[all-commits] [llvm/llvm-project] 2078c4: [X86] Lower insertions into upper half of an 256-b...

[Roman Lebedev via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 2078c4ecfda80f802febc4f98e4a163656093c43
      https://github.com/llvm/llvm-project/commit/2078c4ecfda80f802febc4f98e4a163656093c43
  Author: Roman Lebedev <lebedev.ri at gmail.com>
  Date:   2021-08-17 (Tue, 17 Aug 2021)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/avx-insertelt.ll
    M llvm/test/CodeGen/X86/avx2-masked-gather.ll
    M llvm/test/CodeGen/X86/avx512-insert-extract.ll
    M llvm/test/CodeGen/X86/avx512-masked-memop-64-32.ll
    M llvm/test/CodeGen/X86/insertelement-shuffle.ll
    M llvm/test/CodeGen/X86/masked_expandload.ll
    M llvm/test/CodeGen/X86/masked_gather.ll
    M llvm/test/CodeGen/X86/masked_gather_scatter.ll
    M llvm/test/CodeGen/X86/masked_load.ll

  Log Message:
  -----------
  [X86] Lower insertions into upper half of an 256-bit vector as broadcast+blend (PR50971)

Broadcast is not worse than extract+insert of subvector.
https://godbolt.org/z/aPq98G6Yh

Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D105390