mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson
synced 2025-09-02 16:44:59 +00:00
a9fe4ac7a3
Add metrics taken from Section 1.2 "Performance Measurement" of the Performance Monitor Counters for AMD Family 1Ah Model 00h-0Fh Processors document available at the link below. The recommended metrics are sourced from Table 1 "Guidance for Common Performance Statistics with Complex Event Selects". The pipeline utilization metrics are sourced from Table 2 "Guidance for Pipeline Utilization Analysis Statistics". These are useful for finding performance bottlenecks by analyzing activity at different stages of the pipeline. There are metric groups available for Level 1 and Level 2 analysis. Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Sandipan Das <sandipan.das@amd.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: Stephane Eranian <eranian@google.com> Link: https://bugzilla.kernel.org/attachment.cgi?id=305974 Link: https://lore.kernel.org/r/ee21ff77d89efa99997d3c2ebeeae22ddb6e7e12.1714717230.git.sandipan.das@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
100 lines
4.5 KiB
JSON
100 lines
4.5 KiB
JSON
[
|
|
{
|
|
"MetricName": "total_dispatch_slots",
|
|
"BriefDescription": "Total dispatch slots (up to 8 instructions can be dispatched in each cycle).",
|
|
"MetricExpr": "8 * ls_not_halted_cyc",
|
|
"ScaleUnit": "1slots"
|
|
},
|
|
{
|
|
"MetricName": "frontend_bound",
|
|
"BriefDescription": "Percentage of dispatch slots that remained unused because the frontend did not supply enough instructions/ops.",
|
|
"MetricExpr": "d_ratio(de_no_dispatch_per_slot.no_ops_from_frontend, total_dispatch_slots)",
|
|
"MetricGroup": "PipelineL1",
|
|
"ScaleUnit": "100%slots"
|
|
},
|
|
{
|
|
"MetricName": "bad_speculation",
|
|
"BriefDescription": "Percentage of dispatched ops that did not retire.",
|
|
"MetricExpr": "d_ratio(de_src_op_disp.all - ex_ret_ops, total_dispatch_slots)",
|
|
"MetricGroup": "PipelineL1",
|
|
"ScaleUnit": "100%ops"
|
|
},
|
|
{
|
|
"MetricName": "backend_bound",
|
|
"BriefDescription": "Percentage of dispatch slots that remained unused because of backend stalls.",
|
|
"MetricExpr": "d_ratio(de_no_dispatch_per_slot.backend_stalls, total_dispatch_slots)",
|
|
"MetricGroup": "PipelineL1",
|
|
"ScaleUnit": "100%slots"
|
|
},
|
|
{
|
|
"MetricName": "smt_contention",
|
|
"BriefDescription": "Percentage of dispatch slots that remained unused because the other thread was selected.",
|
|
"MetricExpr": "d_ratio(de_no_dispatch_per_slot.smt_contention, total_dispatch_slots)",
|
|
"MetricGroup": "PipelineL1",
|
|
"ScaleUnit": "100%slots"
|
|
},
|
|
{
|
|
"MetricName": "retiring",
|
|
"BriefDescription": "Percentage of dispatch slots used by ops that retired.",
|
|
"MetricExpr": "d_ratio(ex_ret_ops, total_dispatch_slots)",
|
|
"MetricGroup": "PipelineL1",
|
|
"ScaleUnit": "100%slots"
|
|
},
|
|
{
|
|
"MetricName": "frontend_bound_by_latency",
|
|
"BriefDescription": "Percentage of dispatch slots that remained unused because of a latency bottleneck in the frontend (such as instruction cache or TLB misses).",
|
|
"MetricExpr": "d_ratio((8 * cpu@de_no_dispatch_per_slot.no_ops_from_frontend\\,cmask\\=0x8@), total_dispatch_slots)",
|
|
"MetricGroup": "PipelineL2;frontend_bound_group",
|
|
"ScaleUnit": "100%slots"
|
|
},
|
|
{
|
|
"MetricName": "frontend_bound_by_bandwidth",
|
|
"BriefDescription": "Percentage of dispatch slots that remained unused because of a bandwidth bottleneck in the frontend (such as decode or op cache fetch bandwidth).",
|
|
"MetricExpr": "d_ratio(de_no_dispatch_per_slot.no_ops_from_frontend - (8 * cpu@de_no_dispatch_per_slot.no_ops_from_frontend\\,cmask\\=0x8@), total_dispatch_slots)",
|
|
"MetricGroup": "PipelineL2;frontend_bound_group",
|
|
"ScaleUnit": "100%slots"
|
|
},
|
|
{
|
|
"MetricName": "bad_speculation_from_mispredicts",
|
|
"BriefDescription": "Percentage of dispatched ops that were flushed due to branch mispredicts.",
|
|
"MetricExpr": "d_ratio(bad_speculation * ex_ret_brn_misp, ex_ret_brn_misp + bp_redirects.resync)",
|
|
"MetricGroup": "PipelineL2;bad_speculation_group",
|
|
"ScaleUnit": "100%ops"
|
|
},
|
|
{
|
|
"MetricName": "bad_speculation_from_pipeline_restarts",
|
|
"BriefDescription": "Percentage of dispatched ops that were flushed due to pipeline restarts (resyncs).",
|
|
"MetricExpr": "d_ratio(bad_speculation * bp_redirects.resync, ex_ret_brn_misp + bp_redirects.resync)",
|
|
"MetricGroup": "PipelineL2;bad_speculation_group",
|
|
"ScaleUnit": "100%ops"
|
|
},
|
|
{
|
|
"MetricName": "backend_bound_by_memory",
|
|
"BriefDescription": "Percentage of dispatch slots that remained unused because of stalls due to the memory subsystem.",
|
|
"MetricExpr": "backend_bound * d_ratio(ex_no_retire.load_not_complete, ex_no_retire.not_complete)",
|
|
"MetricGroup": "PipelineL2;backend_bound_group",
|
|
"ScaleUnit": "100%slots"
|
|
},
|
|
{
|
|
"MetricName": "backend_bound_by_cpu",
|
|
"BriefDescription": "Percentage of dispatch slots that remained unused because of stalls not related to the memory subsystem.",
|
|
"MetricExpr": "backend_bound * (1 - d_ratio(ex_no_retire.load_not_complete, ex_no_retire.not_complete))",
|
|
"MetricGroup": "PipelineL2;backend_bound_group",
|
|
"ScaleUnit": "100%slots"
|
|
},
|
|
{
|
|
"MetricName": "retiring_from_fastpath",
|
|
"BriefDescription": "Percentage of dispatch slots used by fastpath ops that retired.",
|
|
"MetricExpr": "retiring * (1 - d_ratio(ex_ret_ucode_ops, ex_ret_ops))",
|
|
"MetricGroup": "PipelineL2;retiring_group",
|
|
"ScaleUnit": "100%slots"
|
|
},
|
|
{
|
|
"MetricName": "retiring_from_microcode",
|
|
"BriefDescription": "Percentage of dispatch slots used by microcode ops that retired.",
|
|
"MetricExpr": "retiring * d_ratio(ex_ret_ucode_ops, ex_ret_ops)",
|
|
"MetricGroup": "PipelineL2;retiring_group",
|
|
"ScaleUnit": "100%slots"
|
|
}
|
|
]
|