Slashdot Mirror
BOINC Exceeds 2 Petaflop/s Barrier
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)."
BOINC finally has enough computing power to handle Vista Ultimate and a few applications!
My blog
We could make T-shirts saying "Computer scientists BOINC faster", but I not sure that sends the right message.
That'll do
Just because you are wrong and I called you out on it doesn't mean I am a Troll.
?? The article is clearly talking about super computers not operating systems, silly.
"The difference between genius and stupidity is that genius has it's limits" - Albert Einstein
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...
No sig. Move along - nothing to see here.
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.
Comment forecast: Bits of genius surrounded by a sea of mediocrity.
Folding@home, 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.
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.
My blog
I wonder what the computing power is of some of the larger botnets. They are not likely to be listed in the "Top500".
Flexible bare-metal recovery for Linux/UNIX
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.
Convert FLACs to a portable format with FlacSquisher
half a million computers, times a couple of hundred watts would gives ~10MW which is about 4 blue whales or 3 diesel locomotives http://en.wikipedia.org/wiki/Orders_of_magnitude_(power)#megawatt_.28106_watts.29
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
Test your net with Netalyzr
That's ridiculous, why would you use ~4 BW or ~3 DLs when you could use 1 POOT (Power Output Of Togo). BOINC uses about 1 POOT.
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?
"Trolls they were, but filled with the evil will of their master: a fell race..." -- J.R.R. Tolkien on Olog-hai
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?
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.
-----BEGIN GEEK CODE BLOCK----- Version: 3.12 GIT d? s: a-- C++++ UL++++ P++ L+++ E- W++ N o-- K- w--- O- M+ V PS+ P
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.
There are some people that if they don't know, you can't tell 'em.
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...".
Comment forecast: Bits of genius surrounded by a sea of mediocrity.
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.
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.
Sent from your iPad.
Strangely enough 410 of the supercomputers listed in the top500, or 82% are of architecture type "cluster".
Help stamp out iliturcy.
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.
Was there some sort of fundamental, theoretical limit that could have made getting to 2 petaflop difficult or impossible? Did a graph of BOINC computer power vs time ramp up from zero, stall around 2 PFLOP, and only now punch through? Did the administrators have to come up with some sort of breakthrough or new insight to reach this mark? Two PFLOP is just a round number - is it really any different from 1.9 or 2.1?
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?
Scientific progress goes BOINC?
The difference between spam and poop is that you don't have to dig through septic tanks looking for real food. -- Me