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>,
James Clark <james.clark@linaro.org>,
Xu Yang <xu.yang_2@nxp.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
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>
Subject: [PATCH v6 05/13] perf jevents: Add software prefetch (swpf) metric group for AMD
Date: Wed, 3 Sep 2025 21:40:39 -0700 [thread overview]
Message-ID: <20250904044047.999031-6-irogers@google.com> (raw)
In-Reply-To: <20250904044047.999031-1-irogers@google.com>
Add metrics that give the utility of software prefetches on zen2, zen3
and zen4.
Signed-off-by: Ian Rogers <irogers@google.com>
---
tools/perf/pmu-events/amd_metrics.py | 96 ++++++++++++++++++++++++++++
1 file changed, 96 insertions(+)
diff --git a/tools/perf/pmu-events/amd_metrics.py b/tools/perf/pmu-events/amd_metrics.py
index 172f04b38d78..acbb4e962814 100755
--- a/tools/perf/pmu-events/amd_metrics.py
+++ b/tools/perf/pmu-events/amd_metrics.py
@@ -120,6 +120,101 @@ def AmdBr():
description="breakdown of retired branch instructions")
+def AmdSwpf() -> Optional[MetricGroup]:
+ """Returns a MetricGroup representing AMD software prefetch metrics."""
+ global _zen_model
+ if _zen_model <= 1:
+ return None
+
+ swp_ld = Event("ls_dispatch.ld_dispatch")
+ swp_t0 = Event("ls_pref_instr_disp.prefetch")
+ swp_w = Event("ls_pref_instr_disp.prefetch_w") # Missing on Zen1
+ swp_nt = Event("ls_pref_instr_disp.prefetch_nta")
+ swp_mab = Event("ls_inef_sw_pref.mab_mch_cnt")
+ swp_l2 = Event("ls_sw_pf_dc_fills.local_l2",
+ "ls_sw_pf_dc_fills.lcl_l2",
+ "ls_sw_pf_dc_fill.ls_mabresp_lcl_l2")
+ swp_lc = Event("ls_sw_pf_dc_fills.local_ccx",
+ "ls_sw_pf_dc_fills.int_cache",
+ "ls_sw_pf_dc_fill.ls_mabresp_lcl_cache")
+ swp_lm = Event("ls_sw_pf_dc_fills.dram_io_near",
+ "ls_sw_pf_dc_fills.mem_io_local",
+ "ls_sw_pf_dc_fill.ls_mabresp_lcl_dram")
+ swp_rc = Event("ls_sw_pf_dc_fills.far_cache",
+ "ls_sw_pf_dc_fills.ext_cache_remote",
+ "ls_sw_pf_dc_fill.ls_mabresp_rmt_cache")
+ swp_rm = Event("ls_sw_pf_dc_fills.dram_io_far",
+ "ls_sw_pf_dc_fills.mem_io_remote",
+ "ls_sw_pf_dc_fill.ls_mabresp_rmt_dram")
+
+ # All the swpf that were satisfied beyond L1D are good.
+ all_pf = swp_t0 + swp_w + swp_nt
+ good_pf = swp_l2 + swp_lc + swp_lm + swp_rc + swp_rm
+ bad_pf = max(all_pf - good_pf, 0)
+
+ loc_pf = swp_l2 + swp_lc + swp_lm
+ rem_pf = swp_rc + swp_rm
+
+ req_pend = max(0, bad_pf - swp_mab)
+
+ r1 = d_ratio(ins, all_pf)
+ r2 = d_ratio(swp_ld, all_pf)
+ r3 = d_ratio(swp_t0, interval_sec)
+ r4 = d_ratio(swp_w, interval_sec)
+ r5 = d_ratio(swp_nt, interval_sec)
+ overview = MetricGroup("lpm_swpf_overview", [
+ Metric("lpm_swpf_ov_insn_bt_swpf", "Insn between SWPF", r1, "insns"),
+ Metric("lpm_swpf_ov_loads_bt_swpf", "Loads between SWPF", r2, "loads"),
+ Metric("lpm_swpf_ov_rate_prefetch_t0_t1_t2", "Rate prefetch TO_T1_T2", r3,
+ "insns/sec"),
+ Metric("lpm_swpf_ov_rate_prefetch_w", "Rate prefetch W", r4, "insns/sec"),
+ Metric("lpm_swpf_ov_rate_preftech_nta", "Rate prefetch NTA", r5, "insns/sec"),
+ ])
+
+ r1 = d_ratio(swp_mab, all_pf)
+ r2 = d_ratio(req_pend, all_pf)
+ usefulness_bad = MetricGroup("lpm_swpf_usefulness_bad", [
