ChanServ changed the topic of #dri-devel to: <ajax> nothing involved with X should ever be unable to find a bar
ahajda has quit [Quit: Going offline, see ya! (www.adiirc.com)]
heat has quit [Read error: No route to host]
heat has joined #dri-devel
edman007_ has joined #dri-devel
edman007 has quit [Read error: Connection reset by peer]
Dr_Who has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
edman007__ has joined #dri-devel
edman007_ has quit [Read error: Connection reset by peer]
yogesh_mohan has quit [Remote host closed the connection]
yogesh_mohan has joined #dri-devel
<alyssa>
HdkR: Boo :p
<HdkR>
:)
yogesh_mohan has quit [Ping timeout: 480 seconds]
yogesh_mohan has joined #dri-devel
<mareko>
zmike: I have a system using zink that runs Unigine Heaven and the window R and B channels are swapped, have you seen this before?
<zmike>
mareko: sounds like maybe the driconf override for dual src blend channel swapping isn't active?
<zmike>
although I think that maybe makes things black and not swapped 🤔
co1umbarius has joined #dri-devel
columbarius has quit [Ping timeout: 480 seconds]
Leopold__ has joined #dri-devel
<mareko>
zmike: can it be caused by a vulkan driver not supporting the expected channel order?
Leopold___ has quit [Ping timeout: 480 seconds]
<zmike>
wouldn't that just mean it doesn't support the right formats?
pcercuei has quit [Quit: dodo]
<zmike>
I'd expect some kind of error to be printed
<zmike>
mareko: I'd suggest trying validation on it (ZINK_DEBUG=validation if it's installed)
<zmike>
will probably give some sort of hint
ybogdano has quit [Ping timeout: 480 seconds]
<alyssa>
zmike: i've been thinking about how i can improve the world
<alyssa>
and i think i figured out what the world really, really needs
<alyssa>
a blog post about descriptor sets and a new pipe CAP
* zmike
dies
Leopold__ has quit [Ping timeout: 480 seconds]
Leopold_ has joined #dri-devel
edman007__ has quit [Read error: Connection reset by peer]
RSpliet has quit [Quit: Bye bye man, bye bye]
RSpliet has joined #dri-devel
yogesh_mohan has quit [Remote host closed the connection]
yogesh_mohan has joined #dri-devel
Company has quit [Quit: Leaving]
yogesh_m1 has joined #dri-devel
Dr_Who has joined #dri-devel
Dr_Who has quit []
yogesh_mohan has quit [Ping timeout: 480 seconds]
jkrzyszt has quit [Remote host closed the connection]
oneforall2 has quit [Remote host closed the connection]
oneforall2 has joined #dri-devel
yogesh_m1 has quit [Remote host closed the connection]
yogesh_m1 has joined #dri-devel
Jeremy_Rand_Talos has quit [Remote host closed the connection]
Jeremy_Rand_Talos has joined #dri-devel
pallavim__ has quit [Ping timeout: 480 seconds]
rmckeever has joined #dri-devel
yogesh_mohan has joined #dri-devel
yogesh_m1 has quit [Ping timeout: 480 seconds]
<mareko>
the world needs more trains
JohnnyonF has joined #dri-devel
yogesh_m1 has joined #dri-devel
<alyssa>
agreed
<alyssa>
especially high speed rail
<alyssa>
but also rail in general
JohnnyonFlame has quit [Ping timeout: 480 seconds]
yogesh_mohan has quit [Ping timeout: 480 seconds]
JohnnyonFlame has joined #dri-devel
yogesh_mohan has joined #dri-devel
JohnnyonF has quit [Ping timeout: 480 seconds]
yogesh_m1 has quit [Ping timeout: 480 seconds]
illwieckz has quit [Ping timeout: 480 seconds]
karolherbst_ has joined #dri-devel
<Lynne>
airlied: tested, your anv patchset works on skylake
<Lynne>
3% FASTER THAN VAAPI!1!
karolherbst has quit [Ping timeout: 480 seconds]
<Lynne>
7% for 4k
<airlied>
\o/
<Lynne>
3% for both a typical yarr 1080p release and 1440p
<Lynne>
and it could be slightly faster still if the sps/pps param buffer wasn't recreated per-frame in the drivers
freemint has quit [Ping timeout: 480 seconds]
JohnnyonFlame has quit [Read error: Connection reset by peer]
kts has joined #dri-devel
<airlied>
Lynne: actually on anv I don't think there is really anything I can see to shave off that would help there
<airlied>
the one cpu saver I dropped for now was prefollowing all the reference slot pNexts into an on stack array
<airlied>
that might be worth a little
<Lynne>
oh, intel needs the parameters sent before each frame?
<airlied>
yes, it's stateless
<Lynne>
fair enough, wonder where we get the extra percent
yogesh_m1 has joined #dri-devel
yogesh_mohan has quit [Ping timeout: 480 seconds]
<airlied>
Lynne: you testing against media-driver or intel-vaapi-driver?
<Lynne>
iHD_drv_video.so, so the not-i965 one?
<airlied>
ah yeah that's media-driver
macromorgan has quit [Read error: Network is unreachable]
macromorgan has joined #dri-devel
kurufu has quit [Read error: Connection reset by peer]
kurufu has joined #dri-devel
<Lynne>
i965's performance is basically on-par with vulkan though :/
yogesh_m1 has quit [Remote host closed the connection]
<Lynne>
(so not only is media-driver very incomplete, it's also slower, what were intel thinking?)
yogesh_m1 has joined #dri-devel
Sachiel has quit [Remote host closed the connection]
Sachiel has joined #dri-devel
yogesh_m1 has quit [Remote host closed the connection]
yogesh_m1 has joined #dri-devel
mbrost has joined #dri-devel
jewins has quit [Ping timeout: 480 seconds]
yogesh_mohan has joined #dri-devel
alatiera has quit [Ping timeout: 480 seconds]
kzd has quit [Quit: kzd]
yogesh_m1 has quit [Ping timeout: 480 seconds]
mbrost has quit [Remote host closed the connection]
mbrost has joined #dri-devel
alatiera has joined #dri-devel
yogesh_m1 has joined #dri-devel
yogesh_mohan has quit [Ping timeout: 480 seconds]
mbrost has quit [Ping timeout: 480 seconds]
lemonzest has quit [Quit: WeeChat 3.6]
yogesh_mohan has joined #dri-devel
yogesh_m1 has quit [Ping timeout: 480 seconds]
bgs has joined #dri-devel
lemonzest has joined #dri-devel
RSpliet has quit [Quit: Bye bye man, bye bye]
RSpliet has joined #dri-devel
kts has quit [Quit: Leaving]
heat has quit [Ping timeout: 480 seconds]
yogesh_m1 has joined #dri-devel
yogesh_mohan has quit [Ping timeout: 480 seconds]
fab has joined #dri-devel
yogesh_m1 has quit [Ping timeout: 480 seconds]
yogesh_m1 has joined #dri-devel
<Lynne>
airlied: VK_QUERY_TYPE_RESULT_STATUS_ONLY_KHR doesn't work on anv btw
<Lynne>
even after forcing it, queries always return VK_NOT_READY
yogesh_m1 has quit [Remote host closed the connection]
yogesh_m1 has joined #dri-devel
kts has joined #dri-devel
Kayden has joined #dri-devel
kts has quit []
ahajda has joined #dri-devel
shankaru has quit [Read error: Connection reset by peer]
shankaru has joined #dri-devel
<airlied>
Lynne: okay I should recheck the code I just wrote, I ran CTS against it, but I didn't dig in
alanc has quit [Remote host closed the connection]
alanc has joined #dri-devel
<Lynne>
queryResultStatusSupport == 0
<Lynne>
so the cts probably didn't pick it up
danvet has joined #dri-devel
fab has quit [Quit: fab]
heat has joined #dri-devel
sghuge has quit [Remote host closed the connection]
sghuge has joined #dri-devel
tzimmermann has joined #dri-devel
sgruszka has joined #dri-devel
fab has joined #dri-devel
rasterman has joined #dri-devel
Leopold_ has quit [Remote host closed the connection]
pochu has joined #dri-devel
mvlad has joined #dri-devel
vliaskov has joined #dri-devel
Leopold has joined #dri-devel
<bbrezillon>
airlied: I'll have a look. Thanks for the heads-up!
