<soreau>
it might need !24700 to make things work to test it though
alanc has quit [Remote host closed the connection]
alanc has joined #dri-devel
Daanct12 has joined #dri-devel
ngcortes_ has quit [Ping timeout: 480 seconds]
zzoon_2 has joined #dri-devel
<zzoon>
anholt: is there any way to get lava rootfs or create it myself? I guess it might be easy to setup since it's x86_64..
kts has joined #dri-devel
<anholt>
zzoon: open a job log, go to the "lava boot" section and expand it, and you'll find a URL where it downloads the rootfs
<anholt>
I took that, mounted proc,sys, and devtmpfs, copied my mesa build in, and chooted in to reproduce.
<zzoon>
Thanks! I'll try
kts has quit [Ping timeout: 480 seconds]
novaisc has quit [Quit: Ping timeout (120 seconds)]
novaisc has joined #dri-devel
mairacanal has quit []
mairacanal has joined #dri-devel
kts has joined #dri-devel
aravind has joined #dri-devel
agd5f_ has joined #dri-devel
agd5f has quit [Ping timeout: 480 seconds]
agd5f has joined #dri-devel
agd5f_ has quit [Read error: Connection reset by peer]
bmodem has joined #dri-devel
zzoon is now known as zzoon_OOO_till_03_Oct[m]
Daanct12 has quit [Ping timeout: 480 seconds]
fab has joined #dri-devel
youresuicidal has joined #dri-devel
_DOOM_ has joined #dri-devel
Daanct12 has joined #dri-devel
<_DOOM_>
What does the link status value in drmModeConnector mean?
<youresuicidal>
Why they got all evicted from freenode was, that on #osdev and here you were very arrogant while being always wrong, and you violated with mental illness talks on top, and terrorising eastern people, osdev had aussie trash who laughed with their garbage while i was searching for 1bit alus, any productive comments were not made, but any bit width alus can be propagated with adder procedures, now the phase is that you can not stop
<youresuicidal>
the abuse against me on my own territory physical territory not IRC, and next obvious thing to do is take you to fields and execute you, not that you stalk me with mental illness talks, rob cash from me, and talk how a whore is my wife, you do not have such permissions. All together you are obnoxious trash.
kts has quit [Ping timeout: 480 seconds]
<_DOOM_>
Did I interrupt something?
rcf has quit [Ping timeout: 480 seconds]
youresuicidal was kicked from #dri-devel by ChanServ [You are not permitted on this channel]
antoniospg has quit [Quit: Connection closed for inactivity]
itoral has joined #dri-devel
tzimmermann has joined #dri-devel
pelmeen has joined #dri-devel
pelmeen was kicked from #dri-devel by ChanServ [You are not permitted on this channel]
pochu has quit [Ping timeout: 480 seconds]
crabbedhaloablut has joined #dri-devel
kzd has quit [Ping timeout: 480 seconds]
sgruszka has joined #dri-devel
YuGiOhJCJ has joined #dri-devel
bmodem has quit [Ping timeout: 480 seconds]
bmodem has joined #dri-devel
bmodem has quit [Excess Flood]
bmodem has joined #dri-devel
pekkari has joined #dri-devel
An0num0us has joined #dri-devel
<orowith2os[m]>
_DOOM_: probably just a bot
<orowith2os[m]>
happens sometimes in other places too
sghuge has quit [Remote host closed the connection]
sghuge has joined #dri-devel
_DOOM_ has quit [Ping timeout: 480 seconds]
sgruszka has joined #dri-devel
yuq825 has joined #dri-devel
bmodem has quit [Ping timeout: 480 seconds]
kts has joined #dri-devel
bmodem has joined #dri-devel
_DOOM_ has joined #dri-devel
mvlad has joined #dri-devel
bmodem has quit [Ping timeout: 480 seconds]
vliaskov has joined #dri-devel
pekkari has quit [Quit: Konversation terminated!]
