Reverse Engineering, Open-Source Driver Writing Continues For Apple's M1 GPU

[abott]

More like he is spot on.

Spot on being half completely off base, sure. Did you not watch the video that mentions it's 4K60 on her desktop for the M1 GPU? As far as I know, Nvidia without reclocking can't do that. So it already isn't as bad as Nvidia.

[calc]

Maybe one day there will be a actual apple hardware competitor thay people flock to when they want the build quality of apple but ability to run Linux on it

Pretty much any business class PC laptop is better build quality than Apple proprietary non-repairable ewaste. Apple going on about how green their hardware is, is clearly a bad joke.

In particular ThinkPad P/T/X series are far better across the board than anything from Apple and all have very detailed hardware maintenance manuals and are easily repairable. And Dell and HP’s business lines are great too.

I wouldn’t use an Apple computer if it was given to me free.

But I’m sure reverse engineering Apple’s proprietary hardware is a fun project for some.

[vb_linux]

Spot on being half completely off base, sure. Did you not watch the video that mentions it's 4K60 on her desktop for the M1 GPU? As far as I know, Nvidia without reclocking can't do that. So it already isn't as bad as Nvidia.

That may not be GPU bound though. Apple has had a hardware chip on their SOC for video decoding for a while.

[lucrus]

As pointed out by another user, you have no idea what you're regurgitating.

And you have no idea about how to be well behaved.

It won't end up the same as long as the reclocking isn't hardware locked.

Reclocking has nothing to do with my statement. I'm not native english, so maybe I'm not able to convey my message well enough, but I was talking about the general situation, not this or that specific feature. And the general situation is that Apple does not give a f*ck about Linux or FOSS in general, as long as they do not need it. So they provide no documentation, no help, no answers, nothing about how their stuff should be programmed. I'd say Nvidia is just the same (*), so both drivers are basically doomed to be very limited in features, like being able to bring up the display and a bit more, but far from being a replacement for the closed source official driver (that, in the case of Apple, won't even exist for Linux).

* I don't mean NVidia === Apple, but I do mean $nvidia === $apple, because when it comes to dollars, their business strategies are the same: a walled garden.

Which would pretty blow low, especially for Apple.

You must be a fanboy. Or living under a rock in the last 45 years. Or you've bought a M1 and you don't want to admit you've been fooled by Apple.

[mdedetrich]

I asked this as well in the other thread as well, and replies indicate that Alyssa has more experience with OpenGL than Vulkan, and that Metal is lower-level than Vulkan.

From what I have heard Metal is not lower level than Vulkan, they are pretty much the same with metal only implementing a subset of Vulkan

[Danny3]

So happy and proud that I have never been an Apple customer !
As I am now by not being a Nvidia customer anymore.
IMO, these companies are not to blame, but their users who enable them by giving them money to sit in a cage.

[computerquip]

From what I have heard Metal is not lower level than Vulkan, they are pretty much the same with metal only implementing a subset of Vulkan

Vulkan is (at its core) lower-level and also more extensible than Metal. You can probably implement Metal with Vulkan. However, since Apple doesn't support Vulkan, what's ended up occurring is a scenario where we need Vulkan over Metal. Sooo, we ended up with an initiative for a particular subset of Vulkan called "Vulkan Portability" that's designed to be implemented over things like Metal. We don't get the full Vulkan API, and we don't even get a very conformant API either. The core extension provided by the Vulkan Portability initiative is VK_KHR_portability_subset which allows you to identify differences in the implementation caused by being forced to implement over something like Metal (or D3D12 for that matter).

The implementation of Vulkan which includes support for VK_KHR_portability_subset and is based on Metal is called MoltenVK.

[Yoshi]

For those who are interested in all the reverse engineering work for M1:

https://twitter.com/handleym99/status/1437537535018684417

[mdedetrich]

Vulkan is (at its core) lower-level and also more extensible than Metal. You can probably implement Metal with Vulkan. However, since Apple doesn't support Vulkan, what's ended up occurring is a scenario where we need Vulkan over Metal. Sooo, we ended up with an initiative for a particular subset of Vulkan called "Vulkan Portability" that's designed to be implemented over things like Metal. We don't get the full Vulkan API, and we don't even get a very conformant API either. The core extension provided by the Vulkan Portability initiative is VK_KHR_portability_subset which allows you to identify differences in the implementation caused by being forced to implement over something like Metal (or D3D12 for that matter).

The implementation of Vulkan which includes support for VK_KHR_portability_subset and is based on Metal is called MoltenVK.

There is already a translation layer called MoltenVK which converts directly from Vulkan to Metals and according to their README at https://github.com/KhronosGroup/Molt...kan-compliance this theoritically shouldn't be too hard.

Note that MoltenVK is just an API translation layer so just because MoltenVK cannot implement some functionality on Metal (because their simply isn't an equivalent API call in Metal) doesn't mean that on the hardware level Apple's integrated GPU cannot implement such functionality.

In any case from what I have heard, Vulkan is so similar to Metal that a lot of game developers consider it a trivial translation so I can understand not implementing Vulkan/Metal because on familiarity of such API's but using the reason that Vulkan is too different to Metal doesn't seem to hold much water.

Also doing a good/performant implementation is likely going to be much easier in Vulkan than OpenGL. Vulkan being low level here is a real advantage because you don't have to implement some over complex high levle API that does a huge amount of magic/trickery behind the scenes.

[kieffer]

So happy and proud that I have never been an Apple customer !
As I am now by not being a Nvidia customer anymore.
IMO, these companies are not to blame, but their users who enable them by giving them money to sit in a cage.

I am an user of both Apple and Nvidia hardware and a fanboy of none of them ... what I can tell, is that the CPU part of the M1 is behaving very well: It is the first time (for a couple of decades) a processor is able to exploit its 2 memory channels *at their full capacity* with a single core/thread ! Caches are pretty large in those chips, especially the L1. To me it is an achievement which justifies the single-thread programming style of the Apple ecosystem.