[PATCH] D57728: Relax constraints for reduction vectorization

[Sanjoy Das via Phabricator via llvm-commits]

sanjoy updated this revision to Diff 189097.
sanjoy added a comment.

Propagate only correct FP fast-math flags.

I'd appreciate a careful review here since I'm not sure all of the ways we
codegen reductions in the loop vectorizer.


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57728/new/

https://reviews.llvm.org/D57728

Files:
  include/llvm/Analysis/IVDescriptors.h
  include/llvm/IR/Operator.h
  include/llvm/Transforms/Utils/LoopUtils.h
  lib/Analysis/IVDescriptors.cpp
  lib/CodeGen/ExpandReductions.cpp
  lib/Transforms/Utils/LoopUtils.cpp
  lib/Transforms/Vectorize/LoopVectorize.cpp
  lib/Transforms/Vectorize/SLPVectorizer.cpp
  test/Transforms/LoopVectorize/reduction-fastmath.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D57728.189097.patch
Type: text/x-patch
Size: 16785 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190303/7570cf3c/attachment.bin>