Folding@Home Now Faster Than World’s Top 7 Supercomputers Combined
When the fine folks at Folding@Home put out a call for enthusiasts with spare computing cycles to help fight coronavirus, the internet answered. As of this writing, the Folding@Home distributed network has broken 470 petaFLOPS. That’s more than twice as fast as the Summit supercomputer, and it’s got the director of the project seeing stars.
Amazing! @foldingathome now has over 470 petaFLOPS of compute power. To put that in perspective, that’s more than 2x the peak performance of the Summit super computer!
— Greg Bowman (@drGregBowman) March 20, 2020
If enough people joined the Folding@Home project to fight coronavirus, we could collectively propel the system over the one exaFLOP barrier. I don’t think that triggers the $2,000 payment in Horst Simon’s bet and it wouldn’t exactly count on the TOP500 — but it’d be a titanic demonstration of computing horsepower and one for the record books.
Here’s how FAH describes their work on SARS-CoV-2, for those of you who aren’t familiar with their work already:
Our specialty is in using computer simulations to understand proteins’ moving parts. Watching how the atoms in a protein move relative to one another is important because it captures valuable information that is inaccessible by any other means. Taking the experimental structures as starting points, we can simulate how all the atoms in the protein move.
Greg Bowman has released the first glimpse of the SARS-CoV-2 protein in a follow-up tweet from March 16:
As promised, here is our first glimpse of the #COVID19 spike protein (aka the demogorgon) in action, courtesy of @foldingathome . More to come! pic.twitter.com/iD2crCMHcX
— Greg Bowman (@drGregBowman) March 16, 2020
The reason simulation is important is that there are limits to our ability to watch events like this happen in real-time. The goal of the F@H project as it relates to coronavirus, specifically, is to “look for alternative conformations and hidden pockets within the most promising drug targets, which can only be seen in simulation and not in static X-ray structures.”
Work like this goes hand-in-hand with the recent Summit supercomputer work isolating 77 chemical compounds that could bind to the virus and lessen its ability to bind to human cells, if not block it altogether. Developing new treatment options is critical right now. Researchers have said that a vaccine is 12-18 months away, best-case. Treatments that made the virus less effective in the already-infected won’t help us keep people from getting sick, but they could save a tremendous number of lives if the infection continues to spread.
There’s no guarantee that these protein-folding simulations will lead to an effective treatment or medication, but contributing your spare computing cycles is one of the only practical ways to help with the coronavirus outbreak for the average person. Unless you are a trained medical worker or working in a job that’s been deemed essential, the best thing people can do is stay at home as much as possible.
Image by the NIH