[Mlir-commits] [mlir] [MLIR] Support non-atomic RMW option for emulated vector stores (PR #124887)

[Alan Li]

================
@@ -611,13 +636,31 @@ struct ConvertVectorStore final : OpConversionPattern<vector::StoreOp> {
       auto backMask = rewriter.create<arith::ConstantOp>(
           loc, DenseElementsAttr::get(subWidthStoreMaskType, maskValues));
 
-      atomicStore(rewriter, loc, memrefBase, currentDestIndex,
-                  cast<VectorValue>(subWidthStorePart), backMask.getResult());
+      subEmulatedWidthStore(rewriter, loc, memrefBase, currentDestIndex,
+                            cast<VectorValue>(subWidthStorePart),
+                            backMask.getResult());
----------------
lialan wrote:

I think you are right! I renamed them to `atomicRMWStore` and `nonAtomicRMWStore` as well.

https://github.com/llvm/llvm-project/pull/124887