From 08ed77e414ab234258166f5628d91a7a0e681ff4 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Tue, 1 Sep 2020 17:09:43 -0500 Subject: [PATCH] perf vendor events amd: Add recommended events MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Add support for events listed in Section 2.1.15.2 "Performance Measurement" of "PPR for AMD Family 17h Model 31h B0 - 55803 Rev 0.54 - Sep 12, 2019". perf now supports these new events (-e): all_dc_accesses all_tlbs_flushed l1_dtlb_misses l2_cache_accesses_from_dc_misses l2_cache_accesses_from_ic_misses l2_cache_hits_from_dc_misses l2_cache_hits_from_ic_misses l2_cache_misses_from_dc_misses l2_cache_misses_from_ic_miss l2_dtlb_misses l2_itlb_misses sse_avx_stalls uops_dispatched uops_retired l3_accesses l3_misses and these metrics (-M): branch_misprediction_ratio all_l2_cache_accesses all_l2_cache_hits all_l2_cache_misses ic_fetch_miss_ratio l2_cache_accesses_from_l2_hwpf l2_cache_hits_from_l2_hwpf l2_cache_misses_from_l2_hwpf l3_read_miss_latency l1_itlb_misses all_remote_links_outbound nps1_die_to_dram The nps1_die_to_dram event may need perf stat's --metric-no-group switch if the number of available data fabric counters is less than the number it uses (8). Committer testing: On a AMD Ryzen 3900x system: Before: # perf list all_dc_accesses all_tlbs_flushed l1_dtlb_misses l2_cache_accesses_from_dc_misses l2_cache_accesses_from_ic_misses l2_cache_hits_from_dc_misses l2_cache_hits_from_ic_misses l2_cache_misses_from_dc_misses l2_cache_misses_from_ic_miss l2_dtlb_misses l2_itlb_misses sse_avx_stalls uops_dispatched uops_retired l3_accesses l3_misses | grep -v "^Metric Groups:$" | grep -v "^$" # After: # perf list all_dc_accesses all_tlbs_flushed l1_dtlb_misses l2_cache_accesses_from_dc_misses l2_cache_accesses_from_ic_misses l2_cache_hits_from_dc_misses l2_cache_hits_from_ic_misses l2_cache_misses_from_dc_misses l2_cache_misses_from_ic_miss l2_dtlb_misses l2_itlb_misses sse_avx_stalls uops_dispatched uops_retired l3_accesses l3_misses | grep -v "^Metric Groups:$" | grep -v "^$" | grep -v "^recommended:$" all_dc_accesses [All L1 Data Cache Accesses] all_tlbs_flushed [All TLBs Flushed] l1_dtlb_misses [L1 DTLB Misses] l2_cache_accesses_from_dc_misses [L2 Cache Accesses from L1 Data Cache Misses (including prefetch)] l2_cache_accesses_from_ic_misses [L2 Cache Accesses from L1 Instruction Cache Misses (including prefetch)] l2_cache_hits_from_dc_misses [L2 Cache Hits from L1 Data Cache Misses] l2_cache_hits_from_ic_misses [L2 Cache Hits from L1 Instruction Cache Misses] l2_cache_misses_from_dc_misses [L2 Cache Misses from L1 Data Cache Misses] l2_cache_misses_from_ic_miss [L2 Cache Misses from L1 Instruction Cache Misses] l2_dtlb_misses [L2 DTLB Misses & Data page walks] l2_itlb_misses [L2 ITLB Misses & Instruction page walks] sse_avx_stalls [Mixed SSE/AVX Stalls] uops_dispatched [Micro-ops Dispatched] uops_retired [Micro-ops Retired] l3_accesses [L3 Accesses. Unit: amd_l3] l3_misses [L3 Misses (includes Chg2X). Unit: amd_l3] # # perf stat -a -e all_dc_accesses,all_tlbs_flushed,l1_dtlb_misses,l2_cache_accesses_from_dc_misses,l2_cache_accesses_from_ic_misses,l2_cache_hits_from_dc_misses,l2_cache_hits_from_ic_misses,l2_cache_misses_from_dc_misses,l2_cache_misses_from_ic_miss,l2_dtlb_misses,l2_itlb_misses,sse_avx_stalls,uops_dispatched,uops_retired,l3_accesses,l3_misses sleep 2 Performance counter stats for 'system wide': 433,439,949 all_dc_accesses (35.66%) 443 all_tlbs_flushed (35.66%) 2,985,885 l1_dtlb_misses (35.66%) 18,318,019 l2_cache_accesses_from_dc_misses (35.68%) 50,114,810 l2_cache_accesses_from_ic_misses (35.72%) 12,423,978 l2_cache_hits_from_dc_misses (35.74%) 40,703,103 l2_cache_hits_from_ic_misses (35.74%) 6,698,673 l2_cache_misses_from_dc_misses (35.74%) 12,090,892 l2_cache_misses_from_ic_miss (35.74%) 614,267 l2_dtlb_misses (35.74%) 216,036 l2_itlb_misses (35.74%) 11,977 sse_avx_stalls (35.74%) 999,276,223 uops_dispatched (35.73%) 1,075,311,620 uops_retired (35.69%) 1,420,763 l3_accesses 540,164 l3_misses 2.002344121 seconds time elapsed # perf stat -a -e all_dc_accesses,all_tlbs_flushed,l1_dtlb_misses,l2_cache_accesses_from_dc_misses,l2_cache_accesses_from_ic_misses sleep 2 Performance counter stats for 'system wide': 175,943,104 all_dc_accesses 310 all_tlbs_flushed 2,280,359 l1_dtlb_misses 11,700,151 l2_cache_accesses_from_dc_misses 25,414,963 l2_cache_accesses_from_ic_misses 2.001957818 seconds time elapsed # Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 Signed-off-by: Kim Phillips Acked-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Borislav