[Bug 111763] ring_gfx hangs/freezes on Navi gpus
bugzilla-daemon at freedesktop.org
bugzilla-daemon at freedesktop.org
Sun Nov 10 14:00:27 UTC 2019
https://bugs.freedesktop.org/show_bug.cgi?id=111763
--- Comment #34 from Marko Popovic <popovic.marko at protonmail.com> ---
(In reply to Daniel Suarez from comment #33)
> (In reply to Marko Popovic from comment #32)
> > (In reply to Daniel Suarez from comment #31)
> > > (In reply to Marko Popovic from comment #30)
> > > > (In reply to Daniel Suarez from comment #29)
> > > > > (In reply to Marko Popovic from comment #28)
> > > > > > I think this bug report can be closed now, Mesa 20 git basically fixes radv
> > > > > > related ring_gfx hangs, there is still hang that happens in Citra emulator
> > > > > > (ngg related) but AMD developers are aware of it so will probably get fixed
> > > > > > too.
> > > > >
> > > > > Yeah.. "soon". Still waiting for them to fix bug 111481
> > > >
> > > > SDMA hangs have nothing to do with ring_gfx hangs which were mostly radv
> > > > related and are fixed now
> > >
> > > Still, I can't even play Vulkan titles reliably because the system
> > > constantly hangs even with the workarounds in the bug report. AMD really
> > > needs to fix them.
> >
> > Mesa 20.0 should fix Vulkan hangs for you, and with nodma SDMA is disabled
> > fully so you can't get any hangs that are SDMA related.
>
> That workaround delays the hangs af best, and I have gotten hangs from
> OpenGl Games and also by using amdvlk.
>
> Don't get me wrong I'm not saying this bug report shouldn't be closed, I'm
> just saying that you saying "soon" is very misleading. AMD hasn't still
> properly fixed bugs that lead to hangs by just watching Firefox, and it's
> been MONTHS. "soon" for them is months apperantly
And where exactly did I say soon?
--
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/dri-devel/attachments/20191110/d4c67c52/attachment-0001.html>
More information about the dri-devel
mailing list