karenthedorf has quit [Remote host closed the connection]
simon-perretta-img has quit [Read error: Connection reset by peer]
simon-perretta-img has joined #dri-devel
yyds has joined #dri-devel
yyds has quit [Remote host closed the connection]
yyds has joined #dri-devel
heat has quit [Ping timeout: 480 seconds]
krushia has quit [Ping timeout: 480 seconds]
Company has quit [Quit: Leaving]
sukuna has joined #dri-devel
<DavidHeidelberg>
let's assume vblank_mode=0 glxgears is pretty CPU bound. I tried to do PGO build, which should be optimized just for the glxgears, but the perf is just slightly WORSE. Same goes for glmark2-wayland, any idea why that may happen?
<airlied>
DavidHeidelberg: are you running against a gpu?
<DavidHeidelberg>
yup.. good point, I should try llvmpipe
glennk has joined #dri-devel
<airlied>
DavidHeidelberg: though PGO won't do much for the CPU bound bits of llvmpipe
<airlied>
since it's all JIT code
<airlied>
with mesa I've a hard time seeing where PGO might really make a useful difference
<DavidHeidelberg>
hmm, 2600 fps to 3900 fps... thou one gear color is broken
kevinmitnick has quit [Remote host closed the connection]
kevinmitnick has joined #dri-devel
frankbinns has quit [Read error: Connection reset by peer]
frankbinns has joined #dri-devel
kts has joined #dri-devel
kts has quit []
simon-perretta-img has quit [Ping timeout: 480 seconds]
simon-perretta-img has joined #dri-devel
EricCurtin[m] has quit []
jsa has joined #dri-devel
frieder has joined #dri-devel
kevinmitnick has quit [Remote host closed the connection]
kevinmitnick has joined #dri-devel
warpme has joined #dri-devel
lemonzest has quit [Quit: WeeChat 4.3.3]
lemonzest has joined #dri-devel
simon-perretta-img has quit [Read error: Connection reset by peer]
simon-perretta-img has joined #dri-devel
i-garrison has quit []
i-garrison has joined #dri-devel
sghuge has quit [Remote host closed the connection]
sghuge has joined #dri-devel
kevinmitnick has quit [Remote host closed the connection]
kevinmitnick has joined #dri-devel
LeviYun has quit [Ping timeout: 480 seconds]
<MrCooper>
DavidHeidelberg: FWIW, on this system "vblank_mode=0 glxgears" isn't CPU-bound in the glxgears process, but in Xwayland
LeviYun has joined #dri-devel
<alice>
try vkcube-wayland :P
rgallaispou has joined #dri-devel
glennk has joined #dri-devel
LeviYun has quit [Ping timeout: 480 seconds]
kevinmitnick has quit [Remote host closed the connection]
kevinmitnick has joined #dri-devel
glennk has quit [Remote host closed the connection]
LeviYun has joined #dri-devel
glennk has joined #dri-devel
smpl has joined #dri-devel
lynxeye has joined #dri-devel
vliaskov has joined #dri-devel
rasterman has joined #dri-devel
kevinmitnick has quit [Remote host closed the connection]
kevinmitnick has joined #dri-devel
warpme has quit []
rgallaispou has quit [Ping timeout: 480 seconds]
<emersion>
daniels: thanks!
rasterman has quit [Quit: Gettin' stinky!]
pcercuei has joined #dri-devel
Calandracas_ has joined #dri-devel
<daniels>
np :)
Calandracas has quit [Ping timeout: 480 seconds]
tzimmermann has joined #dri-devel
rgallaispou has joined #dri-devel
kevinmitnick has quit [Remote host closed the connection]
kevinmitnick has joined #dri-devel
warpme has joined #dri-devel
yyds has quit []
smaeul has quit [Quit: Down for maintenance...]
