How To Write A CUDA Program: The Ninja Edition

Join one of CUDA's architects in a deep dive into how to map an application onto a massively parallel machine, covering a range of different techniques aimed at getting the most out of the GPU. We'll cover principles of parallel program design and connect them to details of GPU programming to see how everything works together.

This session is the next installment in what's becoming a series of annual talks looking at the nuts and bolts of CUDA programming (although there is no requirement to have seen past sessions). Last year aimed at getting started; this year is looking more at people who are familiar with programming — maybe even somewhat familiar with CUDA — but should be informative for everyone who's interested in developing for the GPU.