[llvm] [AMDGPU] Fix typo in v_dot4 combine (PR #115224)

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Wed Nov 6 19:01:43 PST 2024


================
@@ -3450,4 +3450,850 @@ entry:
 }
 
 
+define amdgpu_kernel void @ByteOffsetCorrectness(ptr addrspace(1) noalias readonly align 16 %inptr0, ptr addrspace(1) noalias readonly align 16 %inptr1, ptr addrspace(1) noalias align 16 %inptr2) local_unnamed_addr {
----------------
arsenm wrote:

But what transformations? You can usually massage the test to defeat them. e.g. use volatile loads.

If you avoid using the work item ID intrinsics, you can avoid more transforms 

https://github.com/llvm/llvm-project/pull/115224


More information about the llvm-commits mailing list