glennk has quit [Ping timeout: 480 seconds]
simon-perretta-img has quit [Ping timeout: 480 seconds]
yyds has joined #dri-devel
simon-perretta-img has joined #dri-devel
<kevinmitnick>
technically lenght is invariant so when you pass through the length to dependency it would be enough... it's only colliding once you do not have dep for it possibly so async alus could yield incorrect results cause there might be same values involved to remove, as in this case it would forward the smallest possible length with constant subtraction but only for duplicates, in other words
<kevinmitnick>
what i understood it's possible to connect them over fake dependencies.to enforce order, so the smallest length would depend on the smallest pc, for example, as the smallest possible length w ould yield a biggest value the fake dependency needs to pass through a length to smallest value, the smallest value , so next biggest however forwards length to the next smallest, in other words
<kevinmitnick>
async instructions are duplicated and designed with fake operands around all the async alus they appear at. BTW HOW DO YOU LIKE MY NEW NAME zombie sweethearts? kevinmitnick is kinda sexy nick imo i am in rage if you ban this one too.
flynnjiang has quit [Quit: flynnjiang]
kevinmitnick was kicked from #dri-devel by ChanServ [You are not permitted on this channel]
warpme has quit []
yyds has quit [Remote host closed the connection]
yyds has joined #dri-devel
LeviYun has quit [Ping timeout: 480 seconds]
<mlankhorst>
So in ttm, the units of TT/sysmem are in pages, but vram/stolen memory in bytes?
kxkamil has quit []
davispuh has joined #dri-devel
warpme has joined #dri-devel
kxkamil has joined #dri-devel
sukuna has quit [Ping timeout: 480 seconds]
yyds has quit [Remote host closed the connection]
yyds has joined #dri-devel
kts has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
bmodem has quit [Ping timeout: 480 seconds]
feaneron has joined #dri-devel
guludo has joined #dri-devel
alane has quit [Ping timeout: 480 seconds]
fab has joined #dri-devel
evadot has quit [Remote host closed the connection]
evadot has joined #dri-devel
nerdopolis has joined #dri-devel
glennk has joined #dri-devel
itoral has quit [Remote host closed the connection]
bolson has quit [Remote host closed the connection]
bolson has joined #dri-devel
nerdopolis has quit [Ping timeout: 480 seconds]
nerdopolis has joined #dri-devel
krushia has joined #dri-devel
frankbinns has quit [Remote host closed the connection]
nerdopolis has quit [Ping timeout: 480 seconds]
alih has quit []
<Mis012[m]>
Company: actually, am I not completely wasting my time here? Even if I manage to render into a dmabuf with EGL, it doesn't look like I can do the same with Vulkan...
<zamundaaa[m]>
You don't need a surface to render into a dmabuf
<Mis012[m]>
Company: I guess all I really lack currently from Gtk with making my own wayland/x11 subsurfaces is a signal for the widget moving on-screen and the magic to make the corresponding widget transparent all the way through rather than just showing what's behind it
<Mis012[m]>
zamundaaa: the surface is the part that I do need, dmabuf is just what GtkOffload currently allows me to plug in
frankbinns has joined #dri-devel
<daniels>
dmabufs aren't a VkSurfaceKHR type, they're a VkImage
<daniels>
so you need to go up to whatever abstraction layer is forcing you to have a surface, and punch through so you can just render to an image
<Mis012[m]>
well, EGL has EGL_PLATFORM_GBM_MESA
<daniels>
fundamentally it's the same thing, you're 'just' skipping vkQueuePresentKHR (it's a no-op, you're presenting to yourself), and vkAcquireNextImageKHR (you already know what the next image is, because you have the dmabufs)
<daniels>
GBM is a workaround for EGL/GLES not having an explicit image allocation API like Vulkan does
<Mis012[m]>
so I really can't change the code that is insisting on using surfaces
<Mis012[m]>
again, I have stuff working currently, but idk if Gtk is willing to expose subsurfaces
<Mis012[m]>
and I can't really solve the two problems I mentioned with currently public APIs
glennk has joined #dri-devel
<Mis012[m]>
but if Vulkan doesn't have an off-screen surface crutch then I guess convincing Gtk maintainers to expose a subsurface API is the only option
warpme has quit []
Mangix has quit [Read error: Connection reset by peer]
Mangix has joined #dri-devel
<DemiMarie>
Mis012: I suggest a Gtk MR.
<Mis012[m]>
a long time ago I was asking about a subsurface API and it was basically not going to happen, but I guess now that it exists for a different reason maybe making it public is a more reasonable request?
<DemiMarie>
It’s a reasonable request, but I don’t know if the GTK developers would do the work. I think they would be much more likely to accept an MR.
epoch101 has joined #dri-devel
<Mis012[m]>
I'd be willing to even throw in X11 support depending on how painful that would be
<DemiMarie>
I don’t know if they will require that, since GTK is moving Wayland-first.
<belongstoheaven>
invariant means no other variants , the meaning is typically likely unique with only possible duplicates , but yielding the correct variant. It does not look like anyone was interested, but duplicating the length of async operand in compact format means only one entry at maximum of 300 decimal digits range or so it forwards as said length from input pc. The code has some complexity in
<belongstoheaven>
form of just thoughtfullness, but what you do is like so complex that you are suicidal terrorist annoyment to people, cause you lack any strategy or thought you are like random number generators. Performance of your crap is not even , i mean does not compare to any critics even yet, it's just so friggin bad. We could say that 50line java trace is a spectacular FLOSS beef trace. Anyone
<belongstoheaven>
who did not know, Karol on parole looked at java traces, when he was becoming a fecalist, it's like what an excitement it was for a living excrement! We had one bitch with her crankgrangsters in cambodia who would do similar things going in crowded masses to talk how big wanker i am and how stupid freak schizo, she was captured later among with many of his cranks who started to bother
<belongstoheaven>
tourists with all that in our hotels, the abuse bitches teeth were bunched in and lip was marked after their actions in life, they likely do the same with you it is called a rabbitlip in estonian you can recognize abusers having such marking done, totally braindead ghost wants to have more beefs but they get more brutal treatment this time.
belongstoheaven was kicked from #dri-devel by ChanServ [You are not permitted on this channel]
fab has quit [Quit: fab]
<FL4SHK[m]>
Can I write a conforming Vulkan driver for an integer only machine?
<FL4SHK[m]>
floats eat up quite a few logic cells
<FL4SHK[m]>
maybe soft floats would make sense
<FL4SHK[m]>
With some partial support for some float related operations like clz
<FL4SHK[m]>
my thinking is that maybe I can fit more cores if I go integer only
<FL4SHK[m]>
And then maybe there'd actually be a win in performance to do floats in software
<FL4SHK[m]>
An FPU for just 32-bit floats could eat up 3000-4000 LUTs. That is a large amount for my 500k LUT FPGA for the number of cores I want to fit
kzd has joined #dri-devel
kts has joined #dri-devel
smaeul has joined #dri-devel
Haaninjo has joined #dri-devel
cmichael has joined #dri-devel
reactormonk[m] has quit [Remote host closed the connection]
terribletea[m] has quit [Remote host closed the connection]
talcohen[m] has quit [Remote host closed the connection]
nicofee[m] has quit [Remote host closed the connection]
naheemsays[m] has quit [Remote host closed the connection]
kunal_10185[m] has quit [Remote host closed the connection]
MotiH[m] has quit [Remote host closed the connection]
onox[m] has quit [Remote host closed the connection]
kelbaz[m] has quit [Remote host closed the connection]
daniliberman[m] has quit [Remote host closed the connection]
undvasistas[m] has quit [Remote host closed the connection]
Targetball[m] has quit [Remote host closed the connection]
sigmoidfunc[m] has quit [Remote host closed the connection]
znullptr[m] has quit [Remote host closed the connection]
ofirbitt[m] has quit [Remote host closed the connection]
ohadsharabi[m] has quit [Remote host closed the connection]
tleydxdy has quit [Remote host closed the connection]
kunal10710[m] has quit [Remote host closed the connection]
moben[m] has quit [Remote host closed the connection]
bubblethink[m] has quit [Remote host closed the connection]
FloGrauper[m] has quit [Remote host closed the connection]
colinmarc has quit [Remote host closed the connection]
ddlc[m] has quit [Remote host closed the connection]
AlaaEmad[m] has quit [Remote host closed the connection]
aura[m]1 has quit [Remote host closed the connection]
Mershl[m] has quit [Remote host closed the connection]
FL4SHK[m] has quit [Remote host closed the connection]
halfline[m] has quit [Remote host closed the connection]
fkassabri[m] has quit [Remote host closed the connection]
raambm[m] has quit [Remote host closed the connection]
nyorain[m] has quit [Remote host closed the connection]
isinyaaa[m] has quit [Remote host closed the connection]
Alex[m]12345678910111213141522 has quit [Remote host closed the connection]
