[Mlir-commits] [mlir] [MLIR][Vector] Fix transferOps optimization inside maskOp (PR #90835)

[Andrzej Warzyński]

banach-space wrote:

Thanks for working on this and sorry for the delay! Any chance you could use:
* [MaskableOpRewritePattern](https://github.com/llvm/llvm-project/blob/6d44a1ef55b559e59d725b07ffe1da988b4e5f1c/mlir/include/mlir/Dialect/Vector/Utils/VectorUtils.h#L132-L171)

? Feels like that's exactly what we need here. And you might be able to use it for `TransferPermutationMapLoweringPatterns` as well.

https://github.com/llvm/llvm-project/pull/90835