Comment by jsheard
8 hours ago
Does anyone know if M3 support is likely to lead to M4 or M5 support in relatively short order? AIUI M3 took a long time because it was a substantial departure from M1/M2, especially in the GPU architecture, but I don't know if M4 or M5 made similar leaps.
The main reason M3 took a long time isn't related to m3 itself, but rather that the asahi project took on a ton of tech debt to get M1/M2 working. M3 wasn't too difficult, but before taking on the additional tech debt, the Asahi team focused on getting all of their changes upstreamed to the linux kernel.
The main developer was also the target of a harassment campaign from a place that has pushed other targets to straight up suicide. That took almost all of their energy for the last year and they ended up quitting.
Is this the Torvalds/Hector dispute that comes on the Google AI summary, or was this a three-letter agency type of harassment faced by Aaron Swartz?
5 replies →
Prognosis is then that work for m4/m5 should be relatively straight line now that refactoring is done?
M4 is apparently even harder because of some new hardware-level page table protections.
Source from Asahi contributor: https://social.treehouse.systems/@sven/114278224116678776
Memory Integrity Enforcement, perhaps?
https://security.apple.com/blog/memory-integrity-enforcement...
It's "Secure Page Table Monitor". https://support.apple.com/en-il/guide/security/sec8b776536b/.... The kernel requires it so they need to emulate SPTM.
2 replies →
The M5 reportedly has a newer generation GPU compared to the M3/M4. For one thing, the GPU-side Neural Accelerators are obviously new to the M5 series. Other stuff is harder to know for sure until it gets looked into from a technical POV.
It’s not like neural accelerators on non-Apple consumer hardware get much use on Linux, either, so that does not sound like much of a dealbreaker.
The matrix/tensor math units added to GPUs do see widespread use, both for running LLMs and for the ML-based upscaling used by most video games these days (eg. NVIDIA DLSS). The NPUs that are separate from the GPU and designed more with efficiency in mind rather than raw performance are a different thing, and that's what's still looking for a killer app in spite of all the marketing effort.