projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: e53e377) | patch
Support x86 AVX 256-bit instruction intrinsics. Right now support all of them, but
authorBruno Cardoso Lopes <bruno.cardoso@gmail.com>
Tue, 3 Aug 2010 01:53:41 +0000 (01:53 +0000)
committerBruno Cardoso Lopes <bruno.cardoso@gmail.com>
Tue, 3 Aug 2010 01:53:41 +0000 (01:53 +0000)
commite5c500b37d3d4147521c8ff01d7a2b7fa2eca09b
tree8f439fce14e5af9bbb9756789bba34916b302403tree | snapshot
parente53e3772f3c8b4cba69b7d77c8b2148a080fe9aecommit | diff
Support x86 AVX 256-bit instruction intrinsics. Right now support all of them, but
as soon as we properly codegen the simple vector operations in clang, remove the
unnecessary builti-ins/intrinsics from clang and llvm.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110094 91177308-0d34-0410-b5e6-96231b3b80d8
include/llvm/IntrinsicsX86.td diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors