perf vendor events power10: Update JSON/events
PATCH 1/1 perf vendor events power10: Update JSON/events
Update JSON/events for power10 platform with additional events. Also move PM_VECTOR_LD_CMPL event from others.json to frontend.json file.
--- .../arch/powerpc/power10/frontend.json | 5 + .../arch/powerpc/power10/others.json | 100 +++++++++++++++++- 2 files changed, 100 insertions(+), 5 deletions(-)
tools/perf/pmu-events/arch/powerpc/power10/frontend.json +5 -0
@@ -74,6 +74,11 @@ "EventName": "PM_ISSUE_KILL", "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group." }, + { + "EventCode": "0x44054", + "EventName": "PM_VECTOR_LD_CMPL", + "BriefDescription": "Vector load instruction completed." + }, { "EventCode": "0x44056", "EventName": "PM_VECTOR_ST_CMPL",
tools/perf/pmu-events/arch/powerpc/power10/others.json +95 -5
111 lines not on this page · raw message
Signature · 1 line
2.43.0
Quoted 5 lines · Kajol Jain
Update JSON/events for power10 platform with additional events. Also move
PM_VECTOR_LD_CMPLevent from others.json to frontend.json file.Signed-off-by Kajol Jain <[email protected]>
I have tested the patch on power10 machine. Looks good to me.
Quoted 138 lines
--- .../arch/powerpc/power10/frontend.json | 5 + .../arch/powerpc/power10/others.json | 100 +++++++++++++++++- 2 files changed, 100 insertions(+), 5 deletions(-)tools/perf/pmu-events/arch/powerpc/power10/frontend.json +5
-0@@ -74,6 +74,11 @@ "EventName": "PM_ISSUE_KILL", "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group." }, + { + "EventCode": "0x44054", + "EventName": "PM_VECTOR_LD_CMPL", + "BriefDescription": "Vector load instruction completed." + }, { "EventCode": "0x44056", "EventName": "PM_VECTOR_ST_CMPL",tools/perf/pmu-events/arch/powerpc/power10/others.json +95
-5@@ -94,11 +94,6 @@ "EventName": "PM_L1_ICACHE_RELOADED_ALL", "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." }, - { - "EventCode": "0x44054", - "EventName": "PM_VECTOR_LD_CMPL", - "BriefDescription": "Vector load instruction completed." - }, { "EventCode": "0x4D05E", "EventName": "PM_BR_CMPL",@@ -108,5 +103,100 @@ "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", "BriefDescription": "Load missed L1, counted at finish time." + }, + { + "EventCode": "0x00000038BC", + "EventName": "PM_ISYNC_CMPL", + "BriefDescription": "Isync completion count per thread." + }, + { + "EventCode": "0x000000C088", + "EventName": "PM_LD0_32B_FIN", + "BriefDescription": "256-bit load finished in the LD0 load execution unit." + }, + { + "EventCode": "0x000000C888", + "EventName": "PM_LD1_32B_FIN", + "BriefDescription": "256-bit load finished in the LD1 load execution unit." + }, + { + "EventCode": "0x000000C090", + "EventName": "PM_LD0_UNALIGNED_FIN", + "BriefDescription": "Load instructions in LD0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time." + }, + { + "EventCode": "0x000000C890", + "EventName": "PM_LD1_UNALIGNED_FIN", + "BriefDescription": "Load instructions in LD1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time." + }, + { + "EventCode": "0x000000C0A4", + "EventName": "PM_ST0_UNALIGNED_FIN", + "BriefDescription": "Store instructions in ST0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time." + }, + { + "EventCode": "0x000000C8A4", + "EventName": "PM_ST1_UNALIGNED_FIN", + "BriefDescription": "Store instructions in ST1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time." + }, + { + "EventCode": "0x000000C8B8", + "EventName": "PM_STCX_SUCCESS_CMPL", + "BriefDescription": "STCX instructions that completed successfully. Specifically, counts only when a pass status is returned from the nest." + }, + { + "EventCode": "0x000000D0B4", + "EventName": "PM_DC_PREF_STRIDED_CONF", + "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software." + }, + { + "EventCode": "0x000000F880", + "EventName": "PM_SNOOP_TLBIE_CYC", + "BriefDescription": "Cycles in which TLBIE snoops are executed in the LSU." + }, + { + "EventCode": "0x000000F084", + "EventName": "PM_SNOOP_TLBIE_CACHE_WALK_CYC", + "BriefDescription": "TLBIE snoop cycles in which the data cache is being walked." + }, + { + "EventCode": "0x000000F884", + "EventName": "PM_SNOOP_TLBIE_WAIT_ST_CYC", + "BriefDescription": "TLBIE snoop cycles in which older stores are still draining." + }, + { + "EventCode": "0x000000F088", + "EventName": "PM_SNOOP_TLBIE_WAIT_LD_CYC", + "BriefDescription": "TLBIE snoop cycles in which older loads are still draining." + }, + { + "EventCode": "0x000000F08C", + "EventName": "PM_SNOOP_TLBIE_WAIT_MMU_CYC", + "BriefDescription": "TLBIE snoop cycles in which the Load-Store unit is waiting for the MMU to finish invalidation." + }, + { + "EventCode": "0x0000004884", + "EventName": "PM_NO_FETCH_IBUF_FULL_CYC", + "BriefDescription": "Cycles in which no instructions are fetched because there is no room in the instruction buffers." + }, + { + "EventCode": "0x00000048B4", + "EventName": "PM_BR_TKN_UNCOND_FIN", + "BriefDescription": "An unconditional branch finished. All unconditional branches are taken." + }, + { + "EventCode": "0x0B0000016080", + "EventName": "PM_L2_TLBIE_SLBIE_START", + "BriefDescription": "NCU Master received a TLBIE/SLBIEG/SLBIAG operation from the core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + }, + { + "EventCode": "0x0B0000016880", + "EventName": "PM_L2_TLBIE_SLBIE_DELAY", + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG command was held in a hottemp condition by the NCU Master. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_TLBIE_SLBIE_SENT to obtain the average time a TLBIE/SLBIEG/SLBIAG command was held. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + }, + { + "EventCode": "0x0B0000026880", + "EventName": "PM_L2_SNP_TLBIE_SLBIE_DELAY", + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: ’inflight’ means SnpTLB has been sent to core(ie doesn’t include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a ’hottemp’ delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." } ]
