[PATCH] D128756: [AMDGPU] gfx11 WMMA instruction support

[Jay Foad via Phabricator via llvm-commits]

foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIInstrInfo.cpp:3270
+      MIB->addOperand(MI.getOperand(I));
+    MIB.copyImplicitOps(MI);
+
----------------
I think you could just raise the upper bound of the loop above to `E = MI.getNumOperands()` instead of adding this extra call?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128756/new/

https://reviews.llvm.org/D128756