Company has joined #dri-devel
jkrzyszt has joined #dri-devel
Lucretia has quit []
Lucretia has joined #dri-devel
pixelcluster has quit [Ping timeout: 480 seconds]
pixelcluster has joined #dri-devel
<bbrezillon>
jekstrand: sure, I get the point of having a single resv for the whole VM instead of adding job fences to all BOs, just didn't see what it was synchronizing. I mean, if user is expected to pass all fences explicitly to the exec ioctl, it should also make sure access to internal BOs is properly serialized. Now, if the shrinker kicks in and wants to reclaim memory, we probably want
djbw has quit [Read error: Connection reset by peer]
<bbrezillon>
to wait for in-flight jobs to land before reclaiming mem, which I guess is what danvet was referring to.
lynxeye has joined #dri-devel
YuGiOhJCJ has quit [Quit: YuGiOhJCJ]
MajorBiscuit has joined #dri-devel
apinheiro has joined #dri-devel
pcercuei has joined #dri-devel
rmckeever has quit [Quit: Leaving]
<Lynne>
airlied: could you look at !20805? it touches some code radv dec is using
<javierm>
tzimmermann: I tried to figure out yesterday the issue with the ssd130x driver but still couldn't
<javierm>
tzimmermann: while looking at that though I noticed a problem with the DRM fbdev emulation layer
<tzimmermann>
ok?
<javierm>
tzimmermann: drm_fb_helper_generic_probe() sets fbi->fbdefio = &drm_fbdev_defio if shadow fb is used
<javierm>
tzimmermann: but that means that several DRM drivers will share the same struct fb_deferred_io
<tzimmermann>
ok. is that a problem?
<javierm>
tzimmermann: it is, because drivers/video/fbdev/core/fb_defio.c then will use the same mutex fbdefio->lock for all the drivers
<tzimmermann>
ah! there's the pagelist
<javierm>
which means that for example if the driver is removed and fb_deferred_io_cleanup() destroys the mutex, the other drivers won't be able to use it anymore
<tzimmermann>
yeah, i guess we should make this per-device then
<javierm>
tzimmermann: correct
<tzimmermann>
that's a good observation.
<javierm>
tzimmermann: I'll write a patch when have some time, probably later today
<tzimmermann>
i have a number of fbdev patches for next week. i can fix it afterwards
<tzimmermann>
well, if you want to type up seomthing, thats also ok
<tzimmermann>
your choice
<javierm>
tzimmermann: I also have a couple of cleanups / trivial fixes that also noticed while looking the code. Will post it later too
<javierm>
tzimmermann: yeah, it should be trivial. I'm just working on something else today
<tzimmermann>
maybe simply put a defio structure into drm_fb_helper for now
<javierm>
tzimmermann: hmm, that could work too. And set it to that if !fbi->fbdefio
<javierm>
it will be wasted memory if the driver sets its own deferred I/O handler or if not used, but meh
<tzimmermann>
javierm, in a meeting now. sorry
<javierm>
tzimmermann: no worries. Later!
frankbinns has joined #dri-devel
devilhorns has joined #dri-devel
ice9 has joined #dri-devel
jluthra has quit [Remote host closed the connection]
jluthra has joined #dri-devel
srslypascal has quit [Ping timeout: 480 seconds]
srslypascal has joined #dri-devel
ice99 has joined #dri-devel
ice9 has quit [Ping timeout: 480 seconds]
kts has joined #dri-devel
<MrCooper>
jenatali: so the d3d12 driver isn't used for WSL, since you say it can ignore implicit sync?
junaid has joined #dri-devel
<tzimmermann>
javierm, don't worry about the memory impact for now. i have more patches to rework fbdev and that will be an opportunity to sort this out
<tzimmermann>
looks good to me. CONFIG_DRM_FBDEV_EMULATION will auto-select FB_DEFERRED_IO
<tzimmermann>
so the guard might not be needed
<javierm>
tzimmermann: yeah, I noticed and that's why I didn't add a guard in the code but wondered about the struct since is in a public header
<tzimmermann>
well, up to you
Leopold___ has joined #dri-devel
<javierm>
since I guess that drivers could use it and not CONFIG_DRM_FBDEV_EMULATION ?