Quoted 6 lines · Kajol Jain
Update JSON/events for power10 platform with additional events. Also move
PM_VECTOR_LD_CMPLevent from others.json to frontend.json file.Signed-off-by Kajol Jain <[email protected]>
tools/perf/pmu-events/arch/powerpc/power10/others.json
Quoted 25 lines
--- .../arch/powerpc/power10/frontend.json | 5 + .../arch/powerpc/power10/others.json | 100 +++++++++++++++++- 2 files changed, 100 insertions(+), 5 deletions(-)tools/perf/pmu-events/arch/powerpc/power10/frontend.json +5
-0@@ -74,6 +74,11 @@ "EventName": "PM_ISSUE_KILL", "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group." }, + { + "EventCode": "0x44054", + "EventName": "PM_VECTOR_LD_CMPL", + "BriefDescription": "Vector load instruction completed." + }, { "EventCode": "0x44056", "EventName": "PM_VECTOR_ST_CMPL",tools/perf/pmu-events/arch/powerpc/power10/others.json +0
-0
The "topic" of an event is taken from the filename, here the topic will be "others".
Quoted 57 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +41
-5@@ -94,11 +94,6 @@ "EventName": "PM_L1_ICACHE_RELOADED_ALL", "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." }, - { - "EventCode": "0x44054", - "EventName": "PM_VECTOR_LD_CMPL", - "BriefDescription": "Vector load instruction completed." - }, { "EventCode": "0x4D05E", "EventName": "PM_BR_CMPL",@@ -108,5 +103,100 @@ "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", "BriefDescription": "Load missed L1, counted at finish time." + }, + { + "EventCode": "0x00000038BC", + "EventName": "PM_ISYNC_CMPL", + "BriefDescription": "Isync completion count per thread." + }, + { + "EventCode": "0x000000C088", + "EventName": "PM_LD0_32B_FIN", + "BriefDescription": "256-bit load finished in the LD0 load execution unit." + }, + { + "EventCode": "0x000000C888", + "EventName": "PM_LD1_32B_FIN", + "BriefDescription": "256-bit load finished in the LD1 load execution unit." + }, + { + "EventCode": "0x000000C090", + "EventName": "PM_LD0_UNALIGNED_FIN", + "BriefDescription": "Load instructions in LD0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time." + }, + { + "EventCode": "0x000000C890", + "EventName": "PM_LD1_UNALIGNED_FIN", + "BriefDescription": "Load instructions in LD1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time." + }, + { + "EventCode": "0x000000C0A4", + "EventName": "PM_ST0_UNALIGNED_FIN", + "BriefDescription": "Store instructions in ST0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time." + }, + { + "EventCode": "0x000000C8A4", + "EventName": "PM_ST1_UNALIGNED_FIN", + "BriefDescription": "Store instructions in ST1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time." + }, + { + "EventCode": "0x000000C8B8", + "EventName": "PM_STCX_SUCCESS_CMPL", + "BriefDescription": "STCX instructions that completed successfully. Specifically, counts only when a pass status is returned from the nest." + },
tools/perf/pmu-events/arch/powerpc/power10/others.json line 156
Quoted 10 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +10
-0+ { + "EventCode": "0x000000D0B4", + "EventName": "PM_DC_PREF_STRIDED_CONF", + "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software." + }, + { + "EventCode": "0x000000F880", + "EventName": "PM_SNOOP_TLBIE_CYC", + "BriefDescription": "Cycles in which TLBIE snoops are executed in the LSU." + },
Perhaps the topics here should be memory or translation?
Quoted 19 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +19
-0+ { + "EventCode": "0x000000F084", + "EventName": "PM_SNOOP_TLBIE_CACHE_WALK_CYC", + "BriefDescription": "TLBIE snoop cycles in which the data cache is being walked." + }, + { + "EventCode": "0x000000F884", + "EventName": "PM_SNOOP_TLBIE_WAIT_ST_CYC", + "BriefDescription": "TLBIE snoop cycles in which older stores are still draining." + }, + { + "EventCode": "0x000000F088", + "EventName": "PM_SNOOP_TLBIE_WAIT_LD_CYC", + "BriefDescription": "TLBIE snoop cycles in which older loads are still draining." + }, + { + "EventCode": "0x000000F08C", + "EventName": "PM_SNOOP_TLBIE_WAIT_MMU_CYC", + "BriefDescription": "TLBIE snoop cycles in which the Load-Store unit is waiting for the MMU to finish invalidation."
tools/perf/pmu-events/arch/powerpc/power10/others.json line 185
Quoted 10 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +10
-0+ }, + { + "EventCode": "0x0000004884", + "EventName": "PM_NO_FETCH_IBUF_FULL_CYC", + "BriefDescription": "Cycles in which no instructions are fetched because there is no room in the instruction buffers." + }, + { + "EventCode": "0x00000048B4", + "EventName": "PM_BR_TKN_UNCOND_FIN", + "BriefDescription": "An unconditional branch finished. All unconditional branches are taken."
