ChanServ changed the topic of #dri-devel to: <ajax> nothing involved with X should ever be unable to find a bar
<zmike>
karolherbst: there, have fun with it
<karolherbst>
nice nice nice
greyqw[m] has left #dri-devel [#dri-devel]
<airlied>
karolherbst: use c++filt to find out __clc_sw_fma(float __vector(8), float __vector(8), float __vector(8)) after that, it's like something is getting passed to it wrong then
<airlied>
karolherbst: looks like a missing parameter in the call
<karolherbst>
ahh that's plausible
<karolherbst>
maybe
<airlied>
call void @_Z12__clc_sw_fmafff(<8 x i32> %242, ptr %callcontext, <8 x i64> <i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32>, <8 x i32> %ssa_25, <8 x i32> %ssa_26, <8 x i32> %ssa_27)
<airlied>
seesm to have the 8x64 in it before the actual parameters
<airlied>
oh it has a zer0 init one
<karolherbst>
but also why are we calling into the libclc sw fma function for lp 🙃
<airlied>
don't think lp has any input on that decision
<airlied>
I think you'd have to dump the library side to know what it is expecting
<karolherbst>
uhh so much code to delete
<karolherbst>
I might end up more than the size of clover 🙃
<zmike>
how is there no chainsaw emoji
<zmike>
or maybe like a hedge trimmer
<karolherbst>
the fun part is, that I also remove code in zink 🙃
<zmike>
yessss
kj2 has joined #dri-devel
user0 has quit [Ping timeout: 480 seconds]
HerrSpliet has quit [Ping timeout: 480 seconds]
orbea has joined #dri-devel
vliaskov_ has quit [Ping timeout: 480 seconds]
user0 has joined #dri-devel
RSpliet has joined #dri-devel
ursoc^ has quit [Ping timeout: 480 seconds]
<karolherbst>
uhhh.. why is nv50
<dwfreed>
because they wanted to improve nv40?
* dwfreed
ducks
epoch101_ has joined #dri-devel
* zmike
shakes fist
<zmike>
I asked myself that many times this afternoon
FireBurn has joined #dri-devel
<karolherbst>
I'm only at " 46 files changed, 68 insertions(+), 634 deletions(-)" and I'm just getting started
<zmike>
fuck yeah
epoch101 has quit [Ping timeout: 480 seconds]
<karolherbst>
why am I finding more and more stuff to delete.. this is madness
<FireBurn>
Hey I'm getting the following error when trying to build for andorid
<karolherbst>
isn't the new way the gl loading stuff works relying on it?
<zmike>
uhhhh I don't think so?
<zmike>
but also I'm not sure what you're talking about with "gl loading stuff"
CME has joined #dri-devel
<karolherbst>
like it uses the libpipe_loader_dynamic now
soze has joined #dri-devel
qpla has quit [Read error: Connection reset by peer]
<zmike>
huh
<zmike>
I'd have to look closer I guess
<zmike>
a task for tomorrow
glennk has joined #dri-devel
soze has quit [Ping timeout: 480 seconds]
zzyiwei has joined #dri-devel
sima has quit [Ping timeout: 480 seconds]
epoch101_ has quit [Ping timeout: 480 seconds]
user0 has quit [Ping timeout: 480 seconds]
user0 has joined #dri-devel
gnuiyl_ has joined #dri-devel
alane_ has joined #dri-devel
gnuiyl has quit [Ping timeout: 480 seconds]
alane has quit [Ping timeout: 480 seconds]
zzyiwei has quit [Quit: leaving]
epoch101 has joined #dri-devel
yrlf has quit [Quit: Ping timeout (120 seconds)]
yrlf has joined #dri-devel
nerdopolis has quit [Ping timeout: 480 seconds]
alane_ has quit []
alane has joined #dri-devel
amarsh04 has quit []
kj2 has quit [Quit: Connection closed for inactivity]
amarsh04 has joined #dri-devel
alanc has quit [Remote host closed the connection]
alanc has joined #dri-devel
kzd has quit [Ping timeout: 480 seconds]
Daanct12 has joined #dri-devel
riteo has quit [Ping timeout: 480 seconds]
riteo has joined #dri-devel
davispuh has quit [Ping timeout: 480 seconds]
ursoc^ has joined #dri-devel
epoch101 has quit []
dsimic is now known as Guest11226
dsimic has joined #dri-devel
clever has quit [Ping timeout: 480 seconds]
slattann has joined #dri-devel
Guest11226 has quit [Ping timeout: 480 seconds]
clever has joined #dri-devel
Daanct12 has quit [Ping timeout: 480 seconds]
Daanct12 has joined #dri-devel
Company has joined #dri-devel
amarsh04 has quit []
u-amarsh04 has joined #dri-devel
Jeremy_Rand_Talos__ has quit [Remote host closed the connection]
Jeremy_Rand_Talos__ has joined #dri-devel
Kwiboo has quit [Quit: .]
