreshold": "tma_code_stlb_miss_4k > 0.05 & tma_code_stlb_miss > 0.05 & tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by non-taken conditional branches",
+ "MetricExpr": "BR_MISP_RETIRED.COND_NTAKEN_COST * cpu_core@BR_MISP_RETIRED.COND_NTAKEN_COST@R / tma_info_thread_clks",
+ "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_cond_nt_mispredicts",
+ "MetricThreshold": "tma_cond_nt_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by backward-taken conditional branches",
+ "MetricExpr": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST * cpu_core@BR_MISP_RETIRED.COND_TAKEN_BWD_COST@R / tma_info_thread_clks",
+ "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_cond_tk_bwd_mispredicts",
+ "MetricThreshold": "tma_cond_tk_bwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to misprediction by forward-taken conditional branches",
+ "MetricExpr": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST * cpu_core@BR_MISP_RETIRED.COND_TAKEN_FWD_COST@R / tma_info_thread_clks",
+ "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_cond_tk_fwd_mispredicts",
+ "MetricThreshold": "tma_cond_tk_fwd_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses",
+ "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS@R else MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R, MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM@R else MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+ "MetricName": "tma_contested_accesses",
+ "MetricThreshold": "tma_contested_accesses > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD, MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_bottleneck_memory_synchronization, tma_data_sharing, tma_false_sharing, tma_machine_clears",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck",
+ "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)",
+ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
+ "MetricName": "tma_core_bound",
+ "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations)",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses",
+ "MetricExpr": "((min(MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R, MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD@R else MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD * (27 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) + (min(MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R, MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD@R else MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (28 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency)) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricGroup": "BvMS;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group",
+ "MetricName": "tma_data_sharing",
+ "MetricThreshold": "tma_data_sharing > 0.05 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_false_sharing, tma_machine_clears",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active",
+ "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_thread_clks",
+ "MetricGroup": "BvCB;TopdownL3;tma_L3_group;tma_core_bound_group",
+ "MetricName": "tma_divider",
+ "MetricThreshold": "tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIV_ACTIVE",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
+ "MetricExpr": "MEMORY_STALLS.MEM / tma_info_thread_clks",
+ "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
+ "MetricName": "tma_dram_bound",
+ "MetricThreshold": "tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline",
+ "MetricExpr": "(cpu@IDQ.DSB_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ + IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS) * (IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE - IDQ_BUBBLES.FETCH_LATENCY)) / tma_info_thread_clks",
+ "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
+ "MetricName": "tma_dsb",
+ "MetricThreshold": "tma_dsb > 0.15 & tma_fetch_bandwidth > 0.2",
+ "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%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines",
+ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_thread_clks",
+ "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
+ "MetricName": "tma_dsb_switches",
+ "MetricThreshold": "tma_dsb_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS. Related metrics: tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses",
+ "MetricExpr": "(min(MEM_INST_RETIRED.STLB_HIT_LOADS * cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R, MEM_INST_RETIRED.STLB_HIT_LOADS * 7) if 0 < cpu_core@MEM_INST_RETIRED.STLB_HIT_LOADS@R else MEM_INST_RETIRED.STLB_HIT_LOADS * 7) / tma_info_thread_clks + tma_load_stlb_miss",
+ "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group",
+ "MetricName": "tma_dtlb_load",
+ "MetricThreshold": "tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_store",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses",
+ "MetricExpr": "(min(MEM_INST_RETIRED.STLB_HIT_STORES * cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R, MEM_INST_RETIRED.STLB_HIT_STORES * 7) if 0 < cpu_core@MEM_INST_RETIRED.STLB_HIT_STORES@R else MEM_INST_RETIRED.STLB_HIT_STORES * 7) / tma_info_thread_clks + tma_store_stlb_miss",
+ "MetricGroup": "BvMT;MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group",
+ "MetricName": "tma_dtlb_store",
+ "MetricThreshold": "tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES. Related metrics: tma_bottleneck_memory_data_tlbs, tma_dtlb_load",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing",
+ "MetricExpr": "28 * tma_info_system_core_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_thread_clks",
+ "MetricGroup": "BvMS;DataSharing;LockCont;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group",
+ "MetricName": "tma_false_sharing",
+ "MetricThreshold": "tma_false_sharing > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_bottleneck_memory_synchronization, tma_contested_accesses, tma_data_sharing, tma_machine_clears",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed",
+ "MetricExpr": "L1D_MISS.FB_FULL / tma_info_thread_clks",
+ "MetricGroup": "BvMB;MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group",
+ "MetricName": "tma_fb_full",
+ "MetricThreshold": "tma_fb_full > 0.3",
+ "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues",
+ "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)",
+ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB",
+ "MetricName": "tma_fetch_bandwidth",
+ "MetricThreshold": "tma_fetch_bandwidth > 0.2",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues",
+ "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group",
+ "MetricName": "tma_fetch_latency",
+ "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16, FRONTEND_RETIRED.LATENCY_GE_8",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops",
+ "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)",
+ "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0",
+ "MetricName": "tma_few_uops_instructions",
+ "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or more uops. This highly-correlates with the number of uops in such instructions",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)",
+ "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector",
+ "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_fp_arith",
+ "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists",
+ "MetricExpr": "30 * ASSISTS.FP / tma_info_thread_slots",
+ "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group",
+ "MetricName": "tma_fp_assists",
+ "MetricThreshold": "tma_fp_assists > 0.1",
+ "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals)",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles where the Floating-Point Divider unit was active",
+ "MetricExpr": "ARITH.FPDIV_ACTIVE / tma_info_thread_clks",
+ "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
+ "MetricName": "tma_fp_divider",
+ "MetricThreshold": "tma_fp_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired",
+ "MetricExpr": "FP_ARITH_INST_RETIRED.SCALAR / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
+ "MetricName": "tma_fp_scalar",
+ "MetricThreshold": "tma_fp_scalar > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths",
+ "MetricExpr": "FP_ARITH_INST_RETIRED.VECTOR / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P",
+ "MetricName": "tma_fp_vector",
+ "MetricThreshold": "tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors",
+ "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
+ "MetricName": "tma_fp_vector_128b",
+ "MetricThreshold": "tma_fp_vector_128b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors",
+ "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.VECTOR\\,umask\\=0x30@ / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P",
+ "MetricName": "tma_fp_vector_256b",
+ "MetricThreshold": "tma_fp_vector_256b > 0.1 & tma_fp_vector > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting prior to LNL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_int_vector_128b, tma_int_vector_256b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+ "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "BvFB;BvIO;PGO;TmaL1;TopdownL1;tma_L1_group",
+ "MetricName": "tma_frontend_bound",
+ "MetricThreshold": "tma_frontend_bound > 0.15",
+ "MetricgroupNoGroup": "TopdownL1",
+ "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions",
+ "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_fused_instructions",
+ "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions , where one uop can represent multiple contiguous instructions. CMP+JCC or DEC+JCC are common examples of legacy fusions. {([MTL] Note new MOV+OP and Load+OP fusions appear under Other_Light_Ops in MTL!)}",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences",
+ "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
+ "MetricName": "tma_heavy_operations",
+ "MetricThreshold": "tma_heavy_operations > 0.1",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations , instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.([ICL+] Note this may overcount due to approximation using indirect events; [ADL+]). Sample with: UOPS_RETIRED.HEAVY",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses",
+ "MetricExpr": "ICACHE_DATA.STALLS / tma_info_thread_clks",
+ "MetricGroup": "BigFootprint;BvBC;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group",
+ "MetricName": "tma_icache_misses",
+ "MetricThreshold": "tma_icache_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS, FRONTEND_RETIRED.L1I_MISS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect CALL instructions",
+ "MetricExpr": "BR_MISP_RETIRED.INDIRECT_CALL_COST * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R / tma_info_thread_clks",
+ "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_ind_call_mispredicts",
+ "MetricThreshold": "tma_ind_call_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by indirect JMP instructions",
+ "MetricExpr": "max((BR_MISP_RETIRED.INDIRECT_COST * cpu_core@BR_MISP_RETIRED.INDIRECT_COST@R - BR_MISP_RETIRED.INDIRECT_CALL_COST * cpu_core@BR_MISP_RETIRED.INDIRECT_CALL_COST@R) / tma_info_thread_clks, 0)",
+ "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_ind_jump_mispredicts",
+ "MetricThreshold": "tma_ind_jump_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)",
+ "MetricExpr": "tma_bottleneck_mispredictions * tma_info_thread_slots / 8 / BR_MISP_RETIRED.ALL_BRANCHES / 100",
+ "MetricGroup": "Bad;BrMispredicts;tma_issueBM",
+ "MetricName": "tma_info_bad_spec_branch_misprediction_cost",
+ "PublicDescription": "Branch Misprediction Cost: Cycles representing fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_mispredicts_resteers",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per retired Mispredicts for conditional non-taken branches (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN",
+ "MetricGroup": "Bad;BrMispredicts",
+ "MetricName": "tma_info_bad_spec_ipmisp_cond_ntaken",
+ "MetricThreshold": "tma_info_bad_spec_ipmisp_cond_ntaken < 200",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per retired Mispredicts for conditional backward-taken branches (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN_BWD",
+ "MetricGroup": "Bad;BrMispredicts",
+ "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_bwd",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per retired Mispredicts for conditional forward-taken branches (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN_FWD",
+ "MetricGroup": "Bad;BrMispredicts",
+ "MetricName": "tma_info_bad_spec_ipmisp_cond_taken_fwd",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per retired Mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT",
+ "MetricGroup": "Bad;BrMispredicts",
+ "MetricName": "tma_info_bad_spec_ipmisp_indirect",
+ "MetricThreshold": "tma_info_bad_spec_ipmisp_indirect < 1000",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per retired Mispredicts for return branches (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET",
+ "MetricGroup": "Bad;BrMispredicts",
+ "MetricName": "tma_info_bad_spec_ipmisp_ret",
+ "MetricThreshold": "tma_info_bad_spec_ipmisp_ret < 500",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;BadSpec;BrMispredicts",
+ "MetricName": "tma_info_bad_spec_ipmispredict",
+ "MetricThreshold": "tma_info_bad_spec_ipmispredict < 200",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Speculative to Retired ratio of all clears (covering Mispredicts and nukes)",
+ "MetricExpr": "INT_MISC.CLEARS_COUNT / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)",
+ "MetricGroup": "BrMispredicts",
+ "MetricName": "tma_info_bad_spec_spec_clears_ratio",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck",
+ "MetricExpr": "100 * (tma_frontend_bound * (tma_fetch_bandwidth / (tma_fetch_latency + tma_fetch_bandwidth)) * (tma_dsb / (tma_mite + tma_dsb + tma_lsd + tma_ms)))",
+ "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
+ "MetricName": "tma_info_botlnk_l2_dsb_bandwidth",
+ "MetricThreshold": "tma_info_botlnk_l2_dsb_bandwidth > 10",
+ "PublicDescription": "Total pipeline cost of DSB (uop cache) hits - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck",
+ "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb + tma_lsd + tma_ms))",
+ "MetricGroup": "DSBmiss;Fed;tma_issueFB",
+ "MetricName": "tma_info_botlnk_l2_dsb_misses",
+ "MetricThreshold": "tma_info_botlnk_l2_dsb_misses > 10",
+ "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb, tma_lcp",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck",
+ "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_icache_misses + tma_itlb_misses + tma_branch_resteers + tma_ms_switches + tma_lcp + tma_dsb_switches))",
+ "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL",
+ "MetricName": "tma_info_botlnk_l2_ic_misses",
+ "MetricThreshold": "tma_info_botlnk_l2_ic_misses > 5",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fraction of branches that are CALL or RET",
+ "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;Branches",
+ "MetricName": "tma_info_branches_callret",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fraction of branches that are non-taken conditionals",
+ "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;Branches;CodeGen;PGO",
+ "MetricName": "tma_info_branches_cond_nt",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fraction of branches that are forward taken conditionals",
+ "MetricExpr": "BR_INST_RETIRED.COND_TAKEN_BWD / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;Branches;CodeGen;PGO",
+ "MetricName": "tma_info_branches_cond_tk_bwd",
+ "MetricThreshold": "tma_info_branches_cond_tk_bwd > 0.3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fraction of branches that are forward taken conditionals",
+ "MetricExpr": "BR_INST_RETIRED.COND_TAKEN_FWD / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;Branches;CodeGen;PGO",
+ "MetricName": "tma_info_branches_cond_tk_fwd",
+ "MetricThreshold": "tma_info_branches_cond_tk_fwd > 0.2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
+ "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN_BWD - BR_INST_RETIRED.COND_TAKEN_FWD - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;Branches",
+ "MetricName": "tma_info_branches_jump",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)",
+ "MetricExpr": "1 - (tma_info_branches_cond_nt + tma_info_branches_cond_tk_bwd + tma_info_branches_cond_tk_fwd + tma_info_branches_callret + tma_info_branches_jump)",
+ "MetricGroup": "Bad;Branches",
+ "MetricName": "tma_info_branches_other_branches",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "uops Executed per Cycle",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / tma_info_thread_clks",
+ "MetricGroup": "Power",
+ "MetricName": "tma_info_core_epc",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Floating Point Operations Per Cycle",
+ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_thread_clks",
+ "MetricGroup": "Flops;Ret",
+ "MetricName": "tma_info_core_flopc",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)",
+ "MetricExpr": "(FP_ARITH_DISPATCHED.V0 + FP_ARITH_DISPATCHED.V1 + FP_ARITH_DISPATCHED.V2 + FP_ARITH_DISPATCHED.V3) / (4 * tma_info_thread_clks)",
+ "MetricGroup": "Cor;Flops;HPC",
+ "MetricName": "tma_info_core_fp_arith_utilization",
+ "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per thread (logical-processor)",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=0x1@",
+ "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
+ "MetricName": "tma_info_core_ilp",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+ "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY",
+ "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB",
+ "MetricName": "tma_info_frontend_dsb_coverage",
+ "MetricThreshold": "tma_info_frontend_dsb_coverage < 0.7 & tma_info_thread_ipc / 8 > 0.35",
+ "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_inst_mix_iptb, tma_lcp",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details",
+ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+ "MetricGroup": "DSBmiss",
+ "MetricName": "tma_info_frontend_dsb_switch_cost",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired DSB misses",
+ "MetricExpr": "FRONTEND_RETIRED.ANY_DSB_MISS * cpu_core@FRONTEND_RETIRED.ANY_DSB_MISS@R / tma_info_thread_clks",
+ "MetricGroup": "DSBmiss;Fed;FetchLat",
+ "MetricName": "tma_info_frontend_dsb_switches_ret",
+ "MetricThreshold": "tma_info_frontend_dsb_switches_ret > 0.05",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average number of Uops issued by front-end when it issued something",
+ "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=0x1@",
+ "MetricGroup": "Fed;FetchBW",
+ "MetricName": "tma_info_frontend_fetch_upc",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average Latency for L1 instruction cache misses",
+ "MetricExpr": "ICACHE_DATA.STALLS / ICACHE_DATA.STALL_PERIODS",
+ "MetricGroup": "Fed;FetchLat;IcMiss",
+ "MetricName": "tma_info_frontend_icache_miss_latency",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
+ "MetricGroup": "DSBmiss;Fed",
+ "MetricName": "tma_info_frontend_ipdsb_miss_ret",
+ "MetricThreshold": "tma_info_frontend_ipdsb_miss_ret < 50",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)",
+ "MetricExpr": "tma_info_inst_mix_instructions / BACLEARS.ANY",
+ "MetricGroup": "Fed",
+ "MetricName": "tma_info_frontend_ipunknown_branch",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L2 cache true code cacheline misses per kilo instruction",
+ "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "IcMiss",
+ "MetricName": "tma_info_frontend_l2mpki_code",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction",
+ "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "IcMiss",
+ "MetricName": "tma_info_frontend_l2mpki_code_all",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
