Slashdot Mirror
World's Fastest Supercomputer To Be Built At ORNL
Homey R writes "As I'll be joining the staff there in a few months, I'm very excited to see that Oak Ridge National Lab has won a competition within the DOE's Office of Science to build the world's fastest supercomputer at Oak Ridge National Lab in Oak Ridge, Tennessee. It will be based on the promising Cray X1 vector architecture. Unlike many of the other DOE machines that have at some point occupied #1 on the Top 500 supercomputer list, this machine will be dedicated exclusively to non-classified scientific research (i.e., not bombs)."
Cowards Anonymous adds that the system "will be funded over two years by federal grants totaling $50 million. The project involves private companies like Cray, IBM, and SGI, and when complete it will be capable of sustaining 50 trillion calculations per second."
Personally I'm happy to see Cray still making impressive machines. Not every problem can be solved by "divide and conquer" clusters.
As usual, there should be a qualifier as to what is meant by fastest. According to their definition they are, but not according to NEC's, for example.
50 trillion calculations per second.
Wow, that's darn fast.
I wonder if that processing power could be used for rendering like was done by Weta and how the performance could compare to their renderfarm.
This is the sig that says NI (again)
I thought the age of the over-priced supercomputer was over, and the age of the cluster had begun?
Sure, I'd love to have one of those things in my house, but as long as the government is spending my money, I think I'd rather see them go for a more cost effective solution, rather than another 1 ton monster that'll be obsolete in two years.
ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.
> ...capable of sustaining 50 trillion calculations per second.
:D
Hmm...I wonder if I could borrow it for a few days to give my dnet stats a boost
Wow, 50 trillion calculations per second. Thats almost fast enough to finish an infinite loop in under ten hours.
And then VT will add more nodes to their G5 cluster. :P
I claim first use of "Error No. 0B" - or "No. 0B error." It'll be the new ID 10T!
at an Impresive 67fps on this baby...
Still a whole year until they have a full machine, but the 512-way prototype reached 1.4 TFlops (LinPack). The complete machine will have 128 times the nodes and 50% higher frequency. So even with pessimistic scalability, this will be more than twice as fast.
The article mentions that the new supercomputer will be used for non-classified projects. Does anyone have more exact details of what these projects may involve? Will it be a specific application, or more of a 'gun for hire' computing facility, with CPU cycles open to all comers for their own projects? It would be interesting to know what types of applications are planned for the supercomputer, as it may be possible to translate a raw measure of speed like the quoted '50 trillion calculations per second' into something more meaningful, like 'DNA base pairs compared per second', or 'weather cells simulated per hour'. Are there any specialists in these kinds of HPC applications who would like to comment? How fast do people think this supercomputer would run apt-get for instance? Would 50 trillion calculations per second equate to 50 trillion package installs per second? How long would it take to install all of Debian on this thing? Could the performance of the system actually be measured in Debian installs per second? I look forward to the community's response!
Can anyone explain what "DOE" is? I'm assuming it's some american govt thing like department of energy. is that correct?
...because a day later Palm users will massively interconnect to form the World Fastest Clustered Computer Environment. The OS? Linux, of course. .}
Help end the use of Sigs. Tomorrow
or it certainly seems like it (reading the specs of the thing)
. . . it will be capable of sustaining 50 trillion calculations per second.
Does anyone else not gain anything from that statement? 50 trillion calculations means very little if all it can do is flop a bit back and forth 50 trillion times. Perhaps someone could come up with a better benchmark, like the largest number it can factor in a minute, on average. Even then we may be talking about huge exponents in scientific notation. =p
It could just be the fact that it is ten in the morning, but 5*10^13 seems incomprehensbily large.
This statement is false.
I don't think Crays that were build 5 years ago are considered obsolete by anyone's standards.
Clusters solve different jobs than supercomputers. Sometimes they bleed into one another, but there are some things supercomputers will always be better at (because of higher memory bandwidth for one thing).
I couldn't find the source for the "non-classified" bit... These things are often not used for simulating new bombs but for, "evaluating the stability of the nuclear stockpile." Does research into whether the yield of our cold war nukes is down or up a few kilotons qualify as non-classified?
