ChanServ changed the topic of #dri-devel to: <ajax> nothing involved with X should ever be unable to find a bar
alanc has quit [Remote host closed the connection]
alanc has joined #dri-devel
amarsh04 has quit []
u-amarsh04 has joined #dri-devel
asrivats has joined #dri-devel
olivial has quit [Read error: Connection reset by peer]
olivial has joined #dri-devel
a1batross has joined #dri-devel
epoch101 has quit []
The_Company has joined #dri-devel
Company has quit [Ping timeout: 480 seconds]
Nasina has quit [Read error: Connection reset by peer]
Nasina has joined #dri-devel
alane has quit []
alane has joined #dri-devel
guludo has quit [Ping timeout: 480 seconds]
yshui has quit [Ping timeout: 480 seconds]
yshui has joined #dri-devel
olivial has quit [Read error: Connection reset by peer]
ceumsl^ has quit [Ping timeout: 480 seconds]
olivial has joined #dri-devel
ceumsl^ has joined #dri-devel
feaneron has quit [Quit: feaneron]
alane_ has joined #dri-devel
alane has quit [Ping timeout: 480 seconds]
kasper93 has quit [Quit: kasper93]
kasper93 has joined #dri-devel
Daanct12 has joined #dri-devel
Nasina has quit [Ping timeout: 480 seconds]
sarnex has quit [Read error: No route to host]
sarnex has joined #dri-devel
nerdopolis has quit [Ping timeout: 480 seconds]
sarnex has quit [Read error: No route to host]
ceumsl^ has quit [Ping timeout: 480 seconds]
ceumsl^ has joined #dri-devel
sarnex has joined #dri-devel
kzd has quit [Ping timeout: 480 seconds]
Nasina has joined #dri-devel
sguddati has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
davispuh has quit [Ping timeout: 480 seconds]
Nasina has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
gnuiyl has quit [Remote host closed the connection]
olivial has quit [Read error: Connection reset by peer]
sguddati has quit []
olivial has joined #dri-devel
oneforall2 has quit [Ping timeout: 480 seconds]
oneforall2 has joined #dri-devel
oneforall2 has quit [Remote host closed the connection]
oneforall2 has joined #dri-devel
kzd has joined #dri-devel
glennk has joined #dri-devel
ceumsl^ has quit [Ping timeout: 480 seconds]
The_Company has quit []
Daanct12 has quit [Quit: WeeChat 4.6.1]
Daanct12 has joined #dri-devel
riteo_ has quit [Remote host closed the connection]
Nasina has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
Nasina has joined #dri-devel
fab has joined #dri-devel
gnuiyl has joined #dri-devel
Duke`` has joined #dri-devel
jsa1 has joined #dri-devel
dolphin has joined #dri-devel
itoral has joined #dri-devel
alarumbe has quit [Quit: ZNC 1.8.2+deb3.1+deb12u1 - https://znc.in]
riteo has joined #dri-devel
tzimmermann has joined #dri-devel
TMM has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]
TMM has joined #dri-devel
Duke`` has quit [Ping timeout: 480 seconds]
i-garrison has quit []
i-garrison has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
Nasina has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
fab has quit [Ping timeout: 480 seconds]
Nasina has joined #dri-devel
etehtsea has joined #dri-devel
coldfeet has joined #dri-devel
kzd has quit [Ping timeout: 480 seconds]
olivial has quit [Read error: Connection reset by peer]
olivial has joined #dri-devel
sima has joined #dri-devel
rasterman has joined #dri-devel
kts has joined #dri-devel
gnuiyl has quit [Remote host closed the connection]
asrivats has quit [Read error: Connection reset by peer]
asrivats has joined #dri-devel
gnuiyl has joined #dri-devel
mehdi-djait3397165695212282475 has joined #dri-devel
fab has joined #dri-devel
sghuge has quit [Remote host closed the connection]
sghuge has joined #dri-devel
fab has quit [Remote host closed the connection]
vliaskov has joined #dri-devel
fab has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
phasta has joined #dri-devel
bolson has quit [Ping timeout: 480 seconds]
sima has quit [Remote host closed the connection]
lynxeye has joined #dri-devel
<pq> melissawen, zamundaaa[m], re: missing kernel logs; what about the thing that the DRM flight-recorder idea became? The problem with that is integration, because people explicitly did not want a compositor to have access to that log.