+ "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY",
+ "MetricGroup": "Fed;LSD",
+ "MetricName": "tma_info_frontend_lsd_coverage",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired operations that invoke the Microcode Sequencer",
+ "MetricExpr": "FRONTEND_RETIRED.MS_FLOWS * cpu_core@FRONTEND_RETIRED.MS_FLOWS@R / tma_info_thread_clks",
+ "MetricGroup": "Fed;FetchLat;MicroSeq",
+ "MetricName": "tma_info_frontend_ms_latency_ret",
+ "MetricThreshold": "tma_info_frontend_ms_latency_ret > 0.05",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Taken Branches retired Per Cycle",
+ "MetricExpr": "BR_INST_RETIRED.NEAR_TAKEN / tma_info_thread_clks",
+ "MetricGroup": "Branches;FetchBW",
+ "MetricName": "tma_info_frontend_tbpc",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection",
+ "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / cpu@INT_MISC.UNKNOWN_BRANCH_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@",
+ "MetricGroup": "Fed",
+ "MetricName": "tma_info_frontend_unknown_branch_cost",
+ "PublicDescription": "Average number of cycles the front-end was delayed due to an Unknown Branch detection. See Unknown_Branches node",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to retired branches who got branch address clears",
+ "MetricExpr": "FRONTEND_RETIRED.UNKNOWN_BRANCH * cpu_core@FRONTEND_RETIRED.UNKNOWN_BRANCH@R / tma_info_thread_clks",
+ "MetricGroup": "Fed;FetchLat",
+ "MetricName": "tma_info_frontend_unknown_branches_ret",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Branch instructions per taken branch",
+ "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+ "MetricGroup": "Branches;Fed;PGO",
+ "MetricName": "tma_info_inst_mix_bptkbranch",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total number of retired Instructions",
+ "MetricExpr": "INST_RETIRED.ANY",
+ "MetricGroup": "Summary;TmaL1;tma_L1_group",
+ "MetricName": "tma_info_inst_mix_instructions",
+ "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR)",
+ "MetricGroup": "Flops;InsType",
+ "MetricName": "tma_info_inst_mix_iparith",
+ "MetricThreshold": "tma_info_inst_mix_iparith < 10",
+ "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting. Approximated prior to BDW",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)",
+ "MetricGroup": "Flops;FpVector;InsType",
+ "MetricName": "tma_info_inst_mix_iparith_avx128",
+ "MetricThreshold": "tma_info_inst_mix_iparith_avx128 < 10",
+ "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)",
+ "MetricGroup": "Flops;FpVector;InsType",
+ "MetricName": "tma_info_inst_mix_iparith_avx256",
+ "MetricThreshold": "tma_info_inst_mix_iparith_avx256 < 10",
+ "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+ "MetricGroup": "Flops;FpScalar;InsType",
+ "MetricName": "tma_info_inst_mix_iparith_scalar_dp",
+ "MetricThreshold": "tma_info_inst_mix_iparith_scalar_dp < 10",
+ "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+ "MetricGroup": "Flops;FpScalar;InsType",
+ "MetricName": "tma_info_inst_mix_iparith_scalar_sp",
+ "MetricThreshold": "tma_info_inst_mix_iparith_scalar_sp < 10",
+ "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). Values < 1 are possible due to intentional FMA double counting",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Branches;Fed;InsType",
+ "MetricName": "tma_info_inst_mix_ipbranch",
+ "MetricThreshold": "tma_info_inst_mix_ipbranch < 8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+ "MetricGroup": "Branches;Fed;PGO",
+ "MetricName": "tma_info_inst_mix_ipcall",
+ "MetricThreshold": "tma_info_inst_mix_ipcall < 200",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)",
+ "MetricGroup": "Flops;InsType",
+ "MetricName": "tma_info_inst_mix_ipflop",
+ "MetricThreshold": "tma_info_inst_mix_ipflop < 10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+ "MetricGroup": "InsType",
+ "MetricName": "tma_info_inst_mix_ipload",
+ "MetricThreshold": "tma_info_inst_mix_ipload < 3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per PAUSE (lower number means higher occurrence rate)",
+ "MetricExpr": "tma_info_inst_mix_instructions / CPU_CLK_UNHALTED.PAUSE_INST",
+ "MetricGroup": "Flops;FpVector;InsType",
+ "MetricName": "tma_info_inst_mix_ippause",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+ "MetricGroup": "InsType",
+ "MetricName": "tma_info_inst_mix_ipstore",
+ "MetricThreshold": "tma_info_inst_mix_ipstore < 8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_SWPF",
+ "MetricGroup": "Prefetches",
+ "MetricName": "tma_info_inst_mix_ipswpf",
+ "MetricThreshold": "tma_info_inst_mix_ipswpf < 100",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per taken branch",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+ "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB",
+ "MetricName": "tma_info_inst_mix_iptb",
+ "MetricThreshold": "tma_info_inst_mix_iptb < 8 * 2 + 1",
+ "PublicDescription": "Instructions per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_lcp",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
+ "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem",
+ "MetricName": "tma_info_memory_fb_hpki",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / tma_info_system_time",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "tma_info_memory_l1d_cache_fill_bw",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the Level 0 within L1D cache [GB / sec]",
+ "MetricExpr": "64 * L1D.L0_REPLACEMENT / 1e9 / tma_info_system_time",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "tma_info_memory_l1dl0_cache_fill_bw",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+ "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem",
+ "MetricName": "tma_info_memory_l1mpki",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)",
+ "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem",
+ "MetricName": "tma_info_memory_l1mpki_load",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / tma_info_system_time",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "tma_info_memory_l2_cache_fill_bw",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+ "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem",
+ "MetricName": "tma_info_memory_l2hpki_all",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)",
+ "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem",
+ "MetricName": "tma_info_memory_l2hpki_load",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+ "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "Backend;CacheHits;Mem",
+ "MetricName": "tma_info_memory_l2mpki",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)",
+ "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem;Offcore",
+ "MetricName": "tma_info_memory_l2mpki_all",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)",
+ "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "CacheHits;Mem",
+ "MetricName": "tma_info_memory_l2mpki_load",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Offcore requests (L2 cache miss) per kilo instruction for demand RFOs",
+ "MetricExpr": "1e3 * L2_RQSTS.RFO_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "CacheMisses;Offcore",
+ "MetricName": "tma_info_memory_l2mpki_rfo",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
+ "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / tma_info_system_time",
+ "MetricGroup": "Mem;MemoryBW;Offcore",
+ "MetricName": "tma_info_memory_l3_cache_access_bw",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / tma_info_system_time",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "tma_info_memory_l3_cache_fill_bw",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+ "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+ "MetricGroup": "Mem",
+ "MetricName": "tma_info_memory_l3mpki",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average Parallel L2 cache miss data reads",
+ "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+ "MetricGroup": "Memory_BW;Offcore",
+ "MetricName": "tma_info_memory_latency_data_l2_mlp",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average Latency for L2 cache miss demand Loads",
+ "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
+ "MetricGroup": "LockCont;Memory_Lat;Offcore",
+ "MetricName": "tma_info_memory_latency_load_l2_miss_latency",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average Parallel L2 cache miss demand Loads",
+ "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
+ "MetricGroup": "Memory_BW;Offcore",
+ "MetricName": "tma_info_memory_latency_load_l2_mlp",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average Latency for L3 cache miss demand Loads",
+ "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+ "MetricGroup": "Memory_Lat;Offcore",
+ "MetricName": "tma_info_memory_latency_load_l3_miss_latency",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
+ "MetricExpr": "L1D_PENDING.LOAD / L1D_MISS.LOAD",
+ "MetricGroup": "Mem;MemoryBound;MemoryLat",
+ "MetricName": "tma_info_memory_load_miss_real_latency",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "\"Bus lock\" per kilo instruction",
+ "MetricExpr": "1e3 * SQ_MISC.BUS_LOCK / INST_RETIRED.ANY",
+ "MetricGroup": "Mem",
+ "MetricName": "tma_info_memory_mix_bus_lock_pki",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Un-cacheable retired load per kilo instruction",
+ "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY",
+ "MetricGroup": "Mem",
+ "MetricName": "tma_info_memory_mix_uc_load_pki",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss",
+ "MetricExpr": "L1D_PENDING.LOAD / L1D_PENDING.LOAD_CYCLES",
+ "MetricGroup": "Mem;MemoryBW;MemoryBound",
+ "MetricName": "tma_info_memory_mlp",
+ "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Rate of L2 HW prefetched lines that were not used by demand accesses",
+ "MetricExpr": "L2_LINES_OUT.USELESS_HWPF / (L2_LINES_OUT.SILENT + L2_LINES_OUT.NON_SILENT)",
+ "MetricGroup": "Prefetches",
+ "MetricName": "tma_info_memory_prefetches_useless_hwpf",
+ "MetricThreshold": "tma_info_memory_prefetches_useless_hwpf > 0.15",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
+ "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
+ "MetricGroup": "Fed;MemoryTLB",
+ "MetricName": "tma_info_memory_tlb_code_stlb_mpki",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand loads",
+ "MetricExpr": "MEM_INST_RETIRED.STLB_MISS_LOADS * cpu_core@MEM_INST_RETIRED.STLB_MISS_LOADS@R / tma_info_thread_clks",
+ "MetricGroup": "Mem;MemoryTLB",
+ "MetricName": "tma_info_memory_tlb_load_stlb_miss_ret",
+ "MetricThreshold": "tma_info_memory_tlb_load_stlb_miss_ret > 0.05",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
+ "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
+ "MetricGroup": "Mem;MemoryTLB",
+ "MetricName": "tma_info_memory_tlb_load_stlb_mpki",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+ "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * tma_info_thread_clks)",
+ "MetricGroup": "Mem;MemoryTLB",
+ "MetricName": "tma_info_memory_tlb_page_walks_utilization",
+ "MetricThreshold": "tma_info_memory_tlb_page_walks_utilization > 0.5",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU retirement was stalled likely due to STLB misses by demand stores",
+ "MetricExpr": "MEM_INST_RETIRED.STLB_MISS_STORES * cpu_core@MEM_INST_RETIRED.STLB_MISS_STORES@R / tma_info_thread_clks",
+ "MetricGroup": "Mem;MemoryTLB",
+ "MetricName": "tma_info_memory_tlb_store_stlb_miss_ret",
+ "MetricThreshold": "tma_info_memory_tlb_store_stlb_miss_ret > 0.05",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
+ "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY",
+ "MetricGroup": "Mem;MemoryTLB",
+ "MetricName": "tma_info_memory_tlb_store_stlb_mpki",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average number of uops fetched from DSB per cycle",
+ "MetricExpr": "IDQ.DSB_UOPS / IDQ.DSB_CYCLES_ANY",
+ "MetricGroup": "Fed;FetchBW",
+ "MetricName": "tma_info_pipeline_fetch_dsb",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average number of uops fetched from LSD per cycle",
+ "MetricExpr": "LSD.UOPS / LSD.CYCLES_ACTIVE",
+ "MetricGroup": "Fed;FetchBW",
+ "MetricName": "tma_info_pipeline_fetch_lsd",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average number of uops fetched from MITE per cycle",
+ "MetricExpr": "IDQ.MITE_UOPS / IDQ.MITE_CYCLES_ANY",
+ "MetricGroup": "Fed;FetchBW",
+ "MetricName": "tma_info_pipeline_fetch_mite",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per a microcode Assist invocation",
+ "MetricExpr": "INST_RETIRED.ANY / ASSISTS.ANY",
+ "MetricGroup": "MicroSeq;Pipeline;Ret;Retire",
+ "MetricName": "tma_info_pipeline_ipassist",
+ "MetricThreshold": "tma_info_pipeline_ipassist < 100000",
+ "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired",
+ "MetricExpr": "tma_retiring * tma_info_thread_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+ "MetricGroup": "Pipeline;Ret",
+ "MetricName": "tma_info_pipeline_retire",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions",
+ "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=0x1@",
+ "MetricGroup": "MicroSeq;Pipeline;Ret",
+ "MetricName": "tma_info_pipeline_strings_cycles",
+ "MetricThreshold": "tma_info_pipeline_strings_cycles > 0.1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fraction of cycles the processor is waiting yet unhalted; covering legacy PAUSE instruction, as well as C0.1 / C0.2 power-performance optimized states",
+ "MetricExpr": "CPU_CLK_UNHALTED.C0_WAIT / tma_info_thread_clks",
+ "MetricGroup": "C0Wait",
+ "MetricName": "tma_info_system_c0_wait",
+ "MetricThreshold": "tma_info_system_c0_wait > 0.05",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Measured Average Core Frequency for unhalted processors [GHz]",
+ "MetricExpr": "tma_info_system_turbo_utilization * TSC / 1e9 / tma_info_system_time",
+ "MetricGroup": "Power;Summary",
+ "MetricName": "tma_info_system_core_frequency",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average CPU Utilization (percentage)",
+ "MetricExpr": "tma_info_system_cpus_utilized / #num_cpus_online",
+ "MetricGroup": "HPC;Summary",
+ "MetricName": "tma_info_system_cpu_utilization",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average number of utilized CPUs",
+ "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC",
+ "MetricGroup": "Summary",
+ "MetricName": "tma_info_system_cpus_utilized",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Giga Floating Point Operations Per Second",
+ "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * FP_ARITH_INST_RETIRED.4_FLOPS + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / tma_info_system_time",
+ "MetricGroup": "Cor;Flops;HPC",
+ "MetricName": "tma_info_system_gflops",
+ "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
+ "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
+ "MetricGroup": "Branches;OS",
+ "MetricName": "tma_info_system_ipfarbranch",
+ "MetricThreshold": "tma_info_system_ipfarbranch < 1000000",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+ "MetricGroup": "OS",
+ "MetricName": "tma_info_system_kernel_cpi",
+ "ScaleUnit": "1per_instr",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
+ "MetricGroup": "OS",
+ "MetricName": "tma_info_system_kernel_utilization",
+ "MetricThreshold": "tma_info_system_kernel_utilization > 0.05",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "PerfMon Event Multiplexing accuracy indicator",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P / CPU_CLK_UNHALTED.THREAD",
+ "MetricGroup": "Summary",
+ "MetricName": "tma_info_system_mux",
+ "MetricThreshold": "tma_info_system_mux > 1.1 | tma_info_system_mux < 0.9",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total package Power in Watts",
+ "MetricExpr": "power@energy\\-pkg@ * 61 / (tma_info_system_time * 1e6)",
+ "MetricGroup": "Power;SoC",
+ "MetricName": "tma_info_system_power",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Run duration time in seconds",
+ "MetricExpr": "duration_time",
+ "MetricGroup": "Summary",
+ "MetricName": "tma_info_system_time",
+ "MetricThreshold": "tma_info_system_time < 1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+ "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC",
+ "MetricGroup": "Power",
+ "MetricName": "tma_info_system_turbo_utilization",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active",
+ "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+ "MetricGroup": "Pipeline",
+ "MetricName": "tma_info_thread_clks",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
+ "MetricExpr": "1 / tma_info_thread_ipc",
+ "MetricGroup": "Mem;Pipeline",
+ "MetricName": "tma_info_thread_cpi",
+ "ScaleUnit": "1per_instr",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "The ratio of Executed- by Issued-Uops",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
+ "MetricGroup": "Cor;Pipeline",
+ "MetricName": "tma_info_thread_execute_per_issue",
+ "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
+ "MetricExpr": "INST_RETIRED.ANY / tma_info_thread_clks",
+ "MetricGroup": "Ret;Summary",
+ "MetricName": "tma_info_thread_ipc",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
+ "MetricExpr": "slots",
+ "MetricGroup": "TmaL1;tma_L1_group",
+ "MetricName": "tma_info_thread_slots",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Uops Per Instruction",
+ "MetricExpr": "tma_retiring * tma_info_thread_slots / INST_RETIRED.ANY",
+ "MetricGroup": "Pipeline;Ret;Retire",
+ "MetricName": "tma_info_thread_uoppi",
+ "MetricThreshold": "tma_info_thread_uoppi > 1.05",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Uops per taken branch",
+ "MetricExpr": "tma_retiring * tma_info_thread_slots / BR_INST_RETIRED.NEAR_TAKEN",
+ "MetricGroup": "Branches;Fed;FetchBW",
+ "MetricName": "tma_info_thread_uptb",
+ "MetricThreshold": "tma_info_thread_uptb < 8 * 1.5",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles where the Integer Divider unit was active",
+ "MetricExpr": "tma_divider - tma_fp_divider",
+ "MetricGroup": "TopdownL4;tma_L4_group;tma_divider_group",
+ "MetricName": "tma_int_divider",
+ "MetricThreshold": "tma_int_divider > 0.2 & tma_divider > 0.2 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)",
+ "MetricExpr": "tma_int_vector_128b + tma_int_vector_256b",
+ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_int_operations",
+ "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired",
+ "MetricExpr": "INT_VEC_RETIRED.128BIT / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
+ "MetricName": "tma_int_vector_128b",
+ "MetricThreshold": "tma_int_vector_128b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_256b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired",
+ "MetricExpr": "INT_VEC_RETIRED.256BIT / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P",
+ "MetricName": "tma_int_vector_256b",
+ "MetricThreshold": "tma_int_vector_256b > 0.1 & tma_int_operations > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD/MUL or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_ports_utilized_2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses",
+ "MetricExpr": "ICACHE_TAG.STALLS / tma_info_thread_clks",
+ "MetricGroup": "BigFootprint;BvBC;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group",
+ "MetricName": "tma_itlb_misses",
+ "MetricThreshold": "tma_itlb_misses > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS, FRONTEND_RETIRED.ITLB_MISS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache",
+ "MetricExpr": "MEMORY_STALLS.L1 / tma_info_thread_clks",
+ "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group",
+ "MetricName": "tma_l1_bound",
+ "MetricThreshold": "tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 Data (L1D) cache. The L1D 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 L1D. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit Level 1 after missing Level 0 within the L1D cache",