pcercuei has joined #dri-devel
jfalempe has quit [Read error: No route to host]
lynxeye has joined #dri-devel
jfalempe has joined #dri-devel
_DOOM_ has quit [Ping timeout: 480 seconds]
sarahwalker has joined #dri-devel
jfalempe_ has joined #dri-devel
jfalempe has quit [Read error: No route to host]
sarahwalker has quit [Ping timeout: 480 seconds]
jfalempe_ has quit [Quit: Leaving]
habernir has joined #dri-devel
tursulin has joined #dri-devel
jfalempe has joined #dri-devel
minecrell has quit [Quit: Ping timeout (120 seconds)]
minecrell has joined #dri-devel
zzoon_2 has quit [Ping timeout: 480 seconds]
ungeskriptet has joined #dri-devel
ungeskriptet7 has quit [Ping timeout: 480 seconds]
rasterman has joined #dri-devel
sgruszka has quit [Remote host closed the connection]
bmodem has joined #dri-devel
Daaanct12 has joined #dri-devel
JohnnyonFlame has quit [Read error: Connection reset by peer]
Daanct12 has quit [Ping timeout: 480 seconds]
apinheiro has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
rcf has joined #dri-devel
cmichael has joined #dri-devel
kts has joined #dri-devel
itoral has quit [Quit: Leaving]
kts has quit [Quit: Konversation terminated!]
dtmrzgl has quit []
mszyprow has joined #dri-devel
mszyprow has quit [Read error: Connection reset by peer]
aravind has quit [Ping timeout: 480 seconds]
harrystain has joined #dri-devel
<harrystain>
We know where to go, there is a public toilet called Big Easy on koh rong sanloem, which owner was the hero to assault me, similar to sara resort employer charl they disturbed the tourism on the island and claimed that i did it, and assaulted me and lied about me, similar to their estonian anchestors, owner is a british jew named jack who we pick up when we go there, and give him to treatment inside my team, physical
<harrystain>
assault behind back , there is no complication that guy is done.
<harrystain>
i am not putting up to your assaults alike at all anymore
<harrystain>
you get abused back
<harrystain>
1week later the orderers were captured and treated, i am not sure who assaulted in case they lied about it, i must make a request
<harrystain>
to confirm that it really was the owner of Big Easy
<alyssa>
mattst88: what happened to the agreement? :p
<ccr>
:D
sgruszka has joined #dri-devel
heat has joined #dri-devel
<pinchartl>
alyssa: what was the agreement ? :-)
bmodem has quit [Ping timeout: 480 seconds]
neniagh has quit []
neniagh has joined #dri-devel
mripard has quit [Remote host closed the connection]
<linkmauve>
pinchartl, if mattst88 agreed to stop being a suicidal terrorist, the spammer would stop spamming.
<pinchartl>
I've clearly missed most of the drama
* pinchartl
likes missing drama
<pinchartl>
but it's scary to think that we now have computers that pass the Turing tests, and humans who don't :-S
rcf has quit [Ping timeout: 480 seconds]
Daaanct12 has quit [Ping timeout: 480 seconds]
Leopold_ has quit [Remote host closed the connection]
<karolherbst>
zmike: btw, a similar crash to the sampler one from yesterday still lurks in the code somewhere. hit by `test_api kernel_arg_changes`, but I think this time it has to do with having no samplers, but a sampler view
<zmike>
karolherbst: what driver
<karolherbst>
lvp
agd5f has quit [Remote host closed the connection]
<karolherbst>
the shader only uses txs, so that kinda makes sense
<zmike>
got it
agd5f has joined #dri-devel
<zmike>
hm there's still a sampler
<karolherbst>
maybe there was one before?
