I feel a little gross about headlining aggressive benchmarks with other engines, especially since most of them are free and open source just like bepuphysics. Plus, I learned a lot from projects like bullet, box2d and friends. I'd recommend potential users benchmark their use cases for themselves- those are the most trustworthy benchmarks anyway.

Regarding GPGPU, you're correct that bepuphysics v2 is strictly CPU-side, and also that I could likely make a GPGPU version faster. I wrote a blog post about why I chose to go with CPU-only: https://www.bepuentertainment.com/blog/2019/1/16/-but-gpus-a...

The short version is comparative advantage. I have other things to use the GPU on, and the GPU is even better at those things. And driver bugs.

Also, as I've mentioned elsewhere, while I have not done rigorous benchmarking, a casual evaluation showed that bepuphysics v2 on the CPU compares well with physX 4.1 running on a GPU of similar cost. Collision detection heavy scenes tend to favor GPU physX, while solver-heavy scenes tend to favor bepuphysics v2.

(Except for AMD's Threadripper CPUs unclear reasons. I suspect inter-CCX communication kills effective memory bandwidth in the solver. A 1700x is about as fast as a 2950x, and modern Intel cpus with full rate AVX2 can be much faster. Zen 2 should change things significantly.)