srslypascal has quit [Remote host closed the connection]
srslypascal has joined #dri-devel
Danct12 is now known as Guest7636
Danct12 has joined #dri-devel
zzoon has joined #dri-devel
kzd has joined #dri-devel
mbrost has joined #dri-devel
srslypascal has quit [Ping timeout: 480 seconds]
srslypascal has joined #dri-devel
Zopolis4 has joined #dri-devel
srslypascal has quit [Quit: Leaving]
K`den has joined #dri-devel
Kayden has quit [Read error: Connection reset by peer]
bmodem has joined #dri-devel
K`den is now known as Kayden
srslypascal has joined #dri-devel
mbrost has quit [Ping timeout: 480 seconds]
bmodem has quit [Ping timeout: 480 seconds]
<airlied>
gfxstrand: uugh looks like might need to pipe the beta flags down unfortunately
<airlied>
let's see how my python is doing today
dviola has quit [Ping timeout: 480 seconds]
<airlied>
gfxstrand: okay I did the horrible thing, it's in 21806 now
fxkamd has quit []
chip_x has quit [Ping timeout: 480 seconds]
ngcortes has quit [Ping timeout: 480 seconds]
tzimmermann has joined #dri-devel
Moe_Icenowy has joined #dri-devel
MoeIcenowy has quit [Read error: Connection reset by peer]
bmodem has joined #dri-devel
itoral has joined #dri-devel
Zopolis4 has quit []
robobub has joined #dri-devel
fab has joined #dri-devel
sghuge has quit [Remote host closed the connection]
sghuge has joined #dri-devel
wind has joined #dri-devel
ngcortes has joined #dri-devel
bgs has quit [Remote host closed the connection]
yuq825 has joined #dri-devel
agd5f has joined #dri-devel
Haaninjo has joined #dri-devel
windleaves has quit [Ping timeout: 480 seconds]
agd5f_ has quit [Ping timeout: 480 seconds]
ngcortes has quit [Ping timeout: 480 seconds]
danvet has joined #dri-devel
kts has joined #dri-devel
rmckeever has quit [Quit: Leaving]
guru_ has joined #dri-devel
oneforall2 has quit [Ping timeout: 480 seconds]
fab has quit [Quit: fab]
<bbrezillon>
danvet: yes, that means it can fail asynchronously, and since we're talking about VM bind failures, it puts the VM in an inconsistent state, likely leading to DEVICE_LOST errors further down the road
frieder has joined #dri-devel
<airlied>
just writing your own pgtable management seems simpler :-P
<danvet>
bbrezillon, yeah that doesn't sound like the best idea
<danvet>
better maybe than kernel deadlock, but you shouldn't just trash apps as part of your kernel locking scheme :-)
<bbrezillon>
airlied: yeah, actually I've been considering that after you pointed it out a couple weeks back
<danvet>
oh is this "it's part of the iommu framework" fun?
<bbrezillon>
then had this discussion with robclark and robmur01 who seemed to think it was still preferable to use the iommu/io-pagetable logic...
pochu has quit [Ping timeout: 480 seconds]
zzoon has quit []
<bbrezillon>
and as robmur01 pointed out, the pre-allocation/reservation might make the situation even worse on memory-constrained systems, because queued VM_BIND jobs will be holding pages (most of the time, more pages than they actually need), while the system is struggling to find memory.
pochu has joined #dri-devel
Ahuj has joined #dri-devel
<bbrezillon>
that's not something that can be solved by duplicating the pagetable logic, it's inherent to the async VM_BIND model
jaganteki has quit [Remote host closed the connection]
kts has quit [Quit: Konversation terminated!]
mvlad has joined #dri-devel
MajorBiscuit has joined #dri-devel
kzd has quit [Quit: kzd]
agd5f_ has joined #dri-devel
hansg has joined #dri-devel
Zopolis4 has joined #dri-devel
fab has joined #dri-devel
agd5f has quit [Ping timeout: 480 seconds]
<bbrezillon>
robmur01: in your '1/512 * N * M' formula, aren't you omitting intermediate levels of the page table tree?