jkrzyszt has joined #dri-devel
coldfeet has quit [Quit: Lost terminal]
jfalempe has quit [Quit: jfalempe]
jfalempe has joined #dri-devel
djbw has quit [Ping timeout: 480 seconds]
<dwt> Which thing is that? That sounds handy
<pq> I'm not sure what it's called nowadays, would need to dig. I think it manifests through the ftrace framework? If it landed yet.
<emersion> yeah, if it's privileged then it's a lot less useful...
<emersion> a hack with dmesg is enough in that case
tsoy7711[m] has joined #dri-devel
tsoy7711[m] has left #dri-devel [#dri-devel]
alarumbe has joined #dri-devel
coldfeet has joined #dri-devel
frieder has joined #dri-devel
yshui has quit [Ping timeout: 480 seconds]
yshui has joined #dri-devel
anholt_ has joined #dri-devel
epoch101 has joined #dri-devel
anholt has quit [Ping timeout: 480 seconds]
phasta has quit [Ping timeout: 480 seconds]
<Lynne> zzoon: in case you're back, could you take a look at the hevc samples? also, https://files.lynne.ee/av1_intel_broken2.ivf and https://files.lynne.ee/av1_intel_broken.ivf
<Lynne> broken2 causes a device lost on intel
<Lynne> dj-death: also ping about the descriptor buffer issue
epoch101 has quit []
<glehmann> has anyone ever written a reassociation NIR pass? something that can eliminate duplicate additions like this: a + (b + c), a + (b + d) -> (a + b) + c, (a + b) + d
epoch101 has joined #dri-devel
<glehmann> alyssa: ^ iirc you were working on something in that area for preambles
epoch101 has quit []
epoch101 has joined #dri-devel
<dj-death> Lynne: still no time to look at it atm
<Lynne> sure, whenever you find time
<dj-death> I hope this week
phasta has joined #dri-devel
epoch101 has quit []
epoch101 has joined #dri-devel
pa has quit [Ping timeout: 480 seconds]
Nasina has quit [Read error: Connection reset by peer]
Nasina has joined #dri-devel
itoral has quit [Remote host closed the connection]
rsalvaterra_ has joined #dri-devel
rsalvaterra_ is now known as rsalvaterra
sima has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
Nasina has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
<zzoon> Lynne: ok.. will look into them. is that av1 or hevc?
<Lynne> both samples I linked are av1
<zzoon> ok
<Lynne> the hevc sample is https://files.lynne.ee/testsamples/hevc_scaling_list4.mkv if you need a link again
<zzoon> ah right
chewitt has joined #dri-devel
Company has joined #dri-devel
etehtsea has quit [Remote host closed the connection]
guludo has joined #dri-devel
etehtsea has joined #dri-devel
Nasina has joined #dri-devel
calebccff has quit [Quit: ZNC 1.8.2+deb3.1+deb12u1 - https://znc.in]
Nasina has quit [Read error: Connection reset by peer]
coldfeet has quit [Quit: leaving]
kcxt has joined #dri-devel
coldfeet has joined #dri-devel
nerdopolis has joined #dri-devel
kcxt has quit []
kcxt has joined #dri-devel
pepp has joined #dri-devel
feaneron has joined #dri-devel
davispuh has joined #dri-devel
riteo has quit [Ping timeout: 480 seconds]
alarumbe has quit [Quit: ZNC 1.8.2+deb3.1+deb12u1 - https://znc.in]
<pq> in GLSL 1.00 ES, if I have a uniform struct variable; if one field of the struct is active, does it imply that all fields of the struct are active even if not used?
