2023-02-22
00:53possiblemeatball has joined #asahi-gpu
01:03Dementor has quit [Read error: Connection reset by peer]
01:04Dementor has joined #asahi-gpu
01:46stipa is now known as Guest5516
01:46stipa has joined #asahi-gpu
01:48Guest5516 has quit [Ping timeout: 480 seconds]
02:23kesslerd_ has joined #asahi-gpu
02:29kesslerd has quit [Ping timeout: 480 seconds]
02:33DarkShadow4444 has quit [Ping timeout: 480 seconds]
02:50ktz has joined #asahi-gpu
02:53ktzits incredible how buttery smooth my desktop experience has been with sway running on alpine, to the extend that it felt like a big downgrade a couple of weeks ago back when I tried the drivier
02:54ktzI'm really curious why that happens tho, I haven't been able to reproduce the performance of this combination in other ways, be it different compositors in combination with other distros
02:55ktzrunning different wms for example or the exact same setup on alarm feels like a borderline torture by the constant tearing and the low frame rates
02:56DarkShadow44 has joined #asahi-gpu
02:57ktzthe way I go about measuring any actual numbers is pretty simple and most likely not a real indicator but the results feel on par with my experience
02:59hightower3 has joined #asahi-gpu
03:01ktzit really makes me wonder what could be the exact cause that with other setups it struggles to even hit consistent 60 frames and frequently hangs sub-40frames while it puts out such an astronomical performance in my case https://ibb.co/7RWSwnT
03:02marcanktz: if you were getting tearing, you were using xorg. xorg is broken in several ways that nobody plans to fix.
03:05ktzah, no sadly, I've always had asahi installed as well but I had to change machine and I got just alpine now
03:05marcanmy bet is you screwed around with expert mode while installing it and ended up with unsupported firmware which means the drivers never actually worked
03:06marcaneither that or you didn't get stuff installed properly (new kernel, new mesa, and grub config update)
03:06ktzthis is something that I've been wondering for quite some time now, out of curiosity, how does this https://testufo.com/ perform on your machine?
03:07hightower2 has quit [Ping timeout: 480 seconds]
03:08ktz has quit [Remote host closed the connection]
03:08ktz has joined #asahi-gpu
03:13marcantestufo detects 60 and shows 60/30/15 and the 60 bar is perfectly smooth which is the optimal experience
03:13ktzwell, I my experience varied even with constant 60 fps, not sure how much improvement one can percieve technically but even capped on 60fps back when I ran the driver felt much more sluggish in comparison
03:14marcan... the screen only does 60, are you saying alpine is giving you more than 60 on a laptop?
03:15marcanthen alpine is broken and giving you a worse experience and you are placebo effecting yourself into thinking it's better :p
03:15marcanthat is the hardware limit and trying to go higher will only increase judder or give you tearing
03:16ktzwell, if you could reproduce it on your machine in person maybe you would change your opninion, even if in papper it doesn't make much sense due to the supposed 60hz refresh rate
03:17marcan... look, I'm looking at the same exact machine right now with all the drivers and it is perfectly smooth and I know how refresh rates work and am very picky about judder
03:17Dementor9 has joined #asahi-gpu
03:17marcando I need to waste my time taking a high-speed video of my screen now to prove to you that it's a solid 60fps?
