An introduction to C++ AMP
David Callahan
Abstract
This appendix introduces C++ AMP, a parallel C++ programing interface for CUDA GPU devices. It introduces the concepts of for-all, iterators, and lambda as the construct for parallel programming. It describes tiling and data transfer optimizations in C++ AMP. The appendix ends with a brief overview of how a C++ AMP program can interface with the DirectX graphics interface.
Keywords
C++; parallel for-all; iterators; lambda; tiling; template; open specification; data transfer; graphics interoperability
Chapter Outline
Get Programming Massively Parallel Processors, 3rd Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