+ "MetricExpr": "(min(MEM_LOAD_RETIRED.L1_HIT_L1 * cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@R, MEM_LOAD_RETIRED.L1_HIT_L1 * 9) if 0 < cpu_core@MEM_LOAD_RETIRED.L1_HIT_L1@R else MEM_LOAD_RETIRED.L1_HIT_L1 * 9) / tma_info_thread_clks",
+ "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
+ "MetricName": "tma_l1_latency_capacity",
+ "MetricThreshold": "tma_l1_latency_capacity > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache",
+ "MetricExpr": "4 * DEPENDENT_LOADS.ANY / tma_info_thread_clks",
+ "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_l1_bound_group",
+ "MetricName": "tma_l1_latency_dependency",
+ "MetricThreshold": "tma_l1_latency_dependency > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric([SKL+] roughly; [LNL]) estimates fraction of cycles with demand load accesses that hit the L1D cache. The short latency of the L1D cache may be exposed in pointer-chasing memory access patterns as an example. Sample with: DEPENDENT_LOADS.ANY",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads",
+ "MetricExpr": "MEMORY_STALLS.L2 / tma_info_thread_clks",
+ "MetricGroup": "BvML;CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
+ "MetricName": "tma_l2_bound",
+ "MetricThreshold": "tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited)",
+ "MetricExpr": "(min(MEM_LOAD_RETIRED.L2_HIT * cpu_core@MEM_LOAD_RETIRED.L2_HIT@R, MEM_LOAD_RETIRED.L2_HIT * (3 * tma_info_system_core_frequency)) if 0 < cpu_core@MEM_LOAD_RETIRED.L2_HIT@R else MEM_LOAD_RETIRED.L2_HIT * (3 * tma_info_system_core_frequency)) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l2_bound_group",
+ "MetricName": "tma_l2_hit_latency",
+ "MetricThreshold": "tma_l2_hit_latency > 0.05 & tma_l2_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L2 cache under unloaded scenarios (possibly L2 latency limited). Avoiding L1 cache misses (i.e. L1 misses/L2 hits) will improve the latency. Sample with: MEM_LOAD_RETIRED.L2_HIT",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core",
+ "MetricExpr": "MEMORY_STALLS.L3 / tma_info_thread_clks",
+ "MetricGroup": "CacheHits;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
+ "MetricName": "tma_l3_bound",
+ "MetricThreshold": "tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)",
+ "MetricExpr": "(min(MEM_LOAD_RETIRED.L3_HIT * cpu_core@MEM_LOAD_RETIRED.L3_HIT@R, MEM_LOAD_RETIRED.L3_HIT * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) if 0 < cpu_core@MEM_LOAD_RETIRED.L3_HIT@R else MEM_LOAD_RETIRED.L3_HIT * (12 * tma_info_system_core_frequency) - 3 * tma_info_system_core_frequency) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_thread_clks",
+ "MetricGroup": "BvML;MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group",
+ "MetricName": "tma_l3_hit_latency",
+ "MetricThreshold": "tma_l3_hit_latency > 0.1 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT. Related metrics: tma_bottleneck_cache_memory_latency, tma_branch_resteers, tma_mem_latency, tma_store_latency",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)",
+ "MetricExpr": "DECODE.LCP / tma_info_thread_clks",
+ "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB",
+ "MetricName": "tma_lcp",
+ "MetricThreshold": "tma_lcp > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_botlnk_l2_dsb_bandwidth, tma_info_botlnk_l2_dsb_misses, tma_info_frontend_dsb_coverage, tma_info_inst_mix_iptb",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation)",
+ "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)",
+ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group",
+ "MetricName": "tma_light_operations",
+ "MetricThreshold": "tma_light_operations > 0.6",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations , instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized code 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. ([ICL+] Note this may undercount due to approximation using indirect events; [ADL+] .). Sample with: INST_RETIRED.PREC_DIST",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations",
+ "MetricExpr": "UOPS_DISPATCHED.LOAD / (3 * tma_info_thread_clks)",
+ "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
+ "MetricName": "tma_load_op_utilization",
+ "MetricThreshold": "tma_load_op_utilization > 0.6",
+ "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.LOAD",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)",
+ "MetricExpr": "max(0, tma_dtlb_load - tma_load_stlb_miss)",
+ "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
+ "MetricName": "tma_load_stlb_hit",
+ "MetricThreshold": "tma_load_stlb_hit > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk",
+ "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_thread_clks",
+ "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group",
+ "MetricName": "tma_load_stlb_miss",
+ "MetricThreshold": "tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data load accesses",
+ "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_1G / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+ "MetricName": "tma_load_stlb_miss_1g",
+ "MetricThreshold": "tma_load_stlb_miss_1g > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data load accesses",
+ "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+ "MetricName": "tma_load_stlb_miss_2m",
+ "MetricThreshold": "tma_load_stlb_miss_2m > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data load accesses",
+ "MetricExpr": "tma_load_stlb_miss * DTLB_LOAD_MISSES.WALK_COMPLETED_4K / (DTLB_LOAD_MISSES.WALK_COMPLETED_4K + DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M + DTLB_LOAD_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_load_stlb_miss_group",
+ "MetricName": "tma_load_stlb_miss_4k",
+ "MetricThreshold": "tma_load_stlb_miss_4k > 0.05 & tma_load_stlb_miss > 0.05 & tma_dtlb_load > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations",
+ "MetricExpr": "MEM_INST_RETIRED.LOCK_LOADS * cpu_core@MEM_INST_RETIRED.LOCK_LOADS@R / tma_info_thread_clks",
+ "MetricGroup": "LockCont;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group",
+ "MetricName": "tma_lock_latency",
+ "MetricThreshold": "tma_lock_latency > 0.2 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS. Related metrics: tma_store_latency",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit",
+ "MetricExpr": "cpu@LSD.UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks",
+ "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
+ "MetricName": "tma_lsd",
+ "MetricThreshold": "tma_lsd > 0.15 & tma_fetch_bandwidth > 0.2",
+ "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears",
+ "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)",
+ "MetricGroup": "BadSpec;BvMS;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn",
+ "MetricName": "tma_machine_clears",
+ "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_bottleneck_memory_synchronization, tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM)",
+ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.DATA_RD\\,cmask\\=0x4@) / tma_info_thread_clks",
+ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW",
+ "MetricName": "tma_mem_bandwidth",
+ "MetricThreshold": "tma_mem_bandwidth > 0.2 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory - DRAM ([SPR-HBM] and/or HBM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_sq_full",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM)",
+ "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_thread_clks - tma_mem_bandwidth",
+ "MetricGroup": "BvML;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat",
+ "MetricName": "tma_mem_latency",
+ "MetricThreshold": "tma_mem_latency > 0.1 & tma_dram_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory - DRAM ([SPR-HBM] and/or HBM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_bottleneck_cache_memory_latency, tma_l3_hit_latency",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck",
+ "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group",
+ "MetricName": "tma_memory_bound",
+ "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "MetricgroupNoGroup": "TopdownL2",
+ "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two)",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions",
+ "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+ "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_thread_clks",
+ "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
+ "MetricName": "tma_memory_fence",
+ "MetricThreshold": "tma_memory_fence > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations , uops for memory load or store accesses",
+ "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_memory_operations",
+ "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit",
+ "MetricExpr": "UOPS_RETIRED.MS / tma_info_thread_slots",
+ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS",
+ "MetricName": "tma_microcode_sequencer",
+ "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1",
+ "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage",
+ "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_thread_clks",
+ "MetricGroup": "BadSpec;BrMispredicts;BvMP;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM",
+ "MetricName": "tma_mispredicts_resteers",
+ "MetricThreshold": "tma_mispredicts_resteers > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_bottleneck_mispredictions, tma_branch_mispredicts, tma_info_bad_spec_branch_misprediction_cost",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)",
+ "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x8\\,inv\\=0x1@ / tma_info_thread_clks + IDQ.MITE_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS) * (IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE - IDQ_BUBBLES.FETCH_LATENCY)) / tma_info_thread_clks",
+ "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
+ "MetricName": "tma_mite",
+ "MetricThreshold": "tma_mite > 0.1 & tma_fetch_bandwidth > 0.2",
+ "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles)",
+ "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_thread_clks",
+ "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group",
+ "MetricName": "tma_mixing_vectors",
+ "MetricThreshold": "tma_mixing_vectors > 0.05",
+ "PublicDescription": "This metric estimates penalty in terms of percentage of([SKL+] injected blend uops out of all Uops Issued , the Count Domain; [ADL+] cycles). Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the Microcode Sequencer (MS) unit - see Microcode_Sequencer node for details",
+ "MetricExpr": "IDQ.MS_CYCLES_ANY / tma_info_thread_clks",
+ "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group",
+ "MetricName": "tma_ms",
+ "MetricThreshold": "tma_ms > 0.05 & tma_fetch_bandwidth > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)",
+ "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_thread_clks",
+ "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO",
+ "MetricName": "tma_ms_switches",
+ "MetricThreshold": "tma_ms_switches > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_bottleneck_irregular_overhead, tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused",
+ "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.BR_FUSED) / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "Branches;BvBO;Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_non_fused_branches",
+ "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions",
+ "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "BvBO;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
+ "MetricName": "tma_nop_instructions",
+ "MetricThreshold": "tma_nop_instructions > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes",
+ "MetricExpr": "max(0, tma_light_operations - (tma_x87_use + (FP_ARITH_INST_RETIRED.SCALAR + FP_ARITH_INST_RETIRED.VECTOR) / (tma_retiring * tma_info_thread_slots) + (INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128 + INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_thread_slots) + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches))",
+ "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group",
+ "MetricName": "tma_other_light_ops",
+ "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of slots the CPU was stalled due to other cases of misprediction (non-retired x86 branches or other types)",
+ "MetricExpr": "max(tma_branch_mispredicts * (1 - BR_MISP_RETIRED.ALL_BRANCHES / (INT_MISC.CLEARS_COUNT - MACHINE_CLEARS.COUNT)), 0.0001)",
+ "MetricGroup": "BrMispredicts;BvIO;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_other_mispredicts",
+ "MetricThreshold": "tma_other_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Nukes (Machine Clears) not related to memory ordering",
+ "MetricExpr": "max(tma_machine_clears * (1 - MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.COUNT), 0.0001)",
+ "MetricGroup": "BvIO;Machine_Clears;TopdownL3;tma_L3_group;tma_machine_clears_group",
+ "MetricName": "tma_other_nukes",
+ "MetricThreshold": "tma_other_nukes > 0.05 & tma_machine_clears > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults",
+ "MetricExpr": "99 * ASSISTS.PAGE_FAULT / tma_info_thread_slots",
+ "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group",
+ "MetricName": "tma_page_faults",
+ "MetricThreshold": "tma_page_faults > 0.05",
+ "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)",
+ "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL)) / tma_info_thread_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_3_PORTS_UTIL) / tma_info_thread_clks)",
+ "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group",
+ "MetricName": "tma_ports_utilization",
+ "MetricThreshold": "tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "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": "EXE_ACTIVITY.EXE_BOUND_0_PORTS / tma_info_thread_clks",
+ "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
+ "MetricName": "tma_ports_utilized_0",
+ "MetricThreshold": "tma_ports_utilized_0 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)",
+ "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_thread_clks",
+ "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group",
+ "MetricName": "tma_ports_utilized_1",
+ "MetricThreshold": "tma_ports_utilized_1 > 0.2 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "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)",
+ "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+ "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_thread_clks",
+ "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group",
+ "MetricName": "tma_ports_utilized_2",
+ "MetricThreshold": "tma_ports_utilized_2 > 0.15 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "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)",
+ "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+ "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_thread_clks",
+ "MetricGroup": "BvCB;PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group",
+ "MetricName": "tma_ports_utilized_3m",
+ "MetricThreshold": "tma_ports_utilized_3m > 0.4 & tma_ports_utilization > 0.15 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to retired misprediction by (indirect) RET instructions",
+ "MetricExpr": "BR_MISP_RETIRED.RET_COST * cpu_core@BR_MISP_RETIRED.RET_COST@R / tma_info_thread_clks",
+ "MetricGroup": "BrMispredicts;TopdownL3;tma_L3_group;tma_branch_mispredicts_group",
+ "MetricName": "tma_ret_mispredicts",
+ "MetricThreshold": "tma_ret_mispredicts > 0.05 & tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+ "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots",
+ "MetricGroup": "BvUW;TmaL1;TopdownL1;tma_L1_group",
+ "MetricName": "tma_retiring",
+ "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1",
+ "MetricgroupNoGroup": "TopdownL1",
+ "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations",
+ "MetricExpr": "(BE_STALLS.SCOREBOARD + CPU_CLK_UNHALTED.C02) / tma_info_thread_clks",
+ "MetricGroup": "BvIO;PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group;tma_issueSO",
+ "MetricName": "tma_serializing_operation",
+ "MetricThreshold": "tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: BE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer)",
+ "MetricExpr": "tma_light_operations * INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_thread_slots)",
+ "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_other_light_ops_group",
+ "MetricName": "tma_shuffles_256b",
+ "MetricThreshold": "tma_shuffles_256b > 0.1 & tma_other_light_ops > 0.3 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric represents fraction of slots where the CPU was retiring Shuffle operations of 256-bit vector size (FP or Integer). Shuffles may incur slow cross \"vector lane\" data transfers",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions",
+ "MetricConstraint": "NO_GROUP_EVENTS_NMI",
+ "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_thread_clks",
+ "MetricGroup": "TopdownL4;tma_L4_group;tma_serializing_operation_group",
+ "MetricName": "tma_slow_pause",
+ "MetricThreshold": "tma_slow_pause > 0.05 & tma_serializing_operation > 0.1 & tma_core_bound > 0.1 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary",
+ "MetricExpr": "(min(MEM_INST_RETIRED.SPLIT_LOADS * cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R, MEM_INST_RETIRED.SPLIT_LOADS * tma_info_memory_load_miss_real_latency) if 0 < cpu_core@MEM_INST_RETIRED.SPLIT_LOADS@R else MEM_INST_RETIRED.SPLIT_LOADS * tma_info_memory_load_miss_real_latency) / tma_info_thread_clks",
+ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
+ "MetricName": "tma_split_loads",
+ "MetricThreshold": "tma_split_loads > 0.3",
+ "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents rate of split store accesses",
+ "MetricExpr": "(min(MEM_INST_RETIRED.SPLIT_STORES * cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R, MEM_INST_RETIRED.SPLIT_STORES) if 0 < cpu_core@MEM_INST_RETIRED.SPLIT_STORES@R else MEM_INST_RETIRED.SPLIT_STORES) / tma_info_thread_clks",
+ "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group",
+ "MetricName": "tma_split_stores",
+ "MetricThreshold": "tma_split_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)",
+ "MetricExpr": "(XQ.FULL + L1D_MISS.L2_STALLS) / tma_info_thread_clks",
+ "MetricGroup": "BvMB;MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group",
+ "MetricName": "tma_sq_full",
+ "MetricThreshold": "tma_sq_full > 0.3 & tma_l3_bound > 0.05 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_bottleneck_cache_memory_bandwidth, tma_fb_full, tma_mem_bandwidth",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write",
+ "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_thread_clks",
+ "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
+ "MetricName": "tma_store_bound",
+ "MetricThreshold": "tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "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 / tma_info_thread_clks",
+ "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group",
+ "MetricName": "tma_store_fwd_blk",
+ "MetricThreshold": "tma_store_fwd_blk > 0.1 & tma_l1_bound > 0.1 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses",
+ "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_thread_clks",
+ "MetricGroup": "BvML;LockCont;MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group",
+ "MetricName": "tma_store_latency",
+ "MetricThreshold": "tma_store_latency > 0.1 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_branch_resteers, tma_fb_full, tma_l3_hit_latency, tma_lock_latency",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations",
+ "MetricExpr": "(UOPS_DISPATCHED.STD + UOPS_DISPATCHED.STA) / (7 * tma_info_thread_clks)",
+ "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group",
+ "MetricName": "tma_store_op_utilization",
+ "MetricThreshold": "tma_store_op_utilization > 0.6",
