4,580 Posts served
11,094 Conversations started
- Academic

- Android

- Art, Music, & Animation

- Embedded Computing

- Events

- Game Development

- Graphics & Media

- Intel SW Partner Program

- Intel® AppUp Developer Program

- Manageability & Security

- Mobility

- Open Source

- Parallel Programming

- Performance and Optimization

- Power Efficiency

- Server

- Site News & Announcements

- Software Tools

- Ultrabook

- Association for Computing Machinery TechNews (ACM)
- Go Parallel! (Dr. Dobbs)
- HPCwire (Tabor Communications, Inc.)
- insideHPC (John West)
- Joe Duffy's Weblog (Microsoft)
- Microsoft Parallel Programming Development Center (Microsoft Germany)
- MultiCoreInfo.com
- scalability.org (Scalable Informatics)
- Software Dev Blog (Intel Germany)
- Soft Talk Blog (Intel United Kingdom)
- The Moth (Microsoft)
I'd prefer reaching Parallel Programming Nirvana
By Clay Breshears (Intel) (196 posts) on May 18, 2011 at 12:38 pm
Have you seen the article "Nine Tips to Parallel Programming Heaven"? This is excerpted advice from an interview of Dr. Yann Golanski by Stephen Blair-Chappell and details Dr. Golanski's recommendations to someone starting to parallelize an application.
Sure, it's got one more point than my own "8 Simple Rules for Designing Threaded Applications" and they all fit onto a single page, but I would take issue with Tip #1 - Just buy a faster machine. Gone are the days of being able to write software, taking 6 months off to go practice your drumming on a beach somewhere, and then running your application on the new faster processors in order to declare a speedup in your code. (Thanks to Michael Wrinn for this scenario.)
Other than that, the remaining eight tips are quite useful. Go read over the Nine Tips yourself, especially if you're just getting started with parallel programming. Practice them as much as you can and you will be on your way to becoming a parallel programming Bodhisattva.
Categories: Academic, Parallel Programming
For more complete information about compiler optimizations, see our Optimization Notice.


Narayan