projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 6f1ae3c) | patch
[AVX512] Don't use i128 masked gather/scatter/load/store. Do more accurately dataWidt...
authorIgor Breger <igor.breger@intel.com>
Tue, 2 Aug 2016 09:15:28 +0000 (09:15 +0000)
committerIgor Breger <igor.breger@intel.com>
Tue, 2 Aug 2016 09:15:28 +0000 (09:15 +0000)
commitf44b79d08ee51523c36edbc786b490afbc42b1be
tree753507739d9ea09e3ac1bb13b46ceaa4a00f92fatree | snapshot
parent6f1ae3c7db43a312d638cbcde2b431026d211d8dcommit | diff
[AVX512] Don't use i128 masked gather/scatter/load/store. Do more accurately dataWidth check.

Differential Revision: http://reviews.llvm.org/D23055

llvm-svn: 277435
llvm/lib/Target/X86/X86TargetTransformInfo.cpp diff | blob | history
llvm/test/Transforms/LoopVectorize/X86/int128_no_gather.ll [new file with mode: 0644] blob
Domain: System / Toolchain;