This is an archive of the discontinued LLVM Phabricator instance.

[X86][AVX512] add convert float to half
ClosedPublic

Authored by AsafBadouh on Oct 27 2015, 4:58 AM.

Details

Summary

convert float to half with mask/maskz for the reg to reg version and mask for the reg to mem version (there is no maskz version for reg to mem).

made naming fix in GCC builtin for cvtph2ps in its 128bit width version (in order to be align with GCC)

Diff Detail

Event Timeline

AsafBadouh updated this revision to Diff 38528.Oct 27 2015, 4:58 AM
AsafBadouh retitled this revision from to [X86][AVX512] add convert float to half.
AsafBadouh updated this object.
AsafBadouh added reviewers: igorb, delena.
AsafBadouh added a subscriber: llvm-commits.
This revision was automatically updated to reflect the committed changes.