Good explanation of my overly terse note.
The current standard interrupt architecture imposes enormous latency and the synchronous timer could be more precise. The simplest implementation would just "fetch" jmp every N instructions (with N programmable) - just like voluntary switching but where the processor would volunteer the program.
> Also the "do system calls by queuing requests to another CPU" is kind of at odds with "we don't need cache coherency"
Can be done with mailboxes/FIFOs, but yes this requires a dedicated design. And of course the CPU that does the call is then idle I think?