olivial has quit [Read error: Connection reset by peer]
olivial has joined #dri-devel
epoch101 has quit [Ping timeout: 480 seconds]
fab has joined #dri-devel
epoch101 has joined #dri-devel
Duke`` has joined #dri-devel
Duke`` has quit [Ping timeout: 480 seconds]
Andre[m] has left #dri-devel [#dri-devel]
sima has joined #dri-devel
azerov has quit [Quit: Gateway shutdown]
azerov has joined #dri-devel
epoch101_ has joined #dri-devel
epoch101 has quit [Ping timeout: 480 seconds]
phasta has joined #dri-devel
jsa1 has joined #dri-devel
bolson has quit [Ping timeout: 480 seconds]
fab has quit [Quit: fab]
blaztinn has quit [Remote host closed the connection]
blaztinn has joined #dri-devel
FANTOM has quit [Ping timeout: 480 seconds]
FANTOM has joined #dri-devel
epoch101_ has quit [Ping timeout: 480 seconds]
sghuge has quit [Remote host closed the connection]
sghuge has joined #dri-devel
fab has joined #dri-devel
fab has quit []
fab has joined #dri-devel
kzd has quit [Ping timeout: 480 seconds]
fab is now known as Guest26243
kts has joined #dri-devel
mwk_ has quit [Ping timeout: 480 seconds]
jkrzyszt has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
kts has joined #dri-devel
tzimmermann has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
kts has joined #dri-devel
kts has quit []
rasterman has joined #dri-devel
Mangix has quit [Ping timeout: 480 seconds]
alarumbe has joined #dri-devel
djgl has joined #dri-devel
pcercuei has joined #dri-devel
<djgl>
Hi, I'd like to make a merge request for a Mesa fix but can't fork the repo on the Freedesktop Gitlab. Who do I have to contact to raise the limit for personal repos above 0?
mwk has joined #dri-devel
<djgl>
never mind, found the answer
_whitelogger has joined #dri-devel
clamor has quit [Read error: Connection reset by peer]
<mlankhorst>
Should drm_mode_createblob_ioctl() allocate memory with __GFP_ACCOUNT ?
<mlankhorst>
Seems a bit of an oversight
sguddati has joined #dri-devel
ahadi has joined #dri-devel
<daniels>
mlankhorst: yeah I wonder which idiot did that
<daniels>
mlankhorst: so if I'm reading this right, that causes the memory to be accounted to the memcg of the current task?
<daniels>
if so, feel free to send the trivial addition with my Rb and also a Fixes all the way back to ... hmm, must've been 2015 when we were doing i915 atomic bringup? yikes.
sguddati has quit [Ping timeout: 480 seconds]
nerdopolis has joined #dri-devel
guludo has quit [Ping timeout: 480 seconds]
alatiera has joined #dri-devel
guludo has joined #dri-devel
<mlankhorst>
Lets just blame robclark, I mean r-b is basically rob already.
dsimic is now known as Guest26262
dsimic has joined #dri-devel
Guest26262 has quit [Ping timeout: 480 seconds]
kts has joined #dri-devel
<vsyrjala>
i think createblob predates __GFP_ACCOUNT
dviola has quit [Read error: Connection reset by peer]
<jenatali>
glehmann: not offhand, I can take a look when I get to the office in a few hours
rgallaispou has joined #dri-devel
amarsh04 has quit []
<mlankhorst>
vsyrjala: then *digs* alloc_kmem_pages() should have been used
feaneron has quit [Remote host closed the connection]
feaneron has joined #dri-devel
epoch101 has joined #dri-devel
<zmike>
nowrep: !
u-amarsh04 has joined #dri-devel
sguddati has joined #dri-devel
macromorgan has quit [Ping timeout: 480 seconds]
Guest26243 has quit []
<zmike>
what does e.g., PIPE_FORMAT_R32_USCALED correspond to in GL terms? I can't find anything related to this in the specs
<Hazematman>
zmike: isn't it for the vertex formats? like glVertexAttribPointer with GL_UNSIGNED_INT and 1 component
<zmike>
wouldn't that be R32_UINT ?
epoch101_ has joined #dri-devel
<Hazematman>
not an expert on this but if you pass `normalized` in I think it uses USCALED instead of UINT
<zmike>
then it's R32_UNORM
<glehmann>
USCALED is UINT, but convert to float
<zmike>
oh
<zmike>
huh
<zmike>
who did this to me
epoch101 has quit [Ping timeout: 480 seconds]
<glehmann>
e.g. R8_USCALED stores 0.0f, 1.0f, 2.0f,..., 255.0f
<glehmann>
32bit USCALED is weird because you can't actually represent that larger integers as float
<glehmann>
I guess that's why it's not a thing in Vulkan
The_Company has quit []
Company has joined #dri-devel
<Company>
you have that problem with 16bit scaled vs float anyway
<zmike>
right...
