Chapter 15
Parallel Programming with OpenACC
Chapter Outline
15.1 OpenACC Versus CUDA C
15.2 Execution Model
15.3 Memory Model
15.4 Basic OpenACC Programs
15.5 Future Directions of OpenACC
15.6 Exercises
The OpenACC Application Programming Interface (API) provides a set of compiler directives, library routines, and environment variables that can be used to write data-parallel FORTRAN, C, and C++ programs that run on accelerator devices, including GPUs. It is an extension to the host language. The OpenACC specification was initially developed by the Portland Group (PGI), Cray Inc., and NVIDIA, with support from CAPS enterprise. This chapter presents an introduction to OpenACC to parallel programmers ...
Get Programming Massively Parallel Processors, 2nd 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.
