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.
Time for your linker vendor to parallelize their algorithm.
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.