<Company>
to me it looks like it was added so you can use int and float textures with the same shader
fab has joined #dri-devel
kzd has joined #dri-devel
YuGiOhJCJ has quit []
epoch101_ has quit [Ping timeout: 480 seconds]
haaninjo has joined #dri-devel
epoch101 has joined #dri-devel
clever has quit [Remote host closed the connection]
<glehmann>
Company: what do you mean? pretty sure all 16bit integers are exactly representable as a 32bit float
<Company>
glehmann: 16bit float
<glehmann>
ah well but image/texture reads in Vk always return a 32bit float
<Company>
true
<Company>
that does indeed make sense
pH5 has quit [Remote host closed the connection]
luc64627490 has quit [Ping timeout: 480 seconds]
phasta has quit [Quit: WeeChat 4.6.2]
clever has joined #dri-devel
kts has joined #dri-devel
epoch101 has quit [Ping timeout: 480 seconds]
Duke`` has joined #dri-devel
<agd5f>
anyone else having problems with the anubis stuff on kernel.org over the last few days? seems to retry like 50-60 times before it decides it's happy
ahadi has quit [Ping timeout: 480 seconds]
haaninjo has quit [Quit: Ex-Chat]
surajkandpal has joined #dri-devel
<dwfreed>
agd5f: loading git.kernel.org worked fine here, I got anubis, and it solved in about a second or so
<jenatali>
Ugh this new PC hadn't built the CTS yet
epoch101 has joined #dri-devel
surajkandpal has quit [Ping timeout: 480 seconds]
<jenatali>
glehmann: Pushed you a fixup. Your new wave size bits are set all the time where previously an incoming wave size was only valid to specify for compute. Emitting the metadata nodes was scoped to only happen for compute shaders, but filling out the psv0 wave sizes wasn't scoped that way
<jenatali>
I also learned that apparently new versions of the dxil validator print out really nice messages on mismatches so we should probably bump that in our container
<glehmann>
thanks, I didn't think about that at all
epoch101 has quit [Ping timeout: 480 seconds]
fab has quit [Quit: fab]
sally has quit []
fab has joined #dri-devel
sally has joined #dri-devel
sally has quit []
sally has joined #dri-devel
sally has quit [Remote host closed the connection]
sally has joined #dri-devel
sally has quit [Remote host closed the connection]
sally has joined #dri-devel
sally has quit [Remote host closed the connection]
sally has joined #dri-devel
sally has quit []
sally has joined #dri-devel
sguddati has quit [Ping timeout: 480 seconds]
oneforall2 has quit [Ping timeout: 480 seconds]
<K900>
Hey folks, does anyone know if there's an ETA for a new Vulkan SDK release
sally has quit []
<K900>
We (NixOS) are trying to upgrade to LLVM 21 and libclc does not build with the latest stable tag of spirv-headers
sally has joined #dri-devel
<K900>
(and possibly other things)
sally has quit []
sally has joined #dri-devel
kts has quit [Ping timeout: 480 seconds]
kts has joined #dri-devel
<agd5f>
dwfreed, weird. still takes 50-60 rounds here
oneforall2 has joined #dri-devel
<dwfreed>
agd5f: to be fair, I do not visit git.kernel.org frequently; perhaps anubis has decided you look like an AI because you go there a lot?
nerdopolis has quit [Read error: Connection reset by peer]
nerdopolis has joined #dri-devel
Company has quit [Quit: Leaving]
epoch101 has joined #dri-devel
kts has quit [Quit: Konversation terminated!]
jkrzyszt has quit [Quit: Konversation terminated!]
npmania has quit [Remote host closed the connection]
npmania has joined #dri-devel
tzimmermann has quit [Quit: Leaving]
norris_ has left #dri-devel [#dri-devel]
norris has joined #dri-devel
<sima>
airlied, I was out all day so didn't get around to processing the PR request from tzimmermann, I guess I'll look at it tomorrow if it's still pending ...