Leopold has quit [Ping timeout: 480 seconds]
<javierm>
tzimmermann: but I guess in those cases the drivers would define their own fbdefio anyways?
<tzimmermann>
javierm, i don't think that would happen
<javierm>
tzimmermann: always happy to drop ifdefery if not needed :)
<tzimmermann>
drm_fb_helper.h is used by a few drivers
fdu has joined #dri-devel
<tzimmermann>
they already leave unused fields blank
<javierm>
tzimmermann: Ok
<tzimmermann>
such as buffer
<tzimmermann>
anyway, if you post this, you can add my r-b already
<javierm>
tzimmermann: cool, I'll add it. Dropped the guard also
illwieckz has joined #dri-devel
hansg has joined #dri-devel
junaid has quit [Ping timeout: 480 seconds]
<javierm>
tzimmermann: I think that should push patch #1 to drm-misc-next and patches #2 and #3 to drm-misc-fixes ?
<javierm>
only patch #3 is really important though
<tzimmermann>
javierm, i think so
<javierm>
tzimmermann: Ok. I'll do it on Monday then if don't get more feedback
<jenatali>
MrCooper: We use WDDM in WSL. Which, now that you mention it, could have app compat problems that I hadn't thought about...
illwieckz has quit [Ping timeout: 480 seconds]
ice9 has joined #dri-devel
illwieckz has joined #dri-devel
MajorBiscuit has quit [Read error: Connection reset by peer]
ice99 has joined #dri-devel
ice9 has quit [Ping timeout: 480 seconds]
ice99 has quit [Remote host closed the connection]
ice99 has joined #dri-devel
apinheiro has quit [Ping timeout: 480 seconds]
linkmauve has joined #dri-devel
MajorBiscuit has joined #dri-devel
RSpliet has quit [Quit: Bye bye man, bye bye]
RSpliet has joined #dri-devel
ice99 has quit []
ice9 has joined #dri-devel
hansg has quit [Quit: Leaving]
Dr_Who has joined #dri-devel
karolherbst_ is now known as karolherbst
genpaku has quit [Read error: Connection reset by peer]
genpaku has joined #dri-devel
pochu has quit [Ping timeout: 480 seconds]
Leopold___ has quit [Ping timeout: 480 seconds]
kts has joined #dri-devel
Leopold_ has joined #dri-devel
heat has quit [Ping timeout: 480 seconds]
zehortigoza has quit [Remote host closed the connection]
<MrCooper>
jenatali: for a specific example, Xwayland draws to FBOs only, and calls glFlush to make sure the Wayland compositor can see the result
<jenatali>
MrCooper: Except that we're swrast and therefore XWayland needs to copy the contents to shmem to send it to the Wayland compositor
<MrCooper>
no HW acceleration in X apps then?
freemint has quit [Ping timeout: 480 seconds]
<jenatali>
There is HW accel, just it comes back to RAM before sending to XWayland too
<MrCooper>
just inefficient then :P
<jenatali>
Eventually I'd like to get an explicit sync protocol in place for removing that readback but it hasn't been a priority for me yet
<jenatali>
Yep!
<jenatali>
Depending on the workload HW accel can be slower than llvmpipe due to those readbacks, but most are at least marginally if not significantly faster
<jenatali>
(and then there's a third round trip for Wayland composed content to come to Windows via remote desktop)
freemint has joined #dri-devel
pallavim__ has joined #dri-devel
heat has joined #dri-devel
mbrost has joined #dri-devel
Leopold_ has quit [Remote host closed the connection]
ybogdano has joined #dri-devel
junaid has joined #dri-devel
Leopold_ has joined #dri-devel
glynnc has joined #dri-devel
junaid has quit [Ping timeout: 480 seconds]
<glynnc>
How to get libGL to speak GLX to XWin.exe? Every time I update the client system, this breaks
fab has quit [Quit: fab]
ice9 has quit [Ping timeout: 480 seconds]
zehortigoza has joined #dri-devel
glynnc has left #dri-devel [Leaving]
<jenatali>
glynnc: That sounds like a recipe for disaster. Why are you trying to do that?
