They’re used by the internal register renamer/allocator so if it sees you’re storing the results to memory then reusing the named register for a new result - it will allocate a new physical register so your instruction doesn’t stall for the previous write to go through.

This has already been tried :)

iirc, in the 2016 a quadcore intel cpu ran the original crysis at ~15fps

Get the DGX Spark computers? They’re exactly what you’re trying to build.

the TB5 link (RDMA) is much slower than direct access to system memory

Nvidia has been investing in confidential compute for inference workloads in cloud - that covers physical ownership/attacks in their thread model.

https://www.nvidia.com/en-us/data-center/solutions/confident...

https://developer.nvidia.com/blog/protecting-sensitive-data-...