[Mlir-commits] [mlir] [MLIR][AMDGPU] Add a wrapper for global LDS load intrinsics in AMDGPU (PR #133498)

[Krzysztof Drewniak]

================
@@ -459,6 +461,29 @@ LogicalResult DPPOp::verify() {
   return success();
 }
 
+LogicalResult GlobalLoadLDSOp::verify() {
+  MemRefType srcType = cast<MemRefType>(getSrc().getType());
+  MemRefType dstType = cast<MemRefType>(getDst().getType());
+
+  if (!memref::isStaticShapeAndContiguousRowMajor(srcType) ||
+      !memref::isStaticShapeAndContiguousRowMajor(dstType))
----------------
krzysz00 wrote:

... I'm actually not sure it's a hard requirement on the destination either, but I'm more open to buying that

https://github.com/llvm/llvm-project/pull/133498