[sytelus]

Yes, but is cuda going to keep its edge 10 years down the line? Do I want to hardcode my algorithms so tightly with today's cuda APIs? Can there be better more generic primitives that are agnostic of propitiatory cuda APIs but would support it as backend without too much perf hit?

[xiaodai]

If you want performance then yeah. If you are after hypothetical performance in future which may not even materialise, then the choice is yours. Everyone knows where the sensible ground is. Which, unfortunately, is CUDA only

[shaklee3]

AMD has a search and replace library that's API compatible with many cuda functions now. It hasn't caught on yet, but if they release decent hardware soon, it might.

[refresh-creds]

That paper is already about 10 years old so I think you are being trolled.