I see PM_BR_TAKEN_CMPL in tools/perf/pmu-events/arch/powerpc/power10/frontend.json, so maybe it makes sense to put this event in that topic?
Thanks,
Ian
Quoted 20 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +15
-1+ }, + { + "EventCode": "0x0B0000016080", + "EventName": "PM_L2_TLBIE_SLBIE_START", + "BriefDescription": "NCU Master received a TLBIE/SLBIEG/SLBIAG operation from the core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + }, + { + "EventCode": "0x0B0000016880", + "EventName": "PM_L2_TLBIE_SLBIE_DELAY", + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG command was held in a hottemp condition by the NCU Master. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_TLBIE_SLBIE_SENT to obtain the average time a TLBIE/SLBIEG/SLBIAG command was held. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + }, + { + "EventCode": "0x0B0000026880", + "EventName": "PM_L2_SNP_TLBIE_SLBIE_DELAY", + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: ’inflight’ means SnpTLB has been sent to core(ie doesn’t include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a ’hottemp’ delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." } ] --2.43.0
Quoted 9 lines · Ian Rogers
Quoted 6 lines · Kajol Jain
Update JSON/events for power10 platform with additional events. Also move
PM_VECTOR_LD_CMPLevent from others.json to frontend.json file.Signed-off-by Kajol Jain <[email protected]>Reviewed-by Ian Rogers <[email protected]>
Thanks, applied to tmp.perf-tools-next,
- Arnaldo
Quoted 156 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json
Quoted 25 lines
--- .../arch/powerpc/power10/frontend.json | 5 + .../arch/powerpc/power10/others.json | 100 +++++++++++++++++- 2 files changed, 100 insertions(+), 5 deletions(-)tools/perf/pmu-events/arch/powerpc/power10/frontend.json +5
-0@@ -74,6 +74,11 @@ "EventName": "PM_ISSUE_KILL", "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group." }, + { + "EventCode": "0x44054", + "EventName": "PM_VECTOR_LD_CMPL", + "BriefDescription": "Vector load instruction completed." + }, { "EventCode": "0x44056", "EventName": "PM_VECTOR_ST_CMPL",tools/perf/pmu-events/arch/powerpc/power10/others.json +0
-0The "topic" of an event is taken from the filename, here the topic will be "others".
Quoted 57 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +41
-5@@ -94,11 +94,6 @@ "EventName": "PM_L1_ICACHE_RELOADED_ALL", "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." }, - { - "EventCode": "0x44054", - "EventName": "PM_VECTOR_LD_CMPL", - "BriefDescription": "Vector load instruction completed." - }, { "EventCode": "0x4D05E", "EventName": "PM_BR_CMPL",@@ -108,5 +103,100 @@ "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", "BriefDescription": "Load missed L1, counted at finish time." + }, + { + "EventCode": "0x00000038BC", + "EventName": "PM_ISYNC_CMPL", + "BriefDescription": "Isync completion count per thread." + }, + { + "EventCode": "0x000000C088", + "EventName": "PM_LD0_32B_FIN", + "BriefDescription": "256-bit load finished in the LD0 load execution unit." + }, + { + "EventCode": "0x000000C888", + "EventName": "PM_LD1_32B_FIN", + "BriefDescription": "256-bit load finished in the LD1 load execution unit." + }, + { + "EventCode": "0x000000C090", + "EventName": "PM_LD0_UNALIGNED_FIN", + "BriefDescription": "Load instructions in LD0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time." + }, + { + "EventCode": "0x000000C890", + "EventName": "PM_LD1_UNALIGNED_FIN", + "BriefDescription": "Load instructions in LD1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time." + }, + { + "EventCode": "0x000000C0A4", + "EventName": "PM_ST0_UNALIGNED_FIN", + "BriefDescription": "Store instructions in ST0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time." + }, + { + "EventCode": "0x000000C8A4", + "EventName": "PM_ST1_UNALIGNED_FIN", + "BriefDescription": "Store instructions in ST1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time." + }, + { + "EventCode": "0x000000C8B8", + "EventName": "PM_STCX_SUCCESS_CMPL", + "BriefDescription": "STCX instructions that completed successfully. Specifically, counts only when a pass status is returned from the nest." + },tools/perf/pmu-events/arch/powerpc/power10/others.json line 156
Quoted 10 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +10
-0+ { + "EventCode": "0x000000D0B4", + "EventName": "PM_DC_PREF_STRIDED_CONF", + "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software." + }, + { + "EventCode": "0x000000F880", + "EventName": "PM_SNOOP_TLBIE_CYC", + "BriefDescription": "Cycles in which TLBIE snoops are executed in the LSU." + },Perhaps the topics here should be memory or translation?
