November 2016
Intermediate to advanced
576 pages
18h 22m
English
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