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

[Artem Kroviakov]

================
@@ -495,8 +495,7 @@ void LayoutInfoPropagation::visitPrefetchNdOp(
   auto [bWidth, bHeight, bCount] = blockWHC.value();
   SmallVector<int> instData;
   int instWidth = xegpu::getLargestDivisor(
-      static_cast<int>(tdescTy.getDimSize(tdescTy.getRank() - 1)), bWidth,
-      bCount);
+      static_cast<int>(tdescTy.getDimSize(tdescTy.getRank() - 1)), bWidth);
----------------
akroviakov wrote:

Yes, VC does not perfectly correspond to what we have in OCL

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