mripard has joined #dri-devel
<bbrezillon> tzimmermann: looks like 266ab86ac1f5 ("drm/panthor: Test for imported buffers with drm_gem_is_imported()") is regressing panthor
<bbrezillon> not sure why yet
riteo has joined #dri-devel
<tzimmermann> bbrezillon, see the discussion on dri-devel
<tzimmermann> the test in drm_gem_is_imported os slightly incorrect
<bbrezillon> ah, so that's a known issue
<tzimmermann> see "drm/gem: Internally test import_attach for imported objects". additional feedback is welcome
Nasina has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
<bbrezillon> I'll have a look. Thanks for the pointer
<alyssa> glehmann: I started trying, it's challenging though
riteo_ has joined #dri-devel
riteo has quit [Ping timeout: 480 seconds]
<sima> tzimmermann, I guess I'll reply there too since I'm partially responsible for that mess :-/
TMM has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]
TMM has joined #dri-devel
<glehmann> alyssa: okay, that looks fundamentally different from what I want I think. basically, I want to reassociate the adds in shaders like this to get vectorized stores in the end: https://gitlab.freedesktop.org/freedesktop/snippets/-/snippets/7836
<zmike> eric_engestrom: I am eagerly awaiting the branchpoint tomorrow
<alyssa> glehmann: yeah, reassoc is just a big rats nest of heuristics that aren't well documented anywhere
<alyssa> gcc's pass basically just says "we copied llvm"
<alyssa> ..
<alyssa> `f2e4m3fn` wtf?
<glehmann> float 2 8bit float format, I'm not married to the name
jsa1 has quit [Ping timeout: 480 seconds]
<glehmann> the issue is that there are at least 4 competing 8bit float formats, so I wanted to be precise
riteo_ has quit [Ping timeout: 480 seconds]
<alyssa> i still have no idea what that means
<alyssa> oh. exponent-4 mantissa-3. ok.
<glehmann> yes and fn for finite
mehdi-djait3397165695212282475 has quit []
<alyssa> agx supports immediate float srcs with exp-3 mant-4
mehdi-djait3397165695212282475 has joined #dri-devel
<pendingchaos> I don't think the load/store vectorizer requires addition reassociation
<alyssa> competint indeed
<pendingchaos> it looks through all the additions and obtains a constant offset and a sorted list of ssa defs and their multipliers
<glehmann> pendingchaos: do you have an idea why it doesn't work here then?
feaneron has quit [Read error: Connection reset by peer]
<pendingchaos> no
<pendingchaos> I don't expect all 3 to be vectorized (hw has no 3-byte stores), but I think the first two are supposed to be
jsa1 has joined #dri-devel
dolphin has quit [Quit: Leaving]
<glehmann> these were 8 8bit stores, and for some reason we and up with one 32bit, 2 8bit and one 16bit store
<glehmann> instead of a single store
RSpliet has quit [Quit: Bye bye man, bye bye]
Caterpillar has quit [Quit: Konversation terminated!]
Caterpillar has joined #dri-devel
riteo has joined #dri-devel
<alyssa> glehmann: possibly we're getting stuck in a local optimum?
<alyssa> wait no that shouldn't apply
<alyssa> the middle 2 stores should indeed be vectorizing :/
<alyssa> oh. i do see the reassocation issue now. ooooof.
<alyssa> spicy.
riteo_ has joined #dri-devel
<alyssa> but indeed it looks like we should handle this ..
riteo has quit [Ping timeout: 480 seconds]
kzd has joined #dri-devel
fab has quit [Quit: fab]
Nasina has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
RSpliet has joined #dri-devel
Nasina has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
phasta has quit [Quit: Leaving]
megastatus has joined #dri-devel
mripard has quit [Quit: WeeChat 4.6.0]
mripard has joined #dri-devel
mehdi-djait3397165695212282475 has quit [Ping timeout: 480 seconds]
<dj-death> Lynne: what do I need to compile rc_vk_test?
<dj-death> Lynne: looks like there is a ffmpeg dependency
<dj-death> Lynne: but meson is not requiring it
rasterman has quit [Quit: Gettin' stinky!]
