projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: fa2f4fd) | patch
The VPERM2F128 is a AVX instruction which permutes between two 256-bit
authorBruno Cardoso Lopes <bruno.cardoso@gmail.com>
Fri, 12 Aug 2011 21:48:26 +0000 (21:48 +0000)
committerBruno Cardoso Lopes <bruno.cardoso@gmail.com>
Fri, 12 Aug 2011 21:48:26 +0000 (21:48 +0000)
commit53cae1362dca8aa312c3e36c10b106ea7d349f93
tree086f5259df8deee05edd159e4b4eaedd80a8796etree | snapshot
parentfa2f4fd9a2838c98966ed30a4e5e404338d8a0f3commit | diff
The VPERM2F128 is a AVX instruction which permutes between two 256-bit
vectors. It operates on 128-bit elements instead of regular scalar
types. Recognize shuffles that are suitable for VPERM2F128 and teach
the x86 legalizer how to handle them.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137519 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/X86/InstPrinter/X86InstComments.cpp diff | blob | history
lib/Target/X86/Utils/X86ShuffleDecode.cpp diff | blob | history
lib/Target/X86/Utils/X86ShuffleDecode.h diff | blob | history
lib/Target/X86/X86ISelLowering.cpp diff | blob | history
lib/Target/X86/X86ISelLowering.h diff | blob | history
lib/Target/X86/X86InstrFragmentsSIMD.td diff | blob | history
lib/Target/X86/X86InstrSSE.td diff | blob | history
test/CodeGen/X86/avx-vperm2f128.ll [new file with mode: 0644] blob
C/C++ LLVM-based compilers that forbids OOTA behaviors