Please create an account to participate in the Slashdot moderation system

 



Forgot your password?
typodupeerror
×
Linux Apple Hardware

Asahi Linux Is Reverse-Engineering Support For Apple Silicon, Including M1 Ultra (arstechnica.com) 46

An anonymous reader quotes a report from Ars Technica: For months, a small group of volunteers has worked to get this Arch Linux-based distribution up and running on Apple Silicon Macs, adapting existing drivers and (in the case of the GPU) painstakingly writing their own. And that work is paying off -- last week, the team released its first alpha installer to the general public, and as of yesterday, the software supports the new M1 Ultra in the Mac Studio. In the current alpha, an impressive list of hardware already works, including Wi-Fi, USB 2.0 over the Thunderbolt ports (USB 3.0 only works on Macs with USB-A ports, but USB 3.0 over Thunderbolt is "coming soon"), and the built-in display. But there are still big features missing, including DisplayPort and Thunderbolt, the webcam, Bluetooth, sleep mode, and GPU acceleration. That said, regarding GPU acceleration, the developers say that the M1 is fast enough that a software-rendered Linux desktop feels faster on the M1 than a GPU-accelerated desktop feels on many other ARM chips.

Asahi's developers don't think the software will be "done," with all basic M1-series hardware and functionality supported and working out of the box, "for another year, maybe two." By then, Apple will probably have introduced another generation or two of M-series chips. But the developers are optimistic that much of the work they're doing now will continue to work on future generations of Apple hardware with relatively minimal effort. [...] If you want to try Asahi Linux on an M1 Mac, the current installer is run from the command line and requires "at least 53GB of free space" for an install with a KDE Plasma desktop. Asahi only needs about 15GB, but the installer requires you to leave at least 38GB of free space to the macOS install so that macOS system updates don't break. From there, dual-booting should work similarly to the process on Intel Macs, with the alternate OS visible from within Startup Disk or the boot picker you can launch when your start your Mac. Future updates should be installable from within your new Asahi Linux installation and shouldn't require you to reinstall from scratch.

This discussion has been archived. No new comments can be posted.

Asahi Linux Is Reverse-Engineering Support For Apple Silicon, Including M1 Ultra

Comments Filter:
  • I like reading about these kinds of projects - trying stuff out "because we can", even if there are bits that don't work yet.

    After all, today's experiments could end up being the basis for tomorrow's core system.

    • by AmiMoJo ( 196126 )

      Some interesting information is coming out of it too. In their efforts to reverse engineer the M1 GPU they have discovered that it's actually quite cut down in terms of features, compared to GPUs from AMD, Nvidia and Intel.

      It doesn't support a lot of features, so either software has to avoid using them or accept the hit of software emulation. That makes porting games to the M1 an interesting challenge. These days all the big game engines will degrade their graphics to suit the hardware, but obviously develo

      • Some interesting information is coming out of it too. In their efforts to reverse engineer the M1 GPU they have discovered that it's actually quite cut down in terms of features, compared to GPUs from AMD, Nvidia and Intel.

        It doesn't support a lot of features, so either software has to avoid using them or accept the hit of software emulation. That makes porting games to the M1 an interesting challenge. These days all the big game engines will degrade their graphics to suit the hardware, but obviously developers would prefer that the M1 version of their game doesn't look significantly worse than the Windows/console version.

        It also explains how Apple got some of their efficiency gains. The silicon is simpler than competing GPUs.

        Doesn't the Metal API hide those "missing hardware features" from software (by transparently emulating them), much like OpenGL (and I assume Vulkan) does? Obviously, there can be performance differences; but if it takes a forensic reverse-engineering deep-dive into low-level atomic GPU primitives to tell that some of those features are being realized in software rather than directly by GPU hardware, who really cares?

        This is somewhat pointed out by the statement "[. . .] the developers say that the M1 is fas

        • by AmiMoJo ( 196126 )

          I don't know much about Metal I'm afraid.

          The M1 has massive memory bandwidth, but it needs it. For a start, the GPU and CPU share that memory. That's another way it's much more like a mobile GPU than a desktop or dedicated laptop one. To try to make up for it Apple has put a massive amount of cache on the CPU, and presumably has some local cache type memory on the GPU too (AMD has been doing that for a while).

          Presumably their comparison with other ARM chips is with ones that don't have particularly good GPU

  • The big down side to spending time and effort on this project (which I don't actually begrudge anyone, it's theirs to spend) is that Apple is notoriously tight-fisted with internals details. The GPU is a big part of what makes the M1 desirable, and not being able to fully utilize it is a huge drawback to not running OSX. Given how hard it is to pry information out of Apple, support for the GPU is likely to be even slower to develop than Nouveau has been.

    I see the utility of being able to use Linux on the pl

    • The big down side to spending time and effort on this project (which I don't actually begrudge anyone, it's theirs to spend) is that Apple is notoriously tight-fisted with internals details. The GPU is a big part of what makes the M1 desirable, and not being able to fully utilize it is a huge drawback to not running OSX. Given how hard it is to pry information out of Apple, support for the GPU is likely to be even slower to develop than Nouveau has been.

      I see the utility of being able to use Linux on the platform, but I wouldn't hold out much hope that it would make sense to use it that way all the time for general purpose application use. Rather, it would be useful for rescue and repair, hardware testing, imaging, network testing, etc.

      I hope I'm wrong, but I doubt it.

      Apple certainly is not alone in being tight-fisted with Trade Secrets. Ask anyone who has actually worked on Driver Development for Linux.

  • NeXTOS predecessor to MacOS was throttled at the CPU speed bump from 25Mhz to 33Mhz upgrade.

    Apple have full control of UX on a iDevice by SoC level. They can compete at any clock if they so choose on responsiveness of the UI.

    • NeXTOS predecessor to MacOS was throttled at the CPU speed bump from 25Mhz to 33Mhz upgrade.

      Apple have full control of UX on a iDevice by SoC level. They can compete at any clock if they so choose on responsiveness of the UI.

      And that is relevant, how, exactly?

  • It's nice to see the progress. I might hold off a bit before I try it out, though - alpha releases sometimes live up to their names in unexpected ways, and doing a complete reimage of an M1 Mac seems to require a second M1 Mac.

Keep up the good work! But please don't ask me to help.

Working...