Quoted 19 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +19
-0+ { + "EventCode": "0x000000F084", + "EventName": "PM_SNOOP_TLBIE_CACHE_WALK_CYC", + "BriefDescription": "TLBIE snoop cycles in which the data cache is being walked." + }, + { + "EventCode": "0x000000F884", + "EventName": "PM_SNOOP_TLBIE_WAIT_ST_CYC", + "BriefDescription": "TLBIE snoop cycles in which older stores are still draining." + }, + { + "EventCode": "0x000000F088", + "EventName": "PM_SNOOP_TLBIE_WAIT_LD_CYC", + "BriefDescription": "TLBIE snoop cycles in which older loads are still draining." + }, + { + "EventCode": "0x000000F08C", + "EventName": "PM_SNOOP_TLBIE_WAIT_MMU_CYC", + "BriefDescription": "TLBIE snoop cycles in which the Load-Store unit is waiting for the MMU to finish invalidation."tools/perf/pmu-events/arch/powerpc/power10/others.json line 185
Quoted 10 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +10
-0+ }, + { + "EventCode": "0x0000004884", + "EventName": "PM_NO_FETCH_IBUF_FULL_CYC", + "BriefDescription": "Cycles in which no instructions are fetched because there is no room in the instruction buffers." + }, + { + "EventCode": "0x00000048B4", + "EventName": "PM_BR_TKN_UNCOND_FIN", + "BriefDescription": "An unconditional branch finished. All unconditional branches are taken."I see
PM_BR_TAKEN_CMPLintools/perf/pmu-events/arch/powerpc/power10/frontend.json, so maybe it makes sense to put this event in that topic?Thanks,
IanQuoted 20 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +15
-1+ }, + { + "EventCode": "0x0B0000016080", + "EventName": "PM_L2_TLBIE_SLBIE_START", + "BriefDescription": "NCU Master received a TLBIE/SLBIEG/SLBIAG operation from the core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + }, + { + "EventCode": "0x0B0000016880", + "EventName": "PM_L2_TLBIE_SLBIE_DELAY", + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG command was held in a hottemp condition by the NCU Master. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_TLBIE_SLBIE_SENT to obtain the average time a TLBIE/SLBIEG/SLBIAG command was held. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + }, + { + "EventCode": "0x0B0000026880", + "EventName": "PM_L2_SNP_TLBIE_SLBIE_DELAY", + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: ’inflight’ means SnpTLB has been sent to core(ie doesn’t include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a ’hottemp’ delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." } ] --2.43.0
Quoted 10 lines · Disha Goel
Quoted 5 lines · Kajol Jain
Update JSON/events for power10 platform with additional events. Also move
PM_VECTOR_LD_CMPLevent from others.json to frontend.json file.Signed-off-by Kajol Jain <[email protected]>I have tested the patch on power10 machine. Looks good to me.
Hi Disha,
Thanks for testing this patch.
Thanks,
Kajol Jain
Quoted 201 lines
Tested-by Disha Goel <[email protected]>Quoted 199 lines
---
.../arch/powerpc/power10/frontend.json | 5 + .../arch/powerpc/power10/others.json | 100 +++++++++++++++++-2 files changed, 100 insertions(+), 5 deletions(-)tools/perf/pmu-events/arch/powerpc/power10/frontend.json +0
-0@@ -74,6 +74,11 @@ "EventName": "PM_ISSUE_KILL","BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group."
},
+ {
+ "EventCode": "0x44054",
+ "EventName": "PM_VECTOR_LD_CMPL",
+ "BriefDescription": "Vector load instruction completed." + },
{
"EventCode": "0x44056",
"EventName": "PM_VECTOR_ST_CMPL",tools/perf/pmu-events/arch/powerpc/power10/others.json +0
-0@@ -94,11 +94,6 @@ "EventName": "PM_L1_ICACHE_RELOADED_ALL","BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch."
},
- {
- "EventCode": "0x44054",
- "EventName": "PM_VECTOR_LD_CMPL",
- "BriefDescription": "Vector load instruction completed." - },
{
"EventCode": "0x4D05E",
"EventName": "PM_BR_CMPL",tools/perf/pmu-events/arch/powerpc/power10/others.json +0
-0@@ -108,5 +103,100 @@ "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN","BriefDescription": "Load missed L1, counted at finish time." + },
+ {
+ "EventCode": "0x00000038BC",
+ "EventName": "PM_ISYNC_CMPL",
+ "BriefDescription": "Isync completion count per thread." + },
+ {
+ "EventCode": "0x000000C088",
+ "EventName": "PM_LD0_32B_FIN",
+ "BriefDescription": "256-bit load finished in the LD0 load execution unit."
+ },
+ {
+ "EventCode": "0x000000C888",
+ "EventName": "PM_LD1_32B_FIN",
+ "BriefDescription": "256-bit load finished in the LD1 load execution unit."
+ },
+ {
+ "EventCode": "0x000000C090",
+ "EventName": "PM_LD0_UNALIGNED_FIN",
+ "BriefDescription": "Load instructions in LD0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time."
+ },
+ {
+ "EventCode": "0x000000C890",
+ "EventName": "PM_LD1_UNALIGNED_FIN",
+ "BriefDescription": "Load instructions in LD1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time."
+ },
+ {
+ "EventCode": "0x000000C0A4",
+ "EventName": "PM_ST0_UNALIGNED_FIN",
+ "BriefDescription": "Store instructions in ST0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time."
+ },
+ {
+ "EventCode": "0x000000C8A4",
+ "EventName": "PM_ST1_UNALIGNED_FIN",
+ "BriefDescription": "Store instructions in ST1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time."
+ },
+ {
+ "EventCode": "0x000000C8B8",
+ "EventName": "PM_STCX_SUCCESS_CMPL",
+ "BriefDescription": "STCX instructions that completed successfully. Specifically, counts only when a pass status is returned from the nest."
+ },
+ {
+ "EventCode": "0x000000D0B4",
+ "EventName": "PM_DC_PREF_STRIDED_CONF",
+ "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software."
+ },
+ {
+ "EventCode": "0x000000F880",
+ "EventName": "PM_SNOOP_TLBIE_CYC",
+ "BriefDescription": "Cycles in which TLBIE snoops are executed in the LSU."
+ },
+ {
+ "EventCode": "0x000000F084",
+ "EventName": "PM_SNOOP_TLBIE_CACHE_WALK_CYC",
+ "BriefDescription": "TLBIE snoop cycles in which the data cache is being walked."
