[Mlir-commits] [mlir] [mlir][xegpu] Relax rank restriction of TensorDescType (PR #145916)

[Adam Siemieniuk]

================
@@ -157,6 +156,7 @@ def XeGPU_TensorDesc: XeGPUTypeDef<"TensorDesc", "tensor_desc",
       return MemorySpace::Global;
     }
 
+    // get the ChunkSize for blocked TensorDesc
----------------
adam-smnk wrote:

`ArrayLength`? It's better to leave `chunk` naming to scatter only

https://github.com/llvm/llvm-project/pull/145916