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

Thu Dec 15 05:15:23 PST 2022

alex-t marked an inline comment as done.
alex-t added inline comments.

================
Comment at: llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp:960
+        MachineInstr *DefMI = D.getSUnit()->getInstr();
+        unsigned Latency =
+            SI->getInstrLatency(ST.getInstrItineraryData(), *DefMI);
----------------
kerbowa wrote:
> What about unbuffered resources like MFMA? I guess maybe it should be considered in future patches.
This is the very first and drafty implementation which aims to find what it yields.
All the specific things like HW hazards and unbuffered resources may be considered further in case we really observe that we need a more precise model.

Repository:
  rG LLVM Github Monorepo

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

https://reviews.llvm.org/D139710