Who do you get to be an expert to tell you something's not obvious? The least insightful person you can find? -J Roberts
They were listed as part of the solution.
Oak Ridge has done extensive evaluations of recent IBM, SGI and Cray technology. Though I am still looking forward to data on IBM's Power5.
Cray X1 Eval
SGI Altix Eval
Sure, personal computers will be faster in a few years, but sheer speed isn't the only thing that makes a supercomputer. What divides massive clusters of $200 Wal-Mart boxes from a mid 80's Cray (those Crays, by the way, still go for ~$20K) is that the Cray uses much faster, wider pipelines between components. With the current trend of lagging the various buses behind the processor almost by orders of magnitude, the desktop PC won't approach current-day supercomputers for a long time.
"Because Science" is one step from "Because old book". Try "Because of my experiment testing my falsifiable assertion".
I think ORNL and PSC know a lot more about supercomputing than you (or Internet rag pundits) do. As others have noted, there are real reasons for Big Iron.
Clusters are great for certain problems but for heavy computation -- think simulating two galaxies colliding or earthquake modeling -- off the shelf clusters don't cut it.
They're not wasting tax-payer money unless you consider basic researcher a waste.
And I'm still waiting for my turn to drive one of the Mars rovers.
--- Ban humanity.
So each node is directly connected to six ajacent nodes. Contrast this with the Thinking Machines Connection Machine CM2 topology, which had 2^N nodes connected in an N dimensional hypercube. So each node in a 16384 node CM2 was directly connected to 16 other nodes. There's a theorem that you can always embed a lower dimensional torus in an N dimensional hypercube, so the CM2 had all the benefits of a torus and more. This topology was criticized because you never needed as much connectivity as you got in the higher node-count machines, to CM2 was in effect selling you too much wiring.
Thinking Machines changed the topology to fat trees in the CM5. One of the cool things about the fat tree is it allows you to buy as much connectivity as you need. I'm really surprised that it seems to have died when Thinking Machines collapsed. On the other hand, any kind of 3D mesh is probably pretty good for simulating physics in 3D. You can have each node model a block of atmosphere for a weather simulation, or a little wedge of hydrogen for an H-bomb simulation. But it might be useful to have one more dimension of connection for distributing global results to the nodes.
--- Often in error; never in doubt!
Man I hope Virginia Tech buys some more Xserve G5s - they are slipping down the ranks :)
50 trillion of calculations per second. Is that a synonym of flop (floating-point operation)? ...
How does this computer compares with the BlueGene/L (131,072 cpus, 0.5 Petaflops -estimated)? Don't be mislead by the name (*Gene)... this will be a computer for classified simulations (it will have a 1-2 year long "science run", for testing purposes with non-classified simulations).
Cheers...
Wow, that's the first Beowulf cluster comment I would mod as interesting.
Sigs? We don't need no stinking sigs!
... to post the usual jokes, I've got to ask: What runs on these kind of machines? What OS do they use, and what kind of software? Can you buy software for supercomputers, or will the customer/new owner have to write all the software to run on it themselves? Anyone out there working on something similar have interesting facts about the software?
I worked in Instrumention and Control for the Free Electron Laser project at the Thomas Jefferson National Accelerator Facility. We also host the CEBAF (Concentrated Electron Beam Accelerator Facility), which is a huge ass particle accelerator.
the DOE does a lot of basic research in nuclear physics, quantam physics, et cetera. the FEL was used to galvanize power rods for VPCO (now Dominion Power) and made them last 3 times as long. Some William & Mary people use it for doing protein research, splicing molecules and stuff.
The DOE does a lot of very useful things that need high amounts of computing power, not just simulating nuclear bombs (although Oak Ridge does taht sort of stuff, as does Los Alamos). We only had a lame Beowulf cluster at TJNAF. I wish we would have had something like this beast.
I want to know how it stacks up to the Earth Simulator.
SGI's IRIX.
That detail is kept under pretty tight wraps by Cray. It is licensed from SGI and is discolosed as a business risk in their regulatory filings.
IRIX has always been my favorite UNIX.
It seems to me that as long as multiprocessor machines qualify as supercomputers, then the Google cluster counts as the fastest right now, and will still count as the fastest long after this new DOE computer is built.
(Tin foil hat on) The labs at Oak Ridge got their start during the 1940's and were the source for the enriched uranium used in the first atomic bombs used against Japan and in the deserts of New Mexico. Perhaps the DOE has ulterior motives when it comes to using those extra floating point operations...
Nonclassified implies that it was never classified, while unclassified implies that it was once classified, but now is not.
:-/
I don't know which is more accurate in this case being the typical slashdotter, and not actually reading the article.
Which brings me to my point. Half the time I don't even bother trying to read the article and the other half the time it is slashdotted, which is about the same result.
Agent K: A *person* is smart. People are dumb, stupid, panicky animals, and you know it.
This is the beginning of the end... Marry this supercomputer with AI and BitKeeper access to the kernel and who knows what will happen next.
Ok, nonclassified means that there is no classification applied.
Unclassified means that the material has been assigned the classification of Unclassified... there are other classifications too.
For example personal e-mail at home is generally nonclassified. e-mail on a government computer would generally be unclassified.
Food not Bombs is a nice platitude but it breaks down when you notice that the Bombees are usually well fed
ASCI Purple (IBM Power5) is capable of 100 teraflops. The Blue Gene/L machine is capable of 367 teraflops.
i es/news/ pressreleases/2002/nov/asci_purple.html
This press release is almost 18 months old, btw...
http://www-1.ibm.com/servers/eserver/pser
Maybe the headline "fastest -unclassified- supercomputer" would be more fitting.
...
"Will it be a specific application, or more of a 'gun for hire' computing facility, with CPU cycles open to all comers for their own projects?"
This will be what is known as a "user facility" at DOE. CPU time will be doled out on a competetive basis, i.e., if someone has a project they would like to use it for, they will submit a proposal which will then be reviewed against others.
Big Mac was tested in a small 128 node configuration as a prelude to the full 1100 nodes.
The 128 node cluster was benchmarked at ~80% efficiency, or ~1.6 Teraflops. The final cluster achieved a RMax of 10.28 TFlops, ~60% of the 17.6 TFLOP theoretical peak.
A 6000 node cluster would be very difficult to manage.
You are speaking about Government definitions, regarding specifically intellegence classification system. I was using a more broad application in my definition, that would be more applicable outside of the intellegence community.
In fact, the intellegence definition is the typical oxymoron. Classified as "unclassified" is typical government stupidity. Think about it.
Agent K: A *person* is smart. People are dumb, stupid, panicky animals, and you know it.
I love how the poster writes that all classified government work deals with bombs. There are just a few more programs than "bombs".
Run a test case of a Navier-Stokes problem (just one of many which spring to mind; solving the Maxwell equations isn't actually fun either) on both a shared memory versus a clustered machine with poor IO bandwidth. Compare. ...
The shared menory machine will beat the shit out of those nowadays (admittedly) cheap clusters. Comparing bang for bucks is an entirely different issue though
Just my 0.01Euro.
And I remember what was happening when the Cold War was declared "over": the lab funding started to dry up. K-25 was shut down while X-10 (aka ORNL) and Y-12 were scaled back a lot. So these labs were forced to re-examine what they do for better funding opportunities.
X-10 (ORNL) has branched out into a lot of helpful areas. Some of its projects include environmental cleanup and alternative energy production. It also spends a lot of resources on testing how to safely store and transport dangerous waste (a friend's dad was one of those people that drops containers all day). Any of these could be candidates for this computer.
Any tin-foil hats should be directed at Y-12. That's the DOD plant; X-10 is just DOE.
In the long run one would like to be able to get such simulations from the 10,000 atom level up to the billion-to-trillion (or more) atom level so you could simulate significant fractions of the volume of cells. Between now and then molecular biologists, geneticists, bioinformaticians, etc. would be happy if we could just get to the level of accurate folding (Folding@Home is working on this from a distributed standpoint) and eventually to be able to model protein-protein interactions so we can figure out how things like DNA repair -- which involves 130+ proteins cooperating in very complex ways -- operate so we can better understand the causes of cancer and aging.