tursulin has joined #dri-devel
gawin has joined #dri-devel
kts has joined #dri-devel
vliaskov has joined #dri-devel
krushia has quit [Ping timeout: 480 seconds]
lynxeye has joined #dri-devel
jkrzyszt has joined #dri-devel
Major_Biscuit has joined #dri-devel
Leopold__ has quit [Remote host closed the connection]
MajorBiscuit has quit [Ping timeout: 480 seconds]
Leopold_ has joined #dri-devel
pcercuei has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
dtmrzgl has quit []
idr has quit [Remote host closed the connection]
idr has joined #dri-devel
dtmrzgl has joined #dri-devel
devilhorns has joined #dri-devel
gawin has quit [Ping timeout: 480 seconds]
gawin has joined #dri-devel
pochu has quit [Quit: Lost terminal]
Leopold___ has joined #dri-devel
pochu has joined #dri-devel
Leopold_ has quit [Ping timeout: 480 seconds]
MajorBiscuit has joined #dri-devel
Major_Biscuit has quit [Ping timeout: 480 seconds]
Haaninjo has quit [Quit: Ex-Chat]
rasterman has joined #dri-devel
smiles has quit [Ping timeout: 480 seconds]
kts has joined #dri-devel
jdavies has joined #dri-devel
jdavies has quit []
smiles has joined #dri-devel
smiles has quit [Ping timeout: 480 seconds]
windleaves has joined #dri-devel
jkrzyszt has quit [Remote host closed the connection]
paulk has joined #dri-devel
wind has quit [Ping timeout: 480 seconds]
wind has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
<robmur01>
bbrezillon: that would be the "somewhat more than", since I couldn't be bothered to quantify 1/512^2+1/512^3 ;)
kts has joined #dri-devel
jkrzyszt has joined #dri-devel
windleaves has quit [Ping timeout: 480 seconds]
bmodem has quit [Ping timeout: 480 seconds]
apinheiro has joined #dri-devel
JohnnyonFlame has joined #dri-devel
<gawin>
which drivers require llvm? maybe in longer run it'd be better to nuke these drivers from amber? llvmpipe, radeonsi and radv?
jaganteki has joined #dri-devel
<gawin>
(amber doesn't build with llvm16)
mohamexiety has joined #dri-devel
<ishitatsuyuki>
iirc there are also other drivers that uses llvm, but I don't really know much about anything other than AMD
<ishitatsuyuki>
for radv, you can disable llvm and still get it to build (the llvm backend and disassembler will be missing)
YuGiOhJCJ has joined #dri-devel
JohnnyonF has quit [Ping timeout: 480 seconds]
hansg has quit [Quit: Leaving]
kts has quit [Quit: Konversation terminated!]
YuGiOhJCJ has quit [Quit: YuGiOhJCJ]
Zopolis4 has quit []
Danct12 has quit [Quit: WeeChat 3.8]
jkrzyszt has quit [Remote host closed the connection]
jkrzyszt has joined #dri-devel
<MrCooper>
gawin: yeah, IIRC amber is about non-Gallium drivers, none of which use LLVM
smiles has joined #dri-devel
ice9 has joined #dri-devel
kts has joined #dri-devel
djbw has quit [Read error: Connection reset by peer]
mohamexiety has quit [Remote host closed the connection]
<mattst88>
I think amber also includes SWR, which uses llvm?
<mattst88>
at least insofar as SWR exists...
Leopold has joined #dri-devel
Leopold___ has quit [Remote host closed the connection]
jaganteki has quit [Remote host closed the connection]
itoral has quit [Remote host closed the connection]
bmodem has joined #dri-devel
<zmike>
mareko: are you sure about your notes for KHR-GL46.gpu_shader_fp64.fp64.state_query ? this test has no shaders
kzd has joined #dri-devel
agd5f has joined #dri-devel
fab has quit [Read error: Connection reset by peer]
fab has joined #dri-devel
bgs has joined #dri-devel
<zmike>
as for dEQP-GLES31.functional.geometry_shading.query.referenced_by_geometry_shader, are you expecting that the test should also check the fs or just that the test be structured in such a way that the uniform can't be promoted?
agd5f_ has quit [Ping timeout: 480 seconds]
zehortigoza has quit [Remote host closed the connection]
<robclark>
bbrezillon, airlied, robmur01: writing our own pgtable builder doesn't really solve the root problem.. it would still need to figure out how to have enough pages avail to do mappings in fence signaling path, so all it really accomplishes is moar codez.. both panfrost and msm skip the iommu framework and use io-pgtable directly so we aren't completely constrained by iommu framework
MrCooper has quit [Ping timeout: 480 seconds]
apinheiro has quit [Ping timeout: 480 seconds]
lemonzest has quit [Quit: WeeChat 3.6]
kts has quit [Quit: Konversation terminated!]
