#asahi-gpu · 2024-10-28 13:04
alyssathat lets you hit all the interesting problems of UAPI translation, without hitting any of the really annoying problems of WSI or fixing Mesa macOS build breakages#asahi-gpu · 2024-10-28 13:03
alyssain Linux#asahi-gpu · 2024-10-28 13:03
alyssathat way you don't have to touch Mesa at all yet, you can just run stock asahi/mesa in a UTM guest and then try to get "gl4.6+vk1.3+cl3.0+gles3.2 working inn inux guest on a macOS host"#asahi-gpu · 2024-10-28 13:02
alyssa4. native context is by far the spiciest question. I think that depends how you implement things. Honestly, that might be the *easiest* place to start though - trying to hack up virglrenderer to translate Linux virtualized UAPI into macOS UAPI#asahi-gpu · 2024-10-28 13:01
alyssaIronically Vulkan would be easier since the MoltenVK and lavapipe interfaces already exist.#asahi-gpu · 2024-10-28 13:01
alyssa3. Effectively. There'd still be a pile of WSI code needed to get OpenGL working in Cocoa windows. For initial driver bring-up, I was just using XQuartz which is... not really what people want from their macOS graphics drivers!#asahi-gpu · 2024-10-28 13:00
alyssa2. More or less, yeah. Should be possible. Timestamps are the one place that the uapi already/will diverge but you don't have to worry about that right now. I also assume sparse will be different but that only matters for DX12, also not a right now problem. (That's all the VM_BIND calls. I don't actually know if macOS has an equivalent. It might?)#asahi-gpu · 2024-10-28 12:58
alyssa1. I don't know. I would assume it's similar, but it's entirely posible added a field in g13x or something like that. Apple doesn't guarantee stability on this interface.#asahi-gpu · 2024-10-28 12:57
alyssaoliverb: great questiosn =D#asahi-gpu · 2024-10-28 11:42
oliverbthat correct? #asahi-gpu · 2024-10-28 11:42
oliverbThird: as a future outlook: If I follow through and get this actually working, there shouldn't be anything that blocks me from having opengl 4.6 working on a Mac, right? If this works somehow, would it be possible to get virgl/native context working too? As I understood it, it would do all the work in the VMs mesa and just forward the ioctl calls to the host, which could then be processed using my theoretical drm shim implementation, is #asahi-gpu · 2024-10-28 11:42
oliverb * first, the data in the command buf that gets submitted to the gpu, is that independed of the actual gpu? You where working with a G13G_B0 while I have a G13X gpu, can I just send the same data as you did in your triangle demo? #asahi-gpu · 2024-10-28 11:42
oliverb * second: is the Linux uabi more or less compatible with what the iokit interface expects? Should it be possible to build a drm shim for mesa/asahi that just translates the drm calls to iokit calls or do you know of some major changes in what the kernel does in Mac/Linux?#asahi-gpu · 2024-10-28 11:42
oliverbalyssa: i know you do not support the mesa driver on mac, I want to try to get this working anyways. I've started to work on the basics in getting your asahi/gpu demo triangle to run on macos 15. Found some changes in the iokit calls as you've talked about in the past and tried to get them in line with what simple metal apps do. So far so good, now i am presented with successful iokit calls and a black window, but I call this success for#asahi-gpu · 2024-10-28 11:42
oliverb now. I just have some questions:#asahi-gpu · 2024-10-24 12:01
chadmeddavid: wrong channel go to #asahi or #asahi-dev. this channel is for gpu work.#asahi-gpu · 2024-10-24 10:18
david3y way to achieve this*#asahi-gpu · 2024-10-24 10:16