03:19ktzhehe no I got no reason to doupt you, I'm just not entirely sure that you wouldn't change your mind if you were to reproduce it
03:19Dementor has quit [Ping timeout: 480 seconds]
03:19Dementor9 is now known as Dementor
03:20ktzmind you I'm running asahi for a year now, I've done countless installs, both alarm as well as alpine, its not just a couple of times I've set it up, and its been consistent this way
03:21marcanI'm trying without the drivers now on kwin_x11 and it's a juddery mess and still capped at 60, sure
03:22marcanI assume sway interacts differently with the dumb framebuffer driver and whatever metadata firefox ends up with means nothing gets capped
03:22marcanwe don't care, that experience is broken anyway (framebuffer driver), that's why the new edge kernel has a real display driver with real buffer swaps
03:23marcanthere is no point in wasting time in improving the dumb framebuffer experience here, that's all obsolete
03:23ktzno idea about x11 stuff, I only tried a couple of wm's to just see if I could get anywhere near the numbers I normally get in an attempt to poinpoint the reason that this particular combination yields such supersonic results hehe
03:24marcanand again we just don't care about simpledrm setups any more, that's going to be discontinued soon
03:26marcanso yeah, I believe you that it looks better on sway than on kwin, but that's not because sway is doing anything right, it's just because it breaks in a different way (burning power and getting smoothness out of it by accident)
03:27marcanmy point is, whatever video you take of your setup isn't going to look any better than what I'm seeing on kwin *with* all the proper drivers
03:27ktzyeah people make a big deal about refresh rates on their phones for some reason, I'm not really using one to such extends but it definitelly feels night and day on my air
03:29ktzI should have done that a couple of months ago before the gpu was really a thing in case others could benefit
03:29marcanor get a 14"/16" laptop once we support promotion and then *that* will be 120Hz which *is* a noticeable improvement :-)
03:30marcanthe thing is counterintuitively, you get a worse experience with the proper display controller driver and no gpu driver, because when software rendering is borderline able to keep up, the additional vsync from a real driver actually ends up making it feel less smooth
03:31ktzhmm, good to know, then maybe alpine could somehow differ config wise in relation to the controller driver in theory? I can't wrap my head around why it only behaves like that in alpine but in alarm it wouldn't
03:31marcanit's sway or something alpine does with those builds. whatever frame rate you get out of firefox in any case without the display driver is fake
03:32ktzyeah what you just described could be the case I didn't really like my experience at constant 60fps back when I test drived the gpu
03:33ktzI remember I checked inxi -G for example which checked out with mps's info just for a cross check
03:34ktzthe only reason you can really tell for yourself is if you had alpine installed and I handed you over my sway config and saw for yourself
03:34marcanlook please just trust me that what I'm seeing here is the limits of the physical screen and you *cannot* do better
03:34TellowKrinklemacOS is always available as a "definitely working" comparison point
03:35marcaneither you've been comparing broken setups, or you somehow like a broken setup over the best case
03:36ktzbut I can't convince myself unless you'd evaluate and then confirm that by your experience as well
03:37marcanand really I've had these kinds of "but you need to see what I'm seeing" discussions more than once and it never goes anywhere, it's always either someone was doing something wrong or placebo effect or something that cannot be confirmed with proper testing
03:38marcanlike the 300fps number on there could easily be biasing your brain into thinking it's better
03:39TellowKrinkleDo you have any actual 120+ hz displays you could compare to? That might help make it more obvious
03:40marcanI would take a high-speed video if I had suspicions about judder, but testufo is actually a very clear test case and I know how to evaluate it with my eyes and be confident that it's objectively smooth (I've had my fair share of staring at panning images like that and noticing the little details of framerate mismatch judders and such, it's why e.g. I have my home projector set up to sync its ...
03:40marcan... frame rate with the frame rate of what I play, because for example 24Hz material on 60Hz *does* cause judder)
03:41marcanbasically if you can track the ufo with your eyes and there are no "jumps" and it looks like a consistently horizontally blurred image, that's a good indicator you have proper frame pacing
03:42ktzgod bless you my man, sending hugs and love to your way, thanks for blessing us with this, it still feels unreal to this day.. it has been such an incredible experience really, I'm very grateful for that. I was rarely touching my air and now I'm daily driving it ever since my mobo broke.. feels like a dream lol
