Thanks Markus! Heheh yeah I finally got to the 10k milestone.

Yeah what sucks with CUDA is that I am on a Mac so I am not likely going to be able to use it.

Seems a bit fragmented this market. Like you can go with OpenCL but Apple seems to have abandoned that for their own efforts like Metal, CoreML etc.

I actually ended up writing about CUDA because I have tried to understand the difference between using vector processing and the approach of GPUs. Maybe you have some experience with that?

I cannot help but think that the CUDA model is actually kind of overcomplicated. Vector processing seems easier to use to me, but I haven't been able to see any APIs for how you work with system having multiple vector processor cores.

I have looked a bit at Esperanto Technologies and their ET-SOC-, which uses 1088 vector processing cores. However I cannot find any tutorials or API documentation giving an idea of how this would work.