[PATCH] D101380: [AMDGPU] Move insertion of function entry waitcnt later

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp:1601
+
+  if (!MFI->isEntryFunction()) {
+    // Wait for any outstanding memory operations that the input registers may
----------------
I thought we made this explicitly a property of the calling convention, so we could have this not be inserted for future conventions. I guess if this isn't checking the function for that already, it's a preexisting problem


================
Comment at: llvm/test/CodeGen/AMDGPU/waitcnt-preexisting.mir:188-190
+    ; GFX9: S_WAITCNT 0
+    ; GFX9-NOT: S_WAITCNT 0
+    ; GFX9: S_ENDPGM 0
----------------
-NEXTs would be a bit more dependable


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D101380/new/

https://reviews.llvm.org/D101380