david │n on active kernel debugging in Apple Silicon systems the result of a software-level restriction, or does it stem from a hardware-level mitigation implemented in the new architecture? If it is a software level then what are the hack#asahi-gpu · 2024-10-24 10:16
davidHey, In the past, Intel-based Macs allowed for active kernel debugging, but with the transition to Apple Silicon, developers are now limited to analyzing memory dumps, as outlined in the KDK (Kernel Debug Kit) README for two-machine debugging. Is this limitatio#asahi-gpu · 2024-09-04 01:54
donierAny resources I can be directed to to learn how to contribute towards the GPU side of things in Asahi Linux? #asahi-gpu · 2024-09-03 10:35
chadmed_sheesh#asahi-gpu · 2024-09-03 10:26
alyssasascha willems terraintessellation going at 120fps on m1 at 4k#asahi-gpu · 2024-09-03 10:26
alyssait's pretty fast shrug#asahi-gpu · 2024-09-03 10:24
chadmed_doesnt mean theyre gonna be fast :p #asahi-gpu · 2024-09-03 10:23
alyssachadmed: also anything .cl is on the gpu :p#asahi-gpu · 2024-09-03 10:17
alyssaMary: no fbfetch wired up in honeykrisp yet so that'd actually be much worse ;P#asahi-gpu · 2024-09-03 10:17
alyssachadmed: yeah, hk definitely lower cpu overhead than gl#asahi-gpu · 2024-09-03 07:18
chadmedbut then again, tesselator.cl....#asahi-gpu · 2024-09-03 07:18
chadmedcould just be less cpu overhead with hk? we know our gl driver is pretty cpu heavy #asahi-gpu · 2024-09-03 06:13
Maryor maybe this? https://github.com/dolphin-emu/dolphin/blob/master/Source/Core/VideoBackends/Vulkan/VulkanContext.cpp#L448#asahi-gpu · 2024-09-03 06:11
MaryOtherwise also give a try without the whole threaded gl on mesa just in case#asahi-gpu · 2024-09-03 06:10
Maryalyssa: Maybe something you expose on OGL and not on VK? Might be worth looking for possible extensions that could be slower than their slowpath...#asahi-gpu · 2024-09-03 01:58
alyssadunno what to make of that#asahi-gpu · 2024-09-03 01:58
alyssainteresting. dolphin is measurably faster with honeykrisp than asahi gl, despite hk having higher intrinsic gpu load#asahi-gpu · 2024-08-23 12:57
chadmedhence why i asked if that is what apple does#asahi-gpu · 2024-08-23 12:56
chadmedalyssa: dw this is in macos not your problem :) #asahi-gpu · 2024-08-23 11:33
alyssathis is why we conformance test...#asahi-gpu · 2024-08-23 11:33
alyssachadmed: umm. it shouldn't. o_o#asahi-gpu · 2024-08-23 02:24
chadmed_does apple just silently drop msaa? ive noticed that forcing it in certain games that support it "works" in the sense that the game doesnt explode and die, but it's obvious that no msaa is actually being done#asahi-gpu · 2024-08-22 18:55
alyssaand if msaa 8x + rgba32 is actually compressible on m3#asahi-gpu · 2024-08-22 18:54
alyssait's unclear to me if apple actually ships msaa 8x on m3 though.#asahi-gpu · 2024-08-22 18:53
alyssaLol#asahi-gpu · 2024-08-22 18:50
jannauwhen will the default SSD be to small to hold all ail tests?#asahi-gpu · 2024-08-22 18:48
alyssaso something had to be reworked there. guess ail is going to get more complicated. bah.#asahi-gpu · 2024-08-22 18:48
alyssasince it would require 16x8 tiles, but those are smaller than the 16x16 compression tiles#asahi-gpu · 2024-08-22 18:47
alyssawhich would conflict with how image layouts work on m1 and m2#asahi-gpu · 2024-08-22 18:47
alyssaThat would require 128 bytes per pixel#asahi-gpu · 2024-08-22 18:47
alyssa...I wonder how MSAA 8x of RGBA32 images works on M3#asahi-gpu · 2024-08-19 22:07
doniernew to GPU reverse engineering, any resources I could read#asahi-gpu · 2024-08-10 21:36
karolherbstahh alyssa not around, oh well