<karolherbst>
mhh, though that doesn't make snese
<karolherbst>
zmike: you mean a sampler or a sampler view
<zmike>
sampler
<karolherbst>
that's odd.. here I see zink_bind_sampler_states being called with num_samplers = 0
<karolherbst>
might also be something locally here
<zmike>
works fine here
<karolherbst>
yeah.. maybe me having an outdated loader or something
<karolherbst>
I didn't update everything
<karolherbst>
let's see what the CTS is saying
apinheiro has quit [Quit: Leaving]
dtmrzgl has joined #dri-devel
pekkari has joined #dri-devel
pcercuei has joined #dri-devel
sgruszka has quit [Ping timeout: 480 seconds]
kzd has joined #dri-devel
An0num0us has quit [Ping timeout: 480 seconds]
Haaninjo has joined #dri-devel
<karolherbst>
zmike: that patch seems to break txf
<zmike>
🤕
<karolherbst>
though I think the solution here is simple...
<karolherbst>
yeah.. I can write a patch for that, looks trivial
<zmike>
I guess it probably needs the same casing in ntv as I did for txs
<zmike>
as do all the similar conditionals
<karolherbst>
yeah. something like that
idr has quit [Ping timeout: 480 seconds]
<karolherbst>
it's the `spirv_builder_emit_image` when dealing with txf, because the image type is already without the sample part
<zmike>
yes, that's why I said changing the conditional to match the others would fix this
<karolherbst>
yep, doing that
yuq825 has quit []
<karolherbst>
mhhh.. now it's running into return type mismatches :'(
<cheako>
Is harrystain in #intel-3d a bot?
<pq>
cheako, probably just that person with mental illness that has been doing just that for a decade or more
<pq>
and now I'm getting PM from them because I said so
<pq>
time to update the ignore lists
xroumegue has quit [Ping timeout: 480 seconds]
Duke`` has joined #dri-devel
xroumegue has joined #dri-devel
macromorgan_ has joined #dri-devel
yyds has joined #dri-devel
macromorgan_ has quit []
macromorgan has quit [Ping timeout: 480 seconds]
harrystain has quit []
idr has joined #dri-devel
heat has quit [Ping timeout: 480 seconds]
<austriancoder>
What should I know about mediump in NIR? What do I need do use it correctly?
<austriancoder>
@alyssa: @gfxstrand: ^
bmodem has quit [Ping timeout: 480 seconds]
<alyssa>
austriancoder: mediump doesn't really exist in NIR
<alyssa>
that's a GLSL concept handled almost entirely in the GLSL compiler (except one detail of conversions you can ignore)
<alyssa>
by the time your driver gets NIR, it's just a 32-bit op or a 16-bit op or whatever, just respect exactly the bit sizes in NIR and it'll work out
<austriancoder>
alyssa: thx
<HdkR>
and then eventually learn to ignore fp16 and operate everything as fp32 because of broken applications? :)
<HdkR>
Thus the circle of fp16 problems continues
<alyssa>
HdkR: the 5 stages of mediump grief
<alyssa>
"everything is 32-bit in my IR"
<alyssa>
"fuuuuuuuck i can't bolt on fp16 fuck"
<alyssa>
"maybe i can half ass it, and can still get some perf back, and it'll work out even tho it's a mess"
<alyssa>
"i spent 100s of hours on fp16 and despite shaderdb wins, zero apps improved their fps"
<alyssa>
"Hey, desktop apps are all fp32 anyway, and ALU is pretty cheap. It's all good!"
<HdkR>
:D
pekkari has quit [Quit: Konversation terminated!]
<DavidHeidelberg>
What about our lord and saviour LLM? There is lot of fp16
<HdkR>
Maybe we should drop FP16 entirely and switch to bfloat16 only. Paradigm shift everyone to avoid problems :P
<alyssa>
i dont know what i dislike more, fp16 or LLMs
<karolherbst>
mood
<alyssa>
LLMs cause far more harm but fp16 have caused so much harm to me personally :P
<DavidHeidelberg>
alyssa: just wait, maybe LLM catch up
<alyssa>
yeah I give it a year
<karolherbst>
I wonder if the solution to fp16 in rusticl will be: f2f16(clc_builtin(f2f32(clc_builting_srcs....))
