O'Reilly logo

High Performance Parallelism Pearls Volume One by James Jeffers, James Reinders

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 20

Data Transfer Using the Intel COI Library

Louis Feng    Intel Corporation, USA

Abstract

There are many ways we can take advantage of the compute power on the Intel® Xeon Phi™ coprocessor. For example, one may use the offload model where the compiler automatically generates sections of code to run on the coprocessor. Data transfers in this model are managed automatically and how they are processed can be opaque to the programmer. For many types of applications, especially compute kernels in legacy applications and tightly coupled computations with hotspot kernels, the offload model is easy to adapt code and works fairly well to gain performance. On the other side of the spectrum, one may write and compile a standalone program (i.e., ...

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