NVIDIA CUDA Tutorial 6: An Embarrassingly Parallel Algorithm 1

In this tute we'll look at a C++ implementation of a nearest neighbor algorithm. Next tute we'll convert this code to CUDA and see what sort of speed up we can get. There's no CUDA in this tute, just the presentation of a challenge. I'll supply my own solutions in the upcoming tutes but have a crack yourself as well, see what sort of speed increase you can get. The tute after next we'll look a little more at using some of the GPU resources better and see if they can help us get more performance. Facebook:   / 167732956665435