mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson
synced 2025-09-01 23:46:45 +00:00
8d40f74ebf
There are cases where a metric requires more events than the number of available counters. E.g. AMD Zen, Zen 2 and Zen 3 processors have four data fabric counters but the "nps1_die_to_dram" metric has eight events. By default, the constituent events are placed in a group and since the events cannot be scheduled at the same time, the metric is not computed. The "all metrics" test also fails because of this. Use the NO_GROUP_EVENTS constraint for such metrics which anyway expect the user to run perf with "--metric-no-group". E.g. $ sudo perf test -v 101 Before: 101: perf all metrics test : --- start --- test child forked, pid 37131 Testing branch_misprediction_ratio Testing all_remote_links_outbound Testing nps1_die_to_dram Metric 'nps1_die_to_dram' not printed in: Error: Invalid event (dram_channel_data_controller_4) in per-thread mode, enable system wide with '-a'. Testing macro_ops_dispatched Testing all_l2_cache_accesses Testing all_l2_cache_hits Testing all_l2_cache_misses Testing ic_fetch_miss_ratio Testing l2_cache_accesses_from_l2_hwpf Testing l2_cache_misses_from_l2_hwpf Testing op_cache_fetch_miss_ratio Testing l3_read_miss_latency Testing l1_itlb_misses test child finished with -1 ---- end ---- perf all metrics test: FAILED! After: 101: perf all metrics test : --- start --- test child forked, pid 43766 Testing branch_misprediction_ratio Testing all_remote_links_outbound Testing nps1_die_to_dram Testing macro_ops_dispatched Testing all_l2_cache_accesses Testing all_l2_cache_hits Testing all_l2_cache_misses Testing ic_fetch_miss_ratio Testing l2_cache_accesses_from_l2_hwpf Testing l2_cache_misses_from_l2_hwpf Testing op_cache_fetch_miss_ratio Testing l3_read_miss_latency Testing l1_itlb_misses test child finished with 0 ---- end ---- perf all metrics test: Ok Reported-by: Ayush Jain <ayush.jain3@amd.com> Suggested-by: Ian Rogers <irogers@google.com> Signed-off-by: Sandipan Das <sandipan.das@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Santosh Shukla <santosh.shukla@amd.com> Link: https://lore.kernel.org/r/20230706063440.54189-1-sandipan.das@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
216 lines
6.8 KiB
JSON
216 lines
6.8 KiB
JSON
[
|
|
{
|
|
"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_data_cache_accesses",
|
|
"EventCode": "0x29",
|
|
"BriefDescription": "All L1 Data Cache Accesses",
|
|
"UMask": "0x07"
|
|
},
|
|
{
|
|
"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": "0xe8"
|
|
},
|
|
{
|
|
"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 Cache 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": "0xf0"
|
|
},
|
|
{
|
|
"EventName": "l2_cache_hits_from_l2_hwpf",
|
|
"EventCode": "0x70",
|
|
"BriefDescription": "L2 Cache Hits from L2 Cache HWPF",
|
|
"UMask": "0xff"
|
|
},
|
|
{
|
|
"EventName": "l3_cache_accesses",
|
|
"EventCode": "0x04",
|
|
"BriefDescription": "L3 Cache Accesses",
|
|
"UMask": "0xff",
|
|
"Unit": "L3PMC"
|
|
},
|
|
{
|
|
"EventName": "l3_misses",
|
|
"EventCode": "0x04",
|
|
"BriefDescription": "L3 Misses (includes cacheline state change requests)",
|
|
"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",
|
|
"MetricGroup": "l3_cache",
|
|
"ScaleUnit": "1core clocks"
|
|
},
|
|
{
|
|
"MetricName": "op_cache_fetch_miss_ratio",
|
|
"BriefDescription": "Op Cache (64B) Fetch Miss Ratio",
|
|
"MetricExpr": "d_ratio(op_cache_hit_miss.op_cache_miss, op_cache_hit_miss.all_op_cache_accesses)",
|
|
"MetricGroup": "l2_cache"
|
|
},
|
|
{
|
|
"MetricName": "ic_fetch_miss_ratio",
|
|
"BriefDescription": "Instruction Cache (32B) Fetch Miss Ratio",
|
|
"MetricExpr": "d_ratio(ic_tag_hit_miss.instruction_cache_miss, ic_tag_hit_miss.all_instruction_cache_accesses)",
|
|
"MetricGroup": "l2_cache",
|
|
"ScaleUnit": "100%"
|
|
},
|
|
{
|
|
"EventName": "l1_data_cache_fills_from_memory",
|
|
"EventCode": "0x44",
|
|
"BriefDescription": "L1 Data Cache Fills: From Memory",
|
|
"UMask": "0x48"
|
|
},
|
|
{
|
|
"EventName": "l1_data_cache_fills_from_remote_node",
|
|
"EventCode": "0x44",
|
|
"BriefDescription": "L1 Data Cache Fills: From Remote Node",
|
|
"UMask": "0x50"
|
|
},
|
|
{
|
|
"EventName": "l1_data_cache_fills_from_within_same_ccx",
|
|
"EventCode": "0x44",
|
|
"BriefDescription": "L1 Data Cache Fills: From within same CCX",
|
|
"UMask": "0x03"
|
|
},
|
|
{
|
|
"EventName": "l1_data_cache_fills_from_external_ccx_cache",
|
|
"EventCode": "0x44",
|
|
"BriefDescription": "L1 Data Cache Fills: From External CCX Cache",
|
|
"UMask": "0x14"
|
|
},
|
|
{
|
|
"EventName": "l1_data_cache_fills_all",
|
|
"EventCode": "0x44",
|
|
"BriefDescription": "L1 Data Cache Fills: All",
|
|
"UMask": "0xff"
|
|
},
|
|
{
|
|
"MetricName": "l1_itlb_misses",
|
|
"BriefDescription": "L1 ITLB Misses",
|
|
"MetricExpr": "bp_l1_tlb_miss_l2_tlb_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": "0xff"
|
|
},
|
|
{
|
|
"MetricName": "macro_ops_dispatched",
|
|
"BriefDescription": "Macro-ops Dispatched",
|
|
"MetricExpr": "de_dis_cops_from_decoder.disp_op_type.any_integer_dispatch + de_dis_cops_from_decoder.disp_op_type.any_fp_dispatch",
|
|
"MetricGroup": "decoder"
|
|
},
|
|
{
|
|
"EventName": "sse_avx_stalls",
|
|
"EventCode": "0x0e",
|
|
"BriefDescription": "Mixed SSE/AVX Stalls",
|
|
"UMask": "0x0e"
|
|
},
|
|
{
|
|
"EventName": "macro_ops_retired",
|
|
"EventCode": "0xc1",
|
|
"BriefDescription": "Macro-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)",
|
|
"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",
|
|
"MetricConstraint": "NO_GROUP_EVENTS",
|
|
"ScaleUnit": "6.1e-5MiB"
|
|
}
|
|
]
|