p_m_c

Do you own the GPUs or are you multiplexing on a 3rd party GPU cloud?

Similarly, workloads where threads frequently access and modify the same objects show reduced improvements or even degradation due to lock contention.

Perhaps I'm stating the obvious, but you deal with this with lock-free data structures, immutable data, siloing data per thread, fine-grain locks, etc.

Basically you avoid locks as much as possible.

I've been working a light-weight API gateway for dev use that supports auth and RBAC

https://github.com/paul-callahan/tiny-gateway

I have worked on bond pricing and inventory systems, systems for options and credit default swaps, security agents for runtimes like java, python, industrial control software (SCADA).

Calculus Made Easy - 1910. It is even entertaining.

"What One Fool Can Do, Another Can. (Ancient Simian Proverb.)"

https://calculusmadeeasy.org/

great job! looks like a fun project.