[Mlir-commits] [mlir] [MLIR][XeGPU] Add support for elementwise ops in Wg to Sg distribute pass [1/N] (PR #142797)

[Adam Siemieniuk]

================
@@ -328,6 +331,63 @@ struct WgToSgPrefetchNdOp : public OpConversionPattern<xegpu::PrefetchNdOp> {
   }
 };
 
+// This pattern transforms elementwise ops in math/arith dialect
----------------
adam-smnk wrote:

nit: I'd slightly update the comment as it doesn't target specific dialects anymore

https://github.com/llvm/llvm-project/pull/142797