korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-09-21 20:22:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

perf vendor events: Update graniterapids events and add counter information

Browse Source 
Update events from v1.01 to v1.02.

Bring in the event updates v1.02:
0ff9f681bd

Add counter information. The most recent RFC patch set using this
information:
https://lore.kernel.org/lkml/20240412210756.309828-1-weilin.wang@intel.com/

There are over 1000 new events.

Co-authored-by: Weilin Wang <weilin.wang@intel.com>
Co-authored-by: Caleb Biggers <caleb.biggers@intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Alexandre Torgue <alexandre.torgue@foss.st.com>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240620181752.3945845-14-irogers@google.com
This commit is contained in:
Ian Rogers 2024-06-20 11:17:27 -07:00 committed by Namhyung Kim
parent 39c1471e3e
commit 917f63ad75
15 changed files with 10975 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

825
tools/perf/pmu-events/arch/x86/graniterapids/cache.json
View File

@ -1,6 +1,135 @@
[
{
"BriefDescription": "L1D.HWPF_MISS",
"Counter": "0,1,2,3",
"EventCode": "0x51",
"EventName": "L1D.HWPF_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x20"
},
{
"BriefDescription": "Counts the number of cache lines replaced in L1 data cache.",
"Counter": "0,1,2,3",
"EventCode": "0x51",
"EventName": "L1D.REPLACEMENT",
"PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.",
"Counter": "0,1,2,3",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.FB_FULL",
"PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability.",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.FB_FULL_PERIODS",
"PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.",
"Counter": "0,1,2,3",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.L2_STALLS",
"PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of L1D misses that are outstanding",
"Counter": "0,1,2,3",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.PENDING",
"PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles with L1D load Misses outstanding.",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x48",
"EventName": "L1D_PEND_MISS.PENDING_CYCLES",
"PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "L2 cache lines filling L2",
"Counter": "0,1,2,3",
"EventCode": "0x25",
"EventName": "L2_LINES_IN.ALL",
"PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.",
"SampleAfterValue": "100003",
"UMask": "0x1f"
},
{
"BriefDescription": "Modified cache lines that are evicted by L2 cache when triggered by an L2 cache fill.",
"Counter": "0,1,2,3",
"EventCode": "0x26",
"EventName": "L2_LINES_OUT.NON_SILENT",
"PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.",
"Counter": "0,1,2,3",
"EventCode": "0x26",
"EventName": "L2_LINES_OUT.SILENT",
"PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses",
"Counter": "0,1,2,3",
"EventCode": "0x26",
"EventName": "L2_LINES_OUT.USELESS_HWPF",
"PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES]",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_REQUEST.ALL",
"PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]",
"SampleAfterValue": "200003",
"UMask": "0xff"
},
{
"BriefDescription": "All requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_REQUEST.HIT",
"PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_RQSTS.HIT]",
"SampleAfterValue": "200003",
"UMask": "0xdf"
},
{
"BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_RQSTS.MISS]",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_REQUEST.MISS",
"PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]",
"SampleAfterValue": "200003",
"UMask": "0x3f"
},
{
"BriefDescription": "L2 code requests",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_CODE_RD",
"PublicDescription": "Counts the total number of L2 code requests.",
@ -9,14 +138,167 @@
},
{
"BriefDescription": "Demand Data Read access L2 cache",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
"PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.",
"SampleAfterValue": "200003",
"UMask": "0xe1"
},
{
"BriefDescription": "Demand requests that miss L2 cache",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_DEMAND_MISS",
"PublicDescription": "Counts demand requests that miss L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0x27"
},
{
"BriefDescription": "Demand requests to L2 cache",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES",
"PublicDescription": "Counts demand requests to L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0xe7"
},
{
"BriefDescription": "L2_RQSTS.ALL_HWPF",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_HWPF",
"SampleAfterValue": "200003",
"UMask": "0xf0"
},
{
"BriefDescription": "RFO requests to L2 cache",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.ALL_RFO",
"PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.",
"SampleAfterValue": "200003",
"UMask": "0xe2"
},
{
"BriefDescription": "L2 cache hits when fetching instructions, code reads.",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.CODE_RD_HIT",
"PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
"SampleAfterValue": "200003",
"UMask": "0xc4"
},
{
"BriefDescription": "L2 cache misses when fetching instructions",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.CODE_RD_MISS",
"PublicDescription": "Counts L2 cache misses when fetching instructions.",
"SampleAfterValue": "200003",
"UMask": "0x24"
},
{
"BriefDescription": "Demand Data Read requests that hit L2 cache",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
"PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0xc1"
},
{
"BriefDescription": "Demand Data Read miss L2 cache",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS",
"PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.",
"SampleAfterValue": "200003",
"UMask": "0x21"
},
{
"BriefDescription": "All requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.HIT",
"PublicDescription": "Counts all requests that hit L2 cache. [This event is alias to L2_REQUEST.HIT]",
"SampleAfterValue": "200003",
"UMask": "0xdf"
},
{
"BriefDescription": "L2_RQSTS.HWPF_MISS",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.HWPF_MISS",
"SampleAfterValue": "200003",
"UMask": "0x30"
},
{
"BriefDescription": "Read requests with true-miss in L2 cache [This event is alias to L2_REQUEST.MISS]",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.MISS",
"PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]",
"SampleAfterValue": "200003",
"UMask": "0x3f"
},
{
"BriefDescription": "All accesses to L2 cache [This event is alias to L2_REQUEST.ALL]",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.REFERENCES",
"PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]",
"SampleAfterValue": "200003",
"UMask": "0xff"
},
{
"BriefDescription": "RFO requests that hit L2 cache",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.RFO_HIT",
"PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0xc2"
},
{
"BriefDescription": "RFO requests that miss L2 cache",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.RFO_MISS",
"PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0x22"
},
{
"BriefDescription": "SW prefetch requests that hit L2 cache.",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.SWPF_HIT",
"PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
"SampleAfterValue": "200003",
"UMask": "0xc8"
},
{
"BriefDescription": "SW prefetch requests that miss L2 cache.",
"Counter": "0,1,2,3",
"EventCode": "0x24",
"EventName": "L2_RQSTS.SWPF_MISS",
"PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
"SampleAfterValue": "200003",
"UMask": "0x28"
},
{
"BriefDescription": "L2 writebacks that access L2 cache",
"Counter": "0,1,2,3",
"EventCode": "0x23",
"EventName": "L2_TRANS.L2_WB",
"PublicDescription": "Counts L2 writebacks that access L2 cache.",
"SampleAfterValue": "200003",
"UMask": "0x40"
},
{
"BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x2e",
"EventName": "LONGEST_LAT_CACHE.MISS",
"PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
@ -25,6 +307,7 @@
},
{
"BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x2e",
"EventName": "LONGEST_LAT_CACHE.REFERENCE",
"PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
@ -33,6 +316,7 @@
},
{
"BriefDescription": "Retired load instructions.",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ALL_LOADS",
@ -43,6 +327,7 @@
},
{
"BriefDescription": "Retired store instructions.",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ALL_STORES",
@ -50,5 +335,545 @@
"PublicDescription": "Counts all retired store instructions.",
"SampleAfterValue": "1000003",
"UMask": "0x82"
},
{
"BriefDescription": "All retired memory instructions.",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.ANY",
"PEBS": "1",
"PublicDescription": "Counts all retired memory instructions - loads and stores.",
