[all-commits] [llvm/llvm-project] 156f83: [X86] combineVectorTruncation - use PACKUSDW(BLEND...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 156f83adc2af453009a3d5fb56c140d8255892f1
      https://github.com/llvm/llvm-project/commit/156f83adc2af453009a3d5fb56c140d8255892f1
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2022-01-30 (Sun, 30 Jan 2022)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/avg.ll
    M llvm/test/CodeGen/X86/avx-trunc.ll
    M llvm/test/CodeGen/X86/cast-vsel.ll
    M llvm/test/CodeGen/X86/masked_store_trunc.ll
    M llvm/test/CodeGen/X86/psubus.ll
    M llvm/test/CodeGen/X86/shuffle-vs-trunc-256.ll
    M llvm/test/CodeGen/X86/vector-pack-256.ll
    M llvm/test/CodeGen/X86/vector-trunc-math.ll
    M llvm/test/CodeGen/X86/vector-trunc.ll

  Log Message:
  -----------
  [X86] combineVectorTruncation - use PACKUSDW(BLENDW(X,0),BLENDW(Y,0)) for v8i32->v8i16 truncation

Limit this to SSE41 - AVX1 targets to avoid UNPCKL(PSHUFB,PSHUFB), pre-SSE41 we don't have PACKUSDW/BLENDW and with AVX2 we can perform this as PERMQ(PSHUFB()).