NVIDIA GPU Programming: Massively Parallel Programming with CUDA

NVIDIA made it easy and understandable to program the rarely used engine inside a PC with CUDA (Compute Unified Device Architecture). It allows for a significant increase in your computer’s performance because it harnesses the power of the GPU. With this book, you’ll learn to switch on that hidden power and turbo charge your programs. CUDA specialist Shane Cook discusses the many uses for CUDA, including image and video processing, computational biology and chemistry, fluid dynamics simulation, CT image reconstruction, seismic analysis, ray tracing, and much more.

• Delves into how NVIDIA introduced CUDA, thereby making it easier to harness the true power of your PC’s GPU
• Provides an overview of CUDA and explains how to set it up
• Highlights grids, blocks, threads, memory models, and more
• Reviews common problems, their causes, and solutions
• Explores hardware revisions and discusses what they mean for programming

NVIDIA GPU Programming is written in a style that assumes no previous knowledge of parallel programming so you can get started using CUDA today.