+ "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.STD, UOPS_DISPATCHED.STA",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)",
+ "MetricExpr": "max(0, tma_dtlb_store - tma_store_stlb_miss)",
+ "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
+ "MetricName": "tma_store_stlb_hit",
+ "MetricThreshold": "tma_store_stlb_hit > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk",
+ "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_thread_clks",
+ "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group",
+ "MetricName": "tma_store_stlb_miss",
+ "MetricThreshold": "tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 1 GB pages for data store accesses",
+ "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_1G / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+ "MetricName": "tma_store_stlb_miss_1g",
+ "MetricThreshold": "tma_store_stlb_miss_1g > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 2 or 4 MB pages for data store accesses",
+ "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+ "MetricName": "tma_store_stlb_miss_2m",
+ "MetricThreshold": "tma_store_stlb_miss_2m > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates the fraction of cycles to walk the memory paging structures to cache translation of 4 KB pages for data store accesses",
+ "MetricExpr": "tma_store_stlb_miss * DTLB_STORE_MISSES.WALK_COMPLETED_4K / (DTLB_STORE_MISSES.WALK_COMPLETED_4K + DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M + DTLB_STORE_MISSES.WALK_COMPLETED_1G)",
+ "MetricGroup": "MemoryTLB;TopdownL6;tma_L6_group;tma_store_stlb_miss_group",
+ "MetricName": "tma_store_stlb_miss_4k",
+ "MetricThreshold": "tma_store_stlb_miss_4k > 0.05 & tma_store_stlb_miss > 0.05 & tma_dtlb_store > 0.05 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores",
+ "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_thread_clks",
+ "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group",
+ "MetricName": "tma_streaming_stores",
+ "MetricThreshold": "tma_streaming_stores > 0.2 & tma_store_bound > 0.2 & tma_memory_bound > 0.2 & tma_backend_bound > 0.2",
+ "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears",
+ "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_thread_clks",
+ "MetricGroup": "BigFootprint;BvBC;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group",
+ "MetricName": "tma_unknown_branches",
+ "MetricThreshold": "tma_unknown_branches > 0.05 & tma_branch_resteers > 0.05 & tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15",
+ "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit) hence called Unknown Branches. Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This metric serves as an approximation of legacy x87 usage",
+ "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD",
+ "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group",
+ "MetricName": "tma_x87_use",
+ "MetricThreshold": "tma_x87_use > 0.1 & tma_fp_arith > 0.2 & tma_light_operations > 0.6",
+ "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint",
+ "ScaleUnit": "100%",
+ "Unit": "cpu_core"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
index 3d12e226d5ef..60daff922a89 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
@@ -1,13 +1,168 @@
[
{
- "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.",
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.ANY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7f",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to any number of reasons, including an L1 miss, WCB full, pagewalk, store address block or store data block, on a load that retires.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.ANY_AT_RET",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xff",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a core bound stall including a store address match, a DTLB miss or a page walk that detains the load from retiring.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.L1_BOUND_AT_RET",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xf4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a DL1 miss.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.L1_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DL1 miss.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.L1_MISS_AT_RET",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x81",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to other block cases.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.OTHER",
+ "PublicDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to other block cases such as pipeline conflicts, fences, etc.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.OTHER_AT_RET",
+ "PublicDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases such as pipeline conflicts, fences, etc.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xc0",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a pagewalk.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.PGWALK",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a pagewalk.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.PGWALK_AT_RET",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xa0",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a store address match.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.ST_ADDR",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a store address match.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.ST_ADDR_AT_RET",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x84",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to store data forward block.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.ST_DATA",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to request buffers full or lock in progress.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.WCB_FULL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to request buffers full or lock in progress.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.WCB_FULL_AT_RET",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x82",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of memory ordering machine clears triggered due to a snoop from an external agent. Does not count internally generated machine clears such as those due to disambiguations.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+ "SampleAfterValue": "20003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Number of machine clears due to memory ordering conflicts.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+ "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine without the use of microcode.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.MEMORY_ORDERING_FAST",
+ "SampleAfterValue": "20003",
+ "UMask": "0x82",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.",
+ "Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
"MSRIndex": "0x3F6",
"MSRValue": "0x400",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "53",
"UMask": "0x1",
@@ -15,13 +170,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
"MSRIndex": "0x3F6",
"MSRValue": "0x80",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "1009",
"UMask": "0x1",
@@ -29,13 +183,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
"MSRIndex": "0x3F6",
"MSRValue": "0x10",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "20011",
"UMask": "0x1",
@@ -43,13 +196,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
"MSRIndex": "0x3F6",
"MSRValue": "0x800",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "23",
"UMask": "0x1",
@@ -57,13 +209,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
"MSRIndex": "0x3F6",
"MSRValue": "0x100",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "503",
"UMask": "0x1",
@@ -71,13 +222,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
"MSRIndex": "0x3F6",
"MSRValue": "0x20",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100007",
"UMask": "0x1",
@@ -85,13 +235,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
"MSRIndex": "0x3F6",
"MSRValue": "0x4",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "100003",
"UMask": "0x1",
@@ -99,13 +248,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
"MSRIndex": "0x3F6",
"MSRValue": "0x200",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "101",
"UMask": "0x1",
@@ -113,13 +261,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
"MSRIndex": "0x3F6",
"MSRValue": "0x40",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "2003",
"UMask": "0x1",
@@ -127,13 +274,12 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "Counter": "2,3,4,5,6,7,8,9",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
"MSRIndex": "0x3F6",
"MSRValue": "0x8",
- "PEBS": "2",
"PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.",
"SampleAfterValue": "50021",
"UMask": "0x1",
@@ -145,54 +291,112 @@
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
- "PEBS": "2",
"PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8",
"SampleAfterValue": "1000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts cacheable demand data reads were not supplied by the L3 cache.",
+ "BriefDescription": "Counts misaligned loads that are 4K page splits.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x13",
+ "EventName": "MISALIGN_MEM_REF.LOAD_PAGE_SPLIT",
+ "SampleAfterValue": "200003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts misaligned stores that are 4K page splits.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x13",
+ "EventName": "MISALIGN_MEM_REF.STORE_PAGE_SPLIT",
+ "SampleAfterValue": "200003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x13FBFC00004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x3FBFC00001",
+ "MSRValue": "0x13FBFC00001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
+ "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0xFE7F8000001",
+ "MSRValue": "0x9E7FA000001",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO were not supplied by the L3 cache.",
+ "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0x3FBFC00002",
+ "MSRValue": "0x13FBFC00002",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
+ "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache and were supplied by the system memory (DRAM, MSC, or MMIO).",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
- "MSRValue": "0xFE7F8000002",
+ "MSRValue": "0x9E7FA000002",
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts demand data read requests that miss the L3 cache.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x21",
+ "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
+ "SampleAfterValue": "100003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles where data return is pending for a Demand Data Read request who miss L3 cache.",
+ "Counter": "0,1,2,3",
+ "CounterMask": "1",
+ "EventCode": "0x20",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
+ "PublicDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x20",
+ "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD",
+ "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/metricgroups.json b/tools/perf/pmu-events/arch/x86/lunarlake/metricgroups.json
new file mode 100644
index 000000000000..855585fe6fae
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/metricgroups.json
@@ -0,0 +1,150 @@
+{
+ "Backend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Bad": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BadSpec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BigFootprint": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BrMispredicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Branches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvBC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvBO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvCB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvFB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvIO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvMB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvML": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvMP": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvMS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvOB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "BvUW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "C0Wait": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "CacheHits": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "CacheMisses": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "CodeGen": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Compute": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Cor": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "DSB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "DSBmiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "DataSharing": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Fed": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "FetchBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "FetchLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Flops": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "FpScalar": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "FpVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Frontend": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "HPC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "IcMiss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Ifetch": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "InsType": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "IntVector": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "L2Evicts": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "LSD": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Load_Store_Miss": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "LockCont": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "MachineClears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Machine_Clears": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "MemOffcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Mem_Exec": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "MemoryBW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "MemoryBound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "MemoryLat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "MemoryTLB": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Memory_BW": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Memory_Lat": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "MicroSeq": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "OS": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Offcore": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "PGO": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Pipeline": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "PortsUtil": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Power": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Prefetches": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Ret": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Retire": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "SMT": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Server": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Snoop": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "SoC": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "Summary": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "TmaL1": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "TmaL2": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "TmaL3mem": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "TopdownL1": "Metrics for top-down breakdown at level 1",
+ "TopdownL2": "Metrics for top-down breakdown at level 2",
+ "TopdownL3": "Metrics for top-down breakdown at level 3",
+ "TopdownL4": "Metrics for top-down breakdown at level 4",
+ "TopdownL5": "Metrics for top-down breakdown at level 5",
+ "TopdownL6": "Metrics for top-down breakdown at level 6",
+ "load_store_bound": "Grouping from Top-down Microarchitecture Analysis Metrics spreadsheet",
+ "tma_L1_group": "Metrics for top-down breakdown at level 1",
+ "tma_L2_group": "Metrics for top-down breakdown at level 2",
+ "tma_L3_group": "Metrics for top-down breakdown at level 3",
+ "tma_L4_group": "Metrics for top-down breakdown at level 4",
+ "tma_L5_group": "Metrics for top-down breakdown at level 5",
+ "tma_L6_group": "Metrics for top-down breakdown at level 6",
+ "tma_alu_op_utilization_group": "Metrics contributing to tma_alu_op_utilization category",
+ "tma_assists_group": "Metrics contributing to tma_assists category",
+ "tma_backend_bound_group": "Metrics contributing to tma_backend_bound category",
+ "tma_bad_speculation_group": "Metrics contributing to tma_bad_speculation category",
+ "tma_branch_mispredicts_group": "Metrics contributing to tma_branch_mispredicts category",
+ "tma_branch_resteers_group": "Metrics contributing to tma_branch_resteers category",
+ "tma_code_stlb_miss_group": "Metrics contributing to tma_code_stlb_miss category",
+ "tma_core_bound_group": "Metrics contributing to tma_core_bound category",
+ "tma_divider_group": "Metrics contributing to tma_divider category",
+ "tma_dram_bound_group": "Metrics contributing to tma_dram_bound category",
+ "tma_dtlb_load_group": "Metrics contributing to tma_dtlb_load category",
+ "tma_dtlb_store_group": "Metrics contributing to tma_dtlb_store category",
+ "tma_fetch_bandwidth_group": "Metrics contributing to tma_fetch_bandwidth category",
+ "tma_fetch_latency_group": "Metrics contributing to tma_fetch_latency category",
+ "tma_fp_arith_group": "Metrics contributing to tma_fp_arith category",
+ "tma_fp_vector_group": "Metrics contributing to tma_fp_vector category",
+ "tma_frontend_bound_group": "Metrics contributing to tma_frontend_bound category",
+ "tma_heavy_operations_group": "Metrics contributing to tma_heavy_operations category",
+ "tma_icache_misses_group": "Metrics contributing to tma_icache_misses category",
+ "tma_ifetch_bandwidth_group": "Metrics contributing to tma_ifetch_bandwidth category",
+ "tma_ifetch_latency_group": "Metrics contributing to tma_ifetch_latency category",
+ "tma_int_operations_group": "Metrics contributing to tma_int_operations category",
+ "tma_issue2P": "Metrics related by the issue $issue2P",
+ "tma_issueBM": "Metrics related by the issue $issueBM",
+ "tma_issueBW": "Metrics related by the issue $issueBW",
+ "tma_issueComp": "Metrics related by the issue $issueComp",
+ "tma_issueD0": "Metrics related by the issue $issueD0",
+ "tma_issueFB": "Metrics related by the issue $issueFB",
+ "tma_issueFL": "Metrics related by the issue $issueFL",
+ "tma_issueL1": "Metrics related by the issue $issueL1",
+ "tma_issueLat": "Metrics related by the issue $issueLat",
+ "tma_issueMC": "Metrics related by the issue $issueMC",
+ "tma_issueMS": "Metrics related by the issue $issueMS",
+ "tma_issueMV": "Metrics related by the issue $issueMV",
+ "tma_issueRFO": "Metrics related by the issue $issueRFO",
+ "tma_issueSL": "Metrics related by the issue $issueSL",
+ "tma_issueSO": "Metrics related by the issue $issueSO",
+ "tma_issueSmSt": "Metrics related by the issue $issueSmSt",
+ "tma_issueSpSt": "Metrics related by the issue $issueSpSt",
+ "tma_issueSyncxn": "Metrics related by the issue $issueSyncxn",
+ "tma_issueTLB": "Metrics related by the issue $issueTLB",
+ "tma_itlb_misses_group": "Metrics contributing to tma_itlb_misses category",
+ "tma_l1_bound_group": "Metrics contributing to tma_l1_bound category",
+ "tma_l2_bound_group": "Metrics contributing to tma_l2_bound category",
+ "tma_l3_bound_group": "Metrics contributing to tma_l3_bound category",
+ "tma_light_operations_group": "Metrics contributing to tma_light_operations category",
+ "tma_load_op_utilization_group": "Metrics contributing to tma_load_op_utilization category",
+ "tma_load_stlb_miss_group": "Metrics contributing to tma_load_stlb_miss category",
+ "tma_machine_clears_group": "Metrics contributing to tma_machine_clears category",