Kwiboo has joined #dri-devel
fab has joined #dri-devel
jsa1 has joined #dri-devel
kts has joined #dri-devel
<anarsoul>
hey folks, I'm working on fixing mipmapping for linear textures for lima. The issue is that texture descriptor allows to specify stride for all the levels globally (i.e. each level has the same stride). As a workaround I'm thinking about an layout that looks like a texture atlas
blaztinn has quit [Remote host closed the connection]
<anarsoul>
is there an existing algorithm to find the optimal dimensions and placement for individual levels? as an additional difficulty individual level dimensions must be aligned to tile boundaries (16x16)
<anarsoul>
obviously it won't work for 3D textures, but should be fine for 2D
tzimmermann has joined #dri-devel
blaztinn has joined #dri-devel
jsa1 has quit [Ping timeout: 480 seconds]
kts has quit [Quit: Konversation terminated!]
sghuge has quit [Remote host closed the connection]
sghuge has joined #dri-devel
fab has quit [Quit: fab]
jsa1 has joined #dri-devel
gnuiyl_ has quit [Remote host closed the connection]
tzimmermann has quit [Ping timeout: 480 seconds]
gnuiyl_ has joined #dri-devel
rasterman has joined #dri-devel
rasterman has quit [Quit: Gettin' stinky!]
azerov has quit [Quit: Gateway shutdown]
rasterman has joined #dri-devel
kts has joined #dri-devel
fab has joined #dri-devel
egbert is now known as Guest11240
egbert has joined #dri-devel
warpme has joined #dri-devel
Guest11240 has quit [Ping timeout: 480 seconds]
azerov has joined #dri-devel
phasta has joined #dri-devel
gnuiyl_ has quit []
gnuiyl has joined #dri-devel
<phasta>
I have to read "Is the bug in the current rc?" as "Is this a new bug that has not yet been in the kernel, but was introduced in the last merge window and that's why it's in the current -rc?", haven't I?
<jani>
alyssa: our CI moving away from patchwork is a separate matter from keeping patchwork running. but once we move away, it might be a question whether there are users for fdo patchwork anymore.
<alyssa>
ahh makes sense
<alyssa>
I don't think I realized kernelci consumed patchwork
<alyssa>
thx for the link :)
MrCooper__ has joined #dri-devel
<jani>
and regardless of all this, people(tm) have questioned the use of patchwork links in the Link: tag when b4 uses lore links
<jani>
oh I don't know about kernelci, this is for intel-gfx-ci
<alyssa>
those are different?-- ah yes of course they are
<jani>
:)
<jani>
we have a lot of historical baggage, and our use of fdo patchwork is one of them. I think it predates gitlab.fd.o by about five years or so
<DragoonAethis>
alyssa: yup, kernelci is more like a central database of results driven by some teams, not a CI system by itself
<DragoonAethis>
I know of it, and would like to eventually push data there... but um, we have bigger problems for now
<jani>
and fdo patchwork is a fork of the original patchwork that never merged back
<karolherbst>
this is nothing compared what I'm gonna do to r600 and radeonsi
<zmike>
you teach em a lesson karol
cyrinux has quit []
cyrinux has joined #dri-devel
MrCooper_ has joined #dri-devel
davispuh has joined #dri-devel
MrCooper__ has quit [Ping timeout: 480 seconds]
<K900>
Massive
<K900>
Should distros still ship Clover for 25.1?
<K900>
I kinda want to at least disable it
dt9_ has joined #dri-devel
dt9 has quit [Ping timeout: 480 seconds]
<mattst88>
I don't think so. I'm not shipping it in Gentoo for a while now and no one has complained
mehdi-djait3397165695212282475 has quit []
mehdi-djait3397165695212282475 has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
<karolherbst>
it's also pretty broken on radeonsi, so normally if you end up using clover there your system just hangs
guludo has quit [Ping timeout: 480 seconds]
warpme has quit []
guludo has joined #dri-devel
vliaskov_ has quit [Read error: Connection reset by peer]
MrCooper__ has joined #dri-devel
Kayden has quit [Quit: -> JF]
MrCooper_ has quit [Ping timeout: 480 seconds]
<K900>
Fun
<mareko>
karolherbst: does radeonsi clover hang with main?