Nasina has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
<dj-death> Lynne: got it to build with master of ffmpeg
<dj-death> Lynne: but now it's crashing in vulkan.c
<dj-death> Lynne: 2914 s->extensions = ff_vk_extensions_to_mask(s->hwctx->enabled_dev_extensions,
<dj-death> s->hwctx = 0xb
hansg has joined #dri-devel
<eric_engestrom> zmike: haha, any particular reason?
<zmike> so much code delete
<eric_engestrom> right, indeed
<eric_engestrom> 🪓
haaninjo has joined #dri-devel
Daanct12 has quit [Quit: WeeChat 4.6.1]
bolson has joined #dri-devel
<eric_engestrom> zmike: you can already post the MRs now if you want, so that they get reviewed and are ready to merge the second 25.1 is branched :P
<zmike> clover deletion has been up for literal years already
mripard has quit [Read error: Connection reset by peer]
<daniels> usually people are asking for more rather than less time before the branchpoint
<zmike> we live in troubled times
mripard has joined #dri-devel
Nasina has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
<eric_engestrom> iirc the clover mr has a couple of missing changes to be good to go (deleting pipe-loader is the one I remember off the top of my head)
<zmike> I thought that was a followup
<daniels> yeah
<eric_engestrom> I don't like leaving dead code around, but sure
<zmike> karolherbst is planning to delete a ton of other gallium stuff too
<zmike> so it won't be left for very long
<eric_engestrom> ack
Nasina has joined #dri-devel
<llyyr> delete more code
Nasina has quit [Read error: Connection reset by peer]
<alyssa> eric_engestrom: clover is the dead code ;)
dsimic is now known as Guest13710
dsimic has joined #dri-devel
Nasina has joined #dri-devel
Guest13710 has quit [Ping timeout: 480 seconds]
Nasina has quit [Read error: Connection reset by peer]
pa has joined #dri-devel
<jenatali> glehmann: If it helps, D3D is adopting that format as F8_E4M3 (per https://github.com/microsoft/hlsl-specs/blob/main/proposals/0029-cooperative-vector.md)
<glehmann> jenatali: what will d3d require for larger f32 -> e4m3 conversions? max finite value or NaN?
<jenatali> > float to float conversion is implementation dependent and preserves the value as accurately as possible
<jenatali> > /// XXX TODO: Error handling for illegal conversions.
<jenatali> :)
djbw has joined #dri-devel
Nasina has joined #dri-devel
<glehmann> also E4M3 and E5M2 are really not precise enough, there are two formats in the wild for each of them
Nasina has quit [Read error: Connection reset by peer]
<jenatali> Oh? News to me but I'm not really in this space (besides helping with the WARP impl of that spec)
<jenatali> Got a link or something I can look at?
<glehmann> one E4M3 format has 0x80 as NaN, the other has 0xff/0x7f. The first format also uses a different bias for the exponent
<glehmann> https://asawicki.info/articles/fp8_tables.php has all of the ones I know
<jenatali> Thanks!
<glehmann> rdna4 supports all of them, but the kernel driver decides which ones and in practice it's FLOAT8E4M3FN and FLOAT8E5M2. CDNA3 only has FLOAT8E4M3FNUZ and FLOAT8E5M2FNUZ
<dj-death> people know that nir_lower_io() is generating incorrect NIR ?
<dj-death> like it's adding load_output in vertex shaders, but then the divergence analysis thinks it's not allowed
jsa1 has quit [Ping timeout: 480 seconds]
<pendingchaos> dj-death: divergence analysis can fail for valid nir if it's not supported by the pass
<pendingchaos> VS output loads can be removed by using nir_lower_io_to_temporaries(, , true, false) sometime before nir_lower_io
<dj-death> pendingchaos: I guess my problem appears with I run with NIR_DEBUG
<dj-death> pendingchaos: but thanks, I'll try to call that pass after lower_io to make sure it cleans things up
<eric_engestrom> alyssa: I guess it's run-time dead code vs compile-time dead code (:
<pendingchaos> NIR_DEBUG=extended_validation? I think that option broke a bit after divergence was made metadata
<pendingchaos> you can remove nir_metadata_divergence from the nir_metadata_require() in nir_metadata_require_all()
Duke`` has joined #dri-devel
<glehmann> jenatali: will d3d not support coop matrix, and instead only coop vector? I know at some point coop matrix was planned for sm6.8 but cancelled/delayed
<jenatali> Yeah matrix was planned for 6.8. Folks are trying to get it back on the roadmap, unclear if that'll be 6.9, 6.10, or 7.0 at this point though
<glehmann> speaking of 7.0, do you know yet if it's structured or unstructured spirv?
