21:42 <ndufresne> mntirc: also getting a correct driver was the milestone achieve, performance is being looked at now as a second step, would be nice to have some metrics to set the expectation, did you mean A311D or A311D2 ? (cause the second have G52 MP8, which might outperform a G610 MP4)

21:43 <mntirc> ndufresne: ah i see, that's what i thought! i ran glmark2-es2-wayland a few hours ago and i get a slightly worse score than on A311D (not D2)

21:44 <mntirc> > Mali G52 MP4(6EE)

21:44 <ndufresne> with default resolution, you got something under 2K ?

21:44 <mntirc> ndufresne: yes

21:44 <ndufresne> that's what a user reported recently, and what will be looked at

21:44 <mntirc> ndufresne: on a311d i get 1669 and i got like 1200 on rk3588

21:44 <mntirc> (will run it again now)

21:44 <ndufresne> interesting, my users ws reporting 1900

21:45 <ndufresne> but you know, not simple, have your force the freq to its highest ? and CPU governor to performance ?

21:45 <ndufresne> letting governor run during benchmark introduce randomness

21:46 <ndufresne> but also lower scores

21:46 <ndufresne> here I was confused for a moment, on an older valhal (G57) I had much better scores, like 2200, but then notice it has a higher core count ...

21:46 <mntirc> ndufresne: i wasn't aware that i can set the gpu freq?

21:49 <ndufresne> echo userspace > /sys/class/devfreq/13000000.gpu/governor

21:49 <mntirc> ohh

21:49 <ndufresne> then you can pick a freq from /sys/class/devfreq/13000000.gpu/available_frequencies

21:49 <ndufresne> the simple_ondemand governor is just like his name says, simple

21:50 <ndufresne> but the GPU governor will also impact the results, driving GL is always a bit CPU intensive

21:50 <mntirc> got a score of 1491 now

21:50 <ndufresne> less ?

21:50 <mntirc> probably because now i'm using 2.4ghz on the big cores (with new opp tables)

21:51 <mntirc> no, i was still running the test before changing the gpu clock, will try that now

21:51 <mntirc> but getting a higher score than on 2.2ghz earlier today

21:52 <mntirc> ndufresne: i don't have a devfreq driver for the gpu it seems

21:52 <mntirc> ndufresne: i.e. /sys/class/devfreq/ doesn't contain 13000000.gpu

21:53 <mntirc> ah, it's fb000000.gpu

21:53 <mntirc> sorry

21:55 <mntirc> ok, testing with 1ghz now

21:55 <ndufresne> yeah, this is soc specific, can't test atm on my rk3588, have to rebuild mesa

21:56 <mntirc> ndufresne: which soc/gpu are you testing with? imx9?

21:56 <ndufresne> I suspect G57 MP5 (880MHz) should outperform G610 MP4 at 1GHz, but I could be wrong

21:56 <ndufresne> MT8195, from mediatek

21:57 <ndufresne> https://www.mediatek.com/products/chromebooks/mediatek-kompanio-1380

21:58 <ndufresne> says MC5, not sure what is the difference betweem MC and MP

21:59 <mntirc> ah

21:59 <ndufresne> this board will be nearly identical, https://radxa.com/products/nio/12l/

22:00 <mntirc> interesting

22:00 <mntirc> ok now i'm getting a score of 2102!

22:01 <ndufresne> hmm, ok, with 880MHz, and perf gov on the CPU, the G57 here did 4041

22:01 <mntirc> ok, did not try perf governor on the cpu yet, but it probably won't get near that score :D

22:02 <ndufresne> I'm under the impression that it should in theory be relatively close, unless it has a limitation somewhere else, like RAM

22:02 <ndufresne> ram frequence is also something to take into account seriously

22:03 <mntirc> makes sense

22:08 <ndufresne> Which board to you use ?

23:17 <mntirc> mntirc: i use firefly icore 3588q with my own adapter for mnt reform

23:18 <mntirc> ndufresne: sorry, i meant to write to you

23:22 <mntirc> ndufresne: btw even at 1ghz gpu and 2.4ghz cpu, i only get 15fps in firefox on webgl blobs, and google maps is very slow, whereas in chromium both are smooth

23:47 <urja> My T760 / RK3288 is running webgl blobs in firefox at 48 ... 60 fps (default settings of 10 blobs, 24^3 resolution)

23:54 <urja> yep that's very different (but also, slower), the point being, yep firefox shouldnt be that slow

23:55 <CounterPillow> so have you checked yet whether it's actually hitting the GPU or whether Firefox is just blocklisting it for webgl use

23:56 <daniels> I think that was verified already

23:56 <daniels> nothing structural I’m sure, just that no-one really looked at Firefox yet

23:56 <urja> the only things i can think of are this is under wayland/kde and i have layers.acceleration.force-enabled and webgl.force-enabled true (but i'm not sure if those matter or are ancient)