MrCooper has joined #dri-devel
mbrost has joined #dri-devel
bmodem has quit []
bmodem has joined #dri-devel
yuq825 has left #dri-devel [#dri-devel]
rsalvaterra has quit []
rsalvaterra has joined #dri-devel
mohamexiety has joined #dri-devel
<tomeu>
gfxstrand: I'm scratching my head over the code that vton generates for exp()
<tomeu>
my HW has a exp instruction, but I don't see a way of using it
mbrost_ has joined #dri-devel
mbrost has quit [Ping timeout: 480 seconds]
agd5f_ has joined #dri-devel
mbrost__ has joined #dri-devel
mbrost_ has quit [Ping timeout: 480 seconds]
jkrzyszt has quit [Remote host closed the connection]
kts has joined #dri-devel
<llyyr>
with vulkan-beta=true, I get build errors about missing prototypes in genX_video.c
<tomeu>
ah, I discovered native_exp()
<tomeu>
so nm
<daniels>
lol
agd5f has quit [Ping timeout: 480 seconds]
<daniels>
tomeu: yeah, was about to say exactly that
<tomeu>
frustratingly enough, native_exp() works as expected, but libclc's impl doesn't :/
<daniels>
src/compiler/spirv/vtn_opencl.c has the list of stuff we have to remap into libclc helpers, because the hardware is never precise enough to satisfy the CL spec
<daniels>
\o/
<karolherbst>
tomeu: how rude of libclc
<karolherbst>
why is it failing tho?
<karolherbst>
the libclc stuff _can_ be a bit scuffed and overengineered
lemonzest has joined #dri-devel
jkrzyszt has joined #dri-devel
<tomeu>
it is failing in a big way:
<tomeu>
Expecting 2.585710 (0x40257c44) with tolerance 0.000001 (3 ulps), but got 3235601.000000 (0x4a457c44)
<karolherbst>
though exp is really just a bunch of mad
mbrost__ has quit [Ping timeout: 480 seconds]
<tomeu>
hopefully it is just a bug in etnaviv
<karolherbst>
mhhh
Shibe has quit []
<karolherbst>
ehh..
<karolherbst>
there is also some subnormal stuff really funky
<tomeu>
daniels: the blob does use their exp() instruction for this, but I haven't ran the CTS yet
<karolherbst>
exp in hardware? insane
<tomeu>
well, maybe in FW, they seem to add a lot of stuff directly from the khronos specs
<karolherbst>
uhh
<karolherbst>
interesting
<karolherbst>
we don't really have a great way to select based on the driver, but maybe we need a callback sooner or later where drivers can select what they actually support in hw
<tomeu>
their first gen was heavily inspired on DX 1.0 ^_^
<karolherbst>
if it works with support for denormals then yeah,, should use the native stuff
<karolherbst>
but I also have to fix the denormal situation at some point
mbrost__ has joined #dri-devel
agd5f_ has quit []
fxkamd has joined #dri-devel
agd5f has joined #dri-devel
fab has quit [Quit: fab]
mbrost__ has quit [Ping timeout: 480 seconds]
agd5f_ has joined #dri-devel
agd5f has quit [Ping timeout: 480 seconds]
agd5f_ has quit [Ping timeout: 480 seconds]
agd5f has joined #dri-devel
aravind has quit [Ping timeout: 480 seconds]
MajorBiscuit has quit [Ping timeout: 480 seconds]
MajorBiscuit has joined #dri-devel
agd5f_ has joined #dri-devel
jkrzyszt has quit [Ping timeout: 480 seconds]
agd5f has quit [Ping timeout: 480 seconds]
agd5f has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
jkrzyszt has joined #dri-devel
agd5f_ has quit [Ping timeout: 480 seconds]
agd5f_ has joined #dri-devel
jkrzyszt has quit [Remote host closed the connection]
fab has joined #dri-devel
mohamexiety has quit [Quit: Konversation terminated!]