<karolherbst>
pretty much everytime I accidentally run a CTS test on it
jkrzyszt has quit [Ping timeout: 480 seconds]
<mareko>
then I think we can remove it
ZeZu has quit [Ping timeout: 480 seconds]
yrlf has quit [Ping timeout: 480 seconds]
varunrmallya has joined #dri-devel
mehdi-djait3397165695212282475 has quit []
yrlf has joined #dri-devel
tzimmermann has quit [Quit: Leaving]
varunrmallya has quit []
xeon has joined #dri-devel
ZeZu has joined #dri-devel
Kayden has joined #dri-devel
coldfeet has joined #dri-devel
<alyssa>
I've heard that drm/sched will elide intra-queue syncobj dependencies, can anyone point me to where in the code that's happening?
<alyssa>
I.e. if you submit two jobs to the same queue back to back, the first signals a syncobj, the second waits on it, drm/sched will just submit them both together without roundtripping to the cpu in the middle
<alyssa>
(It also seems that happens only for binary syncobjs, but not for timeline syncobjs. Judging by a race I've been chasing since yesterday.)
Kayden has quit [Quit: Leaving]
<lynxeye>
alyssa: drm_sched_entity_add_dependency_cb is what you want to look at, I believe.
<alyssa>
lynxeye: ooh, yeah. thanks :)
<alyssa>
now to figure out why this doesn't happen for timeline syncs..
<alyssa>
the second-level question there is .. whose bug is it?
<alyssa>
If I understand the drm/asahi + apple fw behaviour right, drm/asahi is depending on the following invariant
<alyssa>
"Jobs submitted to a queue that only depend on jobs previously submitted to that queue, will be scheduled in finite time after the previous jobs are scheduled"
<alyssa>
drm/sched satisfies that when only binary sync is involved
<alyssa>
but I'm unsure if it's part of the drm/sched contract.. it does seem that we're depending on this only by chance! (because it's a tricky race to hit otherwise)
<robclark>
alyssa: it should all come down to the fence context of the underlying dma_fence.. syncobjs are just syntactic goo on top of fences.
<alyssa>
robclark: duly noted. i am so new to seeing behind the goo :(
<robclark>
iirc container fences should combine fences that are on the same context/timeline.. I wonder if that doesn't happen for dma_fence_chain?
<lynxeye>
alyssa: what makes the firmware depend on those jobs being scheduled in finite time? Isn't a job that hasn't been scheduled simply invisible to the firmware and would thus not cause any harm?
<robclark>
looks like dma_fence_chain_init() does try to do this
<lynxeye>
job submission to a queue might also be blocked by insufficient credits for that queue in which case the scheduler will not schedule any new jobs until a job from that queue finishes
<alyssa>
lynxeye: I think due to a drm/asahi logic bug. But I didn't write this driver and I do not understand the r/e'd firmware yet and it's not like there's docs to consult..
<alyssa>
consider this a working theory
<alyssa>
this is my first time doing serious work on this driver. not loving it :p
<alyssa>
but.. learning lots
rasterman has joined #dri-devel
<alyssa>
lynxeye: credit limit for drm/asahi is impossibly high which would explain that never being hit
<lynxeye>
alyssa: Ah okay, just wanted to point this out as one more potential source to violate your invariant.
Kayden has joined #dri-devel
<alyssa>
lynxeye: appreciate that info, will put it in my comment
<alyssa>
i'm attempting to rework the drm/asahi logic to not depend on this. seems to fix my hang/race C:
jsa1 has joined #dri-devel
rasterman has quit [Quit: Gettin' stinky!]
lynxeye has quit [Quit: Leaving.]
Piraty has quit [Remote host closed the connection]
Piraty has joined #dri-devel
xeon has quit [Ping timeout: 480 seconds]
xeon has joined #dri-devel
sima has quit [Ping timeout: 480 seconds]
jsa1 has quit [Remote host closed the connection]
epoch101_ has quit [Ping timeout: 480 seconds]
Nasina has joined #dri-devel
Nasina has quit []
Nasina has joined #dri-devel
rsalvaterra_ has joined #dri-devel
rsalvaterra_ is now known as rsalvaterra
MrCooper_ has joined #dri-devel
tobiasjakobi has joined #dri-devel
tobiasjakobi has quit []
MrCooper__ has quit [Ping timeout: 480 seconds]
xeon has quit [Ping timeout: 480 seconds]
Nasina has quit [Read error: Connection reset by peer]
<jenatali>
zmike: It's faster for me to click the UI buttons to trigger the pipelines than to pull and build locally, especially while I've got an LLVM build already going...
<zmike>
brutal
<zmike>
ok
<jenatali>
But yeah I'll click those buttons for you :)