<jenatali> I sincerely hope it's structured
<jenatali> I've asked that question myself and I don't think I've gotten a definitive answer but I think people are trending towards structured
<glehmann> I hope so too :D
<jenatali> Thanks for pointing that out :)
tzimmermann has quit [Quit: Leaving]
fab has joined #dri-devel
Nasina has joined #dri-devel
Nasina has quit [Read error: Connection reset by peer]
tobiasjakobi has joined #dri-devel
airlied_ has joined #dri-devel
tobiasjakobi has quit []
airlied has quit [Ping timeout: 480 seconds]
Nasina has joined #dri-devel
rasterman has joined #dri-devel
<dj-death> pendingchaos: not helping unfortunately
<jenatali> dj-death: He said before lower_io, not after
<dj-death> jenatali: yeah I tried that after rereading ;)
<dj-death> jenatali: now I'm left with copy_deref
<jenatali> nir_lower_copies?
<dj-death> which lower_locals_to_regs_block complains about
<jenatali> Er, nir_lower_var_copies?
<dj-death> nope
<dj-death> because that adds back the load_output
<dj-death> which again the divergence pass will complain about
Nasina has quit [Read error: Connection reset by peer]
<jenatali> It shouldn't be copying from the output, only to it
Nasina has joined #dri-devel
<dj-death> guessing I need to call it wayyyy before
<dj-death> yeah that works
<dj-death> really early
rsalvaterra_ has joined #dri-devel
rsalvaterra_ is now known as rsalvaterra
megastatus has quit [Remote host closed the connection]
megastatus has joined #dri-devel
feaneron has joined #dri-devel
jsa1 has joined #dri-devel
FireBurn has quit [Quit: Konversation terminated!]
alexyanov has joined #dri-devel
FireBurn has joined #dri-devel
<FireBurn> Hey is there something up with the ssh side of gitlab?
<pendingchaos> use ssh.gitlab.freedesktop.org
ybogdano has quit [Quit: The Lounge - https://thelounge.chat]
<FireBurn> Ta
ybogdano has joined #dri-devel
Karyon has quit [Ping timeout: 480 seconds]
macromorgan has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]
lynxeye has quit [Quit: Leaving.]
macromorgan has joined #dri-devel
Nasina has quit [Remote host closed the connection]
alexyanov has quit [Remote host closed the connection]
Nasina has joined #dri-devel
frieder has quit [Remote host closed the connection]
olivial has quit [Read error: Connection reset by peer]
olivial has joined #dri-devel
Karyon has joined #dri-devel
Nasina has quit [Ping timeout: 480 seconds]
alexyanov has joined #dri-devel
jkrzyszt has quit [Quit: Konversation terminated!]
alexyanov has quit []
sarnex has quit [Ping timeout: 480 seconds]
<Lynne> dj-death: does that happen with git master of the test program?
<Lynne> also, which ffmpeg version do you have
<Lynne> there's definitely a dependency on ffmpeg in the meson code, so I'm confused
rasterman has quit [Quit: Gettin' stinky!]
