projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 4da3ba8) | patch
[X86] AVX512: Add vbroadcasti*
authorAdam Nemet <anemet@apple.com>
Fri, 27 Jun 2014 00:43:38 +0000 (00:43 +0000)
committerAdam Nemet <anemet@apple.com>
Fri, 27 Jun 2014 00:43:38 +0000 (00:43 +0000)
commita50d4dd9b0378cce9400139c7808204540a1f5a9
tree774257c3803c8d8203b0c88484f373d7194fe458tree | snapshot
parent4da3ba8c2ebe70c16342f90797830931275b2ad7commit | diff
[X86] AVX512: Add vbroadcasti*

For now I used a separate template for these sub-vector/tuple broadcasts
rather than sharing the mem variants with avx512_int_broadcast_rm.

<rdar://problem/17402869>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211828 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/X86/X86InstrAVX512.td diff | blob | history
test/MC/X86/avx512-encodings.s diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors