projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 1d63231) | patch
[x86] Implement AVX2 support for v32i8 in the new vector shuffle
authorChandler Carruth <chandlerc@gmail.com>
Thu, 25 Sep 2014 02:52:12 +0000 (02:52 +0000)
committerChandler Carruth <chandlerc@gmail.com>
Thu, 25 Sep 2014 02:52:12 +0000 (02:52 +0000)
commite3bb4bb2d553003df7d069ee2504c7e9403aac57
treecd93374687bca050a019a558001f0788c5e5d78ftree | snapshot
parent1d632314559b5df65dec086b777a43890e09c238commit | diff
[x86] Implement AVX2 support for v32i8 in the new vector shuffle
lowering.

This completes the basic AVX2 feature support, but there are still some
improvements I'd like to do to really get the last mile of performance
here.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218440 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/X86/X86ISelLowering.cpp diff | blob | history
test/CodeGen/X86/vector-shuffle-256-v32.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors