[Mlir-commits] [mlir] [MLIR][XeGPU] Disable block count usage in layout propagation (PR #168504)

[Artem Kroviakov]

================
@@ -702,8 +701,7 @@ void LayoutInfoPropagation::visitStoreNdOp(
   auto [bWidth, bHeight, bCount] = blockWHC.value();
   SmallVector<int> instData;
   int instWidth = xegpu::getLargestDivisor(
-      static_cast<int>(dataTy.getDimSize(dataTy.getRank() - 1)), bWidth,
-      bCount);
+      static_cast<int>(dataTy.getDimSize(dataTy.getRank() - 1)), bWidth);
----------------
akroviakov wrote:

This change is here to eliminate block count from the propagation, regardless of possible values

https://github.com/llvm/llvm-project/pull/168504