"SampleAfterValue": "1000003",
"UMask": "0x83"
},
{
"BriefDescription": "Retired load instructions with locked access.",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.LOCK_LOADS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with locked access.",
"SampleAfterValue": "100007",
"UMask": "0x21"
},
{
"BriefDescription": "Retired load instructions that split across a cacheline boundary.",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.SPLIT_LOADS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions that split across a cacheline boundary.",
"SampleAfterValue": "100003",
"UMask": "0x41"
},
{
"BriefDescription": "Retired store instructions that split across a cacheline boundary.",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.SPLIT_STORES",
"PEBS": "1",
"PublicDescription": "Counts retired store instructions that split across a cacheline boundary.",
"SampleAfterValue": "100003",
"UMask": "0x42"
},
{
"BriefDescription": "Retired load instructions that hit the STLB.",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_HIT_LOADS",
"PEBS": "1",
"PublicDescription": "Number of retired load instructions with a clean hit in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x9"
},
{
"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",
"PEBS": "1",
"PublicDescription": "Number of retired store instructions that hit in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0xa"
},
{
"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",
"PEBS": "1",
"PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x11"
},
{
"BriefDescription": "Retired store instructions that miss the STLB.",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd0",
"EventName": "MEM_INST_RETIRED.STLB_MISS_STORES",
"PEBS": "1",
"PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x12"
},
{
"BriefDescription": "Completed demand load uops that miss the L1 d-cache.",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY",
"PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)",
"SampleAfterValue": "1000003",
"UMask": "0xfd"
},
{
"BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.",
"SampleAfterValue": "20011",
"UMask": "0x4"
},
{
"BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS",
"PEBS": "1",
"PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
"SampleAfterValue": "20011",
"UMask": "0x1"
},
{
"BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd2",
"EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "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",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.",
"SampleAfterValue": "20011",
"UMask": "0x2"
},
{
"BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM",
"PEBS": "1",
"PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.",
"SampleAfterValue": "100007",
"UMask": "0x1"
},
{
"BriefDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM",
"PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD",
"PEBS": "1",
"PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.",
"SampleAfterValue": "100007",
"UMask": "0x8"
},
{
"BriefDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd3",
"EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM",
"PEBS": "1",
"SampleAfterValue": "1000003",
"UMask": "0x4"
},
{
"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",
"PEBS": "1",
"PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).",
"SampleAfterValue": "100007",
"UMask": "0x4"
},
{
"BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.FB_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
"SampleAfterValue": "100007",
"UMask": "0x40"
},
{
"BriefDescription": "Retired load instructions with L1 cache hits as data sources",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L1_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Retired load instructions missed L1 cache as data sources",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L1_MISS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.",
"SampleAfterValue": "200003",
"UMask": "0x8"
},
{
"BriefDescription": "Retired load instructions with L2 cache hits as data sources",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L2_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.",
"SampleAfterValue": "200003",
"UMask": "0x2"
},
{
"BriefDescription": "Retired load instructions missed L2 cache as data sources",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L2_MISS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions missed L2 cache as data sources.",
"SampleAfterValue": "100021",
"UMask": "0x10"
},
{
"BriefDescription": "Retired load instructions with L3 cache hits as data sources",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L3_HIT",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.",
"SampleAfterValue": "100021",
"UMask": "0x4"
},
{
"BriefDescription": "Retired load instructions missed L3 cache as data sources",
"Counter": "0,1,2,3",
"Data_LA": "1",
"EventCode": "0xd1",
"EventName": "MEM_LOAD_RETIRED.L3_MISS",
"PEBS": "1",
"PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.",
"SampleAfterValue": "50021",
"UMask": "0x20"
},
{
"BriefDescription": "MEM_STORE_RETIRED.L2_HIT",
"Counter": "0,1,2,3",
"EventCode": "0x44",
"EventName": "MEM_STORE_RETIRED.L2_HIT",
"SampleAfterValue": "200003",
"UMask": "0x1"
},
{
"BriefDescription": "Retired memory uops for any access",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe5",
"EventName": "MEM_UOP_RETIRED.ANY",
"PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses",
"SampleAfterValue": "1000003",
"UMask": "0x3"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F803C0004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F803C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x8003C0001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.L3_HIT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F803C0002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10003C0002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.L3_HIT",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F003C4477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Any memory transaction that reached the SQ.",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.ALL_REQUESTS",
"PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Demand and prefetch data reads",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DATA_RD",
"PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Cacheable and Non-Cacheable code read requests",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD",
"PublicDescription": "Counts both cacheable and Non-Cacheable code read requests.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Demand Data Read requests sent to uncore",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD",
"PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.DEMAND_RFO",
"PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"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"
},
{
"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"
},
{
"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"
},
{
"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"
},
{
"BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
"Counter": "0,1,2,3",
"EventCode": "0x20",
"EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"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"
},
{
"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"
},
{
"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"
},
{
"BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.",
"Counter": "0,1,2,3",
"EventCode": "0x2c",
"EventName": "SQ_MISC.BUS_LOCK",
"PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Counts the number of PREFETCHNTA, PREFETCHW, PREFETCHT0, PREFETCHT1 or PREFETCHT2 instructions executed.",
"Counter": "0,1,2,3",
"EventCode": "0x40",
"EventName": "SW_PREFETCH_ACCESS.ANY",
"SampleAfterValue": "100003",
"UMask": "0xf"
},
{
"BriefDescription": "Number of PREFETCHNTA instructions executed.",
"Counter": "0,1,2,3",
"EventCode": "0x40",
"EventName": "SW_PREFETCH_ACCESS.NTA",
"PublicDescription": "Counts the number of PREFETCHNTA instructions executed.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of PREFETCHW instructions executed.",
"Counter": "0,1,2,3",
"EventCode": "0x40",
"EventName": "SW_PREFETCH_ACCESS.PREFETCHW",
"PublicDescription": "Counts the number of PREFETCHW instructions executed.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Number of PREFETCHT0 instructions executed.",
"Counter": "0,1,2,3",
"EventCode": "0x40",
"EventName": "SW_PREFETCH_ACCESS.T0",
"PublicDescription": "Counts the number of PREFETCHT0 instructions executed.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.",
"Counter": "0,1,2,3",
"EventCode": "0x40",
"EventName": "SW_PREFETCH_ACCESS.T1_T2",
"PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.",
"SampleAfterValue": "100003",
"UMask": "0x4"
}
]

