by Jeff Andrews, application engineer, Intel Corp.
Explore different methods for threading a "for-loop," learning how to tailor your application to take best advantage of the Hyper-Threading Technology enabled.
Developers rejoice: When it comes to creating and synchronizing threads there are several Microsoft Windows APIs from which to choose. Knowing which of these methods is best for threading a for-loop is not always easy to determine.
Adding to the available options, Intel® compilers offer OpenMP support, providing an additional method for easy threading. While this method is the simplest and produces the most readable code, in a given case it may not be practical to use it. When best possible performance is required, then too OpenMP may not be the best solution.
In this article I will describe these different methods, explaining which is best suited for a given usage model.
 | Integrating Java and Microsoft .NET by Jon Jagger, Content Master Ltd. Intel Corp. The right techniques... |
| J2EE performance optimization, part 2: the SPECjAppServer family of benchmarks by Kingsum Chow, Ph.D., senior performance architect, Managed Runtime ... |
If you're interested in this topic, these articles may be helpful:
| Three Methods for Speeding up Matrix-Vector Multiplication by Kiefer Kuah, Intel Corp. Speeding up matrix-vector multiplicati... |
| Tutorial: Introduction to Hyper-Threading Technology (online) Tutorial Description: This Intel tutorial details Hyper-Threading (HT)... |
| More WorkSharing with OpenMP Abstract By Richard Gerber As you know, OpenMP* contains a very po... |
| Multi-threading in a Java environment by Allan McNaughton, president, Technical Insights LLC. Intel Corp. ... |
| Artificial neural nets and Hyper-Threading technology by Chuck Desylva, Intel Corp. There are many artificial-intellige... |
Related Jobs:
