This is an archive of the discontinued LLVM Phabricator instance.

[X86] Make use of vpmovwb when possible in LowerMULH
ClosedPublic

Authored by craig.topper on Sep 28 2017, 11:58 AM.

Details

Summary

If we have BWI, we can truncate in a much simpler way by using vpmovwb. This even works without VLX by using the wider zmm->ymm truncate with a subvector extract.

Diff Detail

Event Timeline

craig.topper created this revision.Sep 28 2017, 11:58 AM
craig.topper edited the summary of this revision. (Show Details)
This revision is now accepted and ready to land.Sep 28 2017, 12:09 PM
This revision was automatically updated to reflect the committed changes.