77
tools/perf/pmu-events/arch/x86/graniterapids/counter.json Normal file
View File

@ -0,0 +1,77 @@
[
{
"Unit": "core",
"CountersNumFixed": "4",
"CountersNumGeneric": "8"
},
{
"Unit": "B2CMI",
"CountersNumFixed": "0",
"CountersNumGeneric": "4"
},
{
"Unit": "CHA",
"CountersNumFixed": "0",
"CountersNumGeneric": "4"
},
{
"Unit": "IMC",
"CountersNumFixed": "0",
"CountersNumGeneric": "4"
},
{
"Unit": "B2HOT",
"CountersNumFixed": "0",
"CountersNumGeneric": 4
},
{
"Unit": "IIO",
"CountersNumFixed": "0",
"CountersNumGeneric": "4"
},
{
"Unit": "IRP",
"CountersNumFixed": "0",
"CountersNumGeneric": "4"
},
{
"Unit": "UPI",
"CountersNumFixed": "0",
"CountersNumGeneric": "4"
},
{
"Unit": "B2UPI",
"CountersNumFixed": "0",
"CountersNumGeneric": 4
},
{
"Unit": "B2CXL",
"CountersNumFixed": "0",
"CountersNumGeneric": 4
},
{
"Unit": "PCU",
"CountersNumFixed": "0",
"CountersNumGeneric": 4
},
{
"Unit": "CHACMS",
"CountersNumFixed": "0",
"CountersNumGeneric": 4
},
{
"Unit": "MDF",
"CountersNumFixed": "0",
"CountersNumGeneric": "4"
},
{
"Unit": "CXLCM",
"CountersNumFixed": "0",
"CountersNumGeneric": 8
},
{
"Unit": "CXLDP",
"CountersNumFixed": "0",
"CountersNumGeneric": 4
}
]

242
tools/perf/pmu-events/arch/x86/graniterapids/floating-point.json Normal file
View File

@ -0,0 +1,242 @@
[
{
"BriefDescription": "This event counts the cycles the floating point divider is busy.",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0xb0",
"EventName": "ARITH.FPDIV_ACTIVE",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all microcode FP assists.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.FP",
"PublicDescription": "Counts all microcode Floating Point assists.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "ASSISTS.SSE_AVX_MIX",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.SSE_AVX_MIX",
"SampleAfterValue": "1000003",
"UMask": "0x10"
},
{
"BriefDescription": "FP_ARITH_DISPATCHED.PORT_0 [This event is alias to FP_ARITH_DISPATCHED.V0]",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_0",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "FP_ARITH_DISPATCHED.PORT_1 [This event is alias to FP_ARITH_DISPATCHED.V1]",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_1",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "FP_ARITH_DISPATCHED.PORT_5 [This event is alias to FP_ARITH_DISPATCHED.V2]",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.PORT_5",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "FP_ARITH_DISPATCHED.V0 [This event is alias to FP_ARITH_DISPATCHED.PORT_0]",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.V0",
"SampleAfterValue": "2000003",
"UMask": "0x1"
},
{
"BriefDescription": "FP_ARITH_DISPATCHED.V1 [This event is alias to FP_ARITH_DISPATCHED.PORT_1]",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.V1",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "FP_ARITH_DISPATCHED.V2 [This event is alias to FP_ARITH_DISPATCHED.PORT_5]",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb3",
"EventName": "FP_ARITH_DISPATCHED.V2",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
"PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x18"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
"BriefDescription": "Counts number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
"PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
{
"BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.8_FLOPS",
"PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x60"
},
{
"BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR",
"PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "1000003",
"UMask": "0x3"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of any Vector retired FP arithmetic instructions",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.VECTOR",
"PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "1000003",
"UMask": "0xfc"
},
{
"BriefDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcf",
"EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcf",
"EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcf",
"EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcf",
"EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of all Scalar Half-Precision FP arithmetic instructions(1) retired - regular and complex.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcf",
"EventName": "FP_ARITH_INST_RETIRED2.SCALAR",
"PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR",
"SampleAfterValue": "100003",
"UMask": "0x3"
},
{
"BriefDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcf",
"EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Number of all Vector (also called packed) Half-Precision FP arithmetic instructions(1) retired.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcf",
"EventName": "FP_ARITH_INST_RETIRED2.VECTOR",
"PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR",
"SampleAfterValue": "100003",
"UMask": "0x1c"
}
]

