[all-commits] [llvm/llvm-project] 630a6d: [X86] Fix throughput of AVX2/AVX512VL vector exten...

Simon Pilgrim via All-commits all-commits at lists.llvm.org
Sun Jun 16 02:53:17 PDT 2024


  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 630a6dd687ab4ec2038fc957fc8722c983aa4147
      https://github.com/llvm/llvm-project/commit/630a6dd687ab4ec2038fc957fc8722c983aa4147
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2024-06-16 (Sun, 16 Jun 2024)

  Changed paths:
    M llvm/lib/Target/X86/X86ScheduleZnver4.td
    M llvm/test/tools/llvm-mca/X86/Znver4/resources-avx2.s
    M llvm/test/tools/llvm-mca/X86/Znver4/resources-avx512bwvl.s
    M llvm/test/tools/llvm-mca/X86/Znver4/resources-avx512vl.s

  Log Message:
  -----------
  [X86] Fix throughput of AVX2/AVX512VL vector extension/truncations

These should only consume 1cy on either of the 2 pipes (only zmm ops should double pump) - matches AMD SoG + uops.info

Noticed while updating costs for #90748



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications


More information about the All-commits mailing list