+ Metric("lpm_swpf_use_bad_hit_l1", "Usefulness bad hit L1", r1, "100%"),
+ Metric("lpm_swpf_use_bad_req_pend", "Usefulness bad req pending", r2, "100%"),
+ ])
+
+ r1 = d_ratio(good_pf, all_pf)
+ usefulness_good = MetricGroup("lpm_swpf_usefulness_good", [
+ Metric("lpm_swpf_use_good_other_src", "Usefulness good other src", r1,
+ "100%"),
+ ])
+
+ usefulness = MetricGroup("lpm_swpf_usefulness", [
+ usefulness_bad,
+ usefulness_good,
+ ])
+
+ r1 = d_ratio(swp_l2, good_pf)
+ r2 = d_ratio(swp_lc, good_pf)
+ r3 = d_ratio(swp_lm, good_pf)
+ data_src_local = MetricGroup("lpm_swpf_data_src_local", [
+ Metric("lpm_swpf_data_src_local_l2", "Data source local l2", r1, "100%"),
+ Metric("lpm_swpf_data_src_local_ccx_l3_loc_ccx",
+ "Data source local ccx l3 loc ccx", r2, "100%"),
+ Metric("lpm_swpf_data_src_local_memory_or_io",
+ "Data source local memory or IO", r3, "100%"),
+ ])
+
+ r1 = d_ratio(swp_rc, good_pf)
+ r2 = d_ratio(swp_rm, good_pf)
+ data_src_remote = MetricGroup("lpm_swpf_data_src_remote", [
+ Metric("lpm_swpf_data_src_remote_cache", "Data source remote cache", r1,
+ "100%"),
+ Metric("lpm_swpf_data_src_remote_memory_or_io",
+ "Data source remote memory or IO", r2, "100%"),
+ ])
+
+ data_src = MetricGroup("lpm_swpf_data_src", [data_src_local, data_src_remote])
+
+ return MetricGroup("lpm_swpf", [overview, usefulness, data_src],
+ description="Software prefetch breakdown (CCX L3 = L3 of current thread, Loc CCX = CCX cache on some socket)")
+
+
def AmdUpc() -> Metric:
ops = Event("ex_ret_ops", "ex_ret_cops")
upc = d_ratio(ops, smt_cycles)
@@ -183,6 +278,7 @@ def main() -> None:
all_metrics = MetricGroup("", [
AmdBr(),
+ AmdSwpf(),
AmdUpc(),
Idle(),
Rapl(),
--
2.51.0.338.gd7d06c2dae-goog
next prev parent reply other threads:[~2025-09-04 4:41 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-04 4:40 [PATCH v6 00/13] Python generated AMD Zen metrics Ian Rogers
2025-09-04 4:40 ` [PATCH v6 01/13] perf jevents: Add RAPL event metric for AMD zen models Ian Rogers
2025-09-04 4:40 ` [PATCH v6 02/13] perf jevents: Add idle " Ian Rogers
2025-09-04 4:40 ` [PATCH v6 03/13] perf jevents: Add upc metric for uops per cycle for AMD Ian Rogers
2025-09-04 4:40 ` [PATCH v6 04/13] perf jevents: Add br metric group for branch statistics on AMD Ian Rogers
2025-09-04 4:40 ` Ian Rogers [this message]
2025-09-04 4:40 ` [PATCH v6 06/13] perf jevents: Add hardware prefetch (hwpf) metric group for AMD Ian Rogers
2025-09-04 4:40 ` [PATCH v6 07/13] perf jevents: Add itlb " Ian Rogers
2025-09-04 4:40 ` [PATCH v6 08/13] perf jevents: Add dtlb " Ian Rogers
2025-09-04 4:40 ` [PATCH v6 09/13] perf jevents: Add uncore l3 " Ian Rogers
2025-09-04 4:40 ` [PATCH v6 10/13] perf jevents: Add load store breakdown metrics ldst " Ian Rogers
2025-09-04 4:40 ` [PATCH v6 11/13] perf jevents: Add ILP metrics " Ian Rogers
2025-09-04 4:40 ` [PATCH v6 12/13] perf jevents: Add context switch " Ian Rogers
2025-09-04 4:40 ` [PATCH v6 13/13] perf jevents: Add uop cache hit/miss rates " 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=20250904044047.999031-6-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=james.clark@linaro.org \
--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).