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

[Jakub Kuderski]

================
@@ -112,21 +114,31 @@ LogicalResult FatRawBufferCastOp::verify() {
   return success();
 }
 
+static bool hasGlobalMemorySpace(Attribute memorySpace) {
+  if (!memorySpace)
+    return true;
+  if (auto intMemorySpace = llvm::dyn_cast<IntegerAttr>(memorySpace))
+    return intMemorySpace.getInt() == 0 || intMemorySpace.getInt() == 1;
+  if (auto gpuMemorySpace = llvm::dyn_cast<gpu::AddressSpaceAttr>(memorySpace))
----------------
kuhar wrote:

```suggestion
  if (auto intMemorySpace = dyn_cast<IntegerAttr>(memorySpace))
    return intMemorySpace.getInt() == 0 || intMemorySpace.getInt() == 1;
  if (auto gpuMemorySpace = dyn_cast<gpu::AddressSpaceAttr>(memorySpace))
```

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