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

[Charitha Saumya]

================
@@ -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);
----------------
charithaintc wrote:

for storeND bCount is always 1, so why this is needed? 

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