[PATCH] D19661: [X86] Also try to zero elts when lowering v32i8 shuffle with PSHUFB.

[Ahmed Bougacha via llvm-commits]

ab updated this revision to Diff 58824.
ab added a comment.

I did a final review before committing, but realized I missed the v16i16 case.

Here's an alternative patch, with a generalized PSHUFB lowering, and "zeroable mask" computation.  WDYT?

I went ahead and renamed lowerVectorShuffleAsPSHUFB in r271024.


http://reviews.llvm.org/D19661

Files:
  lib/Target/X86/X86ISelLowering.cpp
  test/CodeGen/X86/vector-shuffle-256-v16.ll
  test/CodeGen/X86/vector-shuffle-256-v32.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D19661.58824.patch
Type: text/x-patch
Size: 8445 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160527/86d778a0/attachment.bin>