5199243
story
Comments: 114 +- Technology: BOINC Exceeds 2 Petaflop/s Barrier on Tuesday July 14, @02:06PM
Posted
by
kdawson
on Tuesday July 14, @02:06PM
from the faster-faster-for-science dept.
from the faster-faster-for-science dept.
background: url(//a.fsdn.com/sd/topics/topicsupercomputing.gif); width:81px; height:72px;
supercomputing
background: url(//a.fsdn.com/sd/topics/topicinternet.gif); width:70px; height:73px;
internet
Myrrh writes "Though an official announcement has not yet been made, it would appear that the BOINC project as a whole has exceeded two petaflop/s performance. The top page features this legend: '24-hour average: 2,793.53 TeraFLOPS.' According to last month's Top500 list of supercomputers, BOINC's performance is now beating that of the fastest supercomputer, RoadRunner, by more than a factor of two (with the caveat that BOINC has not been benchmarked on Linpack)."
Related Stories
I have no doubt that it is a part of the destiny of the human race,
in its gradual improvement, to leave off eating animals.
-- Thoreau
All trademarks and copyrights on this page are owned by their respective owners. Comments are owned by the Poster. The Rest © 1997-2009 Geeknet, Inc.
Finally! (Score:5, Funny)
BOINC finally has enough computing power to handle Vista Ultimate and a few applications!
Re:Finally! (Score:5, Funny)
Parent
Re:Finally! (Score:5, Funny)
Parent
Re: (Score:2)
I think you mean Crysis with graphics set to maximum.
Now all I need is for every BOINC user to download the HertzaHaeon plays Crysis project.
Re: (Score:2)
I think you mean Crysis with graphics set to maximum.
On windows vista?
Missed opportunity (Score:5, Funny)
We could make T-shirts saying "Computer scientists BOINC faster", but I not sure that sends the right message.
Re: (Score:3, Funny)
BOINCing computer scientists: now petaphiles x2!
Re: (Score:2)
We could make T-shirts saying "Computer scientists BOINC faster", but I not sure that sends the right message.
Most women who've slept with computer scientists would agree that they are pretty fast ;)
Re: (Score:2, Funny)
Most women who've slept with computer scientists would agree that they are pretty fast ;)
On the plus side, they know how to press the right buttons. Or, so I'm told.
Re: (Score:2)
"Grid volunteers do it in groups of 571,534"
That'll do Bionic (Score:3, Funny)
Wait a minute... (Score:4, Funny)
Parent
Emacs.... (Score:2)
Re: (Score:3, Funny)
?? The article is clearly talking about super computers not operating systems, silly.
I wonder what BOINC's contribution to CO2 output.. (Score:2, Interesting)
A good question to ask is how many kWh were consumed for that computing output.
Since they know what CPUs are running on every BOINC client and the thermal power of them are generally known, it should be possible to calculate...
Re:I wonder what BOINC's contribution to CO2 outpu (Score:5, Insightful)
Nothing. BOINC requires no CO2 to operate.
It could just as easily be run on computers powered by nuclear or solar power, producing no CO2 (past initial construction).
Why does CO2 have to be the end-all-be-all of everything? Why not ask how much coal dust or mercury is now in the atmosphere thanks to the plants that power most of those computers.
Parent
Re: (Score:2)
I think the main point of the OP is BIONIC is using idle time, which means every second that BIONIC is running is a second your PC could be sleeping in S3 suspend.
Frankly I wonder if everyone running BIONIC relaisezes this... as if they live in an average US State it is basically costing them $10+ / month to run the thing for every PC it is on 24/7.
Re:I wonder what BOINC's contribution to CO2 outpu (Score:5, Insightful)
I'm aware. My point is that I'm tired of "but how much CO2 does it generate?" being tacked on to everything because it's the current fad question.
The coming ice-age was a science disaster fad. So was the coming overpopulation and world famine. And the ozone holes that would cause everyone to get skin cancer. And....
There are more important questions. Much of this energy would be used anyway, but it would be in centralized supercomputers. This way though it's cheaper for the scientists so we can get more research done, even though it's slightly less efficient.
I'm just really tired about CO2 being discussed attached to everything. "Should I buy new shoes?" "Well, the CO2 produced from rubber is... and.... but...".
Parent
Re: (Score:2)
Duh, we're not getting skin cancer because we actually fixed the problem.
1. We discovered a problem: The ozone hole. We found it before it got large enough to start causing really big problems.
2. Predictions were made of what would happen if it continued getting bigger, and the potential consequences were unpleasant.
3. Actions were taken to correct the situation.
4. That made things a lot better. It's not been eliminated, but at least it's on th
Re: (Score:2)
Re: (Score:2)
Plus in colder climates the cost of electricity for running the computer is directly offset by the amount saved on using other sources of heat, whether they be electric, oil-based, or gas-based.
At my parents' house in New Hampshire, my bedroom regularly got to 45 degrees in the winter if the door was closed and no electronics were on, because my room was across the house from the furnace. I'd turn on my computer, overclock my video card, and play games until my room temperature was closer to 60F. Overnight,
Re: (Score:2)
It doesn't matter than nuclear energy has possible waste disposal issues. My point is that discussing the CO2 output caused by this project is useless. The question is how much energy is wasted, not how much CO2 is created.
We just happen to be on a kind of energy that frees previously trapped CO2. We could be mostly on one that produces radioactive waste, or one that uses up silicon (solar), or ones that cool down the earth (hydrothermal, to the teeny-tiny degree it does).
If we are going to discuss the ener
Re: (Score:2, Insightful)
Since they know what CPUs are running on every BOINC client and the thermal power of them are generally known, it should be possible to calculate...
That only counts CPU usage. It doesn't count I/O, which would at least include memory I/O, disk I/O, network I/O.
Re:I wonder what BOINC's contribution to CO2 outpu (Score:5, Insightful)
I can guarantee that several orders of magnitude more kWh are consumed by computers that are needlessly on and idle.
Running BOINC on a computer that's sitting idle helps improve its energy efficiency. It may be consuming electricity, but at least then it's doing something.
Parent
Re:I wonder what BOINC's contribution to CO2 outpu (Score:5, Funny)
Parent
Re:I wonder what BOINC's contribution to CO2 outpu (Score:5, Funny)
Surely we can reduce the inefficiency, and POOT less.
Why are we using a distributed system of energy-inefficient comPOOTers?
The big question is, how many cow farts would we need to harvest to produce one POOT of energy?
Parent
Re: (Score:3, Funny)
Haven't you heard? The POOT is out as a measure of energy. People in the know(TM) these days are using the FART. (Free African Republic of Tonga)
I understand that Taco Bell has chosen to support the FART as well. Something to consider. The POOT's reign has come to an end. Long live the FART.
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Just goes to show...
Even on a decidedly intellectual discussion site, a decent fart joke still blows them away.
Considering a spherical cow: 140 tons/hour CO2 (Score:5, Interesting)
Lets say a typical computer running BOINC contributes 1 GFlop at 100W (1e2W). So at 2e6 GFlops, tats 2e8W or 2e5 kW.
According to the energy department, we can assume that 1.4 pounds of CO2 per KWh, so that says BOINC is at ~3e5 pounds/hour of CO2, or about 140 tons/hour of CO2.
I get a very similar number if I back of the envelope what a coal plant should be based on ~500 tons/1 GW.
http://www.eia.doe.gov/cneaf/electricity/page/co2_report/co2report.html [doe.gov]
Parent
Re: (Score:2)
The irony that climate models usually require super computers to run in a timely manner is not lost on me.
Re:I wonder what BOINC's contribution to CO2 outpu (Score:4, Interesting)
Once that's done, we can do a comparative analysis of CO2 of all the machines machines running WoW (factoring in the increased power draw of a machine with a higher end video card, plus increased disk & memory I/O compared to a machine running BOINC). I'd be willing to be the BOINC 24x7x365 number works out to be smaller, or at least on par with a WoW machine going 4 hours a night several times a week.
Waste is, and will always be, a relative term.
Parent
Re: (Score:2, Informative)
Actually I run the Linpack HPL here at the lab, once with two clusters (one 228 nodes 4cpus x 4cores each x 4 float ops per cycle, and one 1152 node cluster of the same AMD configuration) we hit 1.069 MegaWatts and I started peeling the paint off of a huge transformer in the basement. I had to do one at a time. Linpack is a power pig with double precision floating point if your cpu/thread/mpi balance is correct.
Still far behind... (Score:5, Informative)
Folding@home [wikipedia.org], which has passed 5 petaflops on February. Note that Folding is a single project, while the Petaflop measurement for BOINC are the aggregate total for that platform, which runs many independent and often unrelated projects.
Getting that thing bundled on PS3 was brilliant.
Re: (Score:2)
Re: (Score:2, Interesting)
Re: (Score:2)
Botnets (Score:4, Interesting)
How cost effective is this really? (Score:3, Interesting)
BOINC uses 571,534 computers. The indirect cost of supporting and maintaing the software, hardware, etc is borne by the volunteers but it still has to be paid.
Additionally, they claim it uses between $3 and $8 a month extra in energy in the US*, and double to triple that in Europe.
* This number is poorly derived. They based it on an 'average' electrical rate in the US, e.g. it looks like they added up all the rates and divided by 50. The average American however pays more than the average rate, because the majority live in the dense states where electricity costs most. Florida, New York, Caifornia, etc vs the relatively tiny populations in North Dakota where electricity is cheap.
Further, I'm confident that the skew is weighted towards broadband users, which further skews things away from rural North Dakota where electricity is cheap.
Further, they fail to account the extra cooling required as a result of generating more heat. Granted in -some- places where you need more heat this will offset your heating bill in your favor, but again, most people are clustered in areas that require more cooling than heating.
So, bottom line, I'd say their assessment of electrical costs is on the low side.
For the sake of argument, lets say it averaged out to 10$/mo. (Including europe.) What kind of computing power could you build and run with $5.7M/month.
Especially when you have the freedom to install it where you want, and factoring in that industrial electricity is cheaper than residential. With a $68M/year budget, could you beat boinc?
Re: (Score:2)
You easily could, but you're not the one paying the (processing, at least) electric bills, and the huge cost is spread out over hundreds of thousands of contributors, so while it really uses a huge amount of electricity and money, the average user running it is only going to see a relatively small increase in cost of electricity, making it that much more likely that they'll contribute, whereas you'd be pretty hard pressed to find a way to get 68 million for any reason.
Grid computing != supercomputing (Score:5, Informative)
According to last month's Top500 list of supercomputers, BOINC's performance is now beating that of the fastest supercomputer, RoadRunner, by more than a factor of two (with the caveat that BOINC has not been benchmarked on Linpack)
Sigh...why do these projects (BOINC, *@home, etc.) insist on comparing their performance to superpercomputers on the TOP500 list? Of course BOINC has not been benchmarked on Linpack. If it was, the performance wouldn't come close to anything at the top of the TOP500 list. A bunch of workstations running a grid client and talking to each other over the internet is never going to have the same type of message passing bandwidth as a supercomputer using something like locally connected infiniband.
Why is this being compared to top500? (Score:5, Insightful)
This is NOT a supercomputer. This is a cluster, and a very slow cluster at that. It seems like people think that anything fast is a "supercomputer" and as techies, we ought to know better.
What makes a supercomputer "super" is its internode communication. You have extremely fast links so that, in theory, any node can access the memory from any other node as it would its own local memory. Now in reality there are some performance penalties, but still. Basically you really have created one large computer, rather than tons of small ones.
This is a cluster, which is as the name implies just a bunch of little computers networked in some fashion working on the same problem. That's great, but not the same thing. The nodes do not have high speed communication, some may even be on modems and only connected occasionally.
Now, why does this matter? Well it depends on the problem you are trying to solve. Some problems need very little communication. A good example would be cracking cryptography. You just divide up the keyspace among all your nodes. There's also very little data to send back and forth. You send you the problem, consisting of the encrypted message to the nodes, and then all the communication from this on is:
Node: Didn't find the key.
Controller: Ok try this range.
Node: Ok.
As such link speed of the cluster can be very slow. Well other problems still work in a clustered environment, but need higher link speeds like gig Ethernet. 3D rendering would be an example. All the nodes can act independent, they are just divided up on frames to render, or parts of a frame or whatever. However since the problem and results are much larger in this case, they need faster communication to make it practical. A modem won't cut it for transferring images that are 50MB each when you are rendering thousands.
However, there are other problems where there is heavy inter node communication. A particle simulation would be like this. Since what happens with one particle affects all others, nodes have to chat continuously. For this, you need a supercomputer. The bandwidth of links must be extremely high and the latency must be extremely low, or else processor power will be wasted just waiting on getting the data that is needed.
So just because something has a lot of CPUs and can crunch a lot of numbers, doesn't make it a supercomputer.
Re:Why is this being compared to top500? (Score:4, Insightful)
There's no reason "supercomputer" needs to only refer to monolithic machines with high-speed interprocess communication, merely because it has primarily meant that in the past.
Parent
Ok but that makes it a meaningless term then (Score:2)
If any cluster is a supercomputer, then just get rid of the term supercomputer and be done with it.
Also there IS a reason, and that is because, as I mentioned, only certain kinds of problems can be solved by a cluster. Thus it becomes an important distinction. Is this a cluster or a supercomputer? If your application requires a supercomputer, you don't want to get duped in to buying a cluster that is being called a "supercomputer" that won't handle your app.
Re: (Score:3, Insightful)
82% solution (Score:2, Insightful)
Obligatory Calvin & Hobbes (Score:2)
Barrier? (Score:4, Insightful)
I think not: 2 petaflops is just a matter of recruiting enough computers and having them running BOINC at the same time. If it has achieved this mark, then it couldn't have been that much of a barrier, could it?
Re: (Score:2)
A fit human can produce somewhere between 150 and 300 watts continuously, with perhaps the occassional excursion to higher. (In contrast, one horsepower is approximately 750 W.) So, in a day, a person might be able to pump out 1-2 kWh, which on the wholesale electrical market might fetch a whopping $0.10. If the company is clever, they'd store and release that power during peak demand, in which case they might get twice that. Could you live on $0.