+ "tma_mem_latency_group": "Metrics contributing to tma_mem_latency category",
+ "tma_memory_bound_group": "Metrics contributing to tma_memory_bound category",
+ "tma_microcode_sequencer_group": "Metrics contributing to tma_microcode_sequencer category",
+ "tma_mite_group": "Metrics contributing to tma_mite category",
+ "tma_other_light_ops_group": "Metrics contributing to tma_other_light_ops category",
+ "tma_ports_utilization_group": "Metrics contributing to tma_ports_utilization category",
+ "tma_ports_utilized_0_group": "Metrics contributing to tma_ports_utilized_0 category",
+ "tma_ports_utilized_3m_group": "Metrics contributing to tma_ports_utilized_3m category",
+ "tma_resource_bound_group": "Metrics contributing to tma_resource_bound category",
+ "tma_retiring_group": "Metrics contributing to tma_retiring category",
+ "tma_serializing_operation_group": "Metrics contributing to tma_serializing_operation category",
+ "tma_store_bound_group": "Metrics contributing to tma_store_bound category",
+ "tma_store_op_utilization_group": "Metrics contributing to tma_store_op_utilization category",
+ "tma_store_stlb_miss_group": "Metrics contributing to tma_store_stlb_miss category"
+}
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/other.json b/tools/perf/pmu-events/arch/x86/lunarlake/other.json
index 0b49b4684c4b..667707d4fe37 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/other.json
@@ -1,6 +1,345 @@
[
{
- "BriefDescription": "Counts cacheable demand data reads Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored",
+ "BriefDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc1",
+ "EventName": "ASSISTS.HARDWARE",
+ "PublicDescription": "Count all other hardware assists or traps that are not necessarily architecturally exposed (through a software handler) beyond FP; SSE-AVX mix and A/D assists who are counted by dedicated sub-events. This includes, but not limited to, assists at EXE or MEM uop writeback like AVX* load/store/gather/scatter (non-FP GSSE-assist ) , assists generated by ROB like PEBS and RTIT, Uncore trap, RAR (Remote Action Request) and CET (Control flow Enforcement Technology) assists.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "ASSISTS.PAGE_FAULT",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc1",
+ "EventName": "ASSISTS.PAGE_FAULT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa2",
+ "EventName": "BE_STALLS.SCOREBOARD",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of unhalted cycles a Core is blocked due to a lock In Progress issued by another core",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x63",
+ "EventName": "BUS_LOCK.BLOCKED_CYCLES",
+ "PublicDescription": "Counts the number of unhalted cycles a Core is blocked due to a lock In Progress issued by another core. Counts on a per core basis.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of unhalted cycles a Core is blocked due to an Accepted lock it issued, includes both split and non-split lock cycles.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x63",
+ "EventName": "BUS_LOCK.LOCK_CYCLES",
+ "PublicDescription": "Counts the number of unhalted cycles a Core is blocked due to an Accepted lock it issued, includes both split and non-split lock cycles. Counts on a per core basis.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of non-split locks such as UC locks issued by a Core (does not include cache locks)",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x63",
+ "EventName": "BUS_LOCK.NON_SPLIT_LOCKS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of split locks issued by a Core",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x63",
+ "EventName": "BUS_LOCK.SPLIT_LOCKS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Count number of times a load is depending on another load that had just write back its data or in previous or 2 cycles back. This event supports in-direct dependency through a single uop.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x02",
+ "EventName": "DEPENDENT_LOADS.ANY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the L2 Prefetchers are at throttle level 0",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x32",
+ "EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL0_SOC",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 1",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x32",
+ "EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL1_SOC",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 2",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x32",
+ "EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL2_SOC",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 3",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x32",
+ "EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL3_SOC",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles the L2 Prefetcher throttle level is at 4",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x32",
+ "EventName": "DYNAMIC_PREFETCH_THROTTLER.LEVEL4_SOC",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on all Integer ports.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb3",
+ "EventName": "INT_UOPS_EXECUTED.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xff",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on a load port.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb3",
+ "EventName": "INT_UOPS_EXECUTED.LD",
+ "PublicDescription": "Counts the number of uops executed on a load port. This event counts for integer uops even if the destination is FP/vector",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on integer port 0.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb3",
+ "EventName": "INT_UOPS_EXECUTED.P0",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on integer port 1.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb3",
+ "EventName": "INT_UOPS_EXECUTED.P1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on integer port 2.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb3",
+ "EventName": "INT_UOPS_EXECUTED.P2",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on integer port 3.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb3",
+ "EventName": "INT_UOPS_EXECUTED.P3",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on integer port 0,1, 2, 3.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb3",
+ "EventName": "INT_UOPS_EXECUTED.PRIMARY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x78",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on a Store address port.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb3",
+ "EventName": "INT_UOPS_EXECUTED.STA",
+ "PublicDescription": "Counts the number of uops executed on a Store address port. This event counts integer uops even if the data source is FP/vector",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of uops executed on an integer store data and jump port.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xb3",
+ "EventName": "INT_UOPS_EXECUTED.STD_JMP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of LLC prefetches that were throttled due to Dynamic Prefetch Throttling. The throttle requestor/source could be from the uncore/SOC or the Dead Block Predictor. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x29",
+ "EventName": "LLC_PREFETCHES_THROTTLED.DPT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of LLC prefetches throttled due to Demand Throttle Prefetcher. DTP Global Triggered with no Local Override. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x29",
+ "EventName": "LLC_PREFETCHES_THROTTLED.DTP",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of LLC prefetches not throttled by DTP due to local override. These prefetches may still be throttled due to another throttler mechanism. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x29",
+ "EventName": "LLC_PREFETCHES_THROTTLED.DTP_OVERRIDE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of LLC prefetches throttled due to LLC hit rate in <insert knob name here>. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x29",
+ "EventName": "LLC_PREFETCHES_THROTTLED.HIT_RATE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of LLC prefetches throttled due to exceeding the XQ threshold set by either XQ_THRESOLD_DTP or LLC_XQ_THRESHOLD. Counts on a per core basis.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x29",
+ "EventName": "LLC_PREFETCHES_THROTTLED.XQ_THRESH",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L1 cache (that is: no execution & load in flight & no load missed L1 cache)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x46",
+ "EventName": "MEMORY_STALLS.L1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L2 cache (that is: no execution & load in flight & load missed L1 & no load missed L2 cache)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x46",
+ "EventName": "MEMORY_STALLS.L2",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for L3 cache (that is: no execution & load in flight & load missed L1 & load missed L2 cache & no load missed L3 Cache)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x46",
+ "EventName": "MEMORY_STALLS.L3",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts cycles where no execution is happening due to loads waiting for Memory (that is: no execution & load in flight & a load missed L3 cache)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x46",
+ "EventName": "MEMORY_STALLS.MEM",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts all requests that have any type of response.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.ALL_REQUESTS.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0xFF0000001DFFF",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts writebacks of modified cachelines that have any type of response.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.COREWB_M.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10008",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts writebacks of non-modified cachelines that have any type of response.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.COREWB_NONM.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x11000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_CODE_RD.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x1FBC000004",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts demand data reads that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
@@ -22,7 +361,7 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts cacheable demand data reads were supplied by DRAM.",
+ "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_DATA_RD.DRAM",
@@ -44,7 +383,7 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored",
+ "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xB7",
"EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
@@ -64,5 +403,156 @@
"SampleAfterValue": "100003",
"UMask": "0x1",
"Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_RFO.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x1FBC000002",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts full streaming stores (64 bytes, WCiLF) that have any type of response.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.FULL_STREAMING_WR.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x800000010000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts partial streaming stores (less than 64 bytes, WCiL) that have any type of response.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.PARTIAL_STREAMING_WR.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x400000010000",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts streaming stores that have any type of response.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xB7",
+ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10800",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts streaming stores that have any type of response.",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10800",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa5",
+ "EventName": "RS.EMPTY",
+ "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EdgeDetect": "1",
+ "EventCode": "0xa5",
+ "EventName": "RS.EMPTY_COUNT",
+ "Invert": "1",
+ "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)",
+ "SampleAfterValue": "100003",
+ "UMask": "0x7",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa5",
+ "EventName": "RS.EMPTY_RESOURCE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x75",
+ "EventName": "SERIALIZATION.C01_MS_SCB",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number issue slots not consumed due to a color request for an FCW or MXCSR control register when all 4 colors (copies) are already in use",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x75",
+ "EventName": "SERIALIZATION.COLOR_STALLS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Cycles the uncore cannot take further requests",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0x2d",
+ "EventName": "XQ.FULL",
+ "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand request.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xf4",
+ "EventName": "XQ_PROMOTION.ALL",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand code read.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xf4",
+ "EventName": "XQ_PROMOTION.CRDS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand read.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xf4",
+ "EventName": "XQ_PROMOTION.DRDS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of prefetch requests that were promoted in the XQ to a demand RFO.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xf4",
+ "EventName": "XQ_PROMOTION.RFOS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
index 220c2115fec9..59e2ae652b2d 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
@@ -1,325 +1,2002 @@
[
+ {
+ "BriefDescription": "Counts the number of cycles when any of the floating point or integer dividers are active.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "CounterMask": "1",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.DIV_ACTIVE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0xb0",
+ "EventName": "ARITH.DIV_ACTIVE",
+ "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x9",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of active floating point and integer dividers per cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.DIV_OCCUPANCY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of floating point and integer divider uops executed per cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.DIV_UOPS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xc",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles when any of the integer dividers are active.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "CounterMask": "1",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.IDIV_ACTIVE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Cycles when integer divide unit is busy executing divide or square root operations.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0xb0",
+ "EventName": "ARITH.IDIV_ACTIVE",
+ "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer operations only.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of active integer dividers per cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.IDIV_OCCUPANCY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of integer divider uops executed per cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcd",
+ "EventName": "ARITH.IDIV_UOPS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc1",
+ "EventName": "ASSISTS.ANY",
+ "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1f",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts the total number of branch instructions retired for all branch types.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.ALL_BRANCHES",
- "PEBS": "1",
"PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.",
"SampleAfterValue": "200003",
"Unit": "cpu_atom"
},
{
- "BriefDescription": "All branch instructions retired.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0xc4",
- "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
- "PEBS": "1",
- "PublicDescription": "Counts all branch instructions retired.",
- "SampleAfterValue": "400009",
- "Unit": "cpu_core"
+ "BriefDescription": "All branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+ "PublicDescription": "Counts all branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts retired JCC (Jump on Conditional Code) branch instructions retired includes both taken and not taken branches",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND",
+ "SampleAfterValue": "200003",
+ "UMask": "0x7e",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Conditional branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND",
+ "PublicDescription": "Counts conditional branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x111",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of not taken JCC branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND_NTAKEN",
+ "SampleAfterValue": "200003",
+ "UMask": "0x7f",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Not taken branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND_NTAKEN",
+ "PublicDescription": "Counts not taken branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of taken JCC branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND_TAKEN",
+ "SampleAfterValue": "200003",
+ "UMask": "0xfe",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Taken conditional branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND_TAKEN",
+ "PublicDescription": "Counts taken conditional branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x101",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Taken backward conditional branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND_TAKEN_BWD",
+ "PublicDescription": "Counts taken backward conditional branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Taken forward conditional branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.COND_TAKEN_FWD",
+ "PublicDescription": "Counts taken forward conditional branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x102",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of far branch instructions retired, includes far jump, far call and return, and Interrupt call and return",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+ "SampleAfterValue": "200003",
+ "UMask": "0xbf",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Far branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+ "PublicDescription": "Counts far branch instructions retired.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x40",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of near indirect JMP and near indirect CALL branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.INDIRECT",
+ "SampleAfterValue": "200003",
+ "UMask": "0xeb",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Indirect near branch instructions retired (excluding returns)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.INDIRECT",
+ "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x80",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of near indirect CALL branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.INDIRECT_CALL",
+ "SampleAfterValue": "200003",
+ "UMask": "0xfb",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of near indirect JMP branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.INDIRECT_JMP",
+ "SampleAfterValue": "200003",
+ "UMask": "0xef",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of near CALL branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.NEAR_CALL",
+ "SampleAfterValue": "200003",
+ "UMask": "0xf9",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Direct and indirect near call instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.NEAR_CALL",
