warpme_ has quit [Quit: Connection closed for inactivity]
stikonas has quit [Ping timeout: 272 seconds]
gcl has joined #panfrost
tlwoerner has joined #panfrost
_whitelogger has joined #panfrost
kaspter has joined #panfrost
camus1 has joined #panfrost
kaspter has quit [Quit: kaspter]
camus1 is now known as kaspter
kaspter has quit [Read error: Connection reset by peer]
kaspter has joined #panfrost
vstehle has quit [Ping timeout: 265 seconds]
rhyskidd has quit [*.net *.split]
enunes has quit [*.net *.split]
megi has quit [*.net *.split]
rellla has quit [*.net *.split]
endrift has quit [*.net *.split]
forkbomb has quit [*.net *.split]
mmind00 has quit [*.net *.split]
robink has quit [*.net *.split]
mmind00 has joined #panfrost
robink has joined #panfrost
rhyskidd has joined #panfrost
endrift has joined #panfrost
enunes has joined #panfrost
megi has joined #panfrost
rellla has joined #panfrost
davidlt has joined #panfrost
icecream95 has joined #panfrost
icecream95 has quit [Client Quit]
icecream95 has joined #panfrost
camus1 has joined #panfrost
kaspter has quit [Ping timeout: 264 seconds]
camus1 is now known as kaspter
_whitelogger has joined #panfrost
vstehle has joined #panfrost
buzzmarshall has quit [Remote host closed the connection]
_whitelogger has joined #panfrost
MoeIcenowy has quit [Quit: ZNC 1.7.2+deb3 - https://znc.in]
MoeIcenowy has joined #panfrost
unoccupied has quit [Ping timeout: 240 seconds]
unoccupied has joined #panfrost
indy has joined #panfrost
davidlt has quit [Ping timeout: 246 seconds]
raster has joined #panfrost
stikonas has joined #panfrost
warpme_ has joined #panfrost
stikonas has quit [Read error: Connection reset by peer]
stikonas has joined #panfrost
<robmur01>
bbrezillon: FWIW I looked again and I think my rebased coherency patch might not have any effect since the mmap() rework - once I can get my hands on my Juno I'll try to revive it properly
<daniels>
robmur01: ah, did you not manage to get a VIM3?
<daniels>
robmur01: we could send you one of the ones we have in Cambridge
<daniels>
Amlogic FTW
<daniels>
FTsomething, anyway
<robmur01>
daniels: I didn't try ;)
<daniels>
we can fix that far more easily than reviving a Juno!
<robmur01>
but the main thing is that I know Juno's T620, rubbish as it is, is a coherent integration that definitely isn't busted
<daniels>
heh
<daniels>
the 'only' problem is that T6xx is super busted in our userspace
<daniels>
we never put any effort into it since IIRC the only real platforms were Exynos5 (too old to care much about by now, plus Samsung broke mainline in favour of new Tizen features so often that we just gave up) and Juno (lol)
<robmur01>
it works (or has worked) well enough to manage full glmark run - that's enough to confirm whether all the DMA bits are in order
<HdkR>
Even Hardkernel is clearing out their stock of Exynos 5422 at this point :P
<robmur01>
T720 seems to keep SFBD from rotting too badly
<daniels>
unfortunately BayLibre's lab is probably permanently dead at this point, so we'll have to get some Tx20 into our lab
icecream95 has quit [Ping timeout: 256 seconds]
kaspter has quit [Quit: kaspter]
<robmur01>
oh, and I meant revive the patch - the Juno itself is just fine :D
<robmur01>
they helpfully power-cycled the entire office yesterday, so USB should be un-stuck again - unfortunately it also means the machine on the other end of the USB cable is now off...
<alyssa>
robmur01: IIRC there are some nasty t6xx errata that we don't handle since I couldn't test anything etc
indy has joined #panfrost
<robmur01>
yeah, from what I've heard, T604 is probably a lost cause
<alyssa>
heh
<alyssa>
T624 tho..?
<alyssa>
it's always the first, G71 is similarly busted in a lot of ways ... not so much "doesn't do what's expected", but "what's expected is bonkers"
* alyssa
glares at missing FRCP instruction
jernej_ has joined #panfrost
jernej has quit [Read error: Connection reset by peer]
jernej_ is now known as jernej
<alyssa>
so... I'm a little scared to peak under the hood of G77 ;)
kaspter has joined #panfrost
indy has quit [Ping timeout: 256 seconds]
indy has joined #panfrost
_whitelogger has joined #panfrost
indy has quit [Ping timeout: 240 seconds]
indy has joined #panfrost
Lyude has quit [Quit: WeeChat 2.8]
Lyude has joined #panfrost
davidlt has joined #panfrost
davidlt has quit [Read error: Connection reset by peer]
<HdkR>
alyssa: Because you might fall in love with Valhall? :P
HdkR has quit [Quit: leaving]
HdkR has joined #panfrost
<HdkR>
irssi bugged out, weird
<HdkR>
Looks like the Vivo IQOO Z1 is shipping to me
<HdkR>
So Dimensity 1000 on the way
<alyssa>
HdkR: It's a risk, yes.
<HdkR>
:D
<HdkR>
Hopefully Valhall will be here next week
<HdkR>
Even if it is just tinkering on Android again
nerdboy has quit [Ping timeout: 264 seconds]
raster- has joined #panfrost
raster- has quit [Client Quit]
raster- has joined #panfrost
nerdboy has joined #panfrost
raster has quit [Remote host closed the connection]
raster- has quit [Quit: Gettin' stinky!]
forkbomb has joined #panfrost
<endrift>
for a second there I thought this was #dolphin-emu and was just like "wait why is alyssa in #dolphin-emu"
<endrift>
I need to: wake up
<HdkR>
alyssa is now working on Dolphin full time
<HdkR>
No more panfrost, only Dolphins
<alyssa>
endrift: Arp arp!
<endrift>
wark wark wark
<HdkR>
kuwee
<alyssa>
Wake me up when there's an emulator named Pony :p
<HdkR>
I like Stenzek's Duckstation since it constantly makes me think about ducks quacking about
<endrift>
There's also Dobiestation for PS2
<endrift>
by the same person who made CorgiDS and Corgi3DS
<endrift>
but those both got abandoned
<endrift>
no Pony emulators I know of though
icecream95 has joined #panfrost
warpme_ has quit [Quit: Connection closed for inactivity]
remexre has quit [Quit: WeeChat 2.8]
stikonas has quit [Remote host closed the connection]
<alyssa>
I'm almost afraid to ask but -
<alyssa>
Does anyone know why I'm seeing "--kernel-- el0_da do_mem_abort do_page_fault/do_translation_fault" in sysprof, from completely ordinary user functions?
<alyssa>
Does that mean memory corruption or is this just some arcane detail about the aarch64 mmu?
<endrift>
that just looks like a normal page fault
<endrift>
probably from something that was mmapped but not read in from disk yet
<endrift>
dunno for sure though, I've never used sysprof or anything
<endrift>
so grain of salt etc
<endrift>
page faults aren't inherently bad though. They're a normal part of MMU operation. It's only when they're UNHANDLED that it becomes a problem
* HdkR
wonders if sysprof catches fex faults
<endrift>
or I guess "invalid" is the term wikipedia uses