[PATCH] D35146: AMDGPU : Widen extending scalar loads to 32-bits

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp:245
+
+  return !I.isVolatile() && TySize < 32 && Align >= 4 && DA->isUniform(&I);
+}
----------------
This should really be I.isSimple(), in case it's atomic.


Repository:
  rL LLVM

https://reviews.llvm.org/D35146