+ },
+ {
+ "EventCode": "0x000000F884",
+ "EventName": "PM_SNOOP_TLBIE_WAIT_ST_CYC",
+ "BriefDescription": "TLBIE snoop cycles in which older stores are still draining."
+ },
+ {
+ "EventCode": "0x000000F088",
+ "EventName": "PM_SNOOP_TLBIE_WAIT_LD_CYC",
+ "BriefDescription": "TLBIE snoop cycles in which older loads are still draining."
+ },
+ {
+ "EventCode": "0x000000F08C",
+ "EventName": "PM_SNOOP_TLBIE_WAIT_MMU_CYC",
+ "BriefDescription": "TLBIE snoop cycles in which the Load-Store unit is waiting for the MMU to finish invalidation."
+ },
+ {
+ "EventCode": "0x0000004884",
+ "EventName": "PM_NO_FETCH_IBUF_FULL_CYC",
+ "BriefDescription": "Cycles in which no instructions are fetched because there is no room in the instruction buffers."
+ },
+ {
+ "EventCode": "0x00000048B4",
+ "EventName": "PM_BR_TKN_UNCOND_FIN",
+ "BriefDescription": "An unconditional branch finished. All unconditional branches are taken."
+ },
+ {
+ "EventCode": "0x0B0000016080",
+ "EventName": "PM_L2_TLBIE_SLBIE_START",
+ "BriefDescription": "NCU Master received a TLBIE/SLBIEG/SLBIAG operation from the core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads."
+ },
+ {
+ "EventCode": "0x0B0000016880",
+ "EventName": "PM_L2_TLBIE_SLBIE_DELAY",
+ "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG command was held in a hottemp condition by the NCU Master. Multiply this count by 1000 to obtain the total number of cycles. This can be divided byPM_L2_TLBIE_SLBIE_SENTto obtain the average time a TLBIE/SLBIEG/SLBIAG command was held. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads."
+ },
+ {
+ "EventCode": "0x0B0000026880",
+ "EventName": "PM_L2_SNP_TLBIE_SLBIE_DELAY",
+ "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided byPM_L2_SNP_TLBIE_SLBIE_STARTto obtain the overall efficiency. Note: ’inflight’ means SnpTLB has been sent to core(ie doesn’t include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a ’hottemp’ delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads."
}
]
Quoted 9 lines · Ian Rogers
Quoted 6 lines · Kajol Jain
Update JSON/events for power10 platform with additional events. Also move
PM_VECTOR_LD_CMPLevent from others.json to frontend.json file.Signed-off-by Kajol Jain <[email protected]>Reviewed-by Ian Rogers <[email protected]>
Hi Ian,
Thanks for reviewing the patch and for all the suggestions. These json
files generated as per internal format defined, I will send a follow-up patch, if we can move these events.
Thanks,
Kajol Jain
Quoted 157 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json
Quoted 26 lines
--- .../arch/powerpc/power10/frontend.json | 5 + .../arch/powerpc/power10/others.json | 100 +++++++++++++++++- 2 files changed, 100 insertions(+), 5 deletions(-)tools/perf/pmu-events/arch/powerpc/power10/frontend.json +5
-0@@ -74,6 +74,11 @@ "EventName": "PM_ISSUE_KILL", "BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group." }, + { + "EventCode": "0x44054", + "EventName": "PM_VECTOR_LD_CMPL", + "BriefDescription": "Vector load instruction completed." + }, { "EventCode": "0x44056", "EventName": "PM_VECTOR_ST_CMPL",tools/perf/pmu-events/arch/powerpc/power10/others.json +0
-0The "topic" of an event is taken from the filename, here the topic will be "others".
Quoted 57 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +41
-5@@ -94,11 +94,6 @@ "EventName": "PM_L1_ICACHE_RELOADED_ALL", "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." }, - { - "EventCode": "0x44054", - "EventName": "PM_VECTOR_LD_CMPL", - "BriefDescription": "Vector load instruction completed." - }, { "EventCode": "0x4D05E", "EventName": "PM_BR_CMPL",@@ -108,5 +103,100 @@ "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", "BriefDescription": "Load missed L1, counted at finish time." + }, + { + "EventCode": "0x00000038BC", + "EventName": "PM_ISYNC_CMPL", + "BriefDescription": "Isync completion count per thread." + }, + { + "EventCode": "0x000000C088", + "EventName": "PM_LD0_32B_FIN", + "BriefDescription": "256-bit load finished in the LD0 load execution unit." + }, + { + "EventCode": "0x000000C888", + "EventName": "PM_LD1_32B_FIN", + "BriefDescription": "256-bit load finished in the LD1 load execution unit." + }, + { + "EventCode": "0x000000C090", + "EventName": "PM_LD0_UNALIGNED_FIN", + "BriefDescription": "Load instructions in LD0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time." + }, + { + "EventCode": "0x000000C890", + "EventName": "PM_LD1_UNALIGNED_FIN", + "BriefDescription": "Load instructions in LD1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline using the load gather buffer. This typically adds about 10 cycles to the latency of the instruction. This includes loads that cross the 128 byte boundary, octword loads that are not aligned, and a special forward progress case of a load that does not hit in the L1 and crosses the 32 byte boundary and is launched NTC. Counted at finish time." + }, + { + "EventCode": "0x000000C0A4", + "EventName": "PM_ST0_UNALIGNED_FIN", + "BriefDescription": "Store instructions in ST0 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time." + }, + { + "EventCode": "0x000000C8A4", + "EventName": "PM_ST1_UNALIGNED_FIN", + "BriefDescription": "Store instructions in ST1 port that are either unaligned, or treated as unaligned and require an additional recycle through the pipeline. This typically adds about 10 cycles to the latency of the instruction. This only includes stores that cross the 128 byte boundary. Counted at finish time." + }, + { + "EventCode": "0x000000C8B8", + "EventName": "PM_STCX_SUCCESS_CMPL", + "BriefDescription": "STCX instructions that completed successfully. Specifically, counts only when a pass status is returned from the nest." + },tools/perf/pmu-events/arch/powerpc/power10/others.json line 156
Quoted 10 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +10
-0+ { + "EventCode": "0x000000D0B4", + "EventName": "PM_DC_PREF_STRIDED_CONF", + "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software." + }, + { + "EventCode": "0x000000F880", + "EventName": "PM_SNOOP_TLBIE_CYC", + "BriefDescription": "Cycles in which TLBIE snoops are executed in the LSU." + },Perhaps the topics here should be memory or translation?
