Defining Cuda as a Programming Model

Print Friendly, PDF & Email

Nvidia’s Mark Ebersole writes that CUDA is not an API or language – rather, it is a powerful mainstream tool that allows you to easily unlock the power of GPU acceleration.

It is much more than that. CUDA is a parallel computing platform and programming model that makes using a GPU for general purpose computing simple and elegant. The developer still programs in the familiar C, C++, Fortran, or an ever expanding list of supported languages, and incorporates extensions of these languages in the form of a few basic keywords.

Read the Full Story.