linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	 Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	 Mark Rutland <mark.rutland@arm.com>,
	 Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@kernel.org>,  Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	 Kan Liang <kan.liang@linux.intel.com>,
	John Garry <john.g.garry@oracle.com>,
	 Jing Zhang <renyu.zj@linux.alibaba.com>,
	Sandipan Das <sandipan.das@amd.com>,
	 Benjamin Gray <bgray@linux.ibm.com>, Xu Yang <xu.yang_2@nxp.com>,
	linux-kernel@vger.kernel.org,  linux-perf-users@vger.kernel.org
Subject: [PATCH v4 10/12] perf jevents: Add load store breakdown metrics ldst for AMD
Date: Thu, 26 Sep 2024 10:40:59 -0700	[thread overview]
Message-ID: <20240926174101.406874-11-irogers@google.com> (raw)
In-Reply-To: <20240926174101.406874-1-irogers@google.com>

Give breakdown of number of instructions. Use the counter mask (cmask)
to show the number of cycles taken to retire the instructions.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/pmu-events/amd_metrics.py | 75 ++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

diff --git a/tools/perf/pmu-events/amd_metrics.py b/tools/perf/pmu-events/amd_metrics.py
index af99da14d946..3f77d1bbf1c9 100755
--- a/tools/perf/pmu-events/amd_metrics.py
+++ b/tools/perf/pmu-events/amd_metrics.py
@@ -275,6 +275,80 @@ def AmdItlb():
   ], description="Instruction TLB breakdown")
 
 
+def AmdLdSt() -> MetricGroup:
+  ldst_ld = Event("ls_dispatch.ld_dispatch")
+  ldst_st = Event("ls_dispatch.store_dispatch")
+  ldst_ldc1 = Event(f"{ldst_ld}/cmask=1/")
+  ldst_stc1 = Event(f"{ldst_st}/cmask=1/")
+  ldst_ldc2 = Event(f"{ldst_ld}/cmask=2/")
+  ldst_stc2 = Event(f"{ldst_st}/cmask=2/")
+  ldst_ldc3 = Event(f"{ldst_ld}/cmask=3/")
+  ldst_stc3 = Event(f"{ldst_st}/cmask=3/")
+  ldst_cyc = Event("ls_not_halted_cyc")
+
+  ld_rate = d_ratio(ldst_ld, interval_sec)
+  st_rate = d_ratio(ldst_st, interval_sec)
+
+  ld_v1 = max(ldst_ldc1 - ldst_ldc2, 0)
+  ld_v2 = max(ldst_ldc2 - ldst_ldc3, 0)
+  ld_v3 = ldst_ldc3
+
+  st_v1 = max(ldst_stc1 - ldst_stc2, 0)
+  st_v2 = max(ldst_stc2 - ldst_stc3, 0)
+  st_v3 = ldst_stc3
+
+  return MetricGroup("ldst", [
+      MetricGroup("ldst_total", [
+          Metric("ldst_total_ld", "Number of loads dispatched per second.",
+                 ld_rate, "insns/sec"),
+          Metric("ldst_total_st", "Number of stores dispatched per second.",
+                 st_rate, "insns/sec"),
+      ]),
+      MetricGroup("ldst_percent_insn", [
+          Metric("ldst_percent_insn_ld",
+                 "Load instructions as a percentage of all instructions.",
+                 d_ratio(ldst_ld, ins), "100%"),
+          Metric("ldst_percent_insn_st",
+                 "Store instructions as a percentage of all instructions.",
+                 d_ratio(ldst_st, ins), "100%"),
+      ]),
+      MetricGroup("ldst_ret_loads_per_cycle", [
+          Metric(
+              "ldst_ret_loads_per_cycle_1",
+              "Load instructions retiring in 1 cycle as a percentage of all "
+              "unhalted cycles.", d_ratio(ld_v1, ldst_cyc), "100%"),
+          Metric(
+              "ldst_ret_loads_per_cycle_2",
+              "Load instructions retiring in 2 cycles as a percentage of all "
+              "unhalted cycles.", d_ratio(ld_v2, ldst_cyc), "100%"),
+          Metric(
+              "ldst_ret_loads_per_cycle_3",
+              "Load instructions retiring in 3 or more cycles as a percentage"
+              "of all unhalted cycles.", d_ratio(ld_v3, ldst_cyc), "100%"),
+      ]),
+      MetricGroup("ldst_ret_stores_per_cycle", [
+          Metric(
+              "ldst_ret_stores_per_cycle_1",
+              "Store instructions retiring in 1 cycle as a percentage of all "
+              "unhalted cycles.", d_ratio(st_v1, ldst_cyc), "100%"),
+          Metric(
+              "ldst_ret_stores_per_cycle_2",
+              "Store instructions retiring in 2 cycles as a percentage of all "
+              "unhalted cycles.", d_ratio(st_v2, ldst_cyc), "100%"),
+          Metric(
+              "ldst_ret_stores_per_cycle_3",
+              "Store instructions retiring in 3 or more cycles as a percentage"
+              "of all unhalted cycles.", d_ratio(st_v3, ldst_cyc), "100%"),
+      ]),
+      MetricGroup("ldst_insn_bt", [
+          Metric("ldst_insn_bt_ld", "Number of instructions between loads.",
+                 d_ratio(ins, ldst_ld), "insns"),
+          Metric("ldst_insn_bt_st", "Number of instructions between stores.",
+                 d_ratio(ins, ldst_st), "insns"),
+      ])
+  ], description="Breakdown of load/store instructions")
+
+
 def AmdHwpf():
   """Returns a MetricGroup representing AMD hardware prefetch metrics."""
   global _zen_model
@@ -512,6 +586,7 @@ def main() -> None:
       AmdBr(),
       AmdDtlb(),
       AmdItlb(),
+      AmdLdSt(),
       AmdHwpf(),
       AmdSwpf(),
       AmdUpc(),
-- 
2.46.1.824.gd892dcdcdd-goog