srslypascal is now known as Guest7707
srslypascal has joined #dri-devel
mbrost__ has joined #dri-devel
agd5f has quit [Ping timeout: 480 seconds]
Guest7707 has quit [Ping timeout: 480 seconds]
agd5f has joined #dri-devel
agd5f_ has quit [Ping timeout: 480 seconds]
agd5f_ has joined #dri-devel
agd5f has quit [Ping timeout: 480 seconds]
agd5f has joined #dri-devel
agd5f_ has quit [Ping timeout: 480 seconds]
agd5f_ has joined #dri-devel
<gfxstrand>
tomeu: Is it Native_exp2 or a base-10 exp or is it the one that needs full precision?
Duke`` has joined #dri-devel
<tomeu>
gfxstrand: native_exp()
<gfxstrand>
karolherbst, tomeu: If we want Native_exp in HW, we can add a nir_op_fexp
<karolherbst>
so uhm.. what's failing?
<gfxstrand>
We just need to make sure we also add opt_algebraic lowering for it. Should just be exp2() * M_LOG2E
<karolherbst>
ohhh...
<karolherbst>
wait
<gfxstrand>
Or we can make vtn call that instead of libclc
agd5f has quit [Ping timeout: 480 seconds]
<karolherbst>
right.. we use nir_fexp for exp
<gfxstrand>
Hrm... Looks like vtn already should be calling that.
agd5f has joined #dri-devel
<karolherbst>
nir_fexp = exp2(b * M_LOG2E)
<karolherbst>
ehh x
<karolherbst>
but mhh
<karolherbst>
tomeu: soo.. the code using exp2 fails?
<tomeu>
the kernel using exp() instead of native_exp() fails, but I have found the bug and is unrelated to anything exp
<karolherbst>
okay
<tomeu>
just a problem with encoding immediates
<karolherbst>
ahh
<karolherbst>
yeah, I was confused on what's the problem here
<karolherbst>
_but_ if you say you have fexp natively, we could skip the fexp to fexp2 + mul lowering
<karolherbst>
for native_exp that is
<tomeu>
I was just curious about what the plan was regarding using these native instructions when available
<karolherbst>
we just use whatever we have in nir
<tomeu>
as I will hopefully move to perf work soon
<dcbaker>
PSA: I am working on the next meas 23.0 stable release, the situation with the CI is slowing things down. I'll be cutting the release as soon as possible
smiles has joined #dri-devel
lemonzest has quit [Quit: WeeChat 3.6]
<eric_engestrom>
thanks for letting us know dcbaker :)
alanc has quit [Remote host closed the connection]
alanc has joined #dri-devel
smiles has quit [Ping timeout: 480 seconds]
mbrost has quit [Remote host closed the connection]
mbrost has joined #dri-devel
agneli_ has quit [Remote host closed the connection]
agneli has joined #dri-devel
rmckeever has joined #dri-devel
<daniels>
dcbaker: please bounce questions off us if we can help with CI
<dcbaker>
daniels: will do. anholt pointed me at the solution to my most pressing question
apinheiro has joined #dri-devel
agd5f has joined #dri-devel
mvlad has quit [Remote host closed the connection]
<zmike>
anyone have ideas on how I might wrangle driconf into having multiple internal driconfs? I want to set an entry on some drivers and not set it on others
mbrost has quit []
<jenatali>
Can't you already add per-driver entries?
<zmike>
this is for the internal driconf that the frontend sees
<zmike>
so it's already per-driver
<jenatali>
Right. Maybe I'm not understanding what you're looking for then?
<zmike>
I'm trying to enable glthread by default on some drivers (current behavior) and then disable it on other drivers (new behavior)
<jenatali>
Right, there's a driver name entry in driconf already so you can add per-driver entries
<zmike>
🤔
<zmike>
I thought that was just for the external driconf files
<jenatali>
There's plenty of <device driver="..."> entries in 00-mesa-defaults.conf
<zmike>
yeah but I think that's handled differently than the ones that are inlined into the loader
kzd_ has joined #dri-devel
<jenatali>
I don't see how it would be...