cwfitzgerald[m] has quit [Remote host closed the connection]
ella-0[m] has quit [Remote host closed the connection]
gdevi has quit [Remote host closed the connection]
pedrohlc[m] has quit [Remote host closed the connection]
jamen[m] has quit [Remote host closed the connection]
yshui` has quit [Write error: connection closed]
kos_tom has quit [Write error: connection closed]
kallisti5[m] has quit [Write error: connection closed]
jenatali has quit [Write error: connection closed]
Tooniis[m] has quit [Write error: connection closed]
swick[m] has quit [Write error: connection closed]
robertmader[m] has quit [Write error: connection closed]
x512[m] has quit [Write error: connection closed]
dcbaker has quit [Write error: connection closed]
DemiMarie has quit [Write error: connection closed]
oeuaoeuoeu[m] has quit [Write error: connection closed]
Newbyte has quit [Write error: connection closed]
Pierce[m] has quit [Write error: connection closed]
tomba has quit [Write error: connection closed]
tomeu has quit [Write error: connection closed]
jasuarez has quit [Write error: connection closed]
YHNdnzj[moz] has quit [Write error: connection closed]
Mis012[m] has quit [Write error: connection closed]
ttayar[m] has quit [Remote host closed the connection]
koki23[m] has quit [Remote host closed the connection]
exp80[m] has quit [Remote host closed the connection]
healfdanex[m] has quit [Remote host closed the connection]
egalli has quit [Remote host closed the connection]
Anson[m] has quit [Remote host closed the connection]
aradhya7[m] has quit [Remote host closed the connection]
cmeissl[m] has quit [Write error: connection closed]
pushqrdx[m] has quit [Write error: connection closed]
meltq[m] has quit [Write error: connection closed]
JosExpsito[m] has quit [Write error: connection closed]
zamundaaa[m] has quit [Write error: connection closed]
AlexisHernndezGuzmn[m] has quit [Write error: connection closed]
kusma has quit [Write error: connection closed]
<MrCooper>
daniels: just bisected wrong colours (red & blue swapped) in glxgears to 5ca85d75c05d ("dri: Fix BGR format exclusion")
<MrCooper>
I stopped using BE HW about a decade ago :)
<daniels>
yeah, sensible
<daniels>
still, good to know that none of our GLX testing makes sure that we deliver correct colours on screen
<MrCooper>
yeah
glennk has quit [Remote host closed the connection]
FL4SHK[m] has joined #dri-devel
<mattst88>
MrCooper: do I recall you using an Apple laptop as a terminal machine or similar once upon a time?
<MrCooper>
my main machine was a PowerBook for about 15 years, starting around the millennium
<FL4SHK[m]>
dang, 15 years with one computer?
<MrCooper>
not missing the fight against the endianness bug wind mills though
<FL4SHK[m]>
I've never done that
<FL4SHK[m]>
heh
<MrCooper>
3 different PowerBooks
<FL4SHK[m]>
ah
<FL4SHK[m]>
15 years ago I believe I was just starting to learn how to program
<FL4SHK[m]>
and now I'm a computer hardware/software engineer professionally and as a hobby
<MrCooper>
welcome to the club :)
<MrCooper>
well, I'm not a HW engineer though
<MrCooper>
daniels: the new code doesn't filter out PIPE_FORMAT_R8G8B8A8_UNORM at least
<FL4SHK[m]>
MrCooper: my hardware dev is mainly with FPGAs, which the coding languages for I'd argue are like software languages a lot anyway
<FL4SHK[m]>
I think it is feasible to get software engineers to learn the coding parts of FPGA development
<FL4SHK[m]>
Because the model isn't too too different from low level software anyway
<FL4SHK[m]>
I won't get into the details here, as that'd be a bit outside the scope of this channel
Duke`` has joined #dri-devel
<mattst88>
FL4SHK[m]: is there something you'd recommend reading to get started in FPGA development?
<FL4SHK[m]>
mattst88: there's a lot of online resources. I learned mostly from online resources.
<FL4SHK[m]>
I suggest using an HDL like SpinalHDL
<FL4SHK[m]>
I do have a degree in electrical engineering, but I mostly self taught myself FPGA dev
<FL4SHK[m]>
SystemVerilog is a good HDL too; if you want to use open source tooling with SV, check out `sv2v`
<mattst88>
thanks
alih has joined #dri-devel
<FL4SHK[m]>
Verilator is a really good simulator
<FL4SHK[m]>
you can practice with it
<FL4SHK[m]>
no problem
Mis012[m] has joined #dri-devel
<mattst88>
oh, neat
<FL4SHK[m]>
are you talking about mine?