469
tools/perf/pmu-events/arch/x86/graniterapids/frontend.json
View File

@ -1,9 +1,474 @@
[
{
"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": "Clears due to Unknown Branches.",
"Counter": "0,1,2,3",
"EventCode": "0x60",
"EventName": "BACLEARS.ANY",
"PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"Counter": "0,1,2,3",
"EventCode": "0x87",
"EventName": "DECODE.LCP",
"PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.",
"SampleAfterValue": "500009",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles the Microcode Sequencer is busy.",
"Counter": "0,1,2,3",
"EventCode": "0x87",
"EventName": "DECODE.MS_BUSY",
"SampleAfterValue": "500009",
"UMask": "0x2"
},
{
"BriefDescription": "DSB-to-MITE switch true penalty cycles.",
"Counter": "0,1,2,3",
"EventCode": "0x61",
"EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
"PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Retired ANT branches",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ANY_ANT",
"MSRIndex": "0x3F7",
"MSRValue": "0x9",
"PEBS": "1",
"PublicDescription": "Always Not Taken (ANT) conditional retired branches (no BTB entry and not mispredicted)",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired Instructions who experienced DSB miss.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x1",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired Instructions who experienced a critical DSB miss.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
"PEBS": "1",
"PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired Instructions who experienced iTLB true miss.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.ITLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x14",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L1I_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x12",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.L2_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x13",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x600106",
"PEBS": "1",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_128",
"MSRIndex": "0x3F7",
"MSRValue": "0x608006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
"MSRIndex": "0x3F7",
"MSRValue": "0x601006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
"MSRIndex": "0x3F7",
"MSRValue": "0x600206",
"PEBS": "1",
"PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
"MSRIndex": "0x3F7",
"MSRValue": "0x610006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
"MSRIndex": "0x3F7",
"MSRValue": "0x100206",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
"MSRIndex": "0x3F7",
"MSRValue": "0x602006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
"MSRIndex": "0x3F7",
"MSRValue": "0x600406",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
"MSRIndex": "0x3F7",
"MSRValue": "0x620006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
"MSRIndex": "0x3F7",
"MSRValue": "0x604006",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
"MSRIndex": "0x3F7",
"MSRValue": "0x600806",
"PEBS": "1",
"PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "I-Cache miss too close to Code Prefetch Instruction",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.LATE_SWPF",
"MSRIndex": "0x3F7",
"MSRValue": "0x9",
"PEBS": "1",
"PublicDescription": "Number of Instruction Cache demand miss in shadow of an on-going i-fetch cache-line triggered by PREFETCHIT0/1 instructions",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Mispredicted Retired ANT branches",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.MISP_ANT",
"MSRIndex": "0x3F7",
"MSRValue": "0x9",
"PEBS": "1",
"PublicDescription": "ANT retired branches that got just mispredicted",
"SampleAfterValue": "100007",
"UMask": "0x2"
},
{
"BriefDescription": "FRONTEND_RETIRED.MS_FLOWS",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.MS_FLOWS",
"MSRIndex": "0x3F7",
"MSRValue": "0x8",
"PEBS": "1",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.STLB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x15",
"PEBS": "1",
"PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH",
"MSRIndex": "0x3F7",
"MSRValue": "0x17",
"PEBS": "1",
"SampleAfterValue": "100007",
"UMask": "0x3"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALLS",
"PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.",
"SampleAfterValue": "500009",
"UMask": "0x4"
},
{
"BriefDescription": "ICACHE_DATA.STALL_PERIODS",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0x80",
"EventName": "ICACHE_DATA.STALL_PERIODS",
"SampleAfterValue": "500009",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"Counter": "0,1,2,3",
"EventCode": "0x83",
"EventName": "ICACHE_TAG.STALLS",
"PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.",
"SampleAfterValue": "200003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.DSB_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles DSB is delivering optimal number of Uops",
"Counter": "0,1,2,3",
"CounterMask": "6",
"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"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.DSB_UOPS",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
{
"BriefDescription": "Cycles MITE is delivering any Uop",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_ANY",
"PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles MITE is delivering optimal number of Uops",
"Counter": "0,1,2,3",
"CounterMask": "6",
"EventCode": "0x79",
"EventName": "IDQ.MITE_CYCLES_OK",
"PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MITE_UOPS",
"PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
"SampleAfterValue": "2000003",
"UMask": "0x4"
},
{
"BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x79",
"EventName": "IDQ.MS_CYCLES_ANY",
"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"
},
{
"BriefDescription": "Number of switches from DSB or MITE to the MS",
"Counter": "0,1,2,3",
"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"
},
{
"BriefDescription": "Uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy",
"Counter": "0,1,2,3",
"EventCode": "0x79",
"EventName": "IDQ.MS_UOPS",
"PublicDescription": "Counts the number of uops initiated by MITE or Decode Stream Buffer (DSB) and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.",
"SampleAfterValue": "1000003",
"UMask": "0x20"
},
{
"BriefDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.CORE",
"PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nThe count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
"PublicDescription": "This event counts a subset of the Topdown Slots event that when no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "6",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
"PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x9c",
"EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
"Invert": "1",
"PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
"PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "6",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
"PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
"PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
"SampleAfterValue": "1000003",
"UMask": "0x1"
}