<zmike>
that's why I'm asking since I don't see any other drivers that have different sets of internal driconf values
<jenatali>
The frontend gets the driver name and passes it to the driconf parser, which either loads an XML file or uses the pre-parsed data
<jenatali>
Different sets of internal driconf values?
<jenatali>
I see plenty of glthread options for radensi only in the default conf file
<zmike>
I'm talking about the driconf_<driver>.h files in the driver dir
i-garrison has quit [Read error: Connection reset by peer]
<jenatali>
Looks like those are just #included into the driver-specific arrays in drm_helper.h?
<zmike>
yes
<jenatali>
I guess I'm still not following what you're trying to do :)
<zmike>
I'm trying to figure out how to have two sets of those that can be swapped between
<jenatali>
Based on what?
<zmike>
but it's hard
<zmike>
based on what the driver wants
<jenatali>
I see, like a callback?
<zmike>
not sure
<zmike>
wanted to ask here before I took out my chainsaw
kzd has quit [Ping timeout: 480 seconds]
<jenatali>
Looks like currently it's all handled before the screen is created
<zmike>
does seem that way
pendingchaos has quit [Ping timeout: 480 seconds]
<jenatali>
Yeah seems like you'd need a chainsaw, I don't see any existing extension point for dynamic driconf selection for gallium
<zmike>
rats
i-garrison has joined #dri-devel
Zopolis4 has joined #dri-devel
kzd has joined #dri-devel
kzd_ has quit [Ping timeout: 480 seconds]
pendingchaos has joined #dri-devel
Kayden has quit [Ping timeout: 480 seconds]
Kayden has joined #dri-devel
Haaninjo has joined #dri-devel
DPA has quit [Ping timeout: 480 seconds]
gouchi has joined #dri-devel
junaid has quit [Remote host closed the connection]
danvet has quit [Ping timeout: 480 seconds]
gouchi has quit [Quit: Quitte]
ybogdano has joined #dri-devel
tzimmermann has quit [Quit: Leaving]
ybogdano is now known as Guest7728
Guest7714 is now known as ybogdano
crabbedhaloablut has quit []
pixelcluster_ has joined #dri-devel
pixelcluster has quit [Ping timeout: 480 seconds]
crabbedhaloablut has joined #dri-devel
pixelcluster_ has quit []
idr has quit [Remote host closed the connection]
pixelcluster has joined #dri-devel
crabbedhaloablut has quit []
fxkamd has quit []
fxkamd has joined #dri-devel
crabbedhaloablut has joined #dri-devel
ice9 has joined #dri-devel
Duke`` has quit [Ping timeout: 480 seconds]
Guest7728 has quit [Ping timeout: 480 seconds]
mbrost has joined #dri-devel
adjtm has quit [Read error: Connection reset by peer]
adjtm has joined #dri-devel
hansg has joined #dri-devel
hansg has quit []
bgs has quit [Remote host closed the connection]
adjtm is now known as Guest7733
Guest7733 has quit [Read error: Connection reset by peer]
adjtm has joined #dri-devel
mbrost has quit [Ping timeout: 480 seconds]
anujp has joined #dri-devel
mbrost has joined #dri-devel
fxkamd has quit []
ice9 has quit [Ping timeout: 480 seconds]
DPA has joined #dri-devel
DPA- has joined #dri-devel
mbrost has quit [Ping timeout: 480 seconds]
hansg has joined #dri-devel
DPA has quit [Ping timeout: 480 seconds]
hansg has quit []
fab has quit [Quit: fab]
MrCooper_ has joined #dri-devel
MrCooper has quit [Ping timeout: 480 seconds]
vliaskov has quit [Remote host closed the connection]
smiles has joined #dri-devel
DPA has joined #dri-devel
DPA- has quit [Ping timeout: 480 seconds]
MrCooper_ has quit [Remote host closed the connection]
DPA has quit [Ping timeout: 480 seconds]
DPA has joined #dri-devel
Zopolis4 has quit []
MrCooper has joined #dri-devel
pcercuei has quit [Quit: dodo]
MrCooper has quit [Remote host closed the connection]