[PATCH] D17899: [x86, AVX] optimize masked loads with constant masks

[Sanjay Patel via llvm-commits]

spatel updated this revision to Diff 50043.
spatel added a comment.

Patch updated (just code comments, nothing functional):

1. Changed documentation comment to make the benefit of this transform clearer.
2. Added comment to explain why we filter out the undef pass-through case.
3. Changed AVX512 comment from FIXME to TODO. It's not broken; it just could be better based on what I see in the regression tests. And that should be a separate patch.


http://reviews.llvm.org/D17899

Files:
  lib/Target/X86/X86ISelLowering.cpp
  test/CodeGen/X86/masked_memop.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D17899.50043.patch
Type: text/x-patch
Size: 7796 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160308/6b0ef04d/attachment.bin>