No, there are other components that go bad over time.
Also, in nukes, the short-lived component is the initiator, which is based on an alpha emitter with a half-life of a few months. They have to be changed out regularly.
The clearance system sounds logical. It is not. It is completely arbitrary. -- John Bolton
Thank you for your understanding in this matter,
Your friendly neighbourhood IRS agent.
Sorry, it looks like the URL has changed. The home page for Folding@Home is here.
As usual, there should be a qualifier as to what is meant by fastest.
When complete it will be capable of sustaining 50 trillion calculations per second.
Screw that. How many fps can it manage in Quake III?
...will it be able to run Longhorn?
Tim
Warning: abstract thoughts ahead.
Considering the whole of spacetime as a single unit, with our perception limited to only one piece of it at a time, it occurs to me that perhaps everything in both our future and past exists all at once; we're just sliding down a scale as the next section is revealed to us.
That said, wouldn't it make sense that the world's fastest computer is among the very last "super" computers built, many years (centuries? millennia?) in our future (if you want to call it that)? No computer we build today could possibly ever be the world's fastest unless the world cease's to be.
Besides, according to Douglas Adams, Earth itself is the world's fastest computer, designed by Deep Thought.
Why do I have the feeling this is going to be a 64-way nitrous-cooled Athlon64 beast ? And you can bet it will be running SETI.
-Billco, Fnarg.com
At that speed, if it were running Windows XP, the whole internet could be infected with a virus in mere nanoseconds.
as a relative n00b to digital systems (i'm taking part 2 of an intro course), it's my understanding that roundoff in larger digits was one of the major contributing factors to the early cray supercomputers' speed. has cray moved on from that design philosophy?
We're not fat, we're drought and famine resistant.
Slashdot Eds Link Anonymous Posts With Logged Posts
They Are Vermin Feeding On Each Other's Feces.
I Hate \.
I believe the speed was due to many factors. Here are a few.
--- Often in error; never in doubt!
I'm excited that it's going to be a Cray, as they have the best memory-to-processor architecture. Scientific problems can be subdivided, but there will always be heavy communication between the processors. In particular global communication (a global sum for instance) is a killer. The more processors, the slower this operation will run, so for a big enough machine, this can actually dominate the cost. You get to a point where adding more processors does not make you any faster! The Cray has a beautiful architecture, where one processor can put data straight _into_register_ on another processor. No cache and network delays. This is freakin' awesome. In Cray's presentation about the X1 they have an ocean simulation code that keeps scaling way beyond IBM, HP, &c machines, precisely because of the efficiency in global operations. My disappointment is that they are only aiming for 50Tflop. The Earth Simulator hit 37 two years ago! This is no progress. Victor.
Or would it be moving away from you?
Someone mod the parent up, it's funny.
well, 0-4 are all true.
comparing this to early crays is a little difficut though. For the early crays one advantage was vectors and the other was pipelines.
vector processors are cool, because they tend to be much more tolerant of the latency. You issue a load command, and it does loads until the vector-register is full. Equivalent to dozens of loads (and dozens of round trip latency to memory) on a scalar architecture. The same thing applies to the execution units. You tell the CPU ADD R1 R2 R3, and it pumps the first elements of R2 and R3 registers through the ALUs and into R1 and keeps working until it gets through all of the elements in the vector. Later models supported chaining, which allowed the output from one of these operations to feed into the input of another operation. Vector CPUs are very good at keeping the ALUs busy.
The other advantage of the early crays was pipelining. YMP designs, for example, had multiple integer, FP, load/store, and reciprical devide units. All of these (and the dispatch unit) were pipelined, allowing a munch higher clock rate than traditional designs. Multi-pipeline designs are now the norm, (powerPC, Pentium, MIPS, etc.) but were pretty amazing at the time.
The cooling, incidently, was necessary at any clock rate. Early Crays. (well right on through to the T90) used bipolar transistors, rather than CMOS. In this sort of logic you switch current rather than switching voltage. The net result is that the early crays used a TON of electricity and needed massive cooling systems.
