[llvm-branch-commits] [llvm] [AMDGPU] PromoteAlloca: split scalar accesses that span several elements (PR #217056)

[via llvm-branch-commits]

================
@@ -840,6 +861,9 @@ static bool isSupportedAccessType(FixedVectorType *VecTy, Type *AccessTy,
     return AccTS.isKnownMultipleOf(VecTS);
   }
 
+  if (isMultiElementScalarAccess(VecTy->getElementType(), AccessTy, DL))
----------------
ruiling wrote:

The function is mostly duplicating the check against `FixedVectorType`. I think you can just refactor the code above to handle the scalar case.

https://github.com/llvm/llvm-project/pull/217056