pallavim_ has joined #dri-devel
junaid has joined #dri-devel
pallavim__ has quit [Ping timeout: 480 seconds]
djbw has joined #dri-devel
jewins has joined #dri-devel
Leopold_ has quit []
fxkamd has joined #dri-devel
Leopold_ has joined #dri-devel
kzd has joined #dri-devel
<tomba>
A question about drm-misc-next. I have a few v4l2 patches that my DRM patches depend on. Those have been acked by v4l2 maintainers, and I have a -rc1 based branch for the v4l2 changes (in case it needs to be merged also to the media tree). Is it fine to just do a merge of that v4l2 branch to the drm-misc-next, and then apply the DRM patches on top with dim?
fab has joined #dri-devel
<pinchartl>
(Mauro has explicitly acked the patches for merge through the drm tree)
devilhorns has quit []
Duke`` has joined #dri-devel
Leopold___ has joined #dri-devel
bgs has quit [Remote host closed the connection]
Leopold_ has quit [Ping timeout: 480 seconds]
mbrost has quit [Ping timeout: 480 seconds]
ice9 has joined #dri-devel
pcercuei has quit [Read error: Connection reset by peer]
pcercuei has joined #dri-devel
sgruszka has quit [Ping timeout: 480 seconds]
srslypascal has quit [Remote host closed the connection]
srslypascal has joined #dri-devel
ahajda has quit [Quit: Going offline, see ya! (www.adiirc.com)]
mbrost has joined #dri-devel
agd5f_ has joined #dri-devel
tzimmermann has quit [Quit: Leaving]
agd5f_ has quit []
<Venemo>
on NIR intrinsics which have a component offset (for example load_input), is this offset meant in units of the dest bit size, or in 32-bit units?
mbrost_ has joined #dri-devel
mbrost has quit [Remote host closed the connection]
agd5f has quit [Ping timeout: 480 seconds]
agd5f has joined #dri-devel
<Venemo>
jekstrand, cwabbott maybe? ^^
Danct12 has joined #dri-devel
mbrost_ has quit [Ping timeout: 480 seconds]
jkrzyszt has quit [Remote host closed the connection]
<jekstrand>
Venemo: 32-bit units
<Venemo>
jekstrand: good to know, thanks
mbrost_ has joined #dri-devel
MajorBiscuit has quit [Ping timeout: 480 seconds]
MajorBiscuit has joined #dri-devel
lynxeye has quit [Quit: Leaving.]
junaid has quit [Ping timeout: 480 seconds]
<jekstrand>
dcbaker: Ok, I got my proc macro working with cobbled together syn, etc. branches and your meson branch.
<jekstrand>
dcbaker: It meant I had to add includes manually again for bindgen instead of using dependencies (only in meson 1.0.0).
<jekstrand>
dcbaker: It's good enough to survive for now.
<jekstrand>
dcbaker: We are going to need something more proper when the time comes to actually merge into mesa/main
<jekstrand>
dcbaker: If you want a branch that actually uses this stuff to play around with, it's nak/main on my gitlab.
<dcbaker>
jekstrand: i was planning to rebase that branch today, but I’m home with a sick kiddo, so it’ll have to wait until next week :/
<dcbaker>
Glad you got at least a little unblocked
<jekstrand>
dcbaker: That's ok. It'll let me drop one hack patch.
<jekstrand>
dcbaker: Yeah, I'm unblocked enough that I can go write more Rust code :)
<dcbaker>
Lol. Nice
<jekstrand>
I'm not planning to pull in any other crates besides the 4 that are needed for proc macros.
<jekstrand>
So as long as we get something sorted out in the next couple months, I'm not too worried.
<jekstrand>
Worst case, we can fall back to something like what gstreamer does temporarily.
junaid has joined #dri-devel
MajorBiscuit has quit [Quit: WeeChat 3.6]
<jekstrand>
Or we could keep those wrap repos on GitHub. (I don't really like that option.)
deathmist2 has quit [Remote host closed the connection]
deathmist2 has joined #dri-devel
kts has quit [Quit: Leaving]
frankbinns has quit [Remote host closed the connection]
Leopold___ has quit [Ping timeout: 480 seconds]
<airlied>
Lynne: yeah those lifetimes in the vulkan driver are in the apps hands
<Lynne>
cool
<Lynne>
the wait gets skipped?