This project claims many big improvements. First, programmers will be available to help parallalize code of scientists, who may be experts at, say, weather or protein folding but may not be experts at parallel code. Further, the facility is supposed to be open to all scientists from all countries and funded by any agnecy. CPU cycles are to be distributed on a merit-only basis, and not kept witin DOE for DOE grantees to use, as apparently has happened within various agencies in the past.
_ ___
The idea is to make it more like other national labs where - for example in neutron scattering - you don't have to be an expert on neutron scattering to use the facility. They have staff available to help and you may have a grant from NSF or NIH but you can use a facility run by DOE if that's the best one for the job.
I attended this session at the American Physical Society meeting this March and I'm assuming this is the project referred to in the talks - I apologize if I'm wrong there, but this is at least what is being discussed by people within DOE. I'm essentially just summarizing what I heard at the meeting so although it sounds like the obvious list of things to do, apparently it has not been done before.
The prospect of opening such facilities to all scientists from all nations is refreshing during a time where so many problems have arisen from lack of mobility of scientists. For example, many DOE facilities such as neutron scattering at Los Alamos (LANL) have historically relied on a fraction of foreign scientists to come and use the facility and this helps pay to maintain it. Much of this income has been lost and is not being compensated from other sources. Further, many legal immegrants working within the Physics community have had very serious visa problems preventing them from leaving the country to attend foreign conferences. The APS was held in Canada this year and the rate of people who could not show up to attend and speak was perhaps ten times greater then the APS conferences I attended previously. Although moving it to Canada helped many foreign scientists attend, it prevented a great deal of foreign scientists living within the US from going. Even with a visa to live and work within the US, they were not allowed to return to the US without additional paperwork which many people had difficulty getting.
Obviously, security is heightened after 9/11, as it should be. I'm bringing up the detrimental sides to such policies not to argue no such policies should have been implemented, but to suggest the benefits be weighed against the costs - and the obvious costs such as to certain facilities should either be compensated directly or we should be honest and realize we are (indirectly) cutting funding to facilities which are (partly) used for defence in order to increase security.
I mention LANL despite it's dubious history of retaining secrets because I have heard talks by people working there (this is after 9/11) on ways to detect various WMD crossing US boarders. Even though they personally are (probably) well funded, if they facilities they need to use don't operate any more this is a huge net loss. My understanding is that all national labs (in the US) have had similar losses from lost foreign use.
___________________________________________
a war on terrorism? How can we end a war on a method?
...can you image a beowulf clusters of those? :)
No. Big Mac was one of the early nicknames for the virginia tech cluster.
Yeah, but does it run linux?
If you look at the Cray press release, they state it will be 20 Tflops in '04, 100 in '06, and 250 in '07. So the answer is a whole lotta apples.
"Any tin-foil hats should be directed at Y-12. That's the DOD plant; X-10 is just DOE."
You're right, but let me clarify something:
The biggest weapons labs in the country are DOE, not DOD facilities. These are the "tri-labs": Los Alamos, Lawrence Livermore, and Sandia. They are operated by the DOE's NNSA (National Nuclear Security Administration).
The other major DOE labs (including ORNL) are operated by the DOE's Office of Science. These are non-weapons labs. For you conspiracy theorists out there, its pretty obvious that these are non-weapons labs. No guys standing around with M-16's etc., as you would find at a place like Los Alamos. Much, much less security.
the world always has needed more of me.
Well, from that top 500 list, I'm impressed my desktop PC (3200 MHz PIV, not actually listed, 2.5 is fastest).
It smokes the earliest few dozen Crays, not to mention the IBM RS6000 series, and smokes the holy hell out of the IBM 3090 I used at U-Mich in the mid-late '80's.
Of course, if it were to process a ton of data, I dare say the I/O might make it slow down a lot from those machines...
(-1: Post disagrees with my already-settled worldview) is not a valid mod option.
Dude, it's no secret:l -S-2346-23/z1019077484.html
http://www.cray.com/craydoc/manuals/S-2346-23/htm