<mattst88>
I'll add learning FPGA programming to my endless todo list :P
<FL4SHK[m]>
What's designware?
<FL4SHK[m]>
haha
<mattst88>
I was saying 'oh, neat' to the fact that there's a simulator that you can use for development
<FL4SHK[m]>
Yeah there's more than one simulator
<mattst88>
I hope you're not asking me what designware is :P
<FL4SHK[m]>
I just highly suggest Verilator
epoch101_ has quit [Ping timeout: 480 seconds]
<mattst88>
gotcha
<FL4SHK[m]>
no not you
<FL4SHK[m]>
nah I don't plan on using those
<FL4SHK[m]>
If I use non open IP, it'll be hard IP built into my FPGA
<FL4SHK[m]>
but the CPU/GPU should be entirely open
<FL4SHK[m]>
Right
<FL4SHK[m]>
so... I don't know much about developing ASICs
<FL4SHK[m]>
I know that liberty files exist
<FL4SHK[m]>
and that usually the low level blocks are not designed by people doing the HDL development
<FL4SHK[m]>
mostly ASICs just reuse existing low level blocks
<FL4SHK[m]>
There exists synthesis
<FL4SHK[m]>
logic synthesis is mostly a solved problem
<FL4SHK[m]>
apparently, anyway
<FL4SHK[m]>
Most likely I'd use yosys to do the logic synthesis
<FL4SHK[m]>
So I'm aware that there's analog parts to a lot of ASICs.
<FL4SHK[m]>
it's hard for something so exorbitantly expensive to be fully open
<FL4SHK[m]>
if only it weren't so expensive
<FL4SHK[m]>
Google Skywater exists at least
bolson_ has joined #dri-devel
bolson has quit [Remote host closed the connection]
<MrCooper>
daniels: AFAICT the big/little cases are flipped, e.g. PIPE_FORMAT_R8G8B8A8_UNORM has B/A at shift 16/24
<MrCooper>
I wonder if fixing that would reintroduce the s390x issue though
kts has quit [Quit: Konversation terminated!]
amarsh04 has quit []
idr has joined #dri-devel
amarsh04 has joined #dri-devel
warpme has quit []
tzimmermann has quit [Quit: Leaving]
kts has joined #dri-devel
rgallaispou has quit [Quit: WeeChat 4.3.2]
kts_ has joined #dri-devel
frieder has quit [Remote host closed the connection]
kts_ has quit []
M839ty9[m] has joined #dri-devel
kts has quit [Ping timeout: 480 seconds]
coldfeet has joined #dri-devel
bolson_ has quit [Ping timeout: 480 seconds]
alanc has quit [Remote host closed the connection]
alanc has joined #dri-devel
cmichael has quit [Quit: Leaving]
jsa has quit [Ping timeout: 480 seconds]
MrCooper has quit [Remote host closed the connection]
MrCooper has joined #dri-devel
rebelatwork has joined #dri-devel
rebelatwork has quit [Ping timeout: 480 seconds]
rebelatwork has joined #dri-devel
lynxeye has quit [Quit: Leaving.]
rauji____ has quit []
<rebelatwork>
mattst88: first off i wrote very little VHDL, this standard was most powerful in it's initial release in the 80's, but back times i did not get used to ada syntax, while i can do it now i have lost the interest, second point, trust me start with asics, laying out the structures i described, and move to FPGA's cause there they run the best. 3. icarus verilog or verilator is not doing the
<rebelatwork>
best job, i found severe port and instance coercion bugs from them, if you want something on the bar with cadence and synpsys simulators and and open source as well as with permissive licenses choose tachyon verilog simulator, so it supports all verilog standards and the high ones much later in the evolution compared to VHDL initial at nasa times, are on the bar with VHDL. Trust me i
<rebelatwork>
wrote all the time verilog and system verilog back times, so verilog is with pascal syntax.