<airlied>
you wait on semaphores before destroying resources
<Lynne>
we already do that, but we do that from multiple threads, and the patch only has a single semaphore
<alyssa>
jekstrand: Git...Hub?
freemint has quit [Ping timeout: 480 seconds]
<HdkR>
It's like grubhub, for ordering git repos to be delivered to your door
heat_ has joined #dri-devel
<alyssa>
Oh, ok
heat has quit [Ping timeout: 480 seconds]
Leopold has joined #dri-devel
<jenatali>
I don't suppose anybody already has a nir pass for sinking load_vulkan_descriptor to avoid bcsel/phi on the result?
<jenatali>
Apparently DXIL doesn't like any ops on resource handles, so I'd have to convert bcsel to if/else for operating on different resources...
<Venemo>
jenatali: you could add this as an option to nir_opt_sink
<jenatali>
Lemme take a peek
<jenatali>
Venemo: Despite having "sink" in the name, it seems like a pretty different set of ops compared to what the pass is doing
<Venemo>
what do you mean?
<jenatali>
It's more than just moving an instruction from one place to another, it's changing logic
<Venemo>
what logic does it change?
<jenatali>
I.e. converting res_a = a; res_b = b; res = test ? res_a : res_b; use_res(res); into if (test) { use_res(res_a); } else { use_res(res_b); }
<jenatali>
^^ is what I need to do, not what opt_sink currently does. opt_sink preserves block indices so it definitely can't rewrite bcsel to if/else
<Venemo>
opt_sink does not create new CF, it just sinks instructions
<jenatali>
Right. So what I need seems like it should be a different pass :)
<Venemo>
so basically you want to convert bcsel to if-else, and then sink
<alyssa>
you're going to want a vendor pass for that, I expect.
<alyssa>
My gut feeling is that VK capable hw should not need tat
<alyssa>
that
<jenatali>
Any control flow or conditions that are done on the result of load_vulkan_descriptor, instead need to be done on the inputs to it
<jenatali>
alyssa: Yeah, if I wanted to rewrite significant portions of our binding model and limit the set of drivers we can layer on, I could avoid the need for this pass
<pepp>
jekstrand: could you take a quick look at the first commit of !20728? (it's a fix for dma-buf.h)
iive has joined #dri-devel
<alyssa>
jenatali: OOI what hw needs that
<jenatali>
None that I know of. It's just a stupid limitation of DXIL
<alyssa>
can you fix dxil?
<jenatali>
I've been working on it :P
<alyssa>
:-D
<jenatali>
High level, in the original D3D binding model, you declare arrays of resources in the shader. You can index between those resources as long as they're in the same array. If they're not, you have to if/else them
<alyssa>
heaps?
<jenatali>
One of the new shader models added (6.6) added a new thing where you don't declare resources, you just pass an index into a descriptor heap/pool and describe how you want to interpret the descriptor. With that, you wouldn't need to do the if/else
<jenatali>
Either way, there's still a DXIL instruction that returns a "handle" which is pretty identical to load_vulkan_descriptor, except that DXIL says the only thing you can do with that handle is pass it to a resource access intrinsic like load/store
<jenatali>
So any phi/bcsel stuff needs to be done on the inputs to the handle create intrinsic instead of the result
<jenatali>
This is I think the last thing I need for VK1.1
<jenatali>
It's a simple enough transformation, was just wondering if someone else had already done it 🤷
mbrost_ has quit [Ping timeout: 480 seconds]
mbrost_ has joined #dri-devel
bluebugs has quit [Read error: Connection reset by peer]
pret7 has joined #dri-devel
gouchi has joined #dri-devel
q4a1 has quit []
<jekstrand>
pepp: done
jdavies has joined #dri-devel
freemint has joined #dri-devel
jdavies is now known as Guest1964
jdavies_ has joined #dri-devel
Guest1964 has quit [Ping timeout: 480 seconds]
mbrost_ has quit [Remote host closed the connection]
mbrost_ has joined #dri-devel
nuh^ has joined #dri-devel
ice9 has quit [Ping timeout: 480 seconds]
jkrzyszt has joined #dri-devel
mbrost_ has quit [Ping timeout: 480 seconds]
pret7 has quit [Ping timeout: 480 seconds]
pret7 has joined #dri-devel
alyssa has left #dri-devel [#dri-devel]
junaid has quit [Ping timeout: 480 seconds]
junaid has joined #dri-devel
JohnnyonFlame has joined #dri-devel
jdavies__ has joined #dri-devel
jdavies_ has quit [Remote host closed the connection]
<DavidHeidelberg[m]>
robclark: anholt does proxy works well for a630? I just tried twice re-run a630-traces and both times "Downloading file SirYouAreBeingHunted/sir-f750-v2.trace took 32s.", 144M from cache should go faster I think, right?
