alyssa changed the topic of #panfrost to: Panfrost - FLOSS Mali Midgard & Bifrost - Logs https://freenode.irclog.whitequark.org/panfrost - <daniels> avoiding X is a huge feature
archetech has quit [Quit: Konversation terminated!]
<macc24> alyssa: sometimes i wish kevin was smaller and had a 1280x800 screen :/
<macc24> or had bifrost gpu
<alyssa> macc24: It's called bob.
<macc24> alyssa: well i only have kevin, and i only use it for drawing, cadmium cross-device support and performance comparisons
<alyssa> ---Why is the mesa build broken?
<macc24> printing for 5h is forever...
<HdkR> mesa build is broken?
* HdkR tries
<HdkR> looks like it is fine on a fresh upstream/master for me
<alyssa> wt
<HdkR> With an everything build, clang, release
<alyssa> I'm not jealous of your build speed or anything ;o
* alyssa still needs to do a clean mesa build on m1 just to feel envy :p
<HdkR> Testing with gcc now
<alyssa> I rm'd my build and it's still unhappy
<alyssa> so unless it's a ccache bug?
<HdkR> Debug build maybe?
<HdkR> gcc release passed, checking debug
<HdkR> debug passed
<HdkR> gcc version 10.2.0
<alyssa> HdkR: culprit was an accidentally defined empty nir.h in src/compiler
<alyssa> because I can't vim apparently
<HdkR> oops
<alyssa> also, question for someone who knows:
<alyssa> top shows "MiB Swap: 0.0 total, 0.0 free, 0.0 used."
<alyssa> yet I also see activity from kswapd
<HdkR> Might be worth adjusting swappiness
<urjaman> .... for what swap ...
<macc24> alyssa: just yeet swap out of your kernel
<HdkR> Swap is nice to have for the case of a bad actor stealing all ram once in a while
<alyssa> but I will say
<alyssa> the fact that was handled gracefully enough (a small slow down and then back to normal) was...
<alyssa> Well, I shouldn't say impressive since that's the bare minimum
<macc24> HdkR: earlyoom?
<urjaman> yeah i actually have 512M of swap on my C201, i usually dont run into OOM kills (and when they happen, they happen... reasonably)
<alyssa> but I was tensing up ready for the system to completely freeze up
<HdkR> macc24: Maybe I'd prefer a bit of slowness rather than murdering the app though :P
<alyssa> and it was perefctly fine.
<macc24> HdkR: every time my ram got eaten on any of my machines i had to reboot
<HdkR> hehe
<alyssa> Looks like yeeting madvise might not be so tragic
<urjaman> oh geeze early oom ... that was frustrating on my Jolla when i was trying to use it as a linux machine (as opposed to a phone :P)
<HdkR> Definitely depends on machine. If you start swapping to eMMC or gods...microSD, you're dead
<macc24> HdkR: altough the ssd on my desktop is still seen by linux as an ide hard drive
<macc24> that might be part of problem xD
<urjaman> well atleast it's configurable too :P
<macc24> HdkR: duet's emmc is not that slower than ssd on my xeon box
<icecream95> Everyone who has problems with OOM: 1. Install zram 2. Setup 5GB zram swap with zstd 3. Never complain about OOM again
<macc24> icecream95: damn i wish i knew this when i tried to run cities skylines on overclocked phenom 9650 with 4gb of ram
<macc24> it ran for few minutes before freezing, i went as far as disabling my wm to save ram xD
<HdkR> macc24: Just make sure to stick your swap on a 32GB/s NVMe array. :P
<icecream95> macc24: Is that sarcasm?
<macc24> icecream95: nope
<macc24> the mcp78 chipset absolutely sucked under linux, especially with usb input
<macc24> i ran freebsd on it for a while for that reason
<alyssa> --Honestly the fact I can use Chromium at all without fear is an improvement :o
<HdkR> :D
<macc24> alyssa: please tell me that chromium runs on my mt8183 chromebook when it runs linux
stikonas has quit [Remote host closed the connection]
<macc24> finally my 5h print stopped printing base...
<icecream95> macc24: Five hours? Is that printer from HP? :P
<macc24> icecream95: it didn't refuse to work because my filament is not from hp so i guess no
<alyssa> --So, why did my computer shut off randomly?
