[clang] [mlir] [llvm] [OpenMP] Migrate GPU Reductions CodeGen from Clang to OMPIRBuilder (PR #80343)

Akash Banerjee via cfe-commits cfe-commits at lists.llvm.org
Mon Feb 5 07:05:19 PST 2024


================
@@ -2953,7 +2953,7 @@ int bar(int n){
 // CHECK3-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [[STRUCT__GLOBALIZED_LOCALS_TY_0:%.*]], ptr [[TMP4]], i32 [[TMP5]]
 // CHECK3-NEXT:    [[C:%.*]] = getelementptr inbounds [[STRUCT__GLOBALIZED_LOCALS_TY_0]], ptr [[TMP8]], i32 0, i32 0
 // CHECK3-NEXT:    [[TMP9:%.*]] = load i8, ptr [[TMP7]], align 1
-// CHECK3-NEXT:    store i8 [[TMP9]], ptr [[C]], align 4
----------------
TIFitis wrote:

I'm not sure if this change is correct. My intuition says that the alignment was incorrect and this now fixes it, hopefully someone can comment.

https://github.com/llvm/llvm-project/pull/80343


More information about the cfe-commits mailing list