Parallel programming with OpenACC
Jeff Larkin
Abstract
This chapter introduces OpenACC to CUDA programmers. It starts with the kernel and parallel regions and their associated clauses. It further introduces the concept of data regions that allow the programmers to control data transfers. It concludes with important details of performance, portability, and interoperability with CUDA. CUDA programmers typically find the OpenACC directives intuitive and easy to use.
Keywords
OpenACC; pragma; directive; clause; gang; worker; vector; descriptive; prescriptive; interoperability
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.