Quoted 19 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +19
-0+ { + "EventCode": "0x000000F084", + "EventName": "PM_SNOOP_TLBIE_CACHE_WALK_CYC", + "BriefDescription": "TLBIE snoop cycles in which the data cache is being walked." + }, + { + "EventCode": "0x000000F884", + "EventName": "PM_SNOOP_TLBIE_WAIT_ST_CYC", + "BriefDescription": "TLBIE snoop cycles in which older stores are still draining." + }, + { + "EventCode": "0x000000F088", + "EventName": "PM_SNOOP_TLBIE_WAIT_LD_CYC", + "BriefDescription": "TLBIE snoop cycles in which older loads are still draining." + }, + { + "EventCode": "0x000000F08C", + "EventName": "PM_SNOOP_TLBIE_WAIT_MMU_CYC", + "BriefDescription": "TLBIE snoop cycles in which the Load-Store unit is waiting for the MMU to finish invalidation."tools/perf/pmu-events/arch/powerpc/power10/others.json line 185
Quoted 10 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +10
-0+ }, + { + "EventCode": "0x0000004884", + "EventName": "PM_NO_FETCH_IBUF_FULL_CYC", + "BriefDescription": "Cycles in which no instructions are fetched because there is no room in the instruction buffers." + }, + { + "EventCode": "0x00000048B4", + "EventName": "PM_BR_TKN_UNCOND_FIN", + "BriefDescription": "An unconditional branch finished. All unconditional branches are taken."I see
PM_BR_TAKEN_CMPLintools/perf/pmu-events/arch/powerpc/power10/frontend.json, so maybe it makes sense to put this event in that topic?Thanks,
IanQuoted 20 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +15
-1+ }, + { + "EventCode": "0x0B0000016080", + "EventName": "PM_L2_TLBIE_SLBIE_START", + "BriefDescription": "NCU Master received a TLBIE/SLBIEG/SLBIAG operation from the core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + }, + { + "EventCode": "0x0B0000016880", + "EventName": "PM_L2_TLBIE_SLBIE_DELAY", + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG command was held in a hottemp condition by the NCU Master. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_TLBIE_SLBIE_SENT to obtain the average time a TLBIE/SLBIEG/SLBIAG command was held. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + }, + { + "EventCode": "0x0B0000026880", + "EventName": "PM_L2_SNP_TLBIE_SLBIE_DELAY", + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: ’inflight’ means SnpTLB has been sent to core(ie doesn’t include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a ’hottemp’ delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." } ] --2.43.0
Arnaldo Carvalho de Melo
maintainerQuoted 7 lines · Arnaldo Carvalho de Melo
Quoted 6 lines · Ian Rogers
Quoted 5 lines · Kajol Jain
Update JSON/events for power10 platform with additional events. Also move
PM_VECTOR_LD_CMPLevent from others.json to frontend.json file.
Quoted 5 lines
Quoted 3 lines
Quoted 1 line
Signed-off-by Kajol Jain <[email protected]>Reviewed-by Ian Rogers <[email protected]>Thanks, applied to tmp.perf-tools-next,
This seems to be causing this:
Exception processing pmu-events/arch/powerpc/power10/others.json Traceback (most recent call last):
File "pmu-events/jevents.py", line 1309, in <module>
main()
File "pmu-events/jevents.py", line 1291, in main
ftw(arch_path, [], preprocess_one_file) File "pmu-events/jevents.py", line 1241, in ftw
ftw(item.path, parents + [item.name], action)
File "pmu-events/jevents.py", line 1239, in ftw
action(parents, item)
File "pmu-events/jevents.py", line 623, in preprocess_one_file
for event in read_json_events(item.path, topic):
File "pmu-events/jevents.py", line 440, in read_json_events
events = json.load(open(path), object_hook=JsonEvent)
File "/usr/lib/python3.6/json/__init__.py", line 296, in load
CC /tmp/build/perf/bench/evlist-open-close.o
return loads(fp.read(),
File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode
return codecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe2 in position 9231: ordinal not in range(128) pmu-events/Build:35: recipe for target '/tmp/build/perf/pmu-events/pmu-events.c' failed make[3]: *** [/tmp/build/perf/pmu-events/pmu-events.c] Error 1
make[3]: *** Deleting file '/tmp/build/perf/pmu-events/pmu-events.c' Makefile.perf:763: recipe for target '/tmp/build/perf/pmu-events/pmu-events-in.o' failed make[2]: *** [/tmp/build/perf/pmu-events/pmu-events-in.o] Error 2
make[2]: *** Waiting for unfinished jobs....
