General-purpose computing on graphics processing units (GPGPU) is very popular right now, and NVIDIA has the lead in this arena with their Compute Unified Device Architecture (CUDA). While in the future, it looks like people will be moving from CUDA, which is proprietary to NVIDIA, to OpenCL, which should be available from a variety of vendors.
Morgan Kaufmann has published a new book in the GPU Computing Gems series. As to be expected, this book covers a variety of topics including scientific simulation, life sciences, statistical modeling, ray tracing, rendering, computer vision, video processing, signal processing, and medical imaging. You can buy GPU Computing Gems from Amazon for $59.24.
Graphics Processing Units (GPUs) are designed to be parallel – having hundreds of cores versus traditional CPUs. Increasingly, you can leverage GPU power for many computationally-intense applications, not just for graphics. If you’re facing the challenge of programming systems to effectively use these massively parallel processors to achieve efficiency and performance goals, GPU Computing Gems provides a wealth of tested, proven GPU techniques.
GPU Computing Gems: Emerald Edition is the first volume in this new series from Morgan Kaufmann. Different application domains often pose similar algorithm problems, and researchers from diverse application domains often develop similar algorithmic strategies.