Kim, Kyunghun

CuEvent and performance benchmark in device time

1

Implement interface for using cuda events. I did it long time ago in CUDA.jl package, so it will be simple task. https://github.com/moon6pence/CUDA.jl/commit/ab1aed855839cffd0f37da9cc03d69967b2a5e6a And we can implement such `@elapsed` and `tic/toc()`...