<karolherbst>
so uhhhm... I'm very sorry about it, I got GPT-2 running on my M2 🙃
<karolherbst>
*but
<alyssa>
karolherbst: asahicl?
<karolherbst>
yeah
<alyssa>
cursed
<karolherbst>
very
<karolherbst>
it's faster than on iris tho
<karolherbst>
(which isn't hard tbh)
<karolherbst>
I asked it who Asahi Lina is, it answered: Asahi Lina is Asahi Lina. so I guess it's not as stupid afterall
<karolherbst>
so the problem was just that the texture got typed through the txs in the shader, but never updated for the txf following that
<karolherbst>
txf expected float result, where with txs we got uint
<zmike>
🤕
<zmike>
there are other cases of the first conditional that probably still need to be updated tho?
_DOOM_ has joined #dri-devel
<karolherbst>
tbd, I'll run the CTS and see where remaining problems are
<karolherbst>
but it looks fine so far
_DOOM_ has quit []
<zmike>
for consistency it should be updated
<karolherbst>
fair enough
<karolherbst>
mhhh nir_texop_query_levels ... mhhh yeah, I guess I should update those as well as we'll run into them with more gl_sharing related extensions
junaid has quit [Remote host closed the connection]
<cheako>
For updating the drm, how essential is it to compile the whole kernel?
<karolherbst>
40 -> 32 crashes, nice... let's see what the others are all about
<karolherbst>
ahh a crash within JIT code ...
<karolherbst>
might be a lvp only problem
<karolherbst>
anv and radv are more or less the same now
junaid has joined #dri-devel
lynxeye has quit [Quit: Leaving.]
<karolherbst>
let's see if I can finally run stuff with radv
<karolherbst>
mhh.. still crashes the GPU
<karolherbst>
no validation errors at least..
<APic>
l
<APic>
Sorry
tzimmermann has quit [Quit: Leaving]
vliaskov has quit [Read error: Connection reset by peer]
<soreau>
zmike: I was thinking I could run piglit without and with the patches applied but of course xwayland crashes without or no window shows up, so.. is there any way you can try it with your setup? or do you use piglit at all? (on xwayland?)
<zmike>
I use piglit, but I also use hardware with radv modifier support and an xserver with glamor
<soreau>
but I suppose it wouldn't show anything where there is EXT_image_drm_format_modifier because it's basically the same without the patch in that case..
<soreau>
zmike: I am using glamor
<soreau>
if this was without glamor, it would be basically meaningless
<zmike>
oh okay then you're just hitting the implicit modifier case anyway
<zmike>
radv doesn't support modifiers on your hardware gen
<zmike>
you'd have better luck resolving the problem at that end
<soreau>
why does this MR talk about 'broken xservers'?
<soreau>
in what way are they broken exactly? (and can they be fixed?)
<zmike>
because if you don't have modifiers and are trying to use an xserver then your xserver is broken
<soreau>
...
<soreau>
this doesn't seem to make much sense because xservers have worked fine on hw without modifier concept for many yeats
<soreau>
years*
<zmike>
it's a zink problem, not a hardware problem
<zmike>
but to resolve it in zink you either need to get a new vk extension which handles implicit modifiers (which would have to go through the system integration workgroup) or implement modifiers for your hw gen
<soreau>
ok, thanks.. where would modifier support have to be implemented?
<zmike>
cc bnieuwenhuizen ^
<soreau>
kernel, libdrm, mesa? all of the above?
<bnieuwenhuizen>
kernel & mesa
<soreau>
ok, thanks
An0num0us has joined #dri-devel
<bnieuwenhuizen>
basically an uapi chunk in drm_fourcc.h IIRC, then amdgpu DC support in the kernel, and mesa support in src/amd/common/ac_surface.c
<soreau>
bnieuwenhuizen: sounds like a plan, thanks again
<soreau>
bnieuwenhuizen: any reason why it's not already done for i.e GFX8?