+ "PublicDescription": "Counts both direct and indirect near call instructions retired.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of near RET branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+ "SampleAfterValue": "200003",
+ "UMask": "0xf7",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Return instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+ "PublicDescription": "Counts return instructions retired.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of taken branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+ "SampleAfterValue": "200003",
+ "UMask": "0xc0",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Taken branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+ "PublicDescription": "Counts taken branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of near relative CALL branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc4",
+ "EventName": "BR_INST_RETIRED.REL_CALL",
+ "SampleAfterValue": "200003",
+ "UMask": "0xfd",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+ "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+ "SampleAfterValue": "200003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "All mispredicted branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+ "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
+ "SampleAfterValue": "400009",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "All mispredicted branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_COST",
+ "SampleAfterValue": "400009",
+ "UMask": "0x44",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of mispredicted JCC branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND",
+ "SampleAfterValue": "200003",
+ "UMask": "0x7e",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Mispredicted conditional branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND",
+ "PublicDescription": "Counts mispredicted conditional branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x111",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Mispredicted conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_COST",
+ "SampleAfterValue": "400009",
+ "UMask": "0x151",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of mispredicted not taken JCC branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
+ "SampleAfterValue": "200003",
+ "UMask": "0x7f",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Mispredicted non-taken conditional branch instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_NTAKEN",
+ "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Mispredicted non-taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_NTAKEN_COST",
+ "SampleAfterValue": "400009",
+ "UMask": "0x50",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of mispredicted taken JCC branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_TAKEN",
+ "SampleAfterValue": "200003",
+ "UMask": "0xfe",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "number of branch instructions retired that were mispredicted and taken.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_TAKEN",
+ "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x101",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "number of branch instructions retired that were mispredicted and taken backward.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD",
+ "PublicDescription": "Counts taken backward conditional mispredicted branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "number of branch instructions retired that were mispredicted and taken backward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_TAKEN_BWD_COST",
+ "SampleAfterValue": "400009",
+ "UMask": "0x8001",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Mispredicted taken conditional branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_TAKEN_COST",
+ "SampleAfterValue": "400009",
+ "UMask": "0x141",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "number of branch instructions retired that were mispredicted and taken forward.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD",
+ "PublicDescription": "Counts taken forward conditional mispredicted branch instructions retired.",
+ "SampleAfterValue": "400009",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "number of branch instructions retired that were mispredicted and taken forward. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_TAKEN_FWD_COST",
+ "SampleAfterValue": "400009",
+ "UMask": "0x8002",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of mispredicted near indirect JMP and near indirect CALL branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.INDIRECT",
+ "SampleAfterValue": "200003",
+ "UMask": "0xeb",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Miss-predicted near indirect branch instructions retired (excluding returns)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.INDIRECT",
+ "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x80",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
+ "SampleAfterValue": "200003",
+ "UMask": "0xfb",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Mispredicted indirect CALL retired.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.INDIRECT_CALL",
+ "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Mispredicted indirect CALL retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.INDIRECT_CALL_COST",
+ "SampleAfterValue": "400009",
+ "UMask": "0x42",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Mispredicted near indirect branch instructions retired (excluding returns). This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.INDIRECT_COST",
+ "SampleAfterValue": "100003",
+ "UMask": "0xc0",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of mispredicted near indirect JMP branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.INDIRECT_JMP",
+ "SampleAfterValue": "200003",
+ "UMask": "0xef",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+ "SampleAfterValue": "200003",
+ "UMask": "0x80",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+ "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.",
+ "SampleAfterValue": "400009",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Mispredicted taken near branch instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.NEAR_TAKEN_COST",
+ "SampleAfterValue": "400009",
+ "UMask": "0x60",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.RET",
+ "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.",
+ "SampleAfterValue": "100007",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of mispredicted near RET branch instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.RETURN",
+ "SampleAfterValue": "200003",
+ "UMask": "0xf7",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Mispredicted ret instructions retired. This precise event may be used to get the misprediction cost via the Retire_Latency field of PEBS. It fires on the instruction that immediately follows the mispredicted branch.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.RET_COST",
+ "SampleAfterValue": "100007",
+ "UMask": "0x48",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the total number of BTCLEARS.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe8",
+ "EventName": "BTCLEAR.ANY",
+ "PublicDescription": "Counts the total number of BTCLEARS which occurs when the Branch Target Buffer (BTB) predicts a taken branch.",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xec",
+ "EventName": "CPU_CLK_UNHALTED.C01",
+ "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xec",
+ "EventName": "CPU_CLK_UNHALTED.C02",
+ "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Core clocks when the thread is in the C0.1 or C0.2 or running a PAUSE in C0 ACPI state.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xec",
+ "EventName": "CPU_CLK_UNHALTED.C0_WAIT",
+ "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x70",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.",
+ "Counter": "Fixed counter 1",
+ "EventName": "CPU_CLK_UNHALTED.CORE",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Core cycles when the core is not in a halt state.",
+ "Counter": "Fixed counter 1",
+ "EventName": "CPU_CLK_UNHALTED.CORE",
+ "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the programmable counters available for other events.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x3c",
+ "EventName": "CPU_CLK_UNHALTED.CORE_P",
+ "SampleAfterValue": "2000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Thread cycles when thread is not in halt state [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x3c",
+ "EventName": "CPU_CLK_UNHALTED.CORE_P",
+ "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
+ "SampleAfterValue": "2000003",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Core clocks when a PAUSE is pending.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xec",
+ "EventName": "CPU_CLK_UNHALTED.PAUSE",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x40",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of Pause instructions",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EdgeDetect": "1",
+ "EventCode": "0xec",
+ "EventName": "CPU_CLK_UNHALTED.PAUSE_INST",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x40",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles.",
+ "Counter": "Fixed counter 2",
+ "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x3",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Reference cycles when the core is not in halt state.",
+ "Counter": "Fixed counter 2",
+ "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+ "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of unhalted reference clock cycles",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x3c",
+ "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
+ "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Reference cycles when the core is not in halt state.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x3c",
+ "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
+ "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.",
+ "Counter": "Fixed counter 1",
+ "EventName": "CPU_CLK_UNHALTED.THREAD",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Core cycles when the thread is not in a halt state.",
+ "Counter": "Fixed counter 1",
+ "EventName": "CPU_CLK_UNHALTED.THREAD",
+ "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the programmable counters available for other events.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.CORE_P]",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x3c",
+ "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+ "SampleAfterValue": "2000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Thread cycles when thread is not in halt state [This event is alias to CPU_CLK_UNHALTED.CORE_P]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x3c",
+ "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+ "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. [This event is alias to CPU_CLK_UNHALTED.CORE_P]",
+ "SampleAfterValue": "2000003",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles while memory subsystem has an outstanding load.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "16",
+ "EventCode": "0xa3",
+ "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Total execution stalls.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "4",
+ "EventCode": "0xa3",
+ "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa6",
+ "EventName": "EXE_ACTIVITY.1_PORTS_UTIL",
+ "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles total of 2 or 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa6",
+ "EventName": "EXE_ACTIVITY.2_3_PORTS_UTIL",
+ "SampleAfterValue": "2000003",
+ "UMask": "0xc",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa6",
+ "EventName": "EXE_ACTIVITY.2_PORTS_UTIL",
+ "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa6",
+ "EventName": "EXE_ACTIVITY.3_PORTS_UTIL",
+ "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa6",
+ "EventName": "EXE_ACTIVITY.4_PORTS_UTIL",
+ "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "5",
+ "EventCode": "0xa6",
+ "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x21",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "2",
+ "EventCode": "0xa6",
+ "EventName": "EXE_ACTIVITY.BOUND_ON_STORES",
+ "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles no uop executed while RS was not empty, the SB was not full and there was no outstanding load.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa6",
+ "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS",
+ "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x80",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Instruction decoders utilized in a cycle",
+ "Counter": "2",
+ "EventCode": "0x75",
+ "EventName": "INST_DECODED.DECODERS",
+ "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fixed Counter: Counts the number of instructions retired.",
+ "Counter": "Fixed counter 0",
+ "EventName": "INST_RETIRED.ANY",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
+ "Counter": "Fixed counter 0",
+ "EventName": "INST_RETIRED.ANY",
+ "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc0",
+ "EventName": "INST_RETIRED.ANY_P",
+ "SampleAfterValue": "2000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Number of instructions retired. General Counter - architectural event",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc0",
+ "EventName": "INST_RETIRED.ANY_P",
+ "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+ "SampleAfterValue": "2000003",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "retired macro-fused uops when there is a branch in the macro-fused pair (the two instructions that got macro-fused count once in this pmon)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc0",
+ "EventName": "INST_RETIRED.BR_FUSED",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "INST_RETIRED.MACRO_FUSED",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc0",
+ "EventName": "INST_RETIRED.MACRO_FUSED",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x30",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Retired NOP instructions.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc0",
+ "EventName": "INST_RETIRED.NOP",
+ "PublicDescription": "Counts all retired NOP or ENDBR32/64 or PREFETCHIT0/1 instructions",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Precise instruction retired with PEBS precise-distribution",
+ "Counter": "Fixed counter 0",
+ "EventName": "INST_RETIRED.PREC_DIST",
+ "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Iterations of Repeat string retired instructions.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc0",
+ "EventName": "INST_RETIRED.REP_ITERATION",
+ "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Bubble cycles of BPClear.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xad",
+ "EventName": "INT_MISC.BPCLEAR_CYCLES",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0xB",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Clears speculative count",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EdgeDetect": "1",
+ "EventCode": "0xad",
+ "EventName": "INT_MISC.CLEARS_COUNT",
+ "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears",
+ "SampleAfterValue": "500009",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xad",
+ "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES",
+ "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.",
+ "SampleAfterValue": "500009",
+ "UMask": "0x80",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xad",
+ "EventName": "INT_MISC.RECOVERY_CYCLES",
+ "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.",
+ "SampleAfterValue": "500009",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xad",
+ "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x7",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "TMA slots where uops got dropped",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xad",
+ "EventName": "INT_MISC.UOP_DROPPING",
+ "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of vector integer instructions retired of 128-bit vector-width.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe7",
+ "EventName": "INT_VEC_RETIRED.128BIT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x13",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of vector integer instructions retired of 256-bit vector-width.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe7",
+ "EventName": "INT_VEC_RETIRED.256BIT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xac",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "integer ADD, SUB, SAD 128-bit vector instructions.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe7",
+ "EventName": "INT_VEC_RETIRED.ADD_128",
+ "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "integer ADD, SUB, SAD 256-bit vector instructions.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe7",
+ "EventName": "INT_VEC_RETIRED.ADD_256",
+ "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xc",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "INT_VEC_RETIRED.MUL_256",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe7",
+ "EventName": "INT_VEC_RETIRED.MUL_256",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x80",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "INT_VEC_RETIRED.SHUFFLES",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe7",
+ "EventName": "INT_VEC_RETIRED.SHUFFLES",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "INT_VEC_RETIRED.VNNI_128",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe7",
+ "EventName": "INT_VEC_RETIRED.VNNI_128",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "INT_VEC_RETIRED.VNNI_256",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe7",
+ "EventName": "INT_VEC_RETIRED.VNNI_256",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of retired loads that are blocked because it initially appears to be store forward blocked, but subsequently is shown not to be blocked based on 4K alias check.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x03",
+ "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "False dependencies in MOB due to partial compare on address.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x03",
+ "EventName": "LD_BLOCKS.ADDRESS_ALIAS",
+ "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of occurrences a retired load was blocked for any of the following reasons: utlb_miss, 4k_alias, unknown_sta/bad_fwd, unready_fwd (includes md blocks and esp consuming load blocks)",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x03",
+ "EventName": "LD_BLOCKS.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address exactly matches an older store whose data is not ready (a.k.a. unknown). unready_fwd",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x03",
+ "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x03",
+ "EventName": "LD_BLOCKS.NO_SR",
+ "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x88",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with an older store (size mismatch) - unknown_sta/bad_forward",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x03",
+ "EventName": "LD_BLOCKS.STORE_FORWARD",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x03",
+ "EventName": "LD_BLOCKS.STORE_FORWARD",
+ "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x82",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of demand loads that match on a wcb (request buffer) allocated by an L1 hardware prefetch",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x4c",
+ "EventName": "LOAD_HIT_PREFETCH.HW_PF",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0xa8",
+ "EventName": "LSD.CYCLES_ACTIVE",
+ "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "8",
+ "EventCode": "0xa8",
