Thinking big

For about two years now we have been investigating the use of volunteer-based large scale distributed computing for performing design and simulation tasks. The system and code being used is now fairly stable, and it has become an important tool for us. The system uses BOINC to manage the distribution of tasks among volunteer computers. The home page for our project is at AQUA@home.

The AQUA community currently represents a significant chunk of computing power, comprising about 5,000 cores and 10 teraflop/s sustained. As the viability of distributed automated design tools increases systems like AQUA can start playing a bigger role in experimental design and analysis and ultimately help our hardware and algorithms people design better systems.

Most basic science depends on three complementary areas: theory, simulation and experiment. I would like to try to expand the role of simulation at D-Wave.

In order to do this we need to expand the volunteer base on AQUA. I think the concept of having the world’s largest distributed supercomputer working on designing quantum computers is fascinating, and I’d like to aim for this objective. If you’re intrigued by this, you can check out the AQUA site and talk to the current community. They can answer any questions you may have. Joining is really easy and the code runs at low priority in the background. I have never found it to interfere with anything else I’m doing.

Currently I believe that the largest distributed supercomputer is running Folding@home, and is at or around the 10 petaflop/s sustained level. In order for AQUA to reach this, we’d need about one thousand times more cores than we currently have. This is an ambitious objective but given the compelling nature of the project, it might be achievable.

If you or someone you know might be interested in being part of this, please sign up and try it out!

2 thoughts on “Thinking big

  1. The way the processor world is going (more and more cores) is exactly the right direction for monte carlo type apps. I think that in 2010 we’ll get a big jump in the capability and volume of top end processors… the gap between PS3 type chips and the top line will jump a lot. Of course there are a lot more PS3s/cell processors than high end Intel and AMD chips.

Leave a Reply

Please log in using one of these methods to post your comment: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s