In-Depth: Sony, Stanford Experts Talk PS3 Folding@home

Sony has just revealed roll-out details for its Folding@home PS3 service, and Gamasutra attended a Stanford University event revealing the distributed disease-solving PS3 'screensaver', talking to scientists and Sony managers behind the service. Sony will be rolling out the new 'screensaver' next Friday for all PlayStation 3 users with its 1.6 firmware update, but this screensaver does more than display pretty pictures. Instead, this particular program adds your PS3 to a massive computing cluster, distributed throughout the world. The Folding@home project has been active on the Internet for almost seven years now. It's based on the SETI@home project, which distributed, to volunteered desktop computers, the task of filtering through the white noise of radio transmissions from space to look for alien-produced sound. While SETI@home remains a popular addition to most geek-run computers, Folding@home offers a processing objective which has far more direct consequences for humanity. Why PS3, Why Now? “For the most part, it's not that we're looking for a needle in a haystack, but we're looking for broad properties that require good statistics,” said Vijay Pande, associate professor of chemistry at Stanford University. As one of the scientists behind the project, Pande is proud to say that Folding@home has actually provided useful information to the scientific community. SETI@home, however, has yet to discover a single alien transmission. “These successes are documented in peer review journals. Over 50 papers have resulted from Folding@home,” said Pande. He and his students collaborated with developers from Sony Computer Entertainment of America to build a Folding@home client for the PlayStation 3, but that wasn't really Pande's idea. Noam Rimon, software development manager at SCEA, said that he stumbled upon the Folding@home project while looking for ways to utilize the PS3 for non-gaming purposes. “We were looking into the PlayStation 3, researching a little about the Cell processor and what it can do beyond games. One of the projects that caught my eye was folding. There's something about having something nicely shown on the screen, and something that's in the interest of the public. So I contacted Vijay through the Internet and saw that there were already discussions of doing this on consoles,” said Rimon. “I thought it would be a very good match.” The Scientific Specifics Unlike SETI@home, Folding@home seeks to model a very terrestrial problem. Proteins in the human body, and elsewhere in nature, are useful thanks to their shapes. This is typically a long spiral, like DNA. But when proteins are used in the body, they must be “folded,” that is, they must change their physical orientation and positioning. This typically happens shortly after or during protein synthesis within a cell. Bad cells or bad conditions can result in bad folding, and badly folded proteins can cause illnesses like Bovine Spongiform Encephalopathy ('mad cow' disease), Parkinson's, Huntington's, and some forms of Alzheimer's disease. Until now, the Folding@home project has focused exclusively on the modeling of successful protein folds. As the science behind just why proteins decide to fold is still largely a mystery, the project uses that massive distributed computing power to run 3D movement simulations to replicate the shapes proteins can form. But recently, said Pande, the project has begun to take up the task of simulating protein misfolding. “In terms of protein misfolding, that's something that's much more recent, and we're still waiting for peer review to come back,” said Pande. He declined to comment on this research, saying that talking about a study before peer reviews are complete is something of a no-no in the science world. Not Blue Gene, But Not Bad Pande did say that despite the massive amount of power available through distributed community computing projects, the power of crowd-clustering won't be taking the place of the big iron typically used for this type of work. “You can compare what we can do with Folding@home now with what (IBM's super computer) Blue Gene can do. Blue Gene has 64,000 processors. Surprisingly, the processors in Blue Gene are typically slower (than those used by consumers). They do that to reduce the power consumption,” said Pande. “What makes the super computer powerful these days is the network that allows these processors to talk quickly to one another. What you don't have (in Folding@home) is that fast network. The challenge is if you can come up with software that doesn't require that fast network. I see it not as something that would wholly replace big computers, but as filling a niche that was previously left empty.”