[PATCH] D15250: Detecte vector reduction operations just before instruction selection.

[Cong Hou via llvm-commits]

congh updated this revision to Diff 42479.
congh added a comment.

Update the patch according to Hal's comments.

FAdd and FMul are now supported when fast-math is used.


http://reviews.llvm.org/D15250

Files:
  include/llvm/CodeGen/SelectionDAGNodes.h
  lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
  test/CodeGen/Generic/vector-redux.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D15250.42479.patch
Type: text/x-patch
Size: 18986 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20151211/030a2dcb/attachment.bin>