175
tools/perf/pmu-events/arch/x86/graniterapids/memory.json
View File

@ -1,6 +1,85 @@
[
{
"BriefDescription": "Cycles while L3 cache miss demand load is outstanding.",
"Counter": "0,1,2,3",
"CounterMask": "2",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.",
"Counter": "0,1,2,3",
"CounterMask": "6",
"EventCode": "0xa3",
"EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x6"
},
{
"BriefDescription": "Number of machine clears due to memory ordering conflicts.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
"PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Cycles while L1 cache miss demand load is outstanding.",
"Counter": "0,1,2,3",
"CounterMask": "2",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.",
"Counter": "0,1,2,3",
"CounterMask": "3",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS",
"SampleAfterValue": "1000003",
"UMask": "0x3"
},
{
"BriefDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding.",
"Counter": "0,1,2,3",
"CounterMask": "5",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS",
"PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
"SampleAfterValue": "1000003",
"UMask": "0x5"
},
{
"BriefDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding.",
"Counter": "0,1,2,3",
"CounterMask": "9",
"EventCode": "0x47",
"EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS",
"PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).",
"SampleAfterValue": "1000003",
"UMask": "0x9"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024",
"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"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
@ -13,6 +92,7 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
@ -23,8 +103,22 @@
"SampleAfterValue": "20011",
"UMask": "0x1"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
"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"
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
@ -37,6 +131,7 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
@ -49,6 +144,7 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
@ -61,6 +157,7 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
@ -73,6 +170,7 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
@ -85,6 +183,7 @@
},
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
"Counter": "1,2,3,4,5,6,7",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
@ -97,6 +196,7 @@
},
{
"BriefDescription": "Retired memory store access operations. A PDist event for PEBS Store Latency Facility.",
"Counter": "0",
"Data_LA": "1",
"EventCode": "0xcd",
"EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE",
@ -105,8 +205,19 @@
"SampleAfterValue": "1000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_CODE_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3FBFC00004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
@ -116,6 +227,7 @@
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
@ -124,51 +236,40 @@
"UMask": "0x1"
},
{
"BriefDescription": "Number of times an RTM execution aborted.",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.ABORTED",
"PublicDescription": "Counts the number of times RTM abort was triggered.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Number of times an RTM execution successfully committed",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.COMMIT",
"PublicDescription": "Counts the number of times RTM commit succeeded.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of times an RTM execution started.",
"EventCode": "0xc9",
"EventName": "RTM_RETIRED.START",
"PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.",
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.L3_MISS",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F3FC04477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_READ",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads",
"BriefDescription": "Counts demand data read requests that miss the L3 cache.",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
"SampleAfterValue": "100003",
"UMask": "0x80"
"UMask": "0x10"
},
{
"BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CAPACITY_WRITE",
"PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.",
"SampleAfterValue": "100003",
"UMask": "0x2"
"BriefDescription": "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"
},
{
"BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address",
"EventCode": "0x54",
"EventName": "TX_MEM.ABORT_CONFLICT",
"PublicDescription": "Counts the number of times a TSX line had a cache conflict.",
"SampleAfterValue": "100003",
"UMask": "0x1"
"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"
}
]

150
tools/perf/pmu-events/arch/x86/graniterapids/other.json
View File

@ -1,6 +1,53 @@
[
{
"BriefDescription": "ASSISTS.PAGE_FAULT",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc1",
"EventName": "ASSISTS.PAGE_FAULT",
"SampleAfterValue": "1000003",
"UMask": "0x8"
},
{
"BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xb7",
"EventName": "EXE.AMX_BUSY",
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_CODE_RD.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x73C000004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x104000004",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
@ -9,21 +56,112 @@
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
"BriefDescription": "Counts demand data reads that were supplied by DRAM.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM",
"EventName": "OCR.DEMAND_DATA_RD.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x104000001",
"MSRValue": "0x73C000001",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
"EventName": "OCR.DEMAND_RFO.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F3FFC0002",
"MSRValue": "0x73C000002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.DEMAND_RFO.LOCAL_DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x104000002",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10808",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x3F3FFC4477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.READS_TO_CORE.DRAM",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x73C004477",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"Counter": "0,1,2,3",
"EventCode": "0x2A,0x2B",
"EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
"MSRIndex": "0x1a6,0x1a7",
"MSRValue": "0x10800",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa5",
"EventName": "RS.EMPTY",
"PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
"SampleAfterValue": "1000003",
"UMask": "0x7"
},
{
"BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.",
"Counter": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
"EdgeDetect": "1",
"EventCode": "0xa5",
"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"
},
{
"BriefDescription": "Cycles when RS was empty and a resource allocation stall is asserted",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xa5",
"EventName": "RS.EMPTY_RESOURCE",
"SampleAfterValue": "1000003",
"UMask": "0x1"
},
{
"BriefDescription": "Cycles the uncore cannot take further requests",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x2d",
"EventName": "XQ.FULL_CYCLES",
"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"
}
]

1009
tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json
View File

File diff suppressed because it is too large Load Diff

3674
tools/perf/pmu-events/arch/x86/graniterapids/uncore-cache.json Normal file
View File