<sima>
daniels, mlankhorst there's probably a few more we should __GFP_ACCOUNT even if blob is the obvious ones
<sima>
essentially all the userspace-created objects really
olivial has quit [Read error: Connection reset by peer]
olivial has joined #dri-devel
clamor has joined #dri-devel
jsa1 has joined #dri-devel
FergusL has joined #dri-devel
FergusL has quit []
haaninjo has joined #dri-devel
FergusL has joined #dri-devel
Kayden has quit [Quit: -> JF]
clamor has quit [Read error: Connection reset by peer]
sinatosk has quit [Ping timeout: 480 seconds]
sinatosk has joined #dri-devel
Kayden has joined #dri-devel
<robclark>
karolherbst: so looking at `./images/clCopyImage/test_cl_copy_images small_images debug_trace 1Darray` fails (specifically just 1Darray fails!).. if I hack the test to read back the src image instead, it fails with identical results (ie. read back from src and dst img are identical).. so somehow we aren't managing to round trip 1Darray image upload+download without scrambling things somewhere.. but not sure which side of that
<robclark>
is wrong
<karolherbst>
mhhhhhh
<karolherbst>
this is interesting, because I've also seen those to fail on intel xe GPUs
<karolherbst>
and also only 1Darray failing
<karolherbst>
I wouldn't be entirely surprised if something is wrong there with the dimensions, but I couldn't figure out what exactly. It's even weirder that it works on other drivers
<robclark>
zink passes, but ends up using row_pitch/slice_pitch=1 (or rather, tightly packed rather than hw layout.. it seems to be doing a staging blit)
<karolherbst>
mhhh
<robclark>
but for 1x2 1d img array, the hw layout is row_pitch=64, slice_pitch=4096.. so I guess somewhere that isn't handled properly.. but I'm a bit lost in all the different copies rusticl has to do ;-)
<karolherbst>
well at least it's less of a disaster as it used to be
<karolherbst>
image to image copies should just call into resource_copy_region
<karolherbst>
_but_
<karolherbst>
wouldn't surprise me if mapping the images has a bug somewhere?
<robclark>
I'm a bit suspecting that it _isn
<karolherbst>
robclark: is it also broken at Scanline 1 for you?
<robclark>
I'm a bit suspecting that it _isn't_ the img->img copy
<robclark>
but either the READ or WRITE clEnqueueMapImage()
<karolherbst>
let's see what this test is doing...
<robclark>
I guess it would be useful if there is some other test that could narrow down which
<karolherbst>
okay.. create + map + write + unmap for each image, then a copy and then a map + read
<robclark>
right create_image() is where the "upload" happens
<karolherbst>
mhhh
<karolherbst>
could modify the test to use CL_MEM_COPY_HOST_PTR instead...
sima has quit [Ping timeout: 480 seconds]
<karolherbst>
let me try that...
Jeremy_Rand_Talos has quit [Remote host closed the connection]
<karolherbst>
but the region there isn't adjusted for the image 1D array stuff...
<robclark>
hmm, let's see
<robclark>
karolherbst: heh, yeah it does seem to fix it
<karolherbst>
mhh annoying, so I guess there aren't many drivers who return different pitches for 1Darray images
<karolherbst>
*which
<karolherbst>
1Darrays are weird, because the layer is selected in the 2nd coord in CL, but 3rd coord in gallium
<robclark>
ahh
<robclark>
maybe some drivers are not directly exposing the hw img, but do a blit to/from tightly packed?
<karolherbst>
possibly
<karolherbst>
it's just weird that with pre Xe iris GPUs it works
rgallaispou has quit [Ping timeout: 480 seconds]
<karolherbst>
but maybe it's different enough
<robclark>
idk enough about layout on intel things to explain that, but maybe some luck
<karolherbst>
just have to figure out where to swap the cords so it doesn't end up unmaintainable ...
<karolherbst>
.....
<karolherbst>
really...
<karolherbst>
robclark: Image::write does a "src_slice_pitch = src_row_pitch;" for CL_MEM_OBJECT_IMAGE1D_ARRAY and now I'm not sure why Image::read doesn't do it.. well.. that makes things easy at least
<karolherbst>
ehh..
<karolherbst>
need to do the reverse
sima has quit [Ping timeout: 480 seconds]
<karolherbst>
I need to CI this
<robclark>
I suppose it would be nice if we could have a _bit_ of cl cts in mesa ci.. too bad cl cts is it's own bespoke framework
<karolherbst>
yeah....
<karolherbst>
I have a plan (tm)
<karolherbst>
I think deqp-runner can take a list of tests that it would run, but not sure what the details are there
<karolherbst>
so I'd just need to generate a list of things to run