tarceri has quit [Remote host closed the connection]
YuGiOhJCJ has quit [Remote host closed the connection]
YuGiOhJCJ has joined #dri-devel
pixelcluster_ has joined #dri-devel
pixelcluster has quit [Ping timeout: 480 seconds]
bbrezillon has quit [Read error: Connection reset by peer]
ella-0 has joined #dri-devel
bbrezillon has joined #dri-devel
ella-0_ has quit [Read error: Connection reset by peer]
kts has quit [Quit: Konversation terminated!]
tarceri has joined #dri-devel
slattann has quit [Read error: Connection reset by peer]
srslypascal has quit [Remote host closed the connection]
srslypascal has joined #dri-devel
slattann has joined #dri-devel
Duke`` has joined #dri-devel
heat_ has joined #dri-devel
heat has quit [Read error: Connection reset by peer]
Company has quit [Quit: Leaving]
alanc has quit [Remote host closed the connection]
alanc has joined #dri-devel
kts has joined #dri-devel
rasterman has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
mclasen has quit [Ping timeout: 480 seconds]
gouchi has joined #dri-devel
heat_ has quit [Remote host closed the connection]
tango_ has quit [Quit: I'm never quite so stupid as when I'm being smart (Linus van Pel)]
heat_ has joined #dri-devel
heat_ has quit [Remote host closed the connection]
heat_ has joined #dri-devel
tango_ has joined #dri-devel
YuGiOhJCJ has quit [Quit: YuGiOhJCJ]
MajorBiscuit has joined #dri-devel
heat has joined #dri-devel
heat_ has quit [Read error: No route to host]
heat has quit [Read error: No route to host]
heat has joined #dri-devel
kts has joined #dri-devel
pixelcluster has joined #dri-devel
pixelcluster_ has quit [Ping timeout: 480 seconds]
gouchi has quit [Remote host closed the connection]
Haaninjo has joined #dri-devel
heat has quit [Remote host closed the connection]
heat has joined #dri-devel
slattann has quit [Ping timeout: 480 seconds]
pcercuei has joined #dri-devel
<Venemo>
is gitlab down again?
<pixelcluster>
It seems to work for me, just really slowly
libv_ has joined #dri-devel
libv has quit [Ping timeout: 480 seconds]
MajorBiscuit has quit [Quit: WeeChat 3.5]
OftenTimeConsuming is now known as Guest4072
OftenTimeConsuming has joined #dri-devel
Guest4072 has quit [Remote host closed the connection]
sul has joined #dri-devel
mclasen has joined #dri-devel
kts has quit [Ping timeout: 480 seconds]
kts has joined #dri-devel
slattann has joined #dri-devel
kts has quit [Ping timeout: 480 seconds]
kts has joined #dri-devel
pochu has quit [Quit: leaving]
mclasen has quit []
mclasen has joined #dri-devel
mclasen has quit []
mclasen has joined #dri-devel
pixelcluster_ has joined #dri-devel
pixelclu- has joined #dri-devel
pixelcluster has quit [Ping timeout: 480 seconds]
pixelcluster has joined #dri-devel
pixelcluster_ has quit [Ping timeout: 480 seconds]
pixelclu- has quit [Ping timeout: 480 seconds]
sul has quit [Ping timeout: 480 seconds]
sul has joined #dri-devel
JohnnyonF has joined #dri-devel
JohnnyonFlame has quit [Ping timeout: 480 seconds]
pixelcluster_ has joined #dri-devel
pixelcluster has quit [Ping timeout: 480 seconds]
MajorBiscuit has joined #dri-devel
MajorBiscuit has quit []
MajorBiscuit has joined #dri-devel
MajorBiscuit has quit [Ping timeout: 480 seconds]
pixelcluster_ has quit []
pixelcluster has joined #dri-devel
MajorBiscuit has joined #dri-devel
<tango_>
I'm running a hip/rocm program (compute only, in theory) on my amd gpu, and nvtop reports the usage as “Graphics”, apparently it gets the info from libdrm. is the issue in nvtop, libdrm, or rocm workloads are graphics workloads?
libv_ is now known as libv
kts has quit [Quit: Konversation terminated!]
MajorBiscuit has quit [Ping timeout: 480 seconds]
JohnnyonF has quit [Ping timeout: 480 seconds]
tjmercier has quit [Remote host closed the connection]
dviola has quit [Quit: WeeChat 3.5]
Haaninjo has quit [Quit: Ex-Chat]
maxzor_ has joined #dri-devel
sul has quit [Ping timeout: 480 seconds]
sul has joined #dri-devel
maxzor_ has quit [Ping timeout: 480 seconds]
sul has quit [Ping timeout: 480 seconds]
sul has joined #dri-devel
mclasen has left #dri-devel [#dri-devel]
anujp_ has joined #dri-devel
<ishitatsuyuki>
tango_: I guess it's based on which queue is used. It's strange though, because ROCm should always be using a compute queue, unlike things like OpenGL which can only use the graphics queue.
<ishitatsuyuki>
Let me ask: does your cursor lag during the computation? If it does, significantly, then it's the graphics queue; otherwise, it's the compute queue
<tango_>
ishitatsuyuki: I don't actually use the machine for graphics 8-D
<ishitatsuyuki>
bleh
<tango_>
rocm-smi says that it's using the COMPUTE power profile, but that I would assume doesn't necessarily imply anything
<tango_>
and for the KFD processes it doesn't say what kind of processes they are
<tango_>
mah
MajorBiscuit has joined #dri-devel
pixelcluster_ has joined #dri-devel
pixelcluster has quit [Ping timeout: 480 seconds]
Haaninjo has joined #dri-devel
pixelcluster_ has quit [Ping timeout: 480 seconds]
mclasen has joined #dri-devel
sul has quit [Ping timeout: 480 seconds]
sul has joined #dri-devel
heat_ has joined #dri-devel
heat has quit [Read error: No route to host]
chaim has joined #dri-devel
JohnnyonFlame has joined #dri-devel
srslypascal is now known as Guest4090
srslypascal has joined #dri-devel
Guest4090 has quit [Ping timeout: 480 seconds]
Company has joined #dri-devel
MajorBiscuit has quit [Ping timeout: 480 seconds]
lygstate has joined #dri-devel
pixelcluster has joined #dri-devel
lygstate has quit [Remote host closed the connection]
JohnnyonFlame has quit [Ping timeout: 480 seconds]
rasterman has quit [Remote host closed the connection]
rasterman has joined #dri-devel
JoniSt has joined #dri-devel
JohnnyonFlame has joined #dri-devel
fxkamd has joined #dri-devel
Lynne has quit [Quit: Lynne]
Lynne has joined #dri-devel
MajorBiscuit has joined #dri-devel
MajorBiscuit has quit [Quit: WeeChat 3.5]
fxkamd has quit []
sravn_ is now known as sravn
<sravn>
Just pushed three trivial patches to drm-misc-next and now there are problems in rerere - mystified
gouchi has joined #dri-devel
gouchi has quit [Remote host closed the connection]
<sravn>
So I had created a branch that I never pushed, deletign the branch made git pull work in drm-rerere without issues. So I think it is solved.
<sravn>
mlankhorst, mripard - holler if you see I did somethign wrong I need to fix
<sravn>
Pushed two additional commits with no hiccups - so seems all is good now
sravn has quit [Quit: WeeChat 3.5]
pochu has joined #dri-devel
apinheiro has joined #dri-devel
maxzor__ has joined #dri-devel
Haaninjo has quit [Quit: Ex-Chat]
sravn has joined #dri-devel
srslypascal has quit [Ping timeout: 480 seconds]
srslypascal has joined #dri-devel
rasterman has quit [Quit: Gettin' stinky!]
Duke`` has quit [Ping timeout: 480 seconds]
maxzor__ has quit [Ping timeout: 480 seconds]
BobBeck has quit [Quit: Ping timeout (120 seconds)]
dwlsalmeida has joined #dri-devel
leandrohrb has joined #dri-devel
italove has joined #dri-devel
sul has quit [Read error: No route to host]
sul has joined #dri-devel
gallo2 has joined #dri-devel
tomeu has joined #dri-devel
padovan has joined #dri-devel
BobBeck has joined #dri-devel
chaim has quit [Quit: Konversation terminated!]
mclasen has quit [Ping timeout: 480 seconds]
<JoniSt>
mareko: Not sure if you're there, but I gave the TC multi-context rebind problem a bit more thought. If we disable invalidations for shared buffers but leave unsync uploads enabled (if the buffer isn't busy), we should still be able to do buffer uploads without doing a tc_sync in most cases.
<JoniSt>
My reasoning is that if an application wants to write to a shared buffer, it'll have to glFinish anyway on the contexts that share the buffer, at which point the buffer is most likely idle everywhere. If an application doesn't call glFinish before touching the shared buffer, that's a violation of the GL spec and therefore an application bug.
<JoniSt>
Only if all other contexts have called glFinish and the app then uses the shared buffer for some render call, followed by an upload to the same buffer, would we have to call tc_sync because we can't invalidate the buffer (it's both busy and can't be invalidated).
<JoniSt>
That's just a single tc_sync in a weird corner-case... That's not worth the huge complexity of doing cross-context rebinds, in my opinion.
<JoniSt>
I can rework the patch to allow unsync uploads for shared buffers if you like, or we could first merge it with these disabled and then enable them later after some more testing and thinking.
<JoniSt>
I'd really prefer to merge the "play it safe" version of the patch first just so the bug is fixed, of course, before doing performance optimizations.