We are pleased to announce the new book C++ AMP: Accelerated Massive Parallelism with Microsoft Visual C++ by Kate Gregory and Ade Miller. C++ AMP lets you capitalize on the fast GPU processors in today’s computers through the C++ AMP code library, bringing massive parallelism to your project. Experienced C++ developers will learn parallel programming fundamentals with C++ AMP through detailed examples, code snippets, and case studies.
The case studies include:
· An “N-body” case study that uses several different implementations of the classic n-body problem, which models particle movement under gravity, intended to show you how to use C++ AMP to get the most out of your GPU hardware in a computational application
· A “Cartoonizer” case study that demonstrates braided parallelism, using both the available cores on the CPU and any available GPU(s). This project processes video into simpler “cartoonized” images, using two different approaches to solve the problem.
· A “Reduction” case study that shows twelve different implementations of the reduce algorithm. The book shows and discusses each implementation’s performance characteristics and the trade-offs associated with each.
You’ll discover how to:
· Gain huge code performance improvement using graphics processing units (GPUs)
· Choose accelerators that enable you to write code for GPUs
· Program code using the Microsoft DirectX platform
· Apply thread tiles, tile barriers, and tile static memory
· Debug C++ AMP code with Microsoft Visual Studio
· Use profiling tools to track the performance of your code
The full table of contents appears below. You can purchase the book from O’Reilly here: http://shop.oreilly.com/product/0790145341907.do, and find more information on CodePlex: http://ampbook.codeplex.com/. Author Kate Gregory also maintains a page for this book: http://www.gregcons.com/cppamp/.