<bnieuwenhuizen>
I got more pushback with my modifier proposal for gfx6-gfx8 at the time and ChromeOS only really needed it for GFX9+ looking at the feature matrix at the time
<soreau>
bnieuwenhuizen: would you mind if I maybe tried picking up where you left off somehow?
<bnieuwenhuizen>
nope, go for it
<soreau>
bnieuwenhuizen: can you link me to your kernel patch(es)?
agd5f has quit [Read error: Connection reset by peer]
junaid has quit [Remote host closed the connection]
pochu has quit [Ping timeout: 480 seconds]
pochu has joined #dri-devel
flom84 has quit [Ping timeout: 480 seconds]
flom84 has joined #dri-devel
kts has joined #dri-devel
rasterman has quit [Quit: Gettin' stinky!]
rcf has joined #dri-devel
JohnnyonF has quit []
flom84 has quit [Quit: Leaving]
tursulin has quit [Ping timeout: 480 seconds]
gouchi has joined #dri-devel
habernir has quit [Quit: Leaving]
ngcortes has joined #dri-devel
DemiMarie has joined #dri-devel
<DemiMarie>
Can Mesa be told to use a GPU for rendering, but copy the resulting image back to the CPU for use with a display server that doesn’t implement any of the direct rendering APIs?
<karolherbst>
gbm?
<karolherbst>
the CTS and piglit e.g. use gbm if you don't want to have any display server running and just do headless testing
<DemiMarie>
not really
<DemiMarie>
I’m thinking of e.g. a Wayland compositor that only implements wl_shm.
<karolherbst>
well.. you need an API to allocate GPU memory for scanout
<karolherbst>
or rather you need a buffer to render into
<DemiMarie>
in my use-case, scanout is done by copying the memory back to the CPU, where it will likely be copied again one or two times before being finally sent back to the GPU for display
<karolherbst>
yeah.. use gbm for that
<DemiMarie>
gbm?
<karolherbst>
it's a mesa API
<karolherbst>
nvidia supports it as well recently
<DemiMarie>
Is there a way (perhaps via an environment variable) to tell Mesa to do that when an application uses EGL?
<karolherbst>
no? It's an API
<karolherbst>
however you can use gbm memory for EGL through `EGL_MESA_platform_gbm`
<karolherbst>
but anyway, this needs code
<DemiMarie>
Would an MR adding this to Mesa be accepted?
<karolherbst>
it doesn't make sense
<karolherbst>
it's an API for clients to allocate a surfaces
<karolherbst>
like you'd do with wayland or X11
<karolherbst>
just instead of a window or something, it's a raw buffer
<DemiMarie>
I mean for Mesa to use GBM internally, then do the GPU → CPU copy itself
<karolherbst>
gbm is an API mesa provides
<karolherbst>
you need to provide the GL impl some buffer to render into
<karolherbst>
one way or the other
<karolherbst>
instead of Wayland/X11 stuff, you'd use gbm
<DemiMarie>
The broader context is that I want to be able to test GPU acceleration in virtualized contexts without having to wait for cross-VM buffer sharing to be implemented, which will likely take longer
<karolherbst>
yes
<karolherbst>
use gbm
<DemiMarie>
I get that
<karolherbst>
but it can't magically know where to store the result
<DemiMarie>
And I am saying that I want to be able to test this on real-world applications, which won’t use GBM themselves
<karolherbst>
so it's up to the application to do it
<DemiMarie>
wl_shm?
<DemiMarie>
the display server exists, it just only supports CPU-side shared memory
<DemiMarie>
this isn’t a headless situation
<karolherbst>
ahh
<karolherbst>
the thing is, it doesn't work on all GPUs
<DemiMarie>
why?
<karolherbst>
CPU side memory is generally linear, and not all GPUs can render to linear memory
<DemiMarie>
And nobody has implemented CPU-side unswizzling?