<alyssa> Time to go crawl /var/log...
<icecream95> alyssa: An actual power off (as opposed to a freeze) sounds like running out of battery, runaway thermals or pressing the power button
<alyssa> Those are all possible!
<macc24> icecream95: or broken resume after accidentally suspendind
<icecream95> macc24: Hurry up and fix suspend on duet!
<alyssa> "Stopping session 1 of user alyssa"
<macc24> icecream95: when i get bored of my new toy
<macc24> and when i get debug cable to work for more than one second
<alyssa> rk_iommu page fault at 0x3ee5000 of type read
<alyssa> that seems.. bad
* macc24 laughs in mediatek
<alyssa> meh, probably not my fault (tm)
<macc24> woah, chromium runs on duet
<alyssa> it -is- a chromebook..
<macc24> nvm it crashed
<alyssa> what kind of crash?
<macc24> more like freeze
<macc24> didn't look at dmesg
<macc24> just mesa-git-master
<macc24> my spidey sense tells me that it's gpu faults
<icecream95> macc24: Why not try running CrOS in a virtual machine?
<macc24> icecream95: ?
<icecream95> CrOS == Chrome OS
<macc24> yeah but why?
<icecream95> Uhhh... Android app support?
<macc24> icecream95: anbox?
<macc24> ok heres a tip for everyone: if you're trying to figure out why display freezes, starting ssh server is a good idea
<alyssa> macc24: anbox doesn't support microphone input
<macc24> alyssa: cadmium doesn't support microphone input
<icecream95> It doesn't support microphone output, either
taowa has joined #panfrost
<macc24> HA, KNEW IT: https://bpa.st/OPQQ
<icecream95> macc24: That might be the same as the Firefox faults
<alyssa> sigh
atler has quit [Quit: atler]
<macc24> icecream95: if you say it it may actually be true
atler has joined #panfrost
<icecream95> macc24: I can try testing Chromium, but first I need to find a distro package linked against compatible libraries
<macc24> icecream95: apitrace?
icecream95 has quit [Ping timeout: 240 seconds]
raster has quit [Quit: Gettin' stinky!]
BenG83 has quit [Quit: Leaving]
icecream95 has joined #panfrost
atler_ has joined #panfrost
vstehle has quit [Ping timeout: 256 seconds]
atler has quit [Ping timeout: 256 seconds]
_whitelogger has joined #panfrost
<icecream95> macc24: I've got the Debian package for Chromium working now
karolherbst has quit [Ping timeout: 272 seconds]
dstzd has quit [Quit: ZNC - https://znc.in]
jernej has quit [Quit: Free ZNC ~ Powered by LunarBNC: https://LunarBNC.net]
dstzd has joined #panfrost
jernej has joined #panfrost
rcf has quit [Ping timeout: 260 seconds]
rcf has joined #panfrost
yawniek has quit [Ping timeout: 256 seconds]
yawniek has joined #panfrost
yawniek has quit [Ping timeout: 256 seconds]
yawniek has joined #panfrost
davidlt has joined #panfrost
icecream95 has quit [Ping timeout: 246 seconds]
vstehle has joined #panfrost
icecream95 has joined #panfrost
davidlt has quit [Ping timeout: 260 seconds]
<icecream95> alyssa: 96 bytes is an odd size for shader prefetch, don't you think?
<icecream95> I'd expect it at least to be an even multiple of 32 bytes (i.e. multiple of 64 bytes)
<icecream95> Indeed, increasing it to 128 bytes fixes the CI failure for your branch
<icecream95> So why did I come up with the 96 bytes figure in the first place?