LeviYun has joined #dri-devel
heat has joined #dri-devel
<rodrigovivi>
airlied: sima: while preparing drm-xe-next pr here I noticed something odd... because I did a backmerge recently I see some accel/habanalabs pathces when I $tig drm/drm-next..drm-xe/drm-xe-next .. was it something you pulled and then dropped?
<rodrigovivi>
if so, I believe I also need to drop here to ensure that you not pick that up again when pulling our PR...
<sima>
oops
<sima>
yeah airlied merged a bad habanalabs patch and ditched it again because the pr was too busted
<FL4SHK[m]>
So I have a question: could Vulkan use fixed point arithmetic?
<sima>
rodrigovivi, I guess apologies for the fallout, and airlied owes you one for ignoring the dim checks :-)
<pendingchaos>
RTNE might be less surprising to applications than RTZ, though
YunseongKim has joined #dri-devel
<FL4SHK[m]>
<pendingchaos> "unless you want to support the..." <- EXCELLENT
YunseongKim has quit [Remote host closed the connection]
LeviYun has quit [Ping timeout: 480 seconds]
LeviYun has joined #dri-devel
KDDLB has joined #dri-devel
<rodrigovivi>
sima no problem... it looks like only a few patches on top, so I'm going to reset to the previous commit before the merge, then do a new clean backmerge and re-apply and sign-off the 9 patches we have on top...
LeviYun has quit [Ping timeout: 480 seconds]
<rodrigovivi>
hmm.. sima dave daniels could one of you please give the owner role in the gitlab/xe/kernel so I can change the protection option temporary and force-push to drm-xe-next...
sima has quit [Ping timeout: 480 seconds]
<alyssa>
pendingchaos: even if you support float controls, denorms are optinal
<alyssa>
float controls just lets you advertise that you don't have denorms in that case
<alyssa>
(honeykrisp does this, no denorms in hw)
<FL4SHK[m]>
Ooh
<FL4SHK[m]>
that's even better
LeviYun has joined #dri-devel
DemiMarie has joined #dri-devel
<DemiMarie>
alyssa: that’s why I think languages should consider the behavior of denormals to be unspecified
rasterman has joined #dri-devel
<FL4SHK[m]>
I think that would be helpful
LeviYun has quit [Ping timeout: 480 seconds]
warpme has joined #dri-devel
warpme has quit []
guludo has quit [Ping timeout: 480 seconds]
guludo has joined #dri-devel
<glehmann>
d3d12 requires fp16 and fp64 denorm support, fp32 too for higher feature levels
jenatali has joined #dri-devel
<airlied>
mlankhorst: in theory ttm core has no units, each mgr decides what units to manage in
<airlied>
rodrigovivi: is it protected or just the git push block?
LeviYun has joined #dri-devel
coldfeet has quit [Remote host closed the connection]
LeviYun has quit [Ping timeout: 480 seconds]
melonai has quit []
statsaresoclear has joined #dri-devel
rasterman has quit [Quit: Gettin' stinky!]
<statsaresoclear>
you have never learned to think in any real way, and MrCooper appears to be even not the worse, so i interacted some in the channel in 2005 that was very tiny bit, but problems started at overseas starting from 2008...i was one year in australia , one year and three months in new zealand, then 1month in thailand and 3 months in cambodia having last moments of my youth that was about
<statsaresoclear>
to be ruined by meds, but they did not have sane drivers nor sane people involved in development, and cause it upset me, i got into issues with people stalking and abusing me when i said negative things on irc, and they were so nasty people that next occasions twice in cambodia where dad had some businesses they did not give up on harassing me and my people, so i am considering with
<statsaresoclear>
delay a brutal way to finish them, all the estonian sports elite will help me i suppose and underground as well, very strong people, technically we have no problems to make them beg for mercy, however this all was cultural shock to me still as to what idiotic people you have on earth.
statsaresoclear was kicked from #dri-devel by ChanServ [You are not permitted on this channel]
oneforall2 has quit [Remote host closed the connection]
oneforall2 has joined #dri-devel
<DemiMarie>
jenatali: so that means that d3d12 on Vulkan on Asahi will be broken in this way
gouchi has quit [Remote host closed the connection]
Duke`` has quit [Ping timeout: 480 seconds]
melonai has joined #dri-devel
<DemiMarie>
Mis012: looks like you will need to either patch GTK or use a different framework
<Company>
is that because GL doesn't need to enumerate all devices?
