This is an archive of the discontinued LLVM Phabricator instance.

[X86] Lower avx2/avx512f gather intrinsics to X86MaskedGatherSDNode instead of going directly to MachineSDNode.
ClosedPublic

Authored by craig.topper on Jan 16 2019, 11:59 PM.

Details

Summary

This sends these intrinsics through isel in a much more normal way. This should allow addressing mode matching in isel to make better use of the displacement field.

Diff Detail

Repository
rL LLVM

Event Timeline

craig.topper created this revision.Jan 16 2019, 11:59 PM

Update to include tests

RKSimon accepted this revision.Jan 18 2019, 1:29 AM

LGTM

This revision is now accepted and ready to land.Jan 18 2019, 1:29 AM
This revision was automatically updated to reflect the committed changes.