  parent reply	other threads:[~2024-09-26 17:41 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-09-26 17:40 [PATCH v4 00/12] Python generated AMD Zen metrics Ian Rogers
2024-09-26 17:40 ` [PATCH v4 01/12] perf jevents: Add RAPL event metric for AMD zen models Ian Rogers
2024-09-26 17:40 ` [PATCH v4 02/12] perf jevents: Add idle " Ian Rogers
2024-09-26 17:40 ` [PATCH v4 03/12] perf jevents: Add upc metric for uops per cycle for AMD Ian Rogers
2024-09-26 17:40 ` [PATCH v4 04/12] perf jevents: Add br metric group for branch statistics on AMD Ian Rogers
2024-09-26 17:40 ` [PATCH v4 05/12] perf jevents: Add software prefetch (swpf) metric group for AMD Ian Rogers
2024-09-26 17:40 ` [PATCH v4 06/12] perf jevents: Add hardware prefetch (hwpf) " Ian Rogers
2024-09-26 17:40 ` [PATCH v4 07/12] perf jevents: Add itlb " Ian Rogers
2024-09-26 17:40 ` [PATCH v4 08/12] perf jevents: Add dtlb " Ian Rogers
2024-09-26 17:40 ` [PATCH v4 09/12] perf jevents: Add uncore l3 " Ian Rogers
2024-09-26 17:40 ` Ian Rogers [this message]
2024-09-26 17:41 ` [PATCH v4 11/12] perf jevents: Add ILP metrics " Ian Rogers
2024-09-26 17:41 ` [PATCH v4 12/12] perf jevents: Add context switch " Ian Rogers

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240926174101.406874-11-irogers@google.com \
    --to=irogers@google.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=bgray@linux.ibm.com \
    --cc=john.g.garry@oracle.com \
    --cc=jolsa@kernel.org \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=renyu.zj@linux.alibaba.com \
    --cc=sandipan.das@amd.com \
    --cc=xu.yang_2@nxp.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).