[Mlir-commits] [mlir] [mlir][xegpu] Add SIMT distribution support for GEMM transpose B case. (PR #155517)

[Charitha Saumya]

================
@@ -1276,6 +1305,142 @@ struct VectorShapeCastDistribution : public gpu::WarpDistributionPattern {
   }
 };
 
+/// Sink a memref::ExtractAlignedPointerAsIndex op feeding into yield op of an
+/// enclosing `gpu.warp_execute_on_lane_0` region. This will simply move the op
+/// outside of the warp op.
+struct MemrefExtractAlignedPointerAsIndexDistribution final
----------------
charithaintc wrote:

agreed. This op does not participate really in any distribution (as in distributing its types to smaller types). We will add generic `MoveUniformOpOutsideWarpOp` pattern in a separate PR. 

https://github.com/llvm/llvm-project/pull/155517