File diff suppressed because it is too large Load Diff

31
tools/perf/pmu-events/arch/x86/graniterapids/uncore-cxl.json Normal file
View File

@ -0,0 +1,31 @@
[
{
"BriefDescription": "B2CXL Clockticks",
"Counter": "0,1,2,3",
"EventCode": "0x01",
"EventName": "UNC_B2CXL_CLOCKTICKS",
"PerPkg": "1",
"PortMask": "0x000",
"Unit": "B2CXL"
},
{
"BriefDescription": "Number of Allocation to Mem Data Packing buffer",
"Counter": "4,5,6,7",
"EventCode": "0x41",
"EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.MEM_DATA",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x10",
"Unit": "CXLCM"
},
{
"BriefDescription": "Number of Allocation to M2S Data AGF",
"Counter": "0,1,2,3",
"EventCode": "0x02",
"EventName": "UNC_CXLDP_TxC_AGF_INSERTS.M2S_DATA",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x20",
"Unit": "CXLDP"
}
]

1849
tools/perf/pmu-events/arch/x86/graniterapids/uncore-interconnect.json Normal file
View File

File diff suppressed because it is too large Load Diff

1901
tools/perf/pmu-events/arch/x86/graniterapids/uncore-io.json Normal file
View File

File diff suppressed because it is too large Load Diff

449
tools/perf/pmu-events/arch/x86/graniterapids/uncore-memory.json Normal file
View File

