March 2005
Intermediate to advanced
880 pages
18h 59m
English

Real-world computational problems have a variety of needs. Some computations, such as everyday office tasks like word processing, are inherently sequential in nature; others, such as computer graphics, physics simulation, and image processing, exhibit a large amount of data parallelism. Most applications require a mix of sequential and data-parallel computation, and modern computer systems are evolving to support these needs. The wide availability and relatively low cost of GPUs make them uniquely suited to serving the data-parallel needs of modern computing. This part of the book focuses on several ...
Read now
Unlock full access