[PATCH] Using Masked Load / Store intrinsics in Loop Vectorizer

[Elena Demikhovsky]

Hi nadav, aschwaighofer,

The loop vectorizer optimizes loops containing conditional memory accesses by generating masked load and store intrinsics.
This decision is target dependent.

I already submitted the codegen changes for the intrinsics.

http://reviews.llvm.org/D6527

Files:
  lib/Transforms/Vectorize/LoopVectorize.cpp
  test/Transforms/LoopVectorize/X86/mask1.ll
  test/Transforms/LoopVectorize/X86/mask2.ll
  test/Transforms/LoopVectorize/X86/mask3.ll
  test/Transforms/LoopVectorize/X86/mask4.ll
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D6527.16924.patch
Type: text/x-patch
Size: 19045 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20141204/6d6177fc/attachment.bin>