03:43marcan(to be fair I'm pretty sure I've seen the odd dropped frame and such, but it's not a consistent bad pacing thing, that's just a "browser and desktop stacks are still kind of bad at hard realtime deadlines" issue)
03:45marcanwhich is incidentally another thing I'm interested in improving, especially in the context of audio, longer term (hard realtime breaks)
03:46marcanso don't get me wrong, there's definitely work to be done in making things smoother more often and improving performance of various workloads
03:50marcanAlso another counterintuitive thing: with a 300+FPS uncapped setup like yours, you'll be pegging the CPUs, which means you will actually have fewer chances of higher latency problems when the scheduler downclocks CPUs or tries to run things on the e-cores (this is what we were talking about earlier)
03:50marcanso it's possible you have fewer of those rare dropped frames than I do, though it would be a very minor difference, and definitely not worth burning CPU for it, and we can fix that with the scheduler tweaks we discussed
03:51marcan(or you could get the same experience forcing the CPU governor to performance and tasksetting everything that matters to the p-cores, even with the drivers)
03:52ktzoh by the way since we're here, something I wanted to ask for some time now, is there any other antenna I can physically locate besides the two main ones which plug on the mainboard? even when physically unplugging the machine can do wireless with no problem
03:52marcanI have no idea lol, there may be one on the board? I've never taken one of these machines apart
03:53ktzif you ever need to reproduce it there goes my sway config https://git.sr.ht/~ktz/sway, rest is typical, both with rtkit and without if that makes any difference
03:53ktzreally? I should have sent you some pictures then, I did many surgeries on my poor machine hehe, its resting in peace now
03:57cylm has joined #asahi-gpu
04:17ktz has quit [Remote host closed the connection]
04:17ktz has joined #asahi-gpu
04:17ktz has quit []
04:46possiblemeatball has quit [Quit: Quit]
06:43VinDuv has quit [Quit: ZNC 1.8.2+deb2+b1 - https://znc.in]
06:46VinDuv has joined #asahi-gpu
07:47zalyx has quit [Quit: later alligator]
07:49zalyx has joined #asahi-gpu
08:16bisko has joined #asahi-gpu
08:47i509vcb has quit [Quit: Connection closed for inactivity]
08:47bisko has quit [Quit: My Mac has gone to sleep. ZZZzzz…]
09:15nyilas has joined #asahi-gpu
09:32MajorBiscuit has joined #asahi-gpu
10:13darkapex1 has joined #asahi-gpu
10:13darkapex has quit [Read error: Connection reset by peer]
11:06jnn is now known as jn
11:31nyilas has quit [Remote host closed the connection]
11:31nyilas has joined #asahi-gpu
11:32nyilas has quit [Remote host closed the connection]
11:33nyilas has joined #asahi-gpu
11:40nyilas has quit [Remote host closed the connection]
11:55kesslerd_ has quit [Remote host closed the connection]
12:06kesslerd has joined #asahi-gpu
12:15kesslerd_ has joined #asahi-gpu
12:22kesslerd has quit [Remote host closed the connection]
12:24kesslerd_ has quit [Read error: Connection reset by peer]
12:29kesslerd has joined #asahi-gpu
12:29kesslerd has quit [Remote host closed the connection]
12:31kotleni has joined #asahi-gpu
12:34kesslerd has joined #asahi-gpu
12:44stipa is now known as Guest5558
12:44stipa has joined #asahi-gpu
12:49Guest5558 has quit [Ping timeout: 480 seconds]
12:51nyilas has joined #asahi-gpu
12:58nyilas has quit [Quit: nyilas]
12:59kotleni has quit [Quit: Leaving]
13:04bisko has joined #asahi-gpu
13:55hightower3 has quit [Ping timeout: 480 seconds]
13:57nyilas has joined #asahi-gpu
14:15bisko has quit [Quit: My Mac has gone to sleep. ZZZzzz…]
14:18nyilas has quit [Remote host closed the connection]
14:19bisko has joined #asahi-gpu
14:22nyilas has joined #asahi-gpu
14:33mairacanal has joined #asahi-gpu
14:37hightower2 has joined #asahi-gpu
14:52possiblemeatball has joined #asahi-gpu
15:10stipa is now known as Guest5565
15:10stipa has joined #asahi-gpu
15:10Guest5565 has quit [Read error: Connection reset by peer]
15:39kesslerd has quit [Remote host closed the connection]
15:41kesslerd has joined #asahi-gpu
15:43stipa is now known as Guest5568
15:43stipa has joined #asahi-gpu
15:46possiblemeatball has quit [Quit: Quit]
15:49Guest5568 has quit [Ping timeout: 480 seconds]
15:49possiblemeatball has joined #asahi-gpu
15:56bluetail51 has joined #asahi-gpu
16:03bluetail5 has quit [Ping timeout: 480 seconds]
16:13linaThe actual big bug was really obvious, that only took an hour or so to find... I wasn't clearing ctx->batch so after a submission things kept getting piled onto the same batch.
16:15linaBut then there was a much subtler thing that had me stuck for a while... some dEQPs would flake, rarely. The symptom on at least some tests was that a vertex would be processed as all-0, rarely (but always the same one for any given test).
