projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 177b35e) | patch
[x86] lower calls to llvm.maxnum.v4f32 using maxps
authorSanjay Patel <spatel@rotateright.com>
Sat, 26 Dec 2015 21:44:55 +0000 (21:44 +0000)
committerSanjay Patel <spatel@rotateright.com>
Sat, 26 Dec 2015 21:44:55 +0000 (21:44 +0000)
commit39227c5849d4c0acbc228e54433c05833f2fea75
tree5fefa091bd38ca45e279770ec907412fbd79e993tree | snapshot
parent177b35e464b0a17afad4f2d4da61447da027d059commit | diff
[x86] lower calls to llvm.maxnum.v4f32 using maxps

This is a follow-on to:
http://reviews.llvm.org/rL255700

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@256454 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/X86/X86ISelLowering.cpp diff | blob | history
test/CodeGen/X86/fmaxnum.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors