Gizmodo
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.
Here's how:
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 PS3INTRODUCTION
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)BASICS
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.STATS
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.
Folding at Home Stats and FAQ [Stanford]
PS3 Folding [Gizmodo]
Comments
so how much more powerful than PCs is it now?
give pc's a year or two and the PS3 will seem like the stone age...
The title does not say it all.
FLOPs refer to floating point operations per second. Therefore that means FLOPs are dependent on time. So if someone were to stop FAH on their PS3 and play a game, and then re-launch FAH, the time would increase and therefore the value for FLOPs decrease. Expect a lot of people to do this on their PS3 at this point in time
Give PS3 a year or two and it will seem like some very expensive heater.
but the work is for a good reason. LEt's burn some electricity for Cassius Clay and look-a-likes!
Actually they said that certain servers are be updated and thats messing around with the flop counter... Vijay Pande addressed this concervative counting method before 1.6 firmware was released. The numbers should be back to normal within the next couple of days.
Currently the ps3 is extremely powerful compare to most pcs. ive heard they are roughly 4x quicker but i could be wrong
Yeah it looks kind of noble, the lab claims to be non profit and they will just share any discoveries and give it away free. This means the only ones who profit will be the drug companies who get the free R&D. I remember this Seti @ home they did years ago trying to decode space signals to find hints of life. It is a genious way to get a free supercomputer from other people, got to admit it.
Sounds like a good idea, except it's kind of bittersweet as the drug companies are probably hoping they get handed a free meal ticket if they find anything and publish it for the world to use.
30k machines times 200 watts is about 6 MW. That costs about $500 an hour at a rate of 10 cents per kwh. Good deal for the folders.
Hey Hello_Newman,
As a employee of one of those Pharmaceutical companies, I would like to reming you that we too have supercomputers running around the clock doing data crunching. As for getting any free gifts from the research, I assure you Stanford gets shitloads of money for their research from our companies. There is no free lunch in dealing with any research institution! What ever research any company gets from these places is well paid for in many ways that the public is unaware of due to the nature of the studies.
In addition, please remember that even with any information that we do get, we the companies will spend an additional 400 to 800 million to get it to market hopefully in the course of 4 to 7 years to hopefeully have 5 to 6 years of patent protection. Even after all of that money having been spent on additional research, there is a 75% chance that it will fail out in clinical trials and never see the light of day.
There are not too many other industries that have to spend this amount of money to try to find success.
Rob C, brazil101 your making two very big assumptions:
1) Your assuming in a couple years multi-scaler processors technology like the Cell capable of performing 2-teraflops will be readily available. Intel has said they would like to be able to start getting into multi-scaler processors by 2014. The cell technology is way beyond the years of anything out now. The Xbox 360 triple core processor can do at the most 200 and some gigaflops. This gives you an idea of how powerful the processor is.
2) You also assume the ps3 consumes immense amount of power but compared to what? while running folding@home PS3 consumes 200watts which isn't that much considering a modern computer with a dual core CPU, and a high powered Graphics card will run up to 370Watts.
I really hope microsoft gets with folding@home to bring it to the 360 as well its for a good cause and the 360's got a hella lot of power, especially if they can tie in the GPU as well...
not to mention if they can take advantage of the full 512mb and the 10mb of dram for faster calculations.
Screw ps3 vs 360, i want to see 360+ps3 both working at folding at home together.
jimcord: if they were serious about it they would pay people per WU completed even if its a small amount, thats what paypals for, and since foldings getting paid why shouldnt the distributed members get a lil bit as well :)
Yes its for the good of the world, but watch the # of active users increase as you offer payment :) hell i'd get a dozen pc's and ps3's if i was getting paid per WU :)
@phantam
Awwww how sweet!
I would really like to see Folding@home on 360, I saw it on my friend PS3 and got a little jealous its a pretty cool little program theyve got going, especially for a science nerd like me.
Where does it say anything about the data set being limited by the PS3s 512MB of RAM? All I could find was limitations because of the processor type.
Also where did you find the bit about the GPU being utilized as well? All I've read says the Cell processor is used and the GPU is only used for the graphic rendering.
This is interesting. there was a similar project several years back that attempted to use a large cluster of ps2s as a "cheap" clustered supercomputer.
folding@home is all well and good, but i think most of the real cutting edge research on protein folding is being done by small groups of highly funded researchers. check out Joan Emma Shea's group @ UCSB
Jimcord-> i totally agree. people love to point out how "we are non-profit" lalala. of course NIH and DARPA are funding the crap out of them at the same time. I have yet to hear of a research group at a university that has some how made real profit off a discovery. in most cases a patent will be owned almost entirely by the university, with the PI getting a bonus, and grad students getting nothing but notoriety.
the guys at stanford are using a little bit of ingenuity to get around the fact that they dont have enough machines to throw at their problem. they should go out and try to get a nice SMP. hey, if it works for some people @ UCSB, im sure they could pull it off at stanford.
one of my best friends works as a researcher at standford and before that at the school i used to attend. the way he explained it was that the school gets a heft of royalties while he also got a very small percentage if he held (and he does) a patent on anything. the reason for the small percentage is because the research was done at that institute. but when the numbers get into the billions on royalties, a "small" percentage doesn't sound so small anymore.
are you guys serious?, the ps3 is helping cure diseases and all you fan boys still condem it. give me a freaking break, I would like to see how have contributred to the world, leave the console wars to games and other rubbish, we are talking about helping cure diseases here, sheesh! Post reasonable comments not all the fanboy rubbish.
If you do a little number crunching, you can see that the PC graphics cards are 4 times as effective as the PS3.
200 Watts an hour? Watts are a measure of power, which is the rate at which energy is used. 200 Watts = 200 Joules per second. What you really mean is that the PS3 uses 720 KJ, or 0.2KWH every hour.
Run folding at home while you wait for some real cool games on PS3 kekekekeke
Hey some guys are mad with me but I swear I'm running a console-based Folding here in my Linux rig (An AMD K6 II 500MHz). I've seen some MP3 players wich are faster than mine but that's the way I can help by now, and you guys should do the same. Even if some big drug company will make profit over this, some people (rich people?) will have a new hope. It's better to have an expensive solution than no solution at all.
Guys, dont forget the Genome@home was successful in mapping the entire human genome a few years ago, so this type of distributed computing, while each part seems insignificant, and the end seems out of reach is important.
@brazil101
No insult intended but it's not kekekeke it's supposed to be hehehehe or hahahahaha
Has anyone found out anything about Stanford reavaluating the GigaFlop output of the PS3?
Pharmaceutical companies are not allowed to make a profit? Most of those profits are poured back into the company to develop the next drug that most likely will NOT make it to market. The profit margin is not as large as most people think. The drug you are working on now is being funded by the one that Finally made it to market. You better hope you get results, and the faster the better.
If you have ever seen someone waste away from Alzheimer's disease, this is a small price to pay (a couple bucks worth of electricity) to try and rid the world of this terrible disease. I see it as insurance for my old age. Maybe a cure before I get old or someone else I care about.
macbandit: not if he's imitating Popeye the Sailor Man.
Yes, here is a discussion related to PS3 performance including a posting by Prof. Vijay Pande who directs the Folding@Home project at Stanford:
http://forum.folding-community.org/ftopic18790.html
That includes:
...
On top of that, we have been updating the flops per machine update more frequently for the PS3 in order to try to keep this as accurate as possible as we approach a petaflop.
...
-Gary
I'm glad that there are some 360 supporters (fanboy is such and ugly word) that understand that PS3 and Xbox 360 should work together to cure disease. I fold on my PC but will be folding on my PS3 when I eventually get one.
Shame on the supporters that still condemn the PS3 for helping the folding@home project.
You don't want to forget about the X1900 GPUs (and whichever other ones they might support in the future). The x1900 more efficient per FLOP, cost about half as much as the PS3, and has less power consumption on its own. (150W IIRC)
The computer definitely uses more power in total. But look at the PS3 stats right now: they're at about 3/4 the 40,000 peak when everyone started pushing for PS3s to fold. I wouldn't be surprised if PS3 users got bored and started playing games on it. I doubt the active number would reach that level anytime soon. The PS3 can only do one thing at once, and the PS3 is meant to be played on. On the other hand, since GPU folding won't use the CPU, you can run F@H on GPUs with minimal impact on your day-to-day tasks (unless you do graphics work or game a LOT)
I've frequented the Giz for quite awhile now, although I've never actually tried to comment until now. This is more of a question than a comment. I just updated my ps3 and I'm wondering if you fine folks at Gizmodo have a folding team I could join?
Now I hope that Tivo and other set top box companies integrate F@H into their devices. The Tivo is on 24/7, and it has no sort of sleep mode. It's not always indexing, and I believe encoding/decoding is done by a dedicated chip rather than the CPU, so wouldn't it be great to use that power that's sitting around all night?
An ovarian cancer test will determine if a woman has ovarian cancer, which is a tumor on the ovaries. These tests are very accurate and the sooner a woman finds out she has ovarian cancer, the sooner the cancer can be treated.
Start a discussion:
Login with your username and password below. Or comment on this post via email.
Forgot your username or password? New User?