projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 3aca32e) | patch
AVX-512: Floating point conversions for SKX - DAG Lowering.
authorElena Demikhovsky <elena.demikhovsky@intel.com>
Sun, 19 Jul 2015 10:17:33 +0000 (10:17 +0000)
committerElena Demikhovsky <elena.demikhovsky@intel.com>
Sun, 19 Jul 2015 10:17:33 +0000 (10:17 +0000)
commit17b906058e219bdb360c9d35dca55bda6153b161
tree743d4dc3f639d188075d83a0de781574c220237dtree | snapshot
parent3aca32ea4aa2f5c033ada5d43bf85af9981aee97commit | diff
AVX-512: Floating point conversions for SKX - DAG Lowering.
SKX supports conversion for all FP types. Integer types include doublewords and quardwords.
I added "Legal" status for these nodes and a bunch of tests.
I added "NoVLX" for AVX DAG selection to force VLX instructions selection when VLX is supported.

Differential Revision: http://reviews.llvm.org/D11255

llvm-svn: 242637
llvm/lib/Target/X86/X86ISelLowering.cpp diff | blob | history
llvm/lib/Target/X86/X86InstrSSE.td diff | blob | history
llvm/test/CodeGen/X86/avx512-cvt.ll diff | blob | history
Domain: System / Toolchain;