Petkov Cc: Jin Yao Cc: Jiri Olsa Cc: John Garry Cc: Jon Grimm Cc: Kan Liang Cc: Mark Rutland Cc: Martin Jambor Cc: Martin Liška Cc: Michael Petlan Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Vijay Thakkar Cc: William Cohen Cc: Yunfeng Ye Link: http://lore.kernel.org/lkml/20200901220944.277505-3-kim.phillips@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/amdzen1/cache.json | 23 +++ .../pmu-events/arch/x86/amdzen1/data-fabric.json | 98 ++++++++++++ .../pmu-events/arch/x86/amdzen1/recommended.json | 178 +++++++++++++++++++++ tools/perf/pmu-events/arch/x86/amdzen2/cache.json | 23 +++ .../pmu-events/arch/x86/amdzen2/data-fabric.json | 98 ++++++++++++ .../pmu-events/arch/x86/amdzen2/recommended.json | 178 +++++++++++++++++++++ tools/perf/pmu-events/jevents.c | 1 + 7 files changed, 599 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/amdzen1/data-fabric.json create mode 100644 tools/perf/pmu-events/arch/x86/amdzen1/recommended.json create mode 100644 tools/perf/pmu-events/arch/x86/amdzen2/data-fabric.json create mode 100644 tools/perf/pmu-events/arch/x86/amdzen2/recommended.json diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/cache.json b/tools/perf/pmu-events/arch/x86/amdzen1/cache.json index 695ed3f..4ea7ec4 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen1/cache.json +++ b/tools/perf/pmu-events/arch/x86/amdzen1/cache.json @@ -118,6 +118,11 @@ "UMask": "0x1" }, { + "EventName": "l2_request_g1.all_no_prefetch", + "EventCode": "0x60", + "UMask": "0xf9" + }, + { "EventName": "l2_request_g2.group1", "EventCode": "0x61", "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g1 (PMCx060).", @@ -244,6 +249,24 @@ "UMask": "0x1" }, { + "EventName": "l2_cache_req_stat.ic_access_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache requests in L2.", + "UMask": "0x7" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_miss_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request miss in L2 and Data cache request miss in L2 (all types).", + "UMask": "0x9" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_hit_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request hit in L2 and Data cache request hit in L2 (all types).", + "UMask": "0xf6" + }, + { "EventName": "l2_fill_pending.l2_fill_busy", "EventCode": "0x6d", "BriefDescription": "Cycles with fill pending from L2. Total cycles spent with one or more fill requests in flight from L2.", diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/data-fabric.json b/tools/perf/pmu-events/arch/x86/amdzen1/data-fabric.json new file mode 100644 index 0000000..40271df --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen1/data-fabric.json @@ -0,0 +1,98 @@ +[ + { + "EventName": "remote_outbound_data_controller_0", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 0", + "EventCode": "0x7c7", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_1", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 1", + "EventCode": "0x807", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_2", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 2", + "EventCode": "0x847", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_3", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 3", + "EventCode": "0x887", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_0", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x07", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_1", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x47", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_2", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x87", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_3", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0xc7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_4", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x107", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_5", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x147", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_6", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x187", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_7", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x1c7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json new file mode 100644 index 0000000..2cfe2d2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json @@ -0,0 +1,178 @@ +[ + { + "MetricName": "branch_misprediction_ratio", + "BriefDescription": "Execution-Time Branch Misprediction Ratio (Non-Speculative)", + "MetricExpr": "d_ratio(ex_ret_brn_misp, ex_ret_brn)", + "MetricGroup": "branch_prediction", + "ScaleUnit": "100%" + }, + { + "EventName": "all_dc_accesses", + "EventCode": "0x29", + "BriefDescription": "All L1 Data Cache Accesses", + "UMask": "0x7" + }, + { + "MetricName": "all_l2_cache_accesses", + "BriefDescription": "All L2 Cache Accesses", + "MetricExpr": "l2_request_g1.all_no_prefetch + l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_accesses_from_ic_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Instruction Cache Misses (including prefetch)", + "UMask": "0x10" + }, + { + "EventName": "l2_cache_accesses_from_dc_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Data Cache Misses (including prefetch)", + "UMask": "0xc8" + }, + { + "MetricName": "l2_cache_accesses_from_l2_hwpf", + "BriefDescription": "L2 Cache Accesses from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_misses", + "BriefDescription": "All L2 Cache Misses", + "MetricExpr": "l2_cache_req_stat.ic_dc_miss_in_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_misses_from_ic_miss", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Instruction Cache Misses", + "UMask": "0x01" + }, + { + "EventName": "l2_cache_misses_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Data Cache Misses", + "UMask": "0x08" + }, + { + "MetricName": "l2_cache_misses_from_l2_hwpf", + "BriefDescription": "L2 Cache Misses from L2 HWPF", + "MetricExpr": "l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_hits", + "BriefDescription": "All L2 Cache Hits", + "MetricExpr": "l2_cache_req_stat.ic_dc_hit_in_l2 + l2_pf_hit_l2", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_hits_from_ic_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Instruction Cache Misses", + "UMask": "0x06" + }, + { + "EventName": "l2_cache_hits_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Data Cache Misses", + "UMask": "0x70" + }, + { + "MetricName": "l2_cache_hits_from_l2_hwpf", + "BriefDescription": "L2 Cache Hits from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l3_accesses", + "EventCode": "0x04", + "BriefDescription": "L3 Accesses", + "UMask": "0xff", + "Unit": "L3PMC" + }, + { + "EventName": "l3_misses", + "EventCode": "0x04", + "BriefDescription": "L3 Misses (includes Chg2X)", + "UMask": "0x01", + "Unit": "L3PMC" + }, + { + "MetricName": "l3_read_miss_latency", + "BriefDescription": "Average L3 Read Miss Latency (in core clocks)", + "MetricExpr": "(xi_sys_fill_latency * 16) / xi_ccx_sdp_req1.all_l3_miss_req_typs", + "MetricGroup": "l3_cache", + "ScaleUnit": "1core clocks" + }, + { + "MetricName": "ic_fetch_miss_ratio", + "BriefDescription": "L1 Instruction Cache (32B) Fetch Miss Ratio", + "MetricExpr": "d_ratio(l2_cache_req_stat.ic_access_in_l2, bp_l1_tlb_fetch_hit + bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_miss)", + "MetricGroup": "l2_cache", + "ScaleUnit": "100%" + }, + { + "MetricName": "l1_itlb_misses", + "BriefDescription": "L1 ITLB Misses", + "MetricExpr": "bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_miss", + "MetricGroup": "tlb" + }, + { + "EventName": "l2_itlb_misses", + "EventCode": "0x85", + "BriefDescription": "L2 ITLB Misses & Instruction page walks", + "UMask": "0x07" + }, + { + "EventName": "l1_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Misses", + "UMask": "0xff" + }, + { + "EventName": "l2_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L2 DTLB Misses & Data page walks", + "UMask": "0xf0" + }, + { + "EventName": "all_tlbs_flushed", + "EventCode": "0x78", + "BriefDescription": "All TLBs Flushed", + "UMask": "0xdf" + }, + { + "EventName": "uops_dispatched", + "EventCode": "0xaa", + "BriefDescription": "Micro-ops Dispatched", + "UMask": "0x03" + }, + { + "EventName": "sse_avx_stalls", + "EventCode": "0x0e", + "BriefDescription": "Mixed SSE/AVX Stalls", + "UMask": "0x0e" + }, + { + "EventName": "uops_retired", + "EventCode": "0xc1", + "BriefDescription": "Micro-ops Retired" + }, + { + "MetricName": "all_remote_links_outbound", + "BriefDescription": "Approximate: Outbound data bytes for all Remote Links for a node (die)", + "MetricExpr": "remote_outbound_data_controller_0 + remote_outbound_data_controller_1 + remote_outbound_data_controller_2 + remote_outbound_data_controller_3", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "3e-5MiB" + }, + { + "MetricName": "nps1_die_to_dram", + "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die) (may need --metric-no-group)", + "MetricExpr": "dram_channel_data_controller_0 + dram_channel_data_controller_1 + dram_channel_data_controller_2 + dram_channel_data_controller_3 + dram_channel_data_controller_4 + dram_channel_data_controller_5 + dram_channel_data_controller_6 + dram_channel_data_controller_7", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "6.1e-5MiB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/cache.json b/tools/perf/pmu-events/arch/x86/amdzen2/cache.json index 1c60bfa..f61b982 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen2/cache.json +++ b/tools/perf/pmu-events/arch/x86/amdzen2/cache.json @@ -48,6 +48,11 @@ "UMask": "0x1" }, { + "EventName": "l2_request_g1.all_no_prefetch", + "EventCode": "0x60", + "UMask": "0xf9" + }, + { "EventName": "l2_request_g2.group1", "EventCode": "0x61", "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g1 (PMCx060).", @@ -174,6 +179,24 @@ "UMask": "0x1" }, { + "EventName": "l2_cache_req_stat.ic_access_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache requests in L2.", + "UMask": "0x7" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_miss_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request miss in L2 and Data cache request miss in L2 (all types).", + "UMask": "0x9" + }, + { + "EventName": "l2_cache_req_stat.ic_dc_hit_in_l2", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request hit in L2 and Data cache request hit in L2 (all types).", + "UMask": "0xf6" + }, + { "EventName": "l2_fill_pending.l2_fill_busy", "EventCode": "0x6d", "BriefDescription": "Cycles with fill pending from L2. Total cycles spent with one or more fill requests in flight from L2.", diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/data-fabric.json b/tools/perf/pmu-events/arch/x86/amdzen2/data-fabric.json new file mode 100644 index 0000000..40271df --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/data-fabric.json @@ -0,0 +1,98 @@ +[ + { + "EventName": "remote_outbound_data_controller_0", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 0", + "EventCode": "0x7c7", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_1", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 1", + "EventCode": "0x807", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_2", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 2", + "EventCode": "0x847", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "remote_outbound_data_controller_3", + "PublicDescription": "Remote Link Controller Outbound Packet Types: Data (32B): Remote Link Controller 3", + "EventCode": "0x887", + "UMask": "0x02", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_0", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x07", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_1", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x47", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_2", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x87", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_3", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0xc7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_4", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x107", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_5", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x147", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_6", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x187", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + }, + { + "EventName": "dram_channel_data_controller_7", + "PublicDescription": "DRAM Channel Controller Request Types: Requests with Data (64B): DRAM Channel Controller 0", + "EventCode": "0x1c7", + "UMask": "0x38", + "PerPkg": "1", + "Unit": "DFPMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json new file mode 100644 index 0000000..2ef91e2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json @@ -0,0 +1,178 @@ +[ + { + "MetricName": "branch_misprediction_ratio", + "BriefDescription": "Execution-Time Branch Misprediction Ratio (Non-Speculative)", + "MetricExpr": "d_ratio(ex_ret_brn_misp, ex_ret_brn)", + "MetricGroup": "branch_prediction", + "ScaleUnit": "100%" + }, + { + "EventName": "all_dc_accesses", + "EventCode": "0x29", + "BriefDescription": "All L1 Data Cache Accesses", + "UMask": "0x7" + }, + { + "MetricName": "all_l2_cache_accesses", + "BriefDescription": "All L2 Cache Accesses", + "MetricExpr": "l2_request_g1.all_no_prefetch + l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_accesses_from_ic_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Instruction Cache Misses (including prefetch)", + "UMask": "0x10" + }, + { + "EventName": "l2_cache_accesses_from_dc_misses", + "EventCode": "0x60", + "BriefDescription": "L2 Cache Accesses from L1 Data Cache Misses (including prefetch)", + "UMask": "0xc8" + }, + { + "MetricName": "l2_cache_accesses_from_l2_hwpf", + "BriefDescription": "L2 Cache Accesses from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_misses", + "BriefDescription": "All L2 Cache Misses", + "MetricExpr": "l2_cache_req_stat.ic_dc_miss_in_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_misses_from_ic_miss", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Instruction Cache Misses", + "UMask": "0x01" + }, + { + "EventName": "l2_cache_misses_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Misses from L1 Data Cache Misses", + "UMask": "0x08" + }, + { + "MetricName": "l2_cache_misses_from_l2_hwpf", + "BriefDescription": "L2 Cache Misses from L2 HWPF", + "MetricExpr": "l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "MetricName": "all_l2_cache_hits", + "BriefDescription": "All L2 Cache Hits", + "MetricExpr": "l2_cache_req_stat.ic_dc_hit_in_l2 + l2_pf_hit_l2", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l2_cache_hits_from_ic_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Instruction Cache Misses", + "UMask": "0x06" + }, + { + "EventName": "l2_cache_hits_from_dc_misses", + "EventCode": "0x64", + "BriefDescription": "L2 Cache Hits from L1 Data Cache Misses", + "UMask": "0x70" + }, + { + "MetricName": "l2_cache_hits_from_l2_hwpf", + "BriefDescription": "L2 Cache Hits from L2 HWPF", + "MetricExpr": "l2_pf_hit_l2 + l2_pf_miss_l2_hit_l3 + l2_pf_miss_l2_l3", + "MetricGroup": "l2_cache" + }, + { + "EventName": "l3_accesses", + "EventCode": "0x04", + "BriefDescription": "L3 Accesses", + "UMask": "0xff", + "Unit": "L3PMC" + }, + { + "EventName": "l3_misses", + "EventCode": "0x04", + "BriefDescription": "L3 Misses (includes Chg2X)", + "UMask": "0x01", + "Unit": "L3PMC" + }, + { + "MetricName": "l3_read_miss_latency", + "BriefDescription": "Average L3 Read Miss Latency (in core clocks)", + "MetricExpr": "(xi_sys_fill_latency * 16) / xi_ccx_sdp_req1.all_l3_miss_req_typs", + "MetricGroup": "l3_cache", + "ScaleUnit": "1core clocks" + }, + { + "MetricName": "ic_fetch_miss_ratio", + "BriefDescription": "L1 Instruction Cache (32B) Fetch Miss Ratio", + "MetricExpr": "d_ratio(l2_cache_req_stat.ic_access_in_l2, bp_l1_tlb_fetch_hit + bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_tlb_miss)", + "MetricGroup": "l2_cache", + "ScaleUnit": "100%" + }, + { + "MetricName": "l1_itlb_misses", + "BriefDescription": "L1 ITLB Misses", + "MetricExpr": "bp_l1_tlb_miss_l2_hit + bp_l1_tlb_miss_l2_tlb_miss", + "MetricGroup": "tlb" + }, + { + "EventName": "l2_itlb_misses", + "EventCode": "0x85", + "BriefDescription": "L2 ITLB Misses & Instruction page walks", + "UMask": "0x07" + }, + { + "EventName": "l1_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Misses", + "UMask": "0xff" + }, + { + "EventName": "l2_dtlb_misses", + "EventCode": "0x45", + "BriefDescription": "L2 DTLB Misses & Data page walks", + "UMask": "0xf0" + }, + { + "EventName": "all_tlbs_flushed", + "EventCode": "0x78", + "BriefDescription": "All TLBs Flushed", + "UMask": "0xdf" + }, + { + "EventName": "uops_dispatched", + "EventCode": "0xaa", + "BriefDescription": "Micro-ops Dispatched", + "UMask": "0x03" + }, + { + "EventName": "sse_avx_stalls", + "EventCode": "0x0e", + "BriefDescription": "Mixed SSE/AVX Stalls", + "UMask": "0x0e" + }, + { + "EventName": "uops_retired", + "EventCode": "0xc1", + "BriefDescription": "Micro-ops Retired" + }, + { + "MetricName": "all_remote_links_outbound", + "BriefDescription": "Approximate: Outbound data bytes for all Remote Links for a node (die)", + "MetricExpr": "remote_outbound_data_controller_0 + remote_outbound_data_controller_1 + remote_outbound_data_controller_2 + remote_outbound_data_controller_3", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "3e-5MiB" + }, + { + "MetricName": "nps1_die_to_dram", + "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die) (may need --metric-no-group)", + "MetricExpr": "dram_channel_data_controller_0 + dram_channel_data_controller_1 + dram_channel_data_controller_2 + dram_channel_data_controller_3 + dram_channel_data_controller_4 + dram_channel_data_controller_5 + dram_channel_data_controller_6 + dram_channel_data_controller_7", + "MetricGroup": "data_fabric", + "PerPkg": "1", + "ScaleUnit": "6.1e-5MiB" + } +] diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index fc9c158..e37d178 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -240,6 +240,7 @@ static struct map { { "hisi_sccl,hha", "hisi_sccl,hha" }, { "hisi_sccl,l3c", "hisi_sccl,l3c" }, { "L3PMC", "amd_l3" }, + { "DFPMC", "amd_df" }, {} }; -- 2.7.4