This is an archive of the discontinued LLVM Phabricator instance.

[X86][AVX512CD] add mask broadcast intrinsics
ClosedPublic

Authored by AsafBadouh on Nov 11 2015, 6:46 AM.

Diff Detail

Repository
rL LLVM

Event Timeline

AsafBadouh updated this revision to Diff 39911.Nov 11 2015, 6:46 AM
AsafBadouh retitled this revision from to [X86][AVX512CD] add mask broadcast intrinsics.
AsafBadouh updated this object.
AsafBadouh added reviewers: delena, igorb.
AsafBadouh added a subscriber: llvm-commits.
delena added inline comments.Nov 14 2015, 11:05 PM
../llvm/lib/Target/X86/Disassembler/X86Disassembler.cpp
836 ↗(On Diff #39911)

add VK2, VK32 and VK64, please

../llvm/lib/Target/X86/X86ISelLowering.cpp
16431 ↗(On Diff #39911)

I think that MaskVT does not depend on VT. You just take 8 or 16 bits as one integer and broadcast them to all vector elements.

16436 ↗(On Diff #39911)

"else" one line up, like
} else {

AsafBadouh updated this revision to Diff 40381.Nov 17 2015, 3:27 AM

made changes according to Elena's comments

delena accepted this revision.Nov 17 2015, 3:39 AM
delena edited edge metadata.

LGTM

This revision is now accepted and ready to land.Nov 17 2015, 3:39 AM
This revision was automatically updated to reflect the committed changes.