[Mlir-commits] [mlir] [mlir][amdgpu] Add amdgpu.make_dma_descriptor (PR #169407)

[Krzysztof Drewniak]

================
@@ -50,11 +50,49 @@ struct AMDGPUInlinerInterface final : DialectInlinerInterface {
 };
 } // namespace
 
+static ParseResult
+parseDynamicIndex(OpAsmParser &parser,
----------------
krzysz00 wrote:

Shouldn't need this

For the non-vararg cases, we can use an argument.

For the vararg cases (sizes, strides, etc.) we'll want to use the same machinery `memref.subview` does.

https://github.com/llvm/llvm-project/pull/169407