[PATCH] D140599: AMDGPU: Promote array alloca if used by memmove/memcpy

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

Shouldn't these have been expanded into loads and stores already?



================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp:508
+        return dyn_cast<ConstantInt>(calculateVectorIndex(Ptr, GEPVectorIdx));
+      };
+
----------------
Extra ;


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D140599/new/

https://reviews.llvm.org/D140599