+ "EventName": "LSD.CYCLES_OK",
+ "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Number of Uops delivered by the LSD.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa8",
+ "EventName": "LSD.UOPS",
+ "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts all machine clears for any reason including, but not limited to memory ordering, SMC, and FP assist.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.ANY",
+ "SampleAfterValue": "20003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine without the use of microcode.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.ANY_FAST",
+ "SampleAfterValue": "20003",
+ "UMask": "0xff",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Number of machine clears (nukes) of any type.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EdgeDetect": "1",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.COUNT",
+ "PublicDescription": "Counts the number of machine clears (nukes) of any type.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of memory ordering machine clears triggered due to an internal load passing an older store within the same CPU.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.DISAMBIGUATION",
+ "SampleAfterValue": "20003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine without the use of microcode.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.DISAMBIGUATION_FAST",
+ "SampleAfterValue": "20003",
+ "UMask": "0x88",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of nukes due to memory renaming",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.MRN_NUKE",
+ "SampleAfterValue": "20003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine without the use of microcode.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.MRN_NUKE_FAST",
+ "SampleAfterValue": "20003",
+ "UMask": "0x90",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of times that the machine clears due to a page fault. Covers both I-Side and D-Side (Loads/Stores) page faults. A page fault occurs when either the page is not present, or an access violation.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.PAGE_FAULT",
+ "SampleAfterValue": "20003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of machine clears that flush the pipeline and restart the machine with the use of microcode due to SMC, MEMORY_ORDERING, FP_ASSISTS, PAGE_FAULT, DISAMBIGUATION, and FPC_VIRTUAL_TRAP.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.SLOW",
+ "SampleAfterValue": "20003",
+ "UMask": "0x6e",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Self-modifying code (SMC) detected.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.SMC",
+ "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "LFENCE instructions retired",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe0",
+ "EventName": "MISC2_RETIRED.LFENCE",
+ "PublicDescription": "number of LFENCE retired instructions",
+ "SampleAfterValue": "400009",
+ "UMask": "0x20",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe4",
+ "EventName": "MISC_RETIRED.LBR_INSERTS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "LBR record is inserted",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe4",
+ "EventName": "MISC_RETIRED.LBR_INSERTS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of CLFLUSH, CLWB, and CLDEMOTE instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe0",
+ "EventName": "MISC_RETIRED1.CL_INST",
+ "SampleAfterValue": "1000003",
+ "UMask": "0xff",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of LFENCE instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe0",
+ "EventName": "MISC_RETIRED1.LFENCE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of RDPMC, RDTSC, and RDTSCP instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe0",
+ "EventName": "MISC_RETIRED1.RDPMC_RDTSC_P",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Count the number of WRMSR instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe0",
+ "EventName": "MISC_RETIRED1.WRMSR",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of faults and software interrupts with vector < 32.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe1",
+ "EventName": "MISC_RETIRED2.FAULT_ALL",
+ "PublicDescription": "Counts the number of faults and software interrupts with vector < 32, including VOE cases.",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of PSB+ nuke events and ToPA trap events.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe1",
+ "EventName": "MISC_RETIRED2.INTEL_PT_CLEARS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of accesses to KeyLocker cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe1",
+ "EventName": "MISC_RETIRED2.KEYLOCKER_ACCESS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of misses to KeyLocker cache.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe1",
+ "EventName": "MISC_RETIRED2.KEYLOCKER_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x11",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of user interrupts delivered.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe1",
+ "EventName": "MISC_RETIRED2.ULI_DELIVERY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of SENDUIPI instructions retired.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe1",
+ "EventName": "MISC_RETIRED2.ULI_SENDUIPI",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x9",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of VM exits.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe1",
+ "EventName": "MISC_RETIRED2.VM_EXIT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x75",
+ "EventName": "SERIALIZATION.NON_C01_MS_SCB",
+ "PublicDescription": "Counts the number of issue slots not consumed by the backend due to a micro-sequencer (MS) scoreboard, which stalls the front-end from issuing from the UROM until a specified older uop retires. The most commonly executed instruction with an MS scoreboard is PAUSE.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa4",
+ "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
+ "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+ "SampleAfterValue": "10000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "TMA slots wasted due to incorrect speculations.",
+ "Counter": "0",
+ "EventCode": "0xa4",
+ "EventName": "TOPDOWN.BAD_SPEC_SLOTS",
+ "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.",
+ "SampleAfterValue": "10000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions",
+ "Counter": "0",
+ "EventCode": "0xa4",
+ "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
+ "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.",
+ "SampleAfterValue": "10000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "TOPDOWN.MEMORY_BOUND_SLOTS",
+ "Counter": "3",
+ "EventCode": "0xa4",
+ "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS",
+ "SampleAfterValue": "10000003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event",
+ "Counter": "Fixed counter 3",
+ "EventName": "TOPDOWN.SLOTS",
+ "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).",
+ "SampleAfterValue": "10000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xa4",
+ "EventName": "TOPDOWN.SLOTS_P",
+ "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method.",
+ "SampleAfterValue": "10000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Fixed Counter: Counts the number of issue slots not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.",
+ "Counter": "36",
+ "EventName": "TOPDOWN_BAD_SPECULATION.ALL",
+ "PublicDescription": "Fixed Counter: Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the IQ. Also, includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x5",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x73",
+ "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Fast Nukes such as Memory Ordering Machine clears and MRN nukes",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x73",
+ "EventName": "TOPDOWN_BAD_SPECULATION.FASTNUKE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x73",
+ "EventName": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x3",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Branch Mispredict",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x73",
+ "EventName": "TOPDOWN_BAD_SPECULATION.MISPREDICT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to a machine clear (nuke).",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x73",
+ "EventName": "TOPDOWN_BAD_SPECULATION.NUKE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xa4",
+ "EventName": "TOPDOWN_BE_BOUND.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to due to certain allocation restrictions",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.ALL_NON_ARCH",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xa4",
+ "EventName": "TOPDOWN_BE_BOUND.ALL_P",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop). This could be caused by RSV full or load/store buffer block.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to IEC and FPC RAT stalls - which can be due to the FIQ and IEC reservation station stall (integer, FP and SIMD scheduler not being able to accept another uop. )",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to mrbl stall. A 'marble' refers to a physical register file entry, also known as the physical destination (PDST).",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.REGISTER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to ROB full",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to iq/jeu scoreboards or ms scb",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.SERIALIZATION",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls.",
+ "Counter": "37",
+ "EventName": "TOPDOWN_FE_BOUND.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x6",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.ALL_NON_ARCH",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x9c",
+ "EventName": "TOPDOWN_FE_BOUND.ALL_P",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.BRANCH_DETECT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BTClear",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.BRANCH_RESTEER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to ms",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.CISC",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to decode stall",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.DECODE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8d",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to latency related stalls including BACLEARs, BTCLEARs, ITLB misses, and ICache misses.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x72",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to itlb miss",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.ITLB_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend that do not categorize into any other common frontend stall",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.OTHER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x80",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to predecode wrong",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.PREDECODE",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.",
+ "Counter": "38",
+ "EventName": "TOPDOWN_RETIRING.ALL",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x7",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of consumed retirement slots.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x72",
+ "EventName": "TOPDOWN_RETIRING.ALL_NON_ARCH",
+ "SampleAfterValue": "1000003",
+ "Unit": "cpu_atom"
},
{
- "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.",
+ "BriefDescription": "Counts the number of consumed retirement slots.",
"Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0xc5",
- "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
- "PEBS": "1",
- "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
- "SampleAfterValue": "200003",
+ "EventCode": "0xc2",
+ "EventName": "TOPDOWN_RETIRING.ALL_P",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
"Unit": "cpu_atom"
},
{
- "BriefDescription": "All mispredicted branch instructions retired.",
+ "BriefDescription": "Number of non dec-by-all uops decoded by decoder",
"Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0xc5",
- "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
- "PEBS": "1",
- "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.",
- "SampleAfterValue": "400009",
+ "EventCode": "0x76",
+ "EventName": "UOPS_DECODED.DEC0_UOPS",
+ "PublicDescription": "This event counts the number of not dec-by-all uops decoded by decoder 0.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles",
- "Counter": "Fixed counter 1",
- "EventName": "CPU_CLK_UNHALTED.CORE",
- "SampleAfterValue": "2000003",
- "UMask": "0x2",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Core cycles when the core is not in a halt state.",
- "Counter": "Fixed counter 1",
- "EventName": "CPU_CLK_UNHALTED.CORE",
- "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the programmable counters available for other events.",
+ "BriefDescription": "Uops executed on INT EU ALU ports.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb2",
+ "EventName": "UOPS_DISPATCHED.ALU",
+ "PublicDescription": "Number of ALU integer uops dispatch to execution.",
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
- "Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0x3c",
- "EventName": "CPU_CLK_UNHALTED.CORE_P",
+ "BriefDescription": "Uops executed on any INT EU ports",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb2",
+ "EventName": "UOPS_DISPATCHED.INT_EU_ALL",
+ "PublicDescription": "Number of integer uops dispatched to execution.",
"SampleAfterValue": "2000003",
- "Unit": "cpu_atom"
+ "UMask": "0x1",
+ "Unit": "cpu_core"
},
{
- "BriefDescription": "Thread cycles when thread is not in halt state [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
+ "BriefDescription": "Number of Uops dispatched/executed by any of the 3 JEUs (all ups that hold the JEU including macro; micro jumps; fetch-from-eip)",
"Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0x3c",
- "EventName": "CPU_CLK_UNHALTED.CORE_P",
- "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
+ "EventCode": "0xb2",
+ "EventName": "UOPS_DISPATCHED.JMP",
+ "PublicDescription": "Number of jump uops dispatch to execution",
"SampleAfterValue": "2000003",
+ "UMask": "0x40",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles",
- "Counter": "Fixed counter 2",
- "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+ "BriefDescription": "Uops executed on Load ports",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb2",
+ "EventName": "UOPS_DISPATCHED.LOAD",
+ "PublicDescription": "Number of Load uops dispatched to execution.",
"SampleAfterValue": "2000003",
- "UMask": "0x3",
- "Unit": "cpu_atom"
+ "UMask": "0x4",
+ "Unit": "cpu_core"
},
{
- "BriefDescription": "Reference cycles when the core is not in halt state.",
- "Counter": "Fixed counter 2",
- "EventName": "CPU_CLK_UNHALTED.REF_TSC",
- "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+ "BriefDescription": "Number of (shift) 1-cycle Uops dispatched/executed by any of the Shift Eus",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb2",
+ "EventName": "UOPS_DISPATCHED.SHIFT",
+ "PublicDescription": "Number of SHIFT integer uops dispatch to execution",
"SampleAfterValue": "2000003",
- "UMask": "0x3",
+ "UMask": "0x20",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts the number of unhalted reference clock cycles",
- "Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0x3c",
- "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
- "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.",
+ "BriefDescription": "Number of Uops dispatched/executed by Slow EU (e.g. 3+ cycles LEA, >1 cycles shift, iDIVs, CR; *H operation)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb2",
+ "EventName": "UOPS_DISPATCHED.SLOW",
+ "PublicDescription": "Number of Slow integer uops dispatch to execution.",
"SampleAfterValue": "2000003",
- "UMask": "0x1",
- "Unit": "cpu_atom"
+ "UMask": "0x8",
+ "Unit": "cpu_core"
},
{
- "BriefDescription": "Reference cycles when the core is not in halt state.",
+ "BriefDescription": "Number of Uops dispatched on STA ports",
"Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0x3c",
- "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
- "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
+ "EventCode": "0xb2",
+ "EventName": "UOPS_DISPATCHED.STA",
+ "PublicDescription": "Number of STA (Store Address) uops dispatch to execution",
"SampleAfterValue": "2000003",
- "UMask": "0x1",
+ "UMask": "0x80",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles",
- "Counter": "Fixed counter 1",
- "EventName": "CPU_CLK_UNHALTED.THREAD",
+ "BriefDescription": "Uops executed on STD ports",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb2",
+ "EventName": "UOPS_DISPATCHED.STD",
+ "PublicDescription": "Number of STD (Store Data) uops dispatch to execution",
"SampleAfterValue": "2000003",
- "UMask": "0x2",
- "Unit": "cpu_atom"
+ "UMask": "0x10",
+ "Unit": "cpu_core"
},
{
- "BriefDescription": "Core cycles when the thread is not in a halt state.",
- "Counter": "Fixed counter 1",
- "EventName": "CPU_CLK_UNHALTED.THREAD",
- "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the programmable counters available for other events.",
+ "BriefDescription": "Cycles where at least 1 uop was executed per-thread",
+ "Counter": "3",
+ "CounterMask": "1",
+ "EventCode": "0xb1",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_1",
+ "PublicDescription": "Cycles where at least 1 uop was executed per-thread.",
"SampleAfterValue": "2000003",
- "UMask": "0x2",
+ "UMask": "0x1",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.CORE_P]",
- "Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0x3c",
- "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+ "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
+ "Counter": "3",
+ "CounterMask": "2",
+ "EventCode": "0xb1",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_2",
+ "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
"SampleAfterValue": "2000003",
- "Unit": "cpu_atom"
+ "UMask": "0x1",
+ "Unit": "cpu_core"
},
{
- "BriefDescription": "Thread cycles when thread is not in halt state [This event is alias to CPU_CLK_UNHALTED.CORE_P]",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0x3c",
- "EventName": "CPU_CLK_UNHALTED.THREAD_P",
- "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. [This event is alias to CPU_CLK_UNHALTED.CORE_P]",
+ "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+ "Counter": "3",
+ "CounterMask": "3",
+ "EventCode": "0xb1",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_3",
+ "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
"SampleAfterValue": "2000003",
+ "UMask": "0x1",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Fixed Counter: Counts the number of instructions retired",
- "Counter": "Fixed counter 0",
- "EventName": "INST_RETIRED.ANY",
- "PEBS": "1",
+ "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
+ "Counter": "3",
+ "CounterMask": "4",
+ "EventCode": "0xb1",
+ "EventName": "UOPS_EXECUTED.CYCLES_GE_4",
+ "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
"SampleAfterValue": "2000003",
"UMask": "0x1",
- "Unit": "cpu_atom"
+ "Unit": "cpu_core"
},
{
- "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
- "Counter": "Fixed counter 0",
- "EventName": "INST_RETIRED.ANY",
- "PEBS": "1",
- "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+ "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+ "Counter": "3",
+ "CounterMask": "1",
+ "EventCode": "0xb1",
+ "EventName": "UOPS_EXECUTED.STALLS",
+ "Invert": "1",
+ "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
"SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts the number of instructions retired",
