Slashdot Mirror
Jaguar, World's Most Powerful Supercomputer
Protoclown writes "The National Center for Computational Sciences (NCCS), located at Oak Ridge National Labs (ORNL) in Tennessee, has upgraded the Jaguar supercomputer to 1.64-petaflops for use by scientists and engineers working in areas such as climate modeling, renewable energy, materials science, fusion and combustion. The current upgrade is the result of an addition of 200 cabinets of the Cray XT5 to the existing 84 cabinets of the XT4 Jaguar system. Jaguar is now the world's most powerful supercomputer available for open scientific research."
How about economic modeling?
Help fight poverty: Punch a poor person.
But I really got it to play Tempest 2000.
(-1, Raw and Uncut is the only way to read)
So, like, how do so many people use the computer effectively? Do they have a sign-in sheet? I bet there's a long line. :p~
It is pitch black. You are likely to be eaten by a grue.
probably not, its not designed for that sort of thing so its a stupid question to ask, nd probably uses linux anyway
well that got that one out the way
Yeah, Jaguar might look cool with its advanced capabilities, but there's no games for it and the controller design is lame.
Go Team Jaguar!
Boosh!
-=Bang Bang=-
I always knew you could pull it off!!
The current upgrade is the result of an addition of 200 cabinets of the Cray XT5 to the existing 84 cabinets of the XT4 Jaguar system.
That sounds like Cray engineered this to aggregate components across product generations. For short product life cycles that seems like a great idea, not throwing out the old system when you get the new one but combining the two systems instead. Though obviously for long product life cycles it would be a losing proposition; The space and power requirements of inefficient older components would be greater than the space and power savings of upgrading to the latest model + the expense of the upgrade.
Ceci n'est pas une signature.
Can someone please translate the performance into people/hand held calculator/time and space into number of libraries of congress? I am not sure what the numbers they're talking about mean.
Thanks.
Tm
Support TBI Research: http://www.raisinhope.org
Will environmentalists ever stop trying to reverse the second law of thermodynamics?
"Insufficient data for a meaningful answer."
Damn.
There is already a wealth of political will for global warming, whats lacking is evidence ..
There, fixed that for you.
\u262D = \u5350
I would say more than lack of evidence is lack of causation rather than correlation. Scientists appear to agree that at least in the short term the earth is a little warmer. What they can't say with any certainty is why. Anthropogenic warming is the desired cause as that is the only one we can do a damn thing about.
Help fight poverty: Punch a poor person.
They should really upgrade, Jaguar is ancient!
You, sir, are an idiot.
LANL, LLNL, and SNL are all weapons labs. ORNL is primarily a science lab.
I myself have worked at three of these labs and held an account on an earlier iteration of Jaguar as well as some of LANL's other supercomputing clusters, so I ought to know.
ORNL's Jaguar cluster, although parts of it are I think "controlled" rather than open so that it can run export-controlled code, is not at all classified. It's used for biology, astronomy, physics, CFD, etc.
Also, if you knew the first thing about classified security you would realize that disallowing FTP access on a *classified* (Red network) machine to the outside internet is a necessity. To my knowledge, they don't allow *any* interconnection between classified systems and unclassified.
I had but a simple dream, to destroy all humans.
No. Jaguar. 1995 XK12, Six-Litre.
"Flyin' in just a sweet place,
Never been known to fail..."
Who says the climate modeling they are doing is related to global warming?
Even if it is, however, if the modeling increases our knowledge of the subject, it is not a waste of resources for scientists to seek the answers they are looking for.
Darth --
Nil Mortifi, Sine Lucre
remember that its not a true 64-bit multimedia system its two 32-bit systems connected together XD
Why do climate modelling?
Obviously climate modelling has to be carried to out to find out what impact running energy-hungry supercomputers has on the environment.
For all intensive porpoises your a bunch of rediculous loosers
And the only cause that is politically useful.
Computer memory is just fancy paper, CPUs just fancy pens with fancy erasers; the 'net is just a fancy backyard fence.
Having done my graduate work in fluid dynamics, only half your statement is possibly correct. There is historical evidence for global climate change, both warming and cooling. If is our interest to maintain the current status quo, the climate as we know it, it is not at all clear what interventions we need to take, or what effect they might have. Without simulations, that correctly model the real world. We have no way of knowing what our interventions might do. If anyone is interested, I can elaborate. The short (and scary)answer is - resonance.
It would be nice on these sorts of systems to have recurring, perhaps low priority, jobs issued by worthy outside distributed computing projects. Depending upon how busy the system is with other jobs it could make regular contributions to drug research and especially to AIDS research. To have complete and accurate pre-computed models of all steps in the protein folding process for all possible mutations of the AIDS virus, for example, would be a technological triumph and of potentially great benefit to humanity in the development of new drugs and possibly even an effective vaccine.
Hahah, eat it, 3DO.
In Capitalist America, bank robs you!
So, it can find her in under four times the distance to Alpha Centauri? Way to aim for precision.
I am so confused by the mods...the post above this one (posted 1 minute before) says exactly the same thing but gets "-1 Redundant"?!! Is it just because it was an AC, or did the title of "So cool!" really change the joke?!?
Now that I think about it, I'm pretty sure everything I just said is completely wrong.
Anthropogenic warming is the desired cause as that is the only one we can do a damn thing about.
People can do something even if the warming is not man made. If the cause is proven to be man made maybe the people will be persuaded to react faster.
All good points but lets not forget that simulation != observation.
This point was made about astrological observations on older slashdot stories and it holds true for climate prediction too.
