[PATCH] D139710: [AMDGPU] MachineScheduler: schedule execution metric added for the UnclusteredHighRPStage

[Valery Pykhtin via Phabricator via llvm-commits]

vpykhtin added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp:953
+  unsigned CurrCycle = 0;
+  for (auto SU : InputSchedule) {
+#ifndef NDEBUG
----------------
auto &SU


================
Comment at: llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp:1032
+    CurrentSchedule.push_back(*SU);
+  }
+
----------------
vpykhtin wrote:
> Unneeded copy. Add second version of getScheduleMetrics that can perform in MachineInstr*, you can translate an instruction to SUnit inside.
Sorry, I mean not second version but template, something like:

```
// shim accessors
SUnit &getSUnit(&DAG, MachineInstr *MI) { return DAG.getSUnit(MI); }
SUnit &getSUnit(&DAG, SUnit &SU) { return SU; }

template <typename Range>
ScheduleMetrics GCNSchedStage::getScheduleMetrics(Range &&S) {
...
  for (auto &X : S) {
     SUnit &SU = getSUnit(DAG, X);
```


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D139710/new/

https://reviews.llvm.org/D139710