<HdkR> I know of another architecture that prefetches 96bytes at a time, so it isn't entirely unheard of
<icecream95> HdkR: Shhh, I'm telling a story
<HdkR> :>
<icecream95> When I was testing with different sizes, it was off a branch without any of the scheduler stuff, so all of the clauses were 32 bytes
<icecream95> If I read the code properly, with "pan/bi: Don't pad constants" some of the clauses will be only 16 bytes
<icecream95> HdkR: Now you made me forget what I was going to write next
<icecream95> alyssa: Anyway, moral of the story is that BIFROST_SHADER_PREFETCH should be replaced with 128 - sizeof(last_clause)
Elpaulo has joined #panfrost
<icecream95> After seeing the end-of-shader clause, the GPU is going to stay with the 128 bytes it has prefetched (which includes said eos clause) and not prefetch any more
icecream95 has quit [Read error: Connection reset by peer]
icecream95 has joined #panfrost
icecream95 has quit [Quit: leaving]
icecream95[m] has joined #panfrost
icecream95[m] is now known as icecream95
<icecream95> fg
rak-zero has joined #panfrost
davidlt has joined #panfrost
kaspter has joined #panfrost
jschwart has quit [Ping timeout: 264 seconds]
jschwart has joined #panfrost
stikonas has joined #panfrost
leah has quit [Quit: WeeChat 2.8]
karolherbst has joined #panfrost
atler_ has quit [Quit: atler_]
atler has joined #panfrost
embed-3d has quit [Quit: http://quassel-irc.org - Chat comfortably. Anywhere.]
enty has joined #panfrost
ente has quit [Read error: Connection reset by peer]
embed-3d has joined #panfrost
Elpaulo has quit [Quit: Elpaulo]
raster has joined #panfrost
alpernebbi has joined #panfrost
jernej has quit [Quit: Free ZNC ~ Powered by LunarBNC: https://LunarBNC.net]
jernej has joined #panfrost
jernej has quit [Quit: Free ZNC ~ Powered by LunarBNC: https://LunarBNC.net]
jernej has joined #panfrost
unoccupied has joined #panfrost
atler has quit [Quit: atler]
unoccupied is now known as leah
atler has joined #panfrost
<kinkinkijkin> still no idea why supet tux kart hangs the system if you try to open the story mode, but everything else is fine
dstzd has quit [Quit: ZNC - https://znc.in]
dstzd has joined #panfrost
<macc24> kinkinkijkin: story mode is weird
<macc24> it hanged midgard for a while iirc
<macc24> oi po
<macc24> oops
chewitt has quit [Ping timeout: 256 seconds]
chewitt has joined #panfrost
chewitt has quit [Read error: Connection reset by peer]
chewitt_ has joined #panfrost
<alyssa> icecream95: I sure love stories.
kaspter has quit [Quit: kaspter]
raster has quit [Remote host closed the connection]
alpernebbi has quit [Remote host closed the connection]
robertfoss_ has quit [Ping timeout: 256 seconds]
xperia64 has quit [Ping timeout: 256 seconds]
robertfoss_ has joined #panfrost
endrift has quit [Ping timeout: 256 seconds]
tchebb has quit [Ping timeout: 256 seconds]
endrift has joined #panfrost
xperia64 has joined #panfrost
karolherbst has quit [Ping timeout: 272 seconds]
tchebb has joined #panfrost
davidlt has quit [Ping timeout: 246 seconds]
Depau_ has joined #panfrost
alpernebbi has joined #panfrost
Depau has quit [Ping timeout: 240 seconds]
chewitt_ has quit [Read error: Connection reset by peer]
chewitt has joined #panfrost
stikonas has quit [Remote host closed the connection]
stikonas has joined #panfrost
jschwart has quit [Quit: No Ping reply in 180 seconds.]
jschwart has joined #panfrost
stikonas has quit [Remote host closed the connection]
stikonas has joined #panfrost
alpernebbi has quit [Quit: alpernebbi]
<robclark> alyssa: you need to play more stk :-P
<robclark> (you know, or s/play/test/ if you must.. it's the same thing :-P)
<macc24> robclark: i play, err, test stk on g72 and t860 on mesa master fyi
stikonas has quit [Remote host closed the connection]
stikonas has joined #panfrost
<robclark> :-)
<macc24> robclark: fyi qcom chromebook releases soon
<robclark> I heard something about that :-P
warpme_ has quit [Quit: Connection closed for inactivity]
<icecream95> kinkinkijkin: STK story mode is working fine here (except for cacti being purple), maybe you need to update Mesa
raster has joined #panfrost
archetech has joined #panfrost
<alyssa> icecream95: What colour are cacti supposed to be? ELI Canadian.