[PATCH v3 16/20] perf jevents: Add local/remote "mem" breakdown metrics for Intel

[Ian Rogers]

Breakdown local and remote memory bandwidth, read and writes. The
implementation uses the HA and CHA PMUs present in server models
broadwellde, broadwellx cascadelakex, emeraldrapids, haswellx,
icelakex, ivytown, sapphirerapids and skylakex.

Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/pmu-events/intel_metrics.py | 27 ++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tools/perf/pmu-events/intel_metrics.py b/tools/perf/pmu-events/intel_metrics.py
index c7f536d3d4ed..254a4e73d926 100755
--- a/tools/perf/pmu-events/intel_metrics.py
+++ b/tools/perf/pmu-events/intel_metrics.py
@@ -777,6 +777,32 @@ def IntelLdSt() -> Optional[MetricGroup]:
   ], description = "Breakdown of load/store instructions")
 
 
+def UncoreMem() -> Optional[MetricGroup]:
+  try:
+    loc_rds = Event("UNC_CHA_REQUESTS.READS_LOCAL", "UNC_H_REQUESTS.READS_LOCAL")
+    rem_rds = Event("UNC_CHA_REQUESTS.READS_REMOTE", "UNC_H_REQUESTS.READS_REMOTE")
+    loc_wrs = Event("UNC_CHA_REQUESTS.WRITES_LOCAL", "UNC_H_REQUESTS.WRITES_LOCAL")
+    rem_wrs = Event("UNC_CHA_REQUESTS.WRITES_REMOTE", "UNC_H_REQUESTS.WRITES_REMOTE")
+  except:
+    return None
+
+  scale = 64 / 1_000_000
+  return MetricGroup("mem", [
+      MetricGroup("mem_local", [
+          Metric("mem_local_read", "Local memory read bandwidth not including directory updates",
+                 d_ratio(loc_rds, interval_sec), f"{scale}MB/s"),
+          Metric("mem_local_write", "Local memory write bandwidth not including directory updates",
+                 d_ratio(loc_wrs, interval_sec), f"{scale}MB/s"),
+      ]),
+      MetricGroup("mem_remote", [
+          Metric("mem_remote_read", "Remote memory read bandwidth not including directory updates",
+                 d_ratio(rem_rds, interval_sec), f"{scale}MB/s"),
+          Metric("mem_remote_write", "Remote memory write bandwidth not including directory updates",
+                 d_ratio(rem_wrs, interval_sec), f"{scale}MB/s"),
+      ]),
+  ], description = "Memory Bandwidth breakdown local vs. remote (remote requests in). directory updates not included")
+
+
 def UncoreMemBw() -> Optional[MetricGroup]:
   mem_events = []
   try:
@@ -874,6 +900,7 @@ def main() -> None:
       IntelMlp(),
       IntelPorts(),
       IntelSwpf(),
+      UncoreMem(),
       UncoreMemBw(),
   ])
 
-- 
2.44.0.278.ge034bb2e1d-goog