[PATCH] D30123: [InstCombine] shrink truncated splat shuffle

[Eli Friedman via Phabricator via llvm-commits]

efriedma accepted this revision.
efriedma added a comment.
This revision is now accepted and ready to land.

LGTM, but you might want to look into the following...

  define <8 x i16> @wide_splat1(<8 x i32> %x) {
    %shuf = trunc <8 x i32> %x to <8 x i16>
    %trunc = shufflevector <8 x i16> %shuf, <8 x i16> undef, <8 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
    ret <8 x i16> %trunc
  }
  
  define <8 x i16> @wide_splat2(<8 x i32> %x) {
    %trunc = shufflevector <8 x i32> %x, <8 x i32> undef, <8 x i32> <i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
    %shuf = trunc <8 x i32> %trunc to <8 x i16>
    ret <8 x i16> %shuf
  }
  
  llc output (x86-64, no SSSE3):
  
          .text
          .file   "<stdin>"
          .globl  wide_splat1
          .p2align        4, 0x90
          .type   wide_splat1, at function
  wide_splat1:                            # @wide_splat1
          .cfi_startproc
  # BB#0:
          pslld   $16, %xmm1
          psrad   $16, %xmm1
          pslld   $16, %xmm0
          psrad   $16, %xmm0
          packssdw        %xmm1, %xmm0
          pshuflw $170, %xmm0, %xmm0      # xmm0 = xmm0[2,2,2,2,4,5,6,7]
          pshufd  $80, %xmm0, %xmm0       # xmm0 = xmm0[0,0,1,1]
          retq
  .Lfunc_end0:
          .size   wide_splat1, .Lfunc_end0-wide_splat1
          .cfi_endproc
  
          .globl  wide_splat2
          .p2align        4, 0x90
          .type   wide_splat2, at function
  wide_splat2:                            # @wide_splat2
          .cfi_startproc
  # BB#0:
          pshufd  $170, %xmm0, %xmm0      # xmm0 = xmm0[2,2,2,2]
          pslld   $16, %xmm0
          psrad   $16, %xmm0
          packssdw        %xmm0, %xmm0
          retq
  .Lfunc_end1:
          .size   wide_splat2, .Lfunc_end1-wide_splat2
          .cfi_endproc


https://reviews.llvm.org/D30123