<dj-death> Lynne: I took master of ffmpeg
<dj-death> Lynne: and I think master of the test program too
<Lynne> I did do a few updates to it since I linked it last week
<dj-death> Lynne: apparently the ffmpeg from the system wasn't enough
<dj-death> I'll try again tomorrow
fab has quit [Quit: fab]
guludo has quit [Quit: WeeChat 4.6.1]
guludo has joined #dri-devel
nashpa has quit [Ping timeout: 480 seconds]
epoch101 has quit []
dliviu has joined #dri-devel
gabertron has quit [Quit: http://quassel-irc.org - Chat comfortably. Anywhere.]
gouchi has joined #dri-devel
gabertron has joined #dri-devel
jsa1 has quit [Ping timeout: 480 seconds]
kts has joined #dri-devel
gouchi has quit [Quit: Quitte]
dliviu has quit [Ping timeout: 480 seconds]
hansg has quit [Quit: Leaving]
lassebq has joined #dri-devel
coldfeet has quit [Quit: Lost terminal]
lassebq has quit []
kasper93_ has joined #dri-devel
kasper93 is now known as Guest13727
kasper93_ is now known as kasper93
dliviu has joined #dri-devel
Guest13727 has quit [Ping timeout: 480 seconds]
kasper93 has quit [Ping timeout: 480 seconds]
kasper93 has joined #dri-devel
megastatus has quit [Remote host closed the connection]
kts has quit [Quit: Konversation terminated!]
sima has quit [Ping timeout: 480 seconds]
Nasina has joined #dri-devel
Duke`` has quit [Ping timeout: 480 seconds]
rasterman has joined #dri-devel
Caterpillar has quit [Quit: Konversation terminated!]
Sid127 has quit [Quit: ZNC - https://znc.in]
caitcatdev has quit []
Sid127 has joined #dri-devel
caitcatdev has joined #dri-devel
jhugo4 has joined #dri-devel
lumag has quit [Remote host closed the connection]
ngcortes has quit [Remote host closed the connection]
sgerhold2 has joined #dri-devel
sgerhold has quit [Read error: Connection reset by peer]
lumag has joined #dri-devel
ngcortes has joined #dri-devel
<jenatali> Is there a nir pass that can prune a loop that has no side effects?
jhugo has quit [Ping timeout: 480 seconds]
<pendingchaos> nir_opt_dead_cf
<jenatali> That's not pruning it for me
<jenatali> It's a complicated loop that culminates in conditionally breaking, but at no point does the loop ever have any observable side effects besides spending time
sarnex has joined #dri-devel
<jenatali> No storage buffer/image writes or any other kind of data leaving the loop, so it's effectively dead
sarnex has quit []
<anholt_> what's keeping dce from cleaning up the ops in the loop?
sarnex has joined #dri-devel
guludo has quit [Ping timeout: 480 seconds]
<jenatali> At the "end" of a long chain of instructions is a comparison which branches to a conditional break
<pendingchaos> might be used as part of the break condition, I think nir_opt_dead_cf should handle that though
<pendingchaos> it looks like non-reorderable ssbo/shared/global/output loads prevent the loop from being dce'd?
<anholt_> oh, right.
sarnex has quit [Read error: Connection reset by peer]
haaninjo has quit [Quit: Ex-Chat]
sarnex has joined #dri-devel
Nasina has quit [Ping timeout: 480 seconds]
<jenatali> Ah... I see
<jenatali> This is my horrible hacky TCS lowering where I have to split a TCS into two functions, one that handles all patch outputs and a different one that handles control points. I've got a TCS with no control point outputs so I would expect to end up with an empty function, but instead it's got a massive loop in it
JRepin has quit [Remote host closed the connection]
alarumbe has joined #dri-devel
JRepin has joined #dri-devel
alarumbe has quit []
glennk has quit [Ping timeout: 480 seconds]
rasterman has quit [Quit: Gettin' stinky!]
<jenatali> Yeah ok forcing load_output to undef apparently fixes all my problems. Still a horrible hacky solution but I don't have many other options
Nasina has joined #dri-devel
Dark-Show has joined #dri-devel
vliaskov has quit [Ping timeout: 480 seconds]
alarumbe has joined #dri-devel
kugel has joined #dri-devel
ity has quit [Remote host closed the connection]
kugel_ has quit [Ping timeout: 480 seconds]
ity has joined #dri-devel
RAOF has quit [Read error: Connection reset by peer]
sarnex has quit [Ping timeout: 480 seconds]
airlied_ is now known as airlied