@ -0,0 +1,449 @@
[
{
"BriefDescription": "DRAM Activate Count : Counts the number of DRAM Activate commands sent on this channel. Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.",
"Counter": "0,1,2,3",
"EventCode": "0x02",
"EventName": "UNC_M_ACT_COUNT.ALL",
"PerPkg": "1",
"UMask": "0xf7",
"Unit": "IMC"
},
{
"BriefDescription": "DRAM Activate Count : Read transaction on Page Empty or Page Miss : Counts the number of DRAM Activate commands sent on this channel. Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.",
"Counter": "0,1,2,3",
"EventCode": "0x02",
"EventName": "UNC_M_ACT_COUNT.RD",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xf1",
"Unit": "IMC"
},
{
"BriefDescription": "DRAM Activate Count : Underfill Read transaction on Page Empty or Page Miss : Counts the number of DRAM Activate commands sent on this channel. Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.",
"Counter": "0,1,2,3",
"EventCode": "0x02",
"EventName": "UNC_M_ACT_COUNT.UFILL",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xf4",
"Unit": "IMC"
},
{
"BriefDescription": "DRAM Activate Count : Write transaction on Page Empty or Page Miss : Counts the number of DRAM Activate commands sent on this channel. Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.",
"Counter": "0,1,2,3",
"EventCode": "0x02",
"EventName": "UNC_M_ACT_COUNT.WR",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xf2",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 0, all CAS operations",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "UNC_M_CAS_COUNT_SCH0.ALL",
"PerPkg": "1",
"UMask": "0xff",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 0, all reads",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "UNC_M_CAS_COUNT_SCH0.RD",
"PerPkg": "1",
"UMask": "0xcf",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 0 regular reads",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "UNC_M_CAS_COUNT_SCH0.RD_REG",
"PerPkg": "1",
"UMask": "0xc1",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 0 underfill reads",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "UNC_M_CAS_COUNT_SCH0.RD_UNDERFILL",
"PerPkg": "1",
"UMask": "0xc4",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 0, all writes",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "UNC_M_CAS_COUNT_SCH0.WR",
"PerPkg": "1",
"UMask": "0xf0",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 0 regular writes",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "UNC_M_CAS_COUNT_SCH0.WR_NONPRE",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xd0",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 0 auto-precharge writes",
"Counter": "0,1,2,3",
"EventCode": "0x05",
"EventName": "UNC_M_CAS_COUNT_SCH0.WR_PRE",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xe0",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 1, all CAS operations",
"Counter": "0,1,2,3",
"EventCode": "0x06",
"EventName": "UNC_M_CAS_COUNT_SCH1.ALL",
"PerPkg": "1",
"UMask": "0xff",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 1, all reads",
"Counter": "0,1,2,3",
"EventCode": "0x06",
"EventName": "UNC_M_CAS_COUNT_SCH1.RD",
"PerPkg": "1",
"UMask": "0xcf",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 1 regular reads",
"Counter": "0,1,2,3",
"EventCode": "0x06",
"EventName": "UNC_M_CAS_COUNT_SCH1.RD_REG",
"PerPkg": "1",
"UMask": "0xc1",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 1 underfill reads",
"Counter": "0,1,2,3",
"EventCode": "0x06",
"EventName": "UNC_M_CAS_COUNT_SCH1.RD_UNDERFILL",
"PerPkg": "1",
"UMask": "0xc4",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 1, all writes",
"Counter": "0,1,2,3",
"EventCode": "0x06",
"EventName": "UNC_M_CAS_COUNT_SCH1.WR",
"PerPkg": "1",
"UMask": "0xf0",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 1 regular writes",
"Counter": "0,1,2,3",
"EventCode": "0x06",
"EventName": "UNC_M_CAS_COUNT_SCH1.WR_NONPRE",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xd0",
"Unit": "IMC"
},
{
"BriefDescription": "CAS count for SubChannel 1 auto-precharge writes",
"Counter": "0,1,2,3",
"EventCode": "0x06",
"EventName": "UNC_M_CAS_COUNT_SCH1.WR_PRE",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xe0",
"Unit": "IMC"
},
{
"BriefDescription": "Number of DRAM DCLK clock cycles while the event is enabled",
"Counter": "0,1,2,3",
"EventCode": "0x01",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"PublicDescription": "DRAM Clockticks",
"UMask": "0x1",
"Unit": "IMC"
},
{
"BriefDescription": "Number of DRAM HCLK clock cycles while the event is enabled",
"Counter": "0,1,2,3",
"EventCode": "0x01",
"EventName": "UNC_M_HCLOCKTICKS",
"Experimental": "1",
"PerPkg": "1",
"PublicDescription": "DRAM Clockticks",
"Unit": "IMC"
},
{
"BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "UNC_M_PRE_COUNT.ALL",
"PerPkg": "1",
"UMask": "0xff",
"Unit": "IMC"
},
{
"BriefDescription": "DRAM Precharge commands. : Precharge due to (?) : Counts the number of DRAM Precharge commands sent on this channel.",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "UNC_M_PRE_COUNT.PGT",
"PerPkg": "1",
"UMask": "0xf8",
"Unit": "IMC"
},
{
"BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "UNC_M_PRE_COUNT.RD",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xf1",
"Unit": "IMC"
},
{
"BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "UNC_M_PRE_COUNT.UFILL",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xf4",
"Unit": "IMC"
},
{
"BriefDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.",
"Counter": "0,1,2,3",
"EventCode": "0x03",
"EventName": "UNC_M_PRE_COUNT.WR",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xf2",
"Unit": "IMC"
},
{
"BriefDescription": "Read buffer inserts on subchannel 0",
"Counter": "0,1,2,3",
"EventCode": "0x17",
"EventName": "UNC_M_RDB_INSERTS.SCH0",
"PerPkg": "1",
"UMask": "0x40",
"Unit": "IMC"
},
{
"BriefDescription": "Read buffer inserts on subchannel 1",
"Counter": "0,1,2,3",
"EventCode": "0x17",
"EventName": "UNC_M_RDB_INSERTS.SCH1",
"PerPkg": "1",
"UMask": "0x80",
"Unit": "IMC"
},
{
"BriefDescription": "Read buffer occupancy on subchannel 0",
"Counter": "0,1,2,3",
"EventCode": "0x1a",
"EventName": "UNC_M_RDB_OCCUPANCY_SCH0",
"PerPkg": "1",
"Unit": "IMC"
},
{
"BriefDescription": "Read buffer occupancy on subchannel 1",
"Counter": "0,1,2,3",
"EventCode": "0x1b",
"EventName": "UNC_M_RDB_OCCUPANCY_SCH1",
"PerPkg": "1",
"Unit": "IMC"
},
{
"BriefDescription": "Read Pending Queue Allocations : Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.",
"Counter": "0,1,2,3",
"EventCode": "0x10",
"EventName": "UNC_M_RPQ_INSERTS.PCH0",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x50",
"Unit": "IMC"
},
{
"BriefDescription": "Read Pending Queue Allocations : Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.",
"Counter": "0,1,2,3",
"EventCode": "0x10",
"EventName": "UNC_M_RPQ_INSERTS.PCH1",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xa0",
"Unit": "IMC"
},
{
"BriefDescription": "Read Pending Queue inserts for subchannel 0, pseudochannel 0",
"Counter": "0,1,2,3",
"EventCode": "0x10",
"EventName": "UNC_M_RPQ_INSERTS.SCH0_PCH0",
"PerPkg": "1",
"UMask": "0x10",
"Unit": "IMC"
},
{
"BriefDescription": "Read Pending Queue inserts for subchannel 0, pseudochannel 1",
"Counter": "0,1,2,3",
"EventCode": "0x10",
"EventName": "UNC_M_RPQ_INSERTS.SCH0_PCH1",
"PerPkg": "1",
"UMask": "0x20",
"Unit": "IMC"
},
{
"BriefDescription": "Read Pending Queue inserts for subchannel 1, pseudochannel 0",
"Counter": "0,1,2,3",
"EventCode": "0x10",
"EventName": "UNC_M_RPQ_INSERTS.SCH1_PCH0",
"PerPkg": "1",
"UMask": "0x40",
"Unit": "IMC"
},
{
"BriefDescription": "Read Pending Queue inserts for subchannel 1, pseudochannel 1",
"Counter": "0,1,2,3",
"EventCode": "0x10",
"EventName": "UNC_M_RPQ_INSERTS.SCH1_PCH1",
"PerPkg": "1",
"UMask": "0x80",
"Unit": "IMC"
},
{
"BriefDescription": "Read pending queue occupancy for subchannel 0, pseudochannel 0",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_M_RPQ_OCCUPANCY_SCH0_PCH0",
"PerPkg": "1",
"Unit": "IMC"
},
{
"BriefDescription": "Read pending queue occupancy for subchannel 0, pseudochannel 1",
"Counter": "0,1,2,3",
"EventCode": "0x81",
"EventName": "UNC_M_RPQ_OCCUPANCY_SCH0_PCH1",
"PerPkg": "1",
"Unit": "IMC"
},
{
"BriefDescription": "Read pending queue occupancy for subchannel 1, pseudochannel 0",
"Counter": "0,1,2,3",
"EventCode": "0x82",
"EventName": "UNC_M_RPQ_OCCUPANCY_SCH1_PCH0",
"PerPkg": "1",
"Unit": "IMC"
},
{
"BriefDescription": "Read pending queue occupancy for subchannel 1, pseudochannel 1",
"Counter": "0,1,2,3",
"EventCode": "0x83",
"EventName": "UNC_M_RPQ_OCCUPANCY_SCH1_PCH1",
"PerPkg": "1",
"Unit": "IMC"
},
{
"BriefDescription": "Write Pending Queue Allocations",
"Counter": "0,1,2,3",
"EventCode": "0x22",
"EventName": "UNC_M_WPQ_INSERTS.PCH0",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0x50",
"Unit": "IMC"
},
{
"BriefDescription": "Write Pending Queue Allocations",
"Counter": "0,1,2,3",
"EventCode": "0x22",
"EventName": "UNC_M_WPQ_INSERTS.PCH1",
"Experimental": "1",
"PerPkg": "1",
"UMask": "0xa0",
"Unit": "IMC"
},
{
"BriefDescription": "Write Pending Queue inserts for subchannel 0, pseudochannel 0",
"Counter": "0,1,2,3",
"EventCode": "0x22",
"EventName": "UNC_M_WPQ_INSERTS.SCH0_PCH0",
"PerPkg": "1",
"UMask": "0x10",
"Unit": "IMC"
},
{
"BriefDescription": "Write Pending Queue inserts for subchannel 0, pseudochannel 1",
"Counter": "0,1,2,3",
"EventCode": "0x22",
"EventName": "UNC_M_WPQ_INSERTS.SCH0_PCH1",
"PerPkg": "1",
"UMask": "0x20",
"Unit": "IMC"
},
{
"BriefDescription": "Write Pending Queue inserts for subchannel 1, pseudochannel 0",
"Counter": "0,1,2,3",
"EventCode": "0x22",
"EventName": "UNC_M_WPQ_INSERTS.SCH1_PCH0",
"PerPkg": "1",
"UMask": "0x40",
"Unit": "IMC"
},
{
"BriefDescription": "Write Pending Queue inserts for subchannel 1, pseudochannel 1",
"Counter": "0,1,2,3",
"EventCode": "0x22",
"EventName": "UNC_M_WPQ_INSERTS.SCH1_PCH1",
"PerPkg": "1",
"UMask": "0x80",
"Unit": "IMC"
},
{
"BriefDescription": "Write pending queue occupancy for subchannel 0, pseudochannel 0",
"Counter": "0,1,2,3",
"EventCode": "0x84",
"EventName": "UNC_M_WPQ_OCCUPANCY_SCH0_PCH0",
"PerPkg": "1",
"Unit": "IMC"
},
{
"BriefDescription": "Write pending queue occupancy for subchannel 0, pseudochannel 1",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_WPQ_OCCUPANCY_SCH0_PCH1",
"PerPkg": "1",
"Unit": "IMC"
},
{
"BriefDescription": "Write pending queue occupancy for subchannel 1, pseudochannel 0",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_WPQ_OCCUPANCY_SCH1_PCH0",
"PerPkg": "1",
"Unit": "IMC"
},
{
"BriefDescription": "Write pending queue occupancy for subchannel 1, pseudochannel 1",
"Counter": "0,1,2,3",
"EventCode": "0x87",
"EventName": "UNC_M_WPQ_OCCUPANCY_SCH1_PCH1",
"PerPkg": "1",
"Unit": "IMC"
}
]

