This is an archive of the discontinued LLVM Phabricator instance.

[AMDGPU] Always reserve flat scratch SGPR for architected flat scratch
ClosedPublic

Authored by rampitec on Sep 23 2021, 5:50 PM.

Details

Summary

With architected flat scratch it becomes readonly. We must always
reserve SGPR pair for it even if we do not use scratch at all since
an attempt to write to SGPRs mapped to FLAT_SCRATCH results in
memory violation.

This is not needed since GFX10 with architected flat scratch though
since special SGPRs are not carving space from normal SGPRs.

Diff Detail

Event Timeline

rampitec created this revision.Sep 23 2021, 5:50 PM
rampitec requested review of this revision.Sep 23 2021, 5:50 PM
Herald added a project: Restricted Project. · View Herald TranscriptSep 23 2021, 5:50 PM
Herald added a subscriber: wdng. · View Herald Transcript
kzhuravl accepted this revision.Sep 24 2021, 5:35 AM

LGTM, thanks!

This revision is now accepted and ready to land.Sep 24 2021, 5:35 AM
This revision was landed with ongoing or failed builds.Sep 24 2021, 9:47 AM
This revision was automatically updated to reflect the committed changes.