This is very interesting because PC workstations have been stagnating for quite long! It'd be cool to be able to bring medium-sized tasks back from clouds to personal computers.

The CPU performance is impressive but I wonder how well it'd fare against say an AMD ThreadRipper or a dual socket system with an equivalent price? It'd be also interesting to see a deep learning benchmark against Nvidia. Branding and RAM limits suggest this is geared towards video processing, but might also be useful for some other domains.

My workstation has a 3990x.

Our "world" build is slightly faster on my M1 Max.

https://twitter.com/kiratpandya/status/1457438725680480257

The 3990x runs a bit faster on the initial compile stage but the linking is single threaded and the M1 Max catches up at that point. I expect the M1 Ultra to crush the 3990x on compile time.

amelius

Time for your linker vendor to parallelize their algorithm.

kiratp

Osmos.io is built on Rust so that’s LLVM. No commercial vendor involved.

There is Mold (https://github.com/rui314/mold) as an alternative but it doesn’t support MacOS yet and that’s a blocker for our team.