[Mlir-commits] [mlir] [mlir][linalg] Add support for scalable vectorization of linalg.mmt4d (PR #146531)

[Andrzej Warzyński]

================
@@ -871,7 +871,8 @@ FailureOr<VectorizationResult>
 vectorize(RewriterBase &rewriter, Operation *op,
           ArrayRef<int64_t> inputVectorSizes = {},
           ArrayRef<bool> inputScalableVecDims = {},
-          bool vectorizeNDExtract = false, bool flatten1DDepthwiseConv = false);
+          bool vectorizeNDExtract = false, bool flatten1DDepthwiseConv = false,
+          bool assumeScalableSizesMultipleOfDim = false);
----------------
banach-space wrote:

Thanks for the suggestion, I went with `assumeDynamicDimsMatchVecSizes`, see this [commit](https://github.com/llvm/llvm-project/pull/146531/commits/2b6019caf04f37715ca5857b31b3f4fe9c48a417). As mentioned in my other comment, for now I am "assuming" **equality** rather than **divisibility**.  Not sure whether we will need the latter?

https://github.com/llvm/llvm-project/pull/146531