- "Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0xc0",
- "EventName": "INST_RETIRED.ANY_P",
- "PEBS": "1",
+ "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
+ "Counter": "3",
+ "EventCode": "0xb1",
+ "EventName": "UOPS_EXECUTED.THREAD",
"SampleAfterValue": "2000003",
- "Unit": "cpu_atom"
+ "UMask": "0x1",
+ "Unit": "cpu_core"
},
{
- "BriefDescription": "Number of instructions retired. General Counter - architectural event",
+ "BriefDescription": "Counts the number of x87 uops dispatched.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0xc0",
- "EventName": "INST_RETIRED.ANY_P",
- "PEBS": "1",
- "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
+ "EventCode": "0xb1",
+ "EventName": "UOPS_EXECUTED.X87",
+ "PublicDescription": "Counts the number of x87 uops executed.",
"SampleAfterValue": "2000003",
+ "UMask": "0x10",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with an older store (size mismatch) - unknown_sta/bad_forward",
+ "BriefDescription": "When 4-uops are requested and only 2-uops are delivered, the event counts 2. Uops_issued correlates to the number of ROB entries. If uop takes 2 ROB slots it counts as 2 uops_issued.",
"Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0x03",
- "EventName": "LD_BLOCKS.STORE_FORWARD",
- "PEBS": "1",
- "SampleAfterValue": "1000003",
- "UMask": "0x2",
+ "EventCode": "0x0e",
+ "EventName": "UOPS_ISSUED.ANY",
+ "SampleAfterValue": "200003",
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.",
+ "BriefDescription": "Uops that RAT issues to RS",
"Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0x03",
- "EventName": "LD_BLOCKS.STORE_FORWARD",
- "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.",
- "SampleAfterValue": "100003",
- "UMask": "0x82",
- "Unit": "cpu_core"
- },
- {
- "BriefDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL.",
- "Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0xe4",
- "EventName": "MISC_RETIRED.LBR_INSERTS",
- "PEBS": "1",
- "SampleAfterValue": "1000003",
+ "EventCode": "0xae",
+ "EventName": "UOPS_ISSUED.ANY",
+ "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+ "SampleAfterValue": "2000003",
"UMask": "0x1",
- "Unit": "cpu_atom"
+ "Unit": "cpu_core"
},
{
- "BriefDescription": "LBR record is inserted",
+ "BriefDescription": "UOPS_ISSUED.CYCLES",
"Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0xe4",
- "EventName": "MISC_RETIRED.LBR_INSERTS",
- "PEBS": "1",
- "SampleAfterValue": "1000003",
+ "CounterMask": "1",
+ "EventCode": "0xae",
+ "EventName": "UOPS_ISSUED.CYCLES",
+ "SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
- "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.",
- "Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0xa4",
- "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
- "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
- "SampleAfterValue": "10000003",
- "UMask": "0x2",
- "Unit": "cpu_core"
+ "BriefDescription": "Counts the number of uops retired",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.ALL",
+ "SampleAfterValue": "2000003",
+ "Unit": "cpu_atom"
},
{
- "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event",
- "Counter": "Fixed counter 3",
- "EventName": "TOPDOWN.SLOTS",
- "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).",
- "SampleAfterValue": "10000003",
- "UMask": "0x4",
+ "BriefDescription": "Cycles with retired uop(s).",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.CYCLES",
+ "PublicDescription": "Counts cycles where at least one uop has retired.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
"Unit": "cpu_core"
},
{
- "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event",
+ "BriefDescription": "Retired uops except the last uop of each instruction.",
"Counter": "0,1,2,3,4,5,6,7,8,9",
- "EventCode": "0xa4",
- "EventName": "TOPDOWN.SLOTS_P",
- "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method.",
- "SampleAfterValue": "10000003",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.HEAVY",
+ "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.",
+ "SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
- "Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0x73",
- "EventName": "TOPDOWN_BAD_SPECULATION.ALL",
- "SampleAfterValue": "1000003",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]",
- "Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0x73",
- "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P",
- "SampleAfterValue": "1000003",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]",
+ "BriefDescription": "Counts the number of integer divide uops retired",
"Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0xa4",
- "EventName": "TOPDOWN_BE_BOUND.ALL",
- "SampleAfterValue": "1000003",
- "UMask": "0x2",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.IDIV",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x10",
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]",
+ "BriefDescription": "Counts the number of uops retired that were delivered by the loop stream detector (LSD).",
"Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0xa4",
- "EventName": "TOPDOWN_BE_BOUND.ALL_P",
- "SampleAfterValue": "1000003",
- "UMask": "0x2",
- "Unit": "cpu_atom"
- },
- {
- "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls",
- "Counter": "37",
- "EventName": "TOPDOWN_FE_BOUND.ALL",
- "SampleAfterValue": "1000003",
- "UMask": "0x6",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.LSD",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x4",
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls",
+ "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.",
"Counter": "0,1,2,3,4,5,6,7",
- "EventCode": "0x9c",
- "EventName": "TOPDOWN_FE_BOUND.ALL_P",
- "SampleAfterValue": "1000003",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.MS",
+ "SampleAfterValue": "2000003",
"UMask": "0x1",
"Unit": "cpu_atom"
},
{
- "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.",
- "Counter": "38",
- "EventName": "TOPDOWN_RETIRING.ALL",
- "PEBS": "1",
- "SampleAfterValue": "1000003",
- "UMask": "0x7",
- "Unit": "cpu_atom"
+ "BriefDescription": "UOPS_RETIRED.MS",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.MS",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x8",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
},
{
- "BriefDescription": "Counts the number of consumed retirement slots.",
- "Counter": "0,1,2,3,4,5,6,7",
+ "BriefDescription": "Number of non-speculative switches to the Microcode Sequencer (MS)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EdgeDetect": "1",
"EventCode": "0xc2",
- "EventName": "TOPDOWN_RETIRING.ALL_P",
- "PEBS": "1",
- "SampleAfterValue": "1000003",
- "UMask": "0x2",
- "Unit": "cpu_atom"
+ "EventName": "UOPS_RETIRED.MS_SWITCHES",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x8",
+ "PublicDescription": "Switches to the Microcode Sequencer",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
},
{
"BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.",
@@ -330,5 +2007,26 @@
"SampleAfterValue": "2000003",
"UMask": "0x2",
"Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles without actually retired uops.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.STALLS",
+ "Invert": "1",
+ "PublicDescription": "This event counts cycles without actually retired uops.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of x87 uops retired, includes those in ms flows",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.X87",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json
new file mode 100644
index 000000000000..9046b680649d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/uncore-memory.json
@@ -0,0 +1,18 @@
+[
+ {
+ "BriefDescription": "Read CAS command sent to DRAM",
+ "Counter": "0,1,2,3,4",
+ "EventCode": "0x22",
+ "EventName": "UNC_M_CAS_COUNT_RD",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ },
+ {
+ "BriefDescription": "Write CAS command sent to DRAM",
+ "Counter": "0,1,2,3,4",
+ "EventCode": "0x23",
+ "EventName": "UNC_M_CAS_COUNT_WR",
+ "PerPkg": "1",
+ "Unit": "iMC"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json
index 59af79e3466e..defa3a967754 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json
@@ -1,4 +1,70 @@
[
+ {
+ "BriefDescription": "Counts the number of page walks initiated by a demand load that missed the first and second level TLBs.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x08",
+ "EventName": "DTLB_LOAD_MISSES.MISS_CAUSED_WALK",
+ "SampleAfterValue": "200003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts walks that miss the PDE_CACHE",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x08",
+ "EventName": "DTLB_LOAD_MISSES.PDE_CACHE_MISS",
+ "SampleAfterValue": "200003",
+ "UMask": "0x80",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x08",
+ "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+ "SampleAfterValue": "200003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Loads that miss the DTLB and hit the STLB.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x12",
+ "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+ "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
+ "SampleAfterValue": "100003",
+ "UMask": "0x320",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Account for 4k page size only. Will result in a DTLB write from STLB.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x08",
+ "EventName": "DTLB_LOAD_MISSES.STLB_HIT_4K",
+ "SampleAfterValue": "200003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Account for large page sizes only. Will result in a DTLB write from STLB.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x08",
+ "EventName": "DTLB_LOAD_MISSES.STLB_HIT_LGPG",
+ "SampleAfterValue": "200003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0x12",
+ "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
+ "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts the number of page walks completed due to load DTLB misses to any page size.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -19,6 +85,125 @@
"UMask": "0xe",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Page walks completed due to a demand data load to a 1G page.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x12",
+ "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
+ "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 2M or 4M page.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x08",
+ "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
+ "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x12",
+ "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
+ "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 4K page.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x08",
+ "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
+ "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Page walks completed due to a demand data load to a 4K page.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x12",
+ "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
+ "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x08",
+ "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
+ "PublicDescription": "Counts the number of page walks outstanding for Loads (demand or SW prefetch) in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x12",
+ "EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
+ "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks initiated by a store that missed the first and second level TLBs.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x49",
+ "EventName": "DTLB_STORE_MISSES.MISS_CAUSED_WALK",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts walks that miss the PDE_CACHE",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x49",
+ "EventName": "DTLB_STORE_MISSES.PDE_CACHE_MISS",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x80",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of first level TLB misses but second level hits due to stores that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x49",
+ "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+ "PublicDescription": "Counts the number of first level TLB misses but second level hits due to a demand load that did not start a page walk. Accounts for all page sizes. Will result in a DTLB write from STLB.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Stores that miss the DTLB and hit the STLB.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x13",
+ "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+ "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
+ "SampleAfterValue": "100003",
+ "UMask": "0x320",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0x13",
+ "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
+ "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts the number of page walks completed due to store DTLB misses to any page size.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -39,6 +224,134 @@
"UMask": "0xe",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Page walks completed due to a demand data store to a 1G page.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x13",
+ "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
+ "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 2M or 4M page.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x49",
+ "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
+ "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x13",
+ "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
+ "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 4K page.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x49",
+ "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
+ "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Page walks completed due to a demand data store to a 4K page.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x13",
+ "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
+ "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x49",
+ "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
+ "PublicDescription": "Counts the number of page walks outstanding in the page miss handler (PMH) for stores every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x13",
+ "EventName": "DTLB_STORE_MISSES.WALK_PENDING",
+ "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of times there was an ITLB miss and a new translation was filled into the ITLB.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x81",
+ "EventName": "ITLB.FILLS",
+ "PublicDescription": "Counts the number of times the machine was unable to find a translation in the Instruction Translation Lookaside Buffer (ITLB) and a new translation was filled into the ITLB. The event is speculative in nature, but will not count translations (page walks) that are begun and not finished, or translations that are finished but not filled into the ITLB.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks initiated by a instruction fetch that missed the first and second level TLBs.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x85",
+ "EventName": "ITLB_MISSES.MISS_CAUSED_WALK",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts walks that miss the PDE_CACHE",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x85",
+ "EventName": "ITLB_MISSES.PDE_CACHE_MISS",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x80",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of first level TLB misses but second level hits due to an instruction fetch that did not start a page walk. Account for all pages sizes. Will result in an ITLB write from STLB.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x85",
+ "EventName": "ITLB_MISSES.STLB_HIT",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x11",
+ "EventName": "ITLB_MISSES.STLB_HIT",
+ "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
+ "SampleAfterValue": "100003",
+ "UMask": "0x120",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "CounterMask": "1",
+ "EventCode": "0x11",
+ "EventName": "ITLB_MISSES.WALK_ACTIVE",
+ "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.",
"Counter": "0,1,2,3,4,5,6,7",
@@ -58,5 +371,120 @@
"SampleAfterValue": "100003",
"UMask": "0xe",
"Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 2M or 4M page.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x85",
+ "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
+ "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 2M or 4M pages. Includes page walks that page fault.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x11",
+ "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
+ "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to a 4K page.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x85",
+ "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+ "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to 4K pages. Includes page walks that page fault.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x11",
+ "EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
+ "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of page walks outstanding for iside in PMH every cycle.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x85",
+ "EventName": "ITLB_MISSES.WALK_PENDING",
+ "PublicDescription": "Counts the number of page walks outstanding for iside in PMH every cycle. A PMH page walk is outstanding from page walk start till PMH becomes idle again (ready to serve next walk). Includes EPT-walk intervals. Walks could be counted by edge detecting on this event, but would count restarted suspended walks.",
+ "SampleAfterValue": "200003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0x11",
+ "EventName": "ITLB_MISSES.WALK_PENDING",
+ "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x10",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts the number of occurrences a load gets blocked because of a micro TLB miss",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x03",
+ "EventName": "LD_BLOCKS.DTLB_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer is stalled due to a DTLB miss",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.DTLB_MISS",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x10",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DTLB miss.",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x05",
+ "EventName": "LD_HEAD.DTLB_MISS_AT_RET",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x90",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of PMH walks that hit in the L1 or WCBs",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xbc",
+ "EventName": "PAGE_WALKER_LOADS.DTLB_L1_HIT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of PMH walks that hit in the L2",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xbc",
+ "EventName": "PAGE_WALKER_LOADS.DTLB_L2_HIT",
+ "PublicDescription": "Counts the number of PMH walks that hit in the L2. Includes L2 Hit resulting from and L1D eviction of another core in the same module which is longer latency than a typical L2 hit.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Count number of any STLB flush attempts (Entire, PCID, InvPage, CR3 write, etc)",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xbd",
+ "EventName": "TLB_FLUSHES.STLB_ANY",
+ "SampleAfterValue": "20003",
+ "UMask": "0x20",
+ "Unit": "cpu_atom"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 4472efb5bf9f..6a18b70ec19c 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -21,7 +21,7 @@ GenuineIntel-6-3A,v24,ivybridge,core
GenuineIntel-6-3E,v24,ivytown,core
GenuineIntel-6-2D,v24,jaketown,core
GenuineIntel-6-(57|85),v16,knightslanding,core
-GenuineIntel-6-BD,v1.01,lunarlake,core
+GenuineIntel-6-BD,v1.09,lunarlake,core
GenuineIntel-6-A[AC],v1.10,meteorlake,core
GenuineIntel-6-1[AEF],v4,nehalemep,core
GenuineIntel-6-2E,v4,nehalemex,core
--
2.47.1.545.g3c1d2e2a6a-goog© 2016 - 2024 Red Hat, Inc.