The Cuda Handbook: A Comprehensive Guide to GPU Programming

The book will be mostly reference and part cookbook. Careful descriptions of the hardware and software abstractions, best practices, and example source code will be included. Much of the source code will come in the form of reusable GÇ£microbenchmarksGÇ¥ or GÇ£microdemosGÇ¥ designed to expose specific hardware characteristics or highlight specific use cases. Best practices will be discussed and accompanied with source code. One idea that will be emphasized is the GÇ£EERS PrincipleGÇ¥ (Empirical Evidence Reigns Supreme): determining the fastest way to perform a given operation is best done empirically.