[PATCH] D19198: [X86][AVX] Generalized matching for target shuffle combines

[Simon Pilgrim via llvm-commits]

RKSimon updated this revision to Diff 56558.
RKSimon added a comment.

Added AVX512 mask tests - the masked operations are still there.

Annoyingly the shuffle comments doesn't refer to the mask kregister - is there an accepted convention that we could possibly use to make this more clear?


Repository:
  rL LLVM

http://reviews.llvm.org/D19198

Files:
  lib/Target/X86/X86ISelLowering.cpp
  test/CodeGen/X86/vector-shuffle-combining-avx.ll
  test/CodeGen/X86/vector-shuffle-combining-avx512bw.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D19198.56558.patch
Type: text/x-patch
Size: 16559 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160509/9f886060/attachment.bin>