[Mlir-commits] [mlir] [mlir][AMDGPU] Add canonicalizer for folding casts into gather_to_lds (PR #150503)

Jakub Kuderski llvmlistbot at llvm.org
Thu Jul 24 13:46:59 PDT 2025


================
@@ -546,6 +550,42 @@ LogicalResult GatherToLDSOp::verify() {
   return success();
 }
 
+namespace {
+/// If the source/target of a GatherToLDSOp is a CastOp that only removes static
+/// information or changes layout, the cast can be skipped.
+struct FoldGatherToLDSOfCast final : OpRewritePattern<GatherToLDSOp> {
+  using OpRewritePattern<GatherToLDSOp>::OpRewritePattern;
----------------
kuhar wrote:

```suggestion
  using OpRewritePattern::OpRewritePattern;
```

https://github.com/llvm/llvm-project/pull/150503


More information about the Mlir-commits mailing list