Chapter 37. A Toolkit for Computation on GPUs

Ian Buck Stanford University

Tim Purcell Stanford University

Traditionally the GPU has been a rendering coprocessor or, as the name implies, a graphics processing unit to the host PC. Many of the chapters in this book demonstrate how to render cool effects really fast using the GPU. But who says that the GPU is limited just to rendering? The research community has clearly demonstrated how non-graphics-related computing can be performed on the GPU, with more than a dozen papers published in the SIGGRAPH and Graphics Hardware conferences. This chapter discusses some basic approaches for performing general computation on the GPU and demonstrates how to implement some fundamental algorithms needed for many ...

Get GPU Gems: Programming Techniques, Tips and Tricks for Real-Time Graphics now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.