[llvm] [X86] combineX86ShuffleChain - always prefer VPERMQ/PD for unary subvector shuffles on AVX2+ targets (PR #134849)

Phoebe Wang via llvm-commits llvm-commits at lists.llvm.org
Tue Apr 8 08:28:23 PDT 2025


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

LGTM.

https://github.com/llvm/llvm-project/pull/134849


More information about the llvm-commits mailing list