11
tools/perf/pmu-events/arch/x86/graniterapids/uncore-power.json Normal file
View File

@ -0,0 +1,11 @@
[
{
"BriefDescription": "PCU Clockticks",
"Counter": "0,1,2,3",
"EventCode": "0x01",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"PublicDescription": "PCU Clockticks: The PCU runs off a fixed 1 GHz clock. This event counts the number of pclk cycles measured while the counter was enabled. The pclk, like the Memory Controller's dclk, counts at a constant rate making it a good measure of actual wall time.",
"Unit": "PCU"
}
]

159
tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json
View File

@ -1,26 +1,185 @@
[
{
"BriefDescription": "Loads that miss the DTLB and hit the STLB.",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.STLB_HIT",
"PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
"PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 1G page.",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Page walks completed due to a demand data load to a 4K page.",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.",
"Counter": "0,1,2,3",
"EventCode": "0x12",
"EventName": "DTLB_LOAD_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Stores that miss the DTLB and hit the STLB.",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.STLB_HIT",
"PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
"PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 1G page.",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G",
"PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Page walks completed due to a demand data store to a 4K page.",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.",
"Counter": "0,1,2,3",
"EventCode": "0x13",
"EventName": "DTLB_STORE_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.",
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.STLB_HIT",
"PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
{
"BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.",
"Counter": "0,1,2,3",
"CounterMask": "1",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_ACTIVE",
"PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)",
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED",
"PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0xe"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)",
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M",
"PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
{
"BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)",
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_COMPLETED_4K",
"PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.",
"SampleAfterValue": "100003",
"UMask": "0x2"
},
{
"BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.",
"Counter": "0,1,2,3",
"EventCode": "0x11",
"EventName": "ITLB_MISSES.WALK_PENDING",
"PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.",
"SampleAfterValue": "100003",
"UMask": "0x10"
}
]

2
tools/perf/pmu-events/arch/x86/mapfile.csv
View File

@ -11,7 +11,7 @@ GenuineIntel-6-CF,v1.09,emeraldrapids,core
GenuineIntel-6-5[CF],v13,goldmont,core
GenuineIntel-6-7A,v1.01,goldmontplus,core
GenuineIntel-6-B6,v1.03,grandridge,core
GenuineIntel-6-A[DE],v1.01,graniterapids,core
GenuineIntel-6-A[DE],v1.02,graniterapids,core
GenuineIntel-6-(3C|45|46),v35,haswell,core
GenuineIntel-6-3F,v28,haswellx,core
GenuineIntel-6-7[DE],v1.21,icelake,core

1 Family-model Version Filename EventType
11 GenuineIntel-6-5[CF] v13 goldmont core
12 GenuineIntel-6-7A v1.01 goldmontplus core
13 GenuineIntel-6-B6 v1.03 grandridge core
14 GenuineIntel-6-A[DE] v1.01 v1.02 graniterapids core
15 GenuineIntel-6-(3C|45|46) v35 haswell core
16 GenuineIntel-6-3F v28 haswellx core
17 GenuineIntel-6-7[DE] v1.21 icelake core