<DavidHeidelberg[m]>
Over 50% utilized gigabit network it should be max. 5 seconds imho
Leopold has quit [Remote host closed the connection]
junaid has quit [Ping timeout: 480 seconds]
Leopold has joined #dri-devel
jkrzyszt has quit [Remote host closed the connection]
Haaninjo has joined #dri-devel
junaid has joined #dri-devel
lemonzest has quit [Quit: WeeChat 3.6]
fab has quit [Quit: fab]
<robclark>
DavidHeidelberg[m]: not sure if it is gigabit (or even if the poor little NUC w/ usb-eth adapter could saturate it if it was)
<DavidHeidelberg[m]>
well, usb3 could still get around 600-700Mbit; usb2 400Mbit and even in this scenario < 5s
pret7 has quit [Ping timeout: 480 seconds]
<robclark>
it *is* nfsroot, so you are downloading it to rootfs, writing it back to the nuc ;-)
<DavidHeidelberg[m]>
ok, usb2 ~ more like 300Mbit, but still < 10 s for sure
<robclark>
so, like downloading things isn't the best plan
<robclark>
you are sending it multiple times over the network
<DavidHeidelberg[m]>
right, ignore me :P
<DavidHeidelberg[m]>
I forgot the nfs part
<robclark>
and the nuc is serving all the a630's over a single usb-eth
<robclark>
heheh
<DavidHeidelberg[m]>
sometimes I like to live in my imaginations in ideal world :)
<DavidHeidelberg[m]>
ok, we need the md5 piglit MR so we don't have to remove them anymore from NFS (so no new download) and just check the MD5.
<DavidHeidelberg[m]>
No better option I guess.
jluthra has quit [Remote host closed the connection]
jluthra has joined #dri-devel
pret7 has joined #dri-devel
pret7 has quit []
mszyprow has joined #dri-devel
<graphitemaster>
What possible undefined behavior am I hitting here. There's a bunch of random artifacts caused on various GPUs and drivers with this simplex noise. Strange out of place pixels that I cannot explain. The right is much worse, but the left side also has some artifacts https://www.shadertoy.com/view/mlXSz8
* DavidHeidelberg[m]
don't want to say Mold is magical, since around 10% was lost with 1.9.0 version, so this is more like getting back to previous perf)
apinheiro has joined #dri-devel
rasterman has quit [Quit: Gettin' stinky!]
<DavidHeidelberg[m]>
Rant: two magical commit names in the Mold project. "Simplify" and "Refactor"
Frogging101 has quit [Quit: Close the World, Open the nExt]
<psykose>
moldy commit messages
jfalempe has quit [Quit: Leaving]
<jenatali>
Is the Vulkan spec lying to me? It says that clearing a sscaled/uscaled format is supposed to use floats, but the CTS very clearly does it using ints
freemint has quit [Ping timeout: 480 seconds]
<jekstrand>
jenatali: Uh... That sounds like quite the edge case.
<jekstrand>
Why are you allowing them to create images with uscaled and sscaled formats to begin with?
flibitijibibo has quit [Read error: Connection reset by peer]
<jenatali>
Because maintenance1 says I have to
<jekstrand>
No it doesn't
<jenatali>
Oh, wait, no you're totally right this was a bug somewhere else
<jenatali>
We have to support them for vertex elements and I think that was tripping up image support
jewins1 has joined #dri-devel
<jekstrand>
jenatali: Incidentally, this just came up last week: