Morgan Kaufmann has published their second volume of GPU Computing Gems, contains 100% new material covering a variety of application domains: algorithms and data structures, engineering, computational finance, and programming tools.
We are in the golden age of the GPU computing. Since the introduction of CUDA in 2007, more than 100 million computers with CUDA capable GPUs have been shipped to end users. GPU Computing application developers can expect their application to have a mass market. With the introduction of OpenCL in 2010, researchers can now expect to devleop GPU applications that can run on hardware from multiple vendors. Furthermore, from my own experience in teaching CUDA and OpenCL programming, C programmers can begin to write basic programs after attending one lecture and reading one textbook chapter. With such a low barrier of entry, researchers all over the world have been engaged in developing new algorithms and applications to take advantage of the extreme floating point execution throughput of these GPUs.
- Wen-mei W. Hwu
A tip of the hat goes to the GPU Science blog for pointing us to this story.