[all-commits] [llvm/llvm-project] 7e849f: [X86] LowerFunnelShift - allow non-constant vXi8 u...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 7e849fd97b6abd1de30ffc66da1ebf47afc7ab70
      https://github.com/llvm/llvm-project/commit/7e849fd97b6abd1de30ffc66da1ebf47afc7ab70
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2022-01-29 (Sat, 29 Jan 2022)

  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

  Log Message:
  -----------
  [X86] LowerFunnelShift - allow non-constant vXi8 unpack(y,x) << zext(z) lowering pre-AVX512

Without AVX512 (which can efficiently extend/truncate to vXi16/vXi32), unpacking/packing to vXi16 is more efficient that relying on the (uops-heavy) PBLENDV shift expansion