OSDN Git Service

Fix an issue where fast math flags were dropped during scalarization.
authorOwen Anderson <resistor@mac.com>
Tue, 1 Mar 2016 19:35:52 +0000 (19:35 +0000)
committerOwen Anderson <resistor@mac.com>
Tue, 1 Mar 2016 19:35:52 +0000 (19:35 +0000)
commit2b8030cd9725041ab08e22a7804a3c8189196ab4
tree7e81ef247dfa06bd0394288c6507e0768978f3fd
parent2a436300c15092d3fc15884bfb73026fbdceee01
Fix an issue where fast math flags were dropped during scalarization.

Most portions of InstCombine properly propagate fast math flags, but
apparently the vector scalarization section was overlooked.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@262376 91177308-0d34-0410-b5e6-96231b3b80d8
include/llvm/IR/InstrTypes.h
lib/Transforms/InstCombine/InstCombineVectorOps.cpp
test/Transforms/InstCombine/fast-math-scalarization.ll [new file with mode: 0644]