[all-commits] [llvm/llvm-project] afc8ad: [X86] LowerFunnelShift - improve handling of vXi8 ...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: afc8ad0d938b3fa74e92f1d066d28e64a7f7f905
      https://github.com/llvm/llvm-project/commit/afc8ad0d938b3fa74e92f1d066d28e64a7f7f905
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2024-04-19 (Fri, 19 Apr 2024)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/vector-fshl-128.ll
    M llvm/test/CodeGen/X86/vector-fshl-256.ll
    M llvm/test/CodeGen/X86/vector-fshr-128.ll
    M llvm/test/CodeGen/X86/vector-fshr-256.ll

  Log Message:
  -----------
  [X86] LowerFunnelShift - improve handling of vXi8 constant splat funnel shifts

This patch moves the promotion to vXi16 shifts and the upper/lower bit masking into LowerFunnelShift for targets that have a bit-select instruction (XOP's VPCMOV and AVX512's VPTERNLOG).

This prevents the regressions in #89115 due to the masking of ((X << V) | (Y >> (8-V))) vXi8 shifts.



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