heat has joined #dri-devel
tlwoerner has quit [Quit: Leaving]
tlwoerner has joined #dri-devel
LeviYun has joined #dri-devel
<airlied>
Company: yes, GL only deals with one device, though not sure if you have glvnd and nvidia installed if that wakes things up
<Company>
I'm wondering if there's something one could do to avoid the problem in GTK
nerdopolis has joined #dri-devel
<Company>
because it's highly likely people are going to be unhappy, and I'm not sure new kernel API is gonna land quickly enough to fix things in all distros by September
<airlied>
don't think so, the vulkan loader's gonna load
<Company>
woul it help just enumerating one device?
<Company>
or is the loader gonna load anyway?
<airlied>
vulkan doesn't really have an enumerate one device interface I don't think
<jenatali>
Ideally Vulkan didn't need to actually load the drivers to report the physical device info
<jenatali>
But that ship's already sailed unless a new interface gets added
<Company>
airlied: I can vkEnumerateDevices(1, ...)
<Sachiel>
and how do you know that's the one you want?
<Company>
because I take the first one that has the features I need
<Company>
and if it isn't, I can vkEnumerateDevices(2, ...) and check the next one
<airlied>
Company: underneath it has to enumerate them all anyways
<airlied>
since they aren't ordered
<airlied>
we have layers to provide the order to the app
<alyssa>
glehmann: fortunately agx has denorms for fp16, just not fp32
<alyssa>
and also d3d12 on agx is impossible to do properly anyway so..............
<alyssa>
no sampler filter minmax hw and that one can't be emulated in any reasonable way (:
<Company>
then that idea won't work
davispuh has quit [Ping timeout: 480 seconds]
<airlied>
there are some kernel changes that might accidentally help alleviate it but not 100% sure
<jenatali>
FWIW D3D requires vendors to store enough information in the Windows registry that we can populate an adapter list, at least with vendors / device names, without having to load any drivers into the process or wake up GPUs
<jenatali>
But Vulkan physical devices have so many more properties that the driver really needs to get involved
<Company>
theoretically, this just enumerates the devices
<Company>
it's not querying them for details
LeviYun has quit [Ping timeout: 480 seconds]
<Company>
that's done one-by-one later, and GTK just picks the first in 99% of cases (and so does anyone probably), so we only query one device
<karolherbst>
could always add a custom mesa vulkan extension you can use to say "give me the phys device of this GPU I want to use"
<karolherbst>
because that's really want you want to do
<karolherbst>
not pick the first
<Company>
I think the Vulkan spec says to pick the first?
<karolherbst>
electron based applications already have bogus device selection, because they don't care what the compositor renders on
<karolherbst>
so they often end up using the discrete GPU as well
<airlied>
we reorder the list in the mesa layer already
<karolherbst>
ahh, I see
<airlied>
the problem is layers and exts still mean enumeration
<Company>
because I remember thinking about this and not having any idea what I should pick
<airlied>
pick the first will give you the same one as GL usually7
<karolherbst>
okay, that's good enough then (hopefully)
<Company>
I haven't heard any complaints yet - but it's still early
<karolherbst>
but yeah.. ultimately the kernel should cache the information we need in nvk
<airlied>
anyways it's technically a driver bug and we should work out how to fix it there
<airlied>
but also lspci will wake up your GPU
<karolherbst>
I _kinda_ have the same issue with rusticl, because I also have to create pipe_screens on every device for enumeration and...
<airlied>
I found someone put a profile.sh using lspci into /etc/ once
<karolherbst>
yeah.. but lspci is just being lspci...
