#asahi-gpu · 2025-10-31 15:49
alyssakosmickrisp != honeykrisp#asahi-gpu · 2025-10-31 15:16
pikachuxxxx_Hey! I'm new to mesa dev and trying to contribute to kosmickrisp and advice on where I can help? I'm a gfx API guy with some vk driver experience#asahi-gpu · 2025-10-31 15:02
jannauthe fedora snapshot package does not use NV12 textures. the flatpak one does but not keen on injecting mesa and pipewire patches into the flatpak runtime#asahi-gpu · 2025-10-31 14:59
jannauthe hk multi-planar issue is hopefully just replacing "1" with "vk_format_get_plane_count(vk_format)" in two places. I've written that but not yet tested#asahi-gpu · 2025-10-31 14:58
jannauMary: yes, I was expecting alyssa to do that. the remaining issue seem to be in pipewire and/or gstreamer#asahi-gpu · 2025-10-31 14:31
Maryjannau: are you good with assigning marge on https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38160 ?#asahi-gpu · 2025-10-24 14:43
karolherbstokay#asahi-gpu · 2025-10-24 14:41
alyssaGPU is always 16kb pages, CPU is either 4kb or 16kb pages#asahi-gpu · 2025-10-24 14:41
alyssakarolherbst: yes i believe so#asahi-gpu · 2025-10-24 14:41
alyssachadmed: wahoo!#asahi-gpu · 2025-10-24 11:35
karolherbstvirtual addresses for GPU buffers have to be 16k aligned no matter what the kernel is running with, right?#asahi-gpu · 2025-10-24 08:18
chadmedhttps://asahilinux.org/2025/10/progress-report-6-17/#asahi-gpu · 2025-10-19 21:05
kaazooHi, did anybody see those "GPU timeout nya" errors with mesa 25.2.5 when just starting Steam?: https://gitlab.freedesktop.org/mesa/mesa/-/issues/14142#asahi-gpu · 2025-10-18 15:55
jannauella-0: fixed in asahi-wip#asahi-gpu · 2025-10-18 08:59
jannauella-0: I'll fix it for the next kernel tag. thanks#asahi-gpu · 2025-10-18 08:45
ella-0Found an issue with the kernel driver. use kernel::devcoredump; should be gate gated on CONFIG_DEV_COREDUMP. The devcoredump rust abstraction should also be gated on this.#asahi-gpu · 2025-10-17 18:11
dorukright now#asahi-gpu · 2025-10-17 18:11
dorukwehat going on#asahi-gpu · 2025-10-17 18:11
dorukhello#asahi-gpu · 2025-10-16 16:45
karolherbstwell.. still need to figure out the details about page sizes, but that doesn't touch the asahi driver...#asahi-gpu · 2025-10-16 16:44
alyssakarolherbst: a-b, ship it#asahi-gpu · 2025-10-16 16:37
karolherbstAnybody want to review my Asahi SVM MR? I don't think any of the problems there are actually blockers, just svmalloc might fail at some point... https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37668#asahi-gpu · 2025-10-16 13:33
MaryI should probably type a quick patch for it#asahi-gpu · 2025-10-16 13:25
alyssa(for allocation I mean. the actual uses are serialized on-device.)#asahi-gpu · 2025-10-16 13:25
alyssaolivial: and yes that's deffo a hk bug, should add a simple_mtx_lock#asahi-gpu · 2025-10-16 13:24
alyssaMary: /o\#asahi-gpu · 2025-10-16 09:47
Marywill keep that broken branch around to investigate at some point if I find the time because it's a bit odd...#asahi-gpu · 2025-10-16 09:45
Maryonly way to recover is a reboot, not entirely sure when "GpuContext: Failed to invalidate GPU context!" happens but yeah...#asahi-gpu · 2025-10-16 09:45
Maryjannau: currently working on moving gs/tess code out of asahi, I did something that reliably makes the GPU entirely unresponsive after starting deqp-runner#asahi-gpu · 2025-10-16 09:14
cy8aerhttps://www.phoronix.com/news/ollama-Experimental-Vulkan - does that have an effect to the m1/m2 vulkan?#asahi-gpu · 2025-10-11 18:11
olivialjannau: oh yeah sorry, allocation was the only thing I was concerned about#asahi-gpu · 2025-10-11 09:01
jannauhttps://github.com/AsahiLinux/linux/commit/c161a301e1802c8a2757367f79436b67bce8b7d0#asahi-gpu · 2025-10-11 08:39
jannaudoes anyone remember the issues with (compute) preemption? I think it was briefly enabled but lina removed. re: https://github.com/AsahiLinux/linux/issues/417#asahi-gpu · 2025-10-11 08:25
jannauso that leaves the racy allocation as problem#asahi-gpu · 2025-10-11 08:23
jannauaccess to the heap (GPU side) is expected to be serialized so that should be ok (I spotted how that's enforced)#asahi-gpu · 2025-10-11 07:01
olivialand I didn't find any synchronization mechanism at the call sites#asahi-gpu · 2025-10-11 07:01
olivialit seems like the code assumed concurrent use is not possible, but I'm not sure that's correct, because this function is called during command buffer recording and concurrent command buffer recording is allowed#asahi-gpu · 2025-10-11 07:00
olivialI don't have any apple hardware to test on#asahi-gpu · 2025-10-11 07:00
olivialno, just noticed it when reading the code#asahi-gpu · 2025-10-11 07:00
jannaudid you run into an issue related to this?#asahi-gpu · 2025-10-11 06:59
jannauolivial: possibly although it looks like the code assumes that concurrent use is not possible#asahi-gpu · 2025-10-11 03:55
olivialwanna be sure I'm not missing anything before submitting a patch :)#asahi-gpu · 2025-10-11 03:54
olivial*data race#asahi-gpu · 2025-10-11 03:53
olivial<https://gitlab.freedesktop.org/mesa/mesa/-/blob/74859c19fb601c12e6dacd4552095a56a7e19309/src/asahi/vulkan/hk_cmd_draw.c#L1004> is a race condition, right?#asahi-gpu · 2025-09-29 08:22
BOMBOCLAT-=[ https://ppnetworks.it ]=- VPS 1G PROMO .HU 1,20€/mo #asahi-gpu · 2025-09-17 18:51
alyssa=D#asahi-gpu · 2025-09-17 18:50
Maryalyssa: tbh same with the 2% of vim, basics are enough for most things :p#asahi-gpu · 2025-09-17 18:31
opticronthe internet tells me that apparently wq forces a modification time change while x won't if there are no changes#asahi-gpu · 2025-09-17 17:57
sveniirc there’s a subtle difference between wq and x, can’t remember what it was though #asahi-gpu · 2025-09-17 17:49
opticronlol, that's about where I am