CC /tmp/build/perf/tests/hists_cumulate.o CC /tmp/build/perf/arch/powerpc/util/event.o CC /tmp/build/perf/bench/breakpoint.o CC /tmp/build/perf/builtin-data.o
This happened in the past, I'm now trying to figure this out :-\
This was in:
toolsbuilder@five:~$ cat dm.log/ubuntu:18.04-x-powerpc
So 32-bit powerpc, ubuntu 18.04
- Arnaldo
Arnaldo Carvalho de Melo
maintainerQuoted 48 lines · Arnaldo Carvalho de Melo
Quoted 7 lines · Arnaldo Carvalho de Melo
Quoted 6 lines · Ian Rogers
Quoted 5 lines · Kajol Jain
Update JSON/events for power10 platform with additional events. Also move
PM_VECTOR_LD_CMPLevent from others.json to frontend.json file.Quoted 5 lines
Quoted 3 lines
Quoted 1 line
Signed-off-by Kajol Jain <[email protected]>Reviewed-by Ian Rogers <[email protected]>Thanks, applied to tmp.perf-tools-next,
This seems to be causing this:
Exception processing
pmu-events/arch/powerpc/power10/others.jsonTraceback (most recent call last):
File "pmu-events/jevents.py", line 1309, in <module>main() File "pmu-events/jevents.py", line 1291, in main ftw(arch_path, [], preprocess_one_file)File "
pmu-events/jevents.py", line 1241, in ftw
ftw(item.path, parents + [item.name], action)
File "pmu-events/jevents.py", line 1239, in ftw
action(parents, item)
File "pmu-events/jevents.py", line 623, inpreprocess_one_file
for event inread_json_events(item.path, topic):
File "pmu-events/jevents.py", line 440, inread_json_events
events =json.load(open(path), object_hook=JsonEvent)
File "/usr/lib/python3.6/json/__init__.py", line 296, in load
CC/tmp/build/perf/bench/evlist-open-close.o
return loads(fp.read(),
File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode
returncodecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte0xe2in position 9231: ordinal not in range(128) pmu-events/Build:35: recipe for target '/tmp/build/perf/pmu-events/pmu-events.c' failed make[3]: *** [/tmp/build/perf/pmu-events/pmu-events.c] Error 1
make[3]: *** Deleting file '/tmp/build/perf/pmu-events/pmu-events.c' Makefile.perf:763: recipe for target '/tmp/build/perf/pmu-events/pmu-events-in.o' failed make[2]: *** [/tmp/build/perf/pmu-events/pmu-events-in.o] Error 2
make[2]: *** Waiting for unfinished jobs....CC /tmp/build/perf/tests/hists_cumulate.o CC /tmp/build/perf/arch/powerpc/util/event.o CC /tmp/build/perf/bench/breakpoint.o CC /tmp/build/perf/builtin-data.o
Quoted 8 lines
This happened in the past, I'm now trying to figure this out :-\
This was in:
toolsbuilder@five:~$ cat dm.log/ubuntu:18.04-x-powerpcSo 32-bit powerpc, ubuntu 18.04
This did the trick, so I fixed it in my repo, please ack, just replacing ’ with ' :-\
- Arnaldo
tools/perf/pmu-events/arch/powerpc/power10/others.json +1 -1
@@ -197,6 +197,6 @@ { "EventCode": "0x0B0000026880", "EventName": "PM_L2_SNP_TLBIE_SLBIE_DELAY", - "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: ’inflight’ means SnpTLB has been sent to core(ie doesn’t include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a ’hottemp’ delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: 'inflight' means SnpTLB has been sent to core(ie doesn't include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a 'hottemp' delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." } ]
Quoted 56 lines · Arnaldo Carvalho de Melo
Quoted 55 lines · Arnaldo Carvalho de Melo
Quoted 7 lines · Arnaldo Carvalho de Melo
Quoted 6 lines · Ian Rogers
Quoted 5 lines · Kajol Jain
Update JSON/events for power10 platform with additional events. Also move
PM_VECTOR_LD_CMPLevent from others.json to frontend.json file.Quoted 5 lines
Quoted 3 lines
Quoted 1 line
Signed-off-by Kajol Jain <[email protected]>Reviewed-by Ian Rogers <[email protected]>Thanks, applied to tmp.perf-tools-next,
This seems to be causing this:
Exception processing
pmu-events/arch/powerpc/power10/others.jsonTraceback (most recent call last):
File "pmu-events/jevents.py", line 1309, in <module>main() File "pmu-events/jevents.py", line 1291, in main ftw(arch_path, [], preprocess_one_file)File "
pmu-events/jevents.py", line 1241, in ftw
ftw(item.path, parents + [item.name], action)
File "pmu-events/jevents.py", line 1239, in ftw
action(parents, item)
File "pmu-events/jevents.py", line 623, inpreprocess_one_file
for event inread_json_events(item.path, topic):
File "pmu-events/jevents.py", line 440, inread_json_events
events =json.load(open(path), object_hook=JsonEvent)
File "/usr/lib/python3.6/json/__init__.py", line 296, in load
CC/tmp/build/perf/bench/evlist-open-close.o
return loads(fp.read(),
File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode
returncodecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte0xe2in position 9231: ordinal not in range(128) pmu-events/Build:35: recipe for target '/tmp/build/perf/pmu-events/pmu-events.c' failed make[3]: *** [/tmp/build/perf/pmu-events/pmu-events.c] Error 1
make[3]: *** Deleting file '/tmp/build/perf/pmu-events/pmu-events.c' Makefile.perf:763: recipe for target '/tmp/build/perf/pmu-events/pmu-events-in.o' failed make[2]: *** [/tmp/build/perf/pmu-events/pmu-events-in.o] Error 2
make[2]: *** Waiting for unfinished jobs....CC /tmp/build/perf/tests/hists_cumulate.o CC /tmp/build/perf/arch/powerpc/util/event.o CC /tmp/build/perf/bench/breakpoint.o CC /tmp/build/perf/builtin-data.oThis happened in the past, I'm now trying to figure this out :-\
This was in:
toolsbuilder@five:~$ cat dm.log/ubuntu:18.04-x-powerpc
Quoted 7 lines
Quoted 1 line
So 32-bit powerpc, ubuntu 18.04
This did the trick, so I fixed it in my repo, please ack, just replacing ’ with ' :-\
- Arnaldo
Hi Arnaldo,
Thanks for fixing it. I will make sure in next series of patches, we
are also checking for this combination to avoid ascii issue.
