projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 89ddc1b) | patch
[X86, AVX] fix zero-extending integer operand load patterns to use integer instructions
authorSanjay Patel <spatel@rotateright.com>
Tue, 31 Mar 2015 18:43:43 +0000 (18:43 +0000)
committerSanjay Patel <spatel@rotateright.com>
Tue, 31 Mar 2015 18:43:43 +0000 (18:43 +0000)
commit1b103763190e2b4c22ccd589e806915e3c7d96eb
treed168cbcb58931a5900040d482bd04daac62927a0tree | snapshot
parent89ddc1b326cd10a8c8b3c49aba8feb6ae0e3d09acommit | diff
[X86, AVX] fix zero-extending integer operand load patterns to use integer instructions

This is a follow-on to r233704 and another partial fix for PR22685:
https://llvm.org/bugs/show_bug.cgi?id=22685

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@233724 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/X86/X86InstrSSE.td diff | blob | history
test/CodeGen/X86/2012-1-10-buildvector.ll diff | blob | history
test/CodeGen/X86/vector-shuffle-256-v4.ll diff | blob | history
test/CodeGen/X86/vector-shuffle-256-v8.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors