O'Reilly logo

Parallel Programming with OpenACC by Rob Farber

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Chapter 4

Pipelining data transfers with OpenACC

Jeff Larkin     NVIDIA, Santa Clara, CA, United States

Abstract

The purpose of this chapter is to introduce asynchronous programming with OpenACC, particularly in regards to a technique known as pipelining. This chapter will accelerate an existing OpenACC code by enabling the overlap of computation and data transfers.

At the end of this chapter the reader will have an understanding of:

 Asynchronous execution within OpenACC

 Pipelining as a technique to overlap data transfers with computation

 How to use the OpenACC routine directive.

Keywords

Asynchronous programming; Pipelining; Visual Profiler; Blocking; Tiling

The purpose of this chapter is to introduce asynchronous ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required