Change looks fine to me.
Thanks,
Kajol Jain
Quoted 14 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +1
-1@@ -197,6 +197,6 @@ { "EventCode": "0x0B0000026880", "EventName": "PM_L2_SNP_TLBIE_SLBIE_DELAY", - "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: ’inflight’ means SnpTLB has been sent to core(ie doesn’t include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a ’hottemp’ delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: 'inflight' means SnpTLB has been sent to core(ie doesn't include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a 'hottemp' delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." } ]
Arnaldo Carvalho de Melo
maintainerQuoted 64 lines · kajoljain
Quoted 61 lines · Arnaldo Carvalho de Melo
Quoted 48 lines · Arnaldo Carvalho de Melo
Quoted 7 lines · Arnaldo Carvalho de Melo
Quoted 6 lines · Ian Rogers
Quoted 5 lines · Kajol Jain
Update JSON/events for power10 platform with additional events. Also move
PM_VECTOR_LD_CMPLevent from others.json to frontend.json file.Quoted 5 lines
Quoted 3 lines
Quoted 1 line
Signed-off-by Kajol Jain <[email protected]>Reviewed-by Ian Rogers <[email protected]>Thanks, applied to tmp.perf-tools-next,
This seems to be causing this:
Exception processing
pmu-events/arch/powerpc/power10/others.jsonTraceback (most recent call last):
File "pmu-events/jevents.py", line 1309, in <module>main() File "pmu-events/jevents.py", line 1291, in main ftw(arch_path, [], preprocess_one_file)File "
pmu-events/jevents.py", line 1241, in ftw
ftw(item.path, parents + [item.name], action)
File "pmu-events/jevents.py", line 1239, in ftw
action(parents, item)
File "pmu-events/jevents.py", line 623, inpreprocess_one_file
for event inread_json_events(item.path, topic):
File "pmu-events/jevents.py", line 440, inread_json_events
events =json.load(open(path), object_hook=JsonEvent)
File "/usr/lib/python3.6/json/__init__.py", line 296, in load
CC/tmp/build/perf/bench/evlist-open-close.o
return loads(fp.read(),
File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode
returncodecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte0xe2in position 9231: ordinal not in range(128) pmu-events/Build:35: recipe for target '/tmp/build/perf/pmu-events/pmu-events.c' failed make[3]: *** [/tmp/build/perf/pmu-events/pmu-events.c] Error 1
make[3]: *** Deleting file '/tmp/build/perf/pmu-events/pmu-events.c' Makefile.perf:763: recipe for target '/tmp/build/perf/pmu-events/pmu-events-in.o' failed make[2]: *** [/tmp/build/perf/pmu-events/pmu-events-in.o] Error 2
make[2]: *** Waiting for unfinished jobs....CC /tmp/build/perf/tests/hists_cumulate.o CC /tmp/build/perf/arch/powerpc/util/event.o CC /tmp/build/perf/bench/breakpoint.o CC /tmp/build/perf/builtin-data.oQuoted 8 lines
This happened in the past, I'm now trying to figure this out :-\
This was in:
toolsbuilder@five:~$ cat dm.log/ubuntu:18.04-x-powerpcSo 32-bit powerpc, ubuntu 18.04
This did the trick, so I fixed it in my repo, please ack, just replacing ’ with ' :-\
Quoted 8 lines
Quoted 2 lines
- Arnaldo
Hi Arnaldo,
Thanks for fixing it. I will make sure in next series of patches, we
are also checking for this combination to avoid ascii issue.Change looks fine to me.
Thanks for checking,
- Arnaldo
Quoted 17 lines
Thanks,
Kajol JainQuoted 14 lines
tools/perf/pmu-events/arch/powerpc/power10/others.json +1
-1@@ -197,6 +197,6 @@ { "EventCode": "0x0B0000026880", "EventName": "PM_L2_SNP_TLBIE_SLBIE_DELAY", - "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: ’inflight’ means SnpTLB has been sent to core(ie doesn’t include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a ’hottemp’ delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." + "BriefDescription": "Cycles when a TLBIE/SLBIEG/SLBIAG that targets this thread's LPAR was in flight while in a hottemp condition. Multiply this count by 1000 to obtain the total number of cycles. This can be divided by PM_L2_SNP_TLBIE_SLBIE_START to obtain the overall efficiency. Note: 'inflight' means SnpTLB has been sent to core(ie doesn't include when SnpTLB is in NCU waiting to be launched serially behind different SnpTLB). The NCU Snooper gets in a 'hottemp' delay window when it detects it is above its TLBIE/SLBIE threshold for process SnpTLBIE/SLBIE with this core. Event count should be multiplied by 2 since the data is coming from a 2:1 clock domain and the data is time sliced across all 4 threads." } ]