This is an archive of the discontinued LLVM Phabricator instance.

[AMDGPU] Add support for 64 bit buffer atomic artihmetic instructions
ClosedPublic

Authored by rtaylor on Mar 4 2019, 12:28 PM.

Details

Summary

This adds support for 64 bit buffer atomic arithmetic instructions but does not include
cmpswap as that depends on a fix to the way the register pairs are handled

Change-Id: Ib207ea65fb69487ccad5066ea647ae8ddfe2ce61

Diff Detail

Repository
rL LLVM

Event Timeline

rtaylor created this revision.Mar 4 2019, 12:28 PM
Herald added a project: Restricted Project. · View Herald TranscriptMar 4 2019, 12:28 PM
rtaylor updated this revision to Diff 189220.Mar 4 2019, 3:35 PM
This comment was removed by rtaylor.
rtaylor edited the summary of this revision. (Show Details)Mar 4 2019, 3:36 PM
arsenm accepted this revision.Mar 5 2019, 10:43 AM

LGTM

This revision is now accepted and ready to land.Mar 5 2019, 10:43 AM
This revision was automatically updated to reflect the committed changes.

Hi there,
Do you have the cmpswap fix somewhere?
Thanks

Hi there,
Do you have the cmpswap fix somewhere?
Thanks

Sorry, I just saw this, not sure if you are still interested but no I do not. I haven't looked at this for a bit.