This is an archive of the discontinued LLVM Phabricator instance.

[AMDGPU] Use v3f32 type in image instructions
ClosedPublic

Authored by sebastian-ne on Feb 3 2020, 5:27 AM.

Details

Summary

This should lower the amount of used registers for gfx9.

I updated some of the changed tests with the update script because
changing them by hand is tedious.

Event Timeline

sebastian-ne created this revision.Feb 3 2020, 5:27 AM
arsenm accepted this revision.Feb 3 2020, 5:38 AM
This revision is now accepted and ready to land.Feb 3 2020, 5:38 AM
This revision was automatically updated to reflect the committed changes.
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.d16.dim.ll