<airlied>
I wonder if it's still thee
<Company>
yeah, I was just looking for easy workarounds
<airlied>
every time you started a shell it wakes up the gpu
<Company>
so discrete nvidia laptop users don't get sad
<karolherbst>
though fault is really sysfs waking up the GPUs on actually non relevant things
guludo has quit [Quit: WeeChat 4.3.2]
<karolherbst>
I think it parses the PCI config thing because sysfs is lacking interfaces
<airlied>
well you either cache it or read it from pci config space
<karolherbst>
right, but the config space wakes up the device
<airlied>
and if you ask to read it from pci config space it has to wake it up
<karolherbst>
yeah, but the things lspci needs aren't in sysfs, so it has to use the config thing
LeviYun has joined #dri-devel
<karolherbst>
thought he issue of course is, that lspci also parses everything even if it's not relevant for displaying according to the flags used
<airlied>
I think Ben mentioned in passing his work to split nouveau via aux bus has some effect
<airlied>
but I haven't enumerated what yet, esp if it was GL or VK paths
<karolherbst>
definetly not GL
<karolherbst>
we do command submission when creating the pipe_screen, so whatever you end up doing, if it involves a pipe_screen you are screwed
<Company>
airlied: the issue for GTK of course is a GTK 4.16 flatpak being run on Debian stable or RHEL because that will use Vulkan, too, and on an old kernel
<airlied>
if you submit cmds then it'll suck alright
<karolherbst>
but we also allocate the channel + sub-channels there
<karolherbst>
context creation is just brutally expensive on nvidia
<karolherbst>
when I do rusticl + zink run on nvidia, the runtime increases by x5
<rodrigovivi>
airlied: it is protected against force-push... neither with dim push-branch -f we can push... I also need to push a rebase on the topic/xe-for-CI...
cyrinux30 has quit []
cyrinux30 has joined #dri-devel
<airlied>
rodrigovivi: dim -f doesn't work for force pushs for me
<airlied>
not due to protection but due it not sending the correct git cmd lines
<airlied>
I usually sh -x dim push-branch -f then cut-n-paste the last line and fix it :)
<airlied>
but let me go check the protection status
<airlied>
rodrigovivi: okay I've clicked the allow to force push for drm-xe-next
<rodrigovivi>
thank you
<DemiMarie>
alyssa: does that mean that Windows games will be broken on Asahi, or is there an unreasonable way to emulate it?
<jenatali>
Demi: I'm not aware of anyone that actually depends on fp32 denorms, but if there's other problems then those are probably bigger
<jenatali>
Apple has their "game porting toolkit" and got real titles running on it so presumably at least those games don't use the problematic features
<DemiMarie>
jenatali: looks like the hardware sampler can't do min or max
<jenatali>
Yeah that seems somewhat niche
LeviYun has quit [Ping timeout: 480 seconds]
LeviYun has joined #dri-devel
pcercuei has quit [Quit: dodo]
LeviYun has quit [Ping timeout: 480 seconds]
<FL4SHK[m]>
<glehmann> "d3d12 requires fp16 and fp64..." <- ... good thing I'm only interested in Vulkan
<gfxstrand>
Company: Yeah, it's a bit of a problem but there's not much we can do about it at the moment.
<gfxstrand>
Like, the only real workaround in userspace would have to have a tiny little NVK server process that gets forked the first time you start NVK and hands out cached device info.
<gfxstrand>
And that seems kinda mean, TBH
<Company>
yeah, that seems more work than useful
<alyssa>
jenatali: gptk is a gigantic pile of hacks, as far as I can tell
<gfxstrand>
The real solution is for nouveau.ko to create a context at boot, scrape the info, and cache it for us.
<jenatali>
alyssa: Yeah that tracks
<gfxstrand>
Company: It also wouldn't work inside your flatpak scenario because you'd end up with one per flatpak, defeating the point.
<Company>
yeah, we only start once per flatpak
simon-perretta-img has quit [Ping timeout: 480 seconds]
<Company>
people will have to live with it
<Company>
or backport whatever patch you guys come up with
<gfxstrand>
Or it would end up being a zombie that messes with flatpak. "OMG! Why does it say my app is still running?!?"
<gfxstrand>
We just need to fix it in nouveau.ko
<Company>
like, 24.04 LTS will probably be worst off
<gfxstrand>
skeggsb has a plan but IDK if it's back-portable
<gfxstrand>
nouveau.ko is kind-of a mess on the inside and that makes things like this way harder than necessary
<gfxstrand>
It's probably possible to do today, though, if someone really tried.
<Company>
it really depends how many people are affected and how bad it is for them
simon-perretta-img has joined #dri-devel
LeviYun has joined #dri-devel
berberlightning has joined #dri-devel
LeviYun has quit [Ping timeout: 480 seconds]
<DavidHeidelberg>
airlied: after rebuild & new PGO, colors are ok.. problem with benchmarking is my laptop with TDP and small fan
heat has quit [Read error: Connection reset by peer]