[llvm] [AArch64][SVE] Used fixed width vectorization for A510 and A520 (PR #132246)

David Green via llvm-commits llvm-commits at lists.llvm.org
Thu Apr 3 00:10:19 PDT 2025


https://github.com/davemgreen approved this pull request.

LGTM, can you change the title to something like "[AArch64][SVE] Use FeatureUseFixedOverScalableIfEqualCost for A510 and A520". It is only when the scores are equal and the vectorizer has no reason to pick one vs the other that this will cause the vectorizer to pick fixed-width.

https://github.com/llvm/llvm-project/pull/132246


More information about the llvm-commits mailing list