[all-commits] [llvm/llvm-project] 9ec1c8: [X86] Always classify gf2p8affineqb/gf2p8affineinv...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 9ec1c8395710894618076e9931170f3e59e09f4b
      https://github.com/llvm/llvm-project/commit/9ec1c8395710894618076e9931170f3e59e09f4b
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2022-11-12 (Sat, 12 Nov 2022)

  Changed paths:
    M llvm/lib/Target/X86/X86InstrSSE.td
    M llvm/test/tools/llvm-mca/X86/Generic/resources-avx512gfnivl.s
    M llvm/test/tools/llvm-mca/X86/Generic/resources-avxgfni.s
    M llvm/test/tools/llvm-mca/X86/Generic/resources-gfni.s
    M llvm/test/tools/llvm-mca/X86/IceLakeServer/resources-avx512gfnivl.s
    M llvm/test/tools/llvm-mca/X86/IceLakeServer/resources-avxgfni.s
    M llvm/test/tools/llvm-mca/X86/IceLakeServer/resources-gfni.s

  Log Message:
  -----------
  [X86] Always classify gf2p8affineqb/gf2p8affineinvqb instructions with SchedWriteVecIMul

There was a mismatch between the AVX512 and SSE/AVX versions