I have to admit I am sceptical about blindly believing in global warming. I used to in the past however I've become a little smarter since then I can not see any hard observations for it, especially when volcanoes pump out 26 times more CO2 per year then all of humanity on the planet (however I'm slightly sceptical of how they measure the pollution figures too).
Wait, what's this got to do with the story... : /
Check out the gallery if you haven't.
I've always wanted to get some custom graphics like that on my server racks. Maybe a penguin, a butterfly, and a can of Raid. :)
Supercomputers definitely don't look as exciting as they did in the "old days".
42
Stupidity is the root of all evil.
I wonder how much they paid for all those Opterons. I wonder what kind of volume discount is typical for these kinds of supercomputers.
Maybe they thought someone who could actually receive karma deserved it more?
You, sir, can't read.
He was specifically talking about LANL and LLNL rather than ORNL.. that was the entire point.
Granted, yes, his description of disallowing classified non-classified connectivity as "ludicrous" is a little off-base, although writing things down by hand really is stupid- there are plenty of procedures in place for putting data on transportable media and then arranging to declassify that media once it has been verified so that it can be used elsewhere.
That doesn't change his fundamental points, though, that there are larger computing clusters that are locked up in classified nuclear simulation that could (and perhaps should) be used for more general science.
The ringing of the division bell has begun... -PF
If we can get fusion energy working cheap, we won't need the climate modeling. Not only that we can build a hundred of these things cheaper with the technology advances.
Climate change is gradual .. the need for new drugs and fusion energy is more pressing.
In that case, pardon my misunderstanding in thinking that his post was at all related to the posted article.
His title, "Used for open science...", was a quotation from the summary specifically about the ORNL computer. His rant about "much bigger computers around" was plausibly interpreted as the biggest one, the new ORNL cluster. I certainly must have been misled.
I had but a simple dream, to destroy all humans.
Awww shit dude, your day is totally ruined! Don't worry, I think Crysis and Beowulf made it in. Phew! I thought /. was losing its edge!
These systems are not so tightly integrated as you may imagine. True, many size a full-speed fabric just-right, each little bit costs a ton. However, commonly at scale, you only have full-speed fabric in large subsections anyway, and oversubscribe between the subsections. Jobs tend to be scheduled within subsections as they fit, though the subsection interconnects are no slouch.
This is particularly popular as the authortitative Top500 benchmark is not too badly impacted by such a network topology, and real life workloads tend to not be so large as not to fit in a subsection (just all the subsections would be independently at work).
It's kind of akin to saying you designed a couple of desktops well, because you could 'expand' them to host a lan party by hooking more to switches. Not quite so trivial, but the supercomputers aren't that especially exotic either.
XML is like violence. If it doesn't solve the problem, use more.
I noticed this a short time ago, but have yet to see the 'Rmax' performance. They speak to Rpeak, which does beat out the current Rpeak by 23%, though the Rpeak by itself is even more uninformative than Rmax, which is already quite synthetic. Assuming the current #1 hasn't managed tuning or upgrades, this will have to beat 65% efficiency to technically win. 65% is likely an acheiveable goal, though the larger the run, the more difficult to extract a reasonable efficiency number, so it's not certain. I wouldn't expect them to be so loud about it unless they knew the score already though...
I will be interested to see the power consumption figures if offered. For that 25% increase in flops, they are requiring well over twice as many processor packages than RoadRunner (about 18,000 sockets vs 45,000 sockets here).
I do wonder if Cray will be migrating to Intel in the next year given the QPI situation. AMD hasn't kept up compute leadership, and now HT will be lagging performance wise QPI.
XML is like violence. If it doesn't solve the problem, use more.
Why do climate modelling?
Well, purely scientific reasons for one. Climate science existed long before global warming was a concern.
Another reason is to inform adaptation. No matter what policy is realistically put in place, at least some more climate change is expected to occur. People are going to have to adapt to whatever change is not prevented. It's thus important to improve our understanding of what may happen. It also tells us how large and how fast a policy response is required, although as you note, we are not yet even attempting the minimum recommended policy.
Global warming is not based merely on correlation studies. It has a direct and well understood physical cause, which is the greenhouse effect. (What is less understood is the climate system feedbacks which modify the greenhouse effect.) And climate scientists can indeed say with a high degree of confidence that the recent warming is due mostly to human activities. This evidence comes from physical reasoning as well as observational measurements (such as the stratospheric cooling signature of the enhanced greenhouse effect), as well as a quantification of manmade and natural sources of warming and cooling.
No. Jaguar. 1995 XK12, Six-Litre.
I'd rather doubt the 1995 XK12, as cool as it was, was any competitor to the Jaguar XJ220.
Damn_registrars has no butt-hole. Damn_registrars has no use for a butt-hole.
I have to admit I am sceptical about blindly believing in global warming. I used to in the past however I've become a little smarter since then I can not see any hard observations for it, especially when volcanoes pump out 26 times more CO2 per year then all of humanity on the planet
That's not even remotely true. Volcanic CO2 emissions are about 1% of human CO2 emissions (see here). Where did you get the rather specific, and wrong, factor of 26?
Maybe you'd see the hard evidence if you spend a little more time reading about it, since you appear to have some peculiar misconceptions. I recommend Kerry Emanuel's essay "Phaeton's Reins", David Archer's undergrad textbook, and the IPCC AR4 report for technical details.
Who says the climate modeling they are doing is related to global warming?
Oak Ridge does: "Climate scientists are calculating the potential consequences of greenhouse gas emissions and the potential benefits of limiting these emissions