<lina>
alyssa: Speaking of uniforms, I have a patch for that lying around in my compute tree on macOS
<lina>
I'm pretty sure the max load is 64 halfs and that is encoded as size=0
<lina>
You need to split after that (or at least Metal does)
<alyssa>
lina: brrrr okay, that tracks.
<alyssa>
will fix that in the rewrite. thanks for letting me know
<alyssa>
i wasn't sure what the max was
<lina>
Yeah, I saw it with a compute shader with tons of params
<alyssa>
thanks for checking that :)
<alyssa>
i was wondering and then forgot
<alyssa>
as usual
<lina>
^^
possiblemeatball has joined #asahi-gpu
DarkShadow44 has quit [Remote host closed the connection]
DarkShadow44 has joined #asahi-gpu
SSJ_GZ has joined #asahi-gpu
possiblemeatball has quit [Quit: Leaving]
pthariensflame has joined #asahi-gpu
pthariensflame has quit []
zjstraus has quit [Quit: Ping timeout (120 seconds)]
SSJ_GZ has quit [Ping timeout: 480 seconds]
amw has quit [Ping timeout: 480 seconds]
SSJ_GZ has joined #asahi-gpu
SSJ_GZ has quit [Remote host closed the connection]
SSJ_GZ has joined #asahi-gpu
possiblemeatball has joined #asahi-gpu
WindowPa- has quit [Ping timeout: 480 seconds]
bcrumb has joined #asahi-gpu
WindowPain has joined #asahi-gpu
bcrumb has quit [Quit: WeeChat 3.7.1]
possiblemeatball has quit [Quit: Leaving]
possiblemeatball has joined #asahi-gpu
<lina>
alyssa: So one thing I noticed when setting up today's stream is I ended up with (I think) ~4GB of GPU memory usage, which seems a bit excessive considering it was mostly just Inochi2D and OBS
<lina>
I was thinking we might want to add some GPU memory consumption tracking? At the very least the driver should track which process (PID/comm, surviving process termination) initially created each GEM object I think
<lina>
But maybe mesa could also pass some kind of identifier for what each allocation is, at least some kind of class bits? Like what PIPE_USAGE flags were used
<lina>
Also keeping the creation timestamp is a good idea I think
<lina>
That should be enough info to at least begin to analyze/debug memory usage patterns... thoughts? ^^
<lina>
(The 4GB was constant as far as I can tell, so it's either not an outright leak or it's a leak caused by something I don't understand yet and which has a specific trigger, not leaking in the steady state)
<lina>
OK, just closing Inochi2D cleared out half of that usage so yeah. That's not normal, Inochi2D with this model should be using a single 4Kx4K texture atlas plus mipmaps and a few intermediate framebuffers.
<lina>
And opening it immediately uses that RAM.
<lina>
Noting this down to investigate later
cylm_ has quit [Ping timeout: 480 seconds]
wonjongbot has joined #asahi-gpu
jlco_ has quit [Ping timeout: 480 seconds]
<alyssa>
sounds good
<alyssa>
lina: we're working on similar stuff at $WORK for panfrost
<alyssa>
Maybe hold off on this until we figure out what we want to do for panfrost and then copy that some stream ;)
<alyssa>
imho getting the UAPI right (especially sync) is far more important right now
<lina>
Sure ^^
<alyssa>
:+1:
<lina>
Though it's a pretty easy hack to just track some process names so if I ever run into unexplainable GPU usage (this one seems pretty obvious) it might be worth just doing anyway ^^
<lina>
But yeah, the next big thing is compute which is going to change one big part of the UAPI, and if not coincidentally with that, sync/etc will come right after since it follows naturally
jlco_ has joined #asahi-gpu
possiblemeatball has quit [Quit: Leaving]
bcrumb has joined #asahi-gpu
bcrumb has quit []
<karolherbst>
compute, yay!
<karolherbst>
anybody started to figure out images yet?
<karolherbst>
or well.. ssbos?
<karolherbst>
I might be inclined to work on that.. maybe... if I got time...