[all-commits] [llvm/llvm-project] f9bf64: [X86] combineX86ShufflesRecursively - peek through...

Simon Pilgrim via All-commits all-commits at lists.llvm.org
Sun Feb 5 12:19:50 PST 2023


  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: f9bf64798c1aee3d9f1ce754b2d625026e29d197
      https://github.com/llvm/llvm-project/commit/f9bf64798c1aee3d9f1ce754b2d625026e29d197
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2023-02-05 (Sun, 05 Feb 2023)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-7.ll

  Log Message:
  -----------
  [X86] combineX86ShufflesRecursively - peek through free extract_subvector nodes

If we're shuffling an op that is extracted from the lowest subvector of a larger vector then we should try to peek through as much as possible without exceeding the root size

Another step towards removing the widenSubVector call from combineX86ShufflesRecursively (Issue #45319)




More information about the All-commits mailing list