[Mlir-commits] [mlir] [mlir][xegpu] Add layout based SIMT distribution support for `vector.extract/insert_strided_slice` (PR #168626)

[Artem Kroviakov]

================
@@ -1469,6 +1485,227 @@ struct VectorShapeCastDistribution : public gpu::WarpDistributionPattern {
   }
 };
 
+// Distribute a `vector.extract_strided_slice` op feeding into yield op of an
+// enclosing `gpu.warp_execute_on_lane_0` region. This pattern only handles
+// advanced cases where the distributed is partially extracted and currently not
----------------
akroviakov wrote:

Did you mean
```suggestion
// advanced cases where the distributed vector is partially extracted and currently not
```
?

https://github.com/llvm/llvm-project/pull/168626