<karolherbst>
e.g. nvidia GPUs can't do it if you have a depth buffer attached
<DemiMarie>
In my case only Intel and AMD matter
<karolherbst>
GPUs can't render tiled to host memory
<karolherbst>
afaik
<DemiMarie>
render to temporary GPU buffer, then copy
<karolherbst>
well.. then you need application changes
<DemiMarie>
why?
<karolherbst>
though I guess prime offloading also kinda works like that...
<karolherbst>
just more cursed
<DemiMarie>
“not yet implemented” is a valid answer, but I don’t see a reason it couldn’t work
<karolherbst>
well.. in the end you can provide any kinda of buffer which is accepted through EGL/GLX
<karolherbst>
and platform specific extensions
<DemiMarie>
would I be better off having the display server (which I control) do the copy?
crabbedhaloablut has quit []
<karolherbst>
probably, once you leave EGL/GLX/GL or whatever vulkan provides it's not really a concern of mesa anymore what happens with the rendered output
<DemiMarie>
The other part is that this is all blocked on virtio-GPU native context support for Intel, AMD, and Xen landing
fab has quit [Quit: fab]
<Kayden>
sounds a lot like prime
<Kayden>
there's code in src/loader for doing blits on the rendering GPU to a linear buffer for handing off to another device
idr has quit [Ping timeout: 480 seconds]
Duke`` has quit [Ping timeout: 480 seconds]
<karolherbst>
right.. but I think we added that code to workaround shortcommings of GLX/EGL at that time :')
<karolherbst>
but yeah.. compositors should just allocate GPU memory for a specific device and do whatever they want with it afterwards
Daanct12 has joined #dri-devel
Danct12 has quit [Ping timeout: 480 seconds]
halfline has joined #dri-devel
ngcortes has quit [Ping timeout: 480 seconds]
gouchi has quit [Quit: Quitte]
Haaninjo has quit [Quit: Ex-Chat]
Peste_Bubonica has quit [Remote host closed the connection]
halfline has quit [Quit: Page closed]
tobiasjakobi has joined #dri-devel
tobiasjakobi has quit []
kasper93 has quit [Remote host closed the connection]
An0num0us has quit [Ping timeout: 480 seconds]
nukelet has joined #dri-devel
mvlad has quit [Remote host closed the connection]
Dark-Show has joined #dri-devel
pcercuei has quit [Quit: dodo]
nukelet has quit [Quit: Leaving]
tobiasjakobi has joined #dri-devel
idr has joined #dri-devel
tobiasjakobi has quit [Remote host closed the connection]
ngcortes has joined #dri-devel
shashanks__ has joined #dri-devel
idr has quit [Read error: Connection reset by peer]
jernej_ has joined #dri-devel
shashanks_ has quit [Ping timeout: 480 seconds]
jernej has quit [Ping timeout: 480 seconds]
ngcortes has quit [Remote host closed the connection]
ngcortes has joined #dri-devel
<kode54>
hey
<kode54>
would this be a DXVK failure
<kode54>
there's a shader that DXVK produces that has Vec2 input and Vec4 output
<kode54>
and validation layers complains about this
<kode54>
that exact frame of the render commands causes xe.ko to crash the GuC
kts has quit [Ping timeout: 480 seconds]
OftenTimeConsuming is now known as Guest1521
OftenTimeConsuming has joined #dri-devel
Guest1521 has quit [Remote host closed the connection]
<DemiMarie>
kode54: no, this is a xe.ko bug
<kode54>
gotcha
<DemiMarie>
Even malicious userspace should not be able to crash the kernel or GuC
<kode54>
wish the vm logging worked so I could produce logs of what is crashing it
<DemiMarie>
(okay, there are a few exceptions, but all of them require root privileges and none apply here)
<DemiMarie>
DXVK making invalid Vulkan API calls is a bug in DXVK unless the DirectX API calls also had undefined behavior. However, the kernel is not allowed to crash the GuC, and that is a potential security problem so fixing it should take priority.