16:17linaMy conclusion was that the USC caches persist and are not invalidated when you queue things back to back on the GPU, so if the CPU writes some vertices to a VBO, submits a batch, writes some more, submits another batch, the first one could load a whole cache line before the second one's vertices were written, and then the second one would read those (usually just the first vertex) as zero from the cache.
16:19linaI don't know what the "official" way to fix this is, it's possible macOS just never hits it because it never actually pipelines GL commands into hardware queues? (It might always roundtrip through the CPU)
16:20linaBut trying random stuff I found out that one bit in the VDM barrier command you found fixes everything, so now I always put one of those at the beginning of every batch.
16:20linaSo now we're back to passing the dEQPs, GLES2 and EGL, except now with no flakes and with gallium sync = flush, not sync ^^
16:21linaThat mystery didn't take up my whole day, so I still had time to implement render stats and fault feedback ^^
16:25linaMESA: warning: [Batch 1] Render Complete: TVB 196608/ 1048576 bytes (0 ovf) | vtx 0.000006 frag 0.000011
16:25linaMESA: warning: [Batch 2] Render Complete: TVB 3080192/ 1048576 bytes (3 ovf) O | vtx 0.001174 frag 0.000807
16:25linaMESA: warning: [Batch 0] Render Complete: TVB 196608/ 1048576 bytes (0 ovf) | vtx 0.000005 frag 0.000018
16:25linaMESA: warning: [Batch 4] Render Complete: TVB 196608/ 1048576 bytes (0 ovf) | vtx 0.000006 frag 0.000035
16:25linaMESA: warning: [Batch 1] Render Complete: TVB 196608/ 9306112 bytes (0 ovf) G | vtx 0.000005 frag 0.000015
16:26kotleni has joined #asahi-gpu
16:26kotleniI builded all PKGBUILDs from github, but driver for gpu not installed (i still use llvmpipe for rendering.
16:27marcankotleni: this is not a support channel, see the blog for how to install the driver (you don't need to build anything) or go to #asahi if you have questions.
16:28kotleni has left #asahi-gpu [#asahi-gpu]
16:41mkurz has quit [Ping timeout: 480 seconds]
16:47kesslerd has quit [Quit: Leaving]
16:52kesslerd has joined #asahi-gpu
16:55hightower2 has quit [Ping timeout: 480 seconds]
16:56kesslerd has quit [Quit: Konversation terminated!]
16:56kesslerd has joined #asahi-gpu
16:59kesslerd has quit []
17:00kesslerd has joined #asahi-gpu
17:02kesslerd has quit []
17:02kesslerd has joined #asahi-gpu
17:06kesslerd has quit [Remote host closed the connection]
17:06kesslerd has joined #asahi-gpu
17:09mkurz has joined #asahi-gpu
17:15possiblemeatball has quit [Quit: Quit]
17:24cwabbottlina: I don't know how things work in GL, but for vulkan, there's a line in the spec that all user writes become visible to the GPU upon submit, so if your GPU has any sort of non-coherent cache then you have to invalidate it at the beginning and flush it at the end of a submission
17:26hightower2 has joined #asahi-gpu
17:26cwabbottthere should be a flush and invalidate/clean command and you probably also need to flush at the end of a submission in addition to cleaning at the beginning
17:26linaI think the flushing is handled by the firmware, I already ran into that with compute and it seems to be related to a sequence number in some firmware structures.
17:27linaYeah, that's what that VDM barrier seems to accomplish. I don't know if there is another way, like a field in the firmware structs...
17:35MajorBiscuit has quit [Quit: WeeChat 3.6]
18:29possiblemeatball has joined #asahi-gpu
18:34cylm has quit [Ping timeout: 480 seconds]
19:05possiblemeatball has quit [Quit: Quit]
19:26kode54 has quit [Quit: Ping timeout (120 seconds)]
19:26kode54 has joined #asahi-gpu
19:45mkurz has quit [Ping timeout: 480 seconds]
21:00mkurz has joined #asahi-gpu
21:02mkurz has quit [Remote host closed the connection]
21:29zzywysm has quit [Ping timeout: 480 seconds]
21:36zzywysm has joined #asahi-gpu
21:56nyilas has quit [Remote host closed the connection]
23:09possiblemeatball has joined #asahi-gpu