Open mclarsen opened 10 years ago
Matt points out there are good libraries for doing this on a GPU (like curand), though of course we need to abstract it so it's not CUDA-specific.
I believe curand I believe needs a state vector (basically one int per thread?), so there's some chance an abstraction like the "counting iterator" (see issue #10) might be useful here.
I would like to request the addition of an random number generator for Monte Carlo simulations that can be accessed inside a functor.