Just Friday we were gushing that the Folding@Home project, with the help of a few Spartanesque PS3s, had topped 500 teraflops. Apparently, that was too good to be true. Just now, as approximately 30k PS3s were about to push Folding over a PFLOP (1000 TFLOPS), Folding staff at Stanford seem to have reestimated the PS3's power of calculation to be about 50% less than previously thought. No matter. We're not that far off from PFLOPing, according to the FAQ, if you all get off your asses and buy PS3s for Folding.
Basically, If we can get another 20k of the 2 million PS3's out there now to start folding, the Stanford distributed computing project can still be the first to hit the Petaflop level. That's more crunch than the fastest super computer we know of, the MDGRAPE-3 in Japan. For now, Folding is merely the most powerful distributed computing system in the world...never mind the only system capable of playing HD games and movies.
While we wait for the PS3 to make history, Stanford's put an FAQ up that answers some of the mysteries we'd be wondering about.
*The Cell processor's strength is in crunching small sets of data — the PS3's 512MB of RAM limits
*The PS3 uses 200w per hour while folding.
*The PS3's GPU is being used by the Folding client.
Jump for more...
Folding@Home on the PS3– Mark Wilson
Since 2000, Folding@Home (FAH) has led to a major jump in the capabilities of molecular simulation. By joining together hundreds of thousands of PCs throughout the world, calculations which were previously considered impossible have now become routine. FAH has targeted the study of of protein folding and protein folding disease, and numerous scientific advances have come from the project.
Now in 2006, we are looking forward to another major advance in capabilities. This advance utilizes the new Cell processor in Sony's PLAYSTATION 3 (PS3) to achieve performance previously only possible on supercomputers. With this new technology (as well as new advances with GPUs), we will likely be able to attain performance on the 20 gigaflop scale per computer. With about 50,000 such machines, we would be able to achieve performance on the petaflop scale. With software from Sony, the PlayStation 3 will now be able to contribute to the Folding@Home project, pushing Folding@Home a major step forward.
Our goal is to apply this new technology to push Folding@Home into a new level of capabilities, applying our simulations to further study of protein folding and related diseases, including Alzheimer's Disease, Huntington's Disease, and certain forms of cancer. With these computational advances, coupled with new simulation methodologies to harness the new techniques, we will be able to address questions previously considered impossible to tackle computationally, and make even greater impacts on our knowledge of folding and folding related diseases.
FREQUENTLY ASKED QUESTIONS (FAQ)
How do I get a copy of Folding@home for the PS3?
If you have PS3 system version 1.6 or later, you will see a Folding@Home icon in the Network column of the XBR (PS3 menu). Just click on the icon and that's it. If you don't have 1.6 or later, please perform a system upgrade.
Which keys do what?
Press square to see what the other controls do.
What is the power consumption of the PS3 running the FAH client? Is it safe to run the PS3 24X7?
We expect the PS3 to use about 200W while running Folding@Home. We have several PS3's running in our lab, running Folding@Home 24/7 and have had good results so far.
What type of calculations the PS3 client is capable of running?
The PS3 right now runs what are called implicit solvation calculations, including some simple ones (sigmodal dependent dielectric) and some more sophisticated ones (AGBNP, a type of Generalized Born method from Prof. Ron Levy's group at Rutgers). In this respect, the PS3 client is much like our GPU client. However, the PS3 client is more flexible, in that it can also run explicit solvent calculations as well, although not at the same speed increase relative to PC's. We are working to increase the speed of explicit solvent on the PS3 and would then run these calculations on the PS3 as well. In a nutshell, the PS3 takes the middle ground between GPU's (extreme speed, but at limited types of WU's) and CPU's (less speed, but more flexibility in types of WU's).
Can I change the donator name and team number?
Press triangle while in the visual client to change your username and team number.
How long will it take to complete the work unit (WU)?
We have set PS3 WU's to take approximately 8 hours to complete. The logic behind this was to ensure that the PS3 could be run only over night and still yield a useful result. We will likely decrease this time in the future to try to make it easier for PS3 donors to only briefly run their machines, but still make useful contributions.
When will my points show up in my account?
It can take 1-2 hours after the WU has been received for the points to be entered into our database. We usually run hourly updates, but during periods of heavy activity, it can become less frequent.
How are the number of active machines calculated?
One central problem in distributed computing is the calculation of how many computers are actively part of the project. Many projects merely cite the "total number of devices", i.e. the number of computers to ever be a part of the calculation. This can of course grossly overestimate the current power of the distributed computing network.
Instead, we calculate the number of "active" clients, i.e. machines that have returned work recently. Active PS3's are defined as those which have returned WUs within 2 days. This is a much shorter timeout than what we set for normal CPU clients, as the PS3 clients Work Unit deadline is much shorter (typically 2 days). However, as we communicate with the distributed clients fairly infrequently (no more frequently than every 8 hours), it is hard to precisely know how many machines are running and these numbers are best used as an order of magnitude estimate of the power of our network.
How are the FLOPS calculated?
People often use the number of Floating point operations per second (FLOPS) as a metric for the speed of a computer. One question that arises is how to compare machines with radically different architectures. In particular, what requires only a few operations (or even just a single operation) on one machine could require many operations on another. Classic examples are evaluations of functions like the exp(x) or sin(x). One GPU and Cell hardware, functions like this can often be calculated very quickly, say in one cycle, while this is often counted as 10-20 operations for other machines.
We take a conservative approach to FLOP calculation, rendering quantities such as exp(x) or sqrt(x) as a single FLOP, if the hardware supports it. This can significantly underestimate the FLOP count (as others would count an exp(x) as 10 or 20 FLOPS, for example). Others take a much less conservative approach and we are considering giving two counts, adding a more traditional (less conservative) count as well.
The ideal comparison would be to run Folding@Home on the supercomputer itself to test its speed. In this sort of comparison, Folding@Home would likely do very well, and we are investigating the best way to perform this benchmark, as we expect people would be interested.
It seems that the PS3 is more than 10X powerful as an average PC. Why doesn't it get 10X PPD as well?
We balance the points based on both speed and the flexibility of the client. The GPU client is still the fastest, but it is the least flexible and can only run a very, very limited set of WU's. Thus, its points are not linearly proportional to the speed increase. The PS3 takes the middle ground between GPU's (extreme speed, but at limited types of WU's) and CPU's (less speed, but more flexibility in types of WU's). We have picked the PS3 as the natural benchmark machine for PS3 calculations and set its points per day to 900 to reflect this middle ground between speed (faster than CPU, but slower than GPU) and flexibility (more flexible than GPU, less than CPU).
The PS3 is outrunning all the rest of the FAH client types. Should I stop my existing PC/GPU/... FAH clients?
No, the other clients are valuable to us too and we have chosen a points system to try to reflect the relative merits of each different platform to our scientific research. For example, the SMP client has been producing some very exciting scientific results and continues to be very important in our work. By supporting machines with lots of different functionality, we have a very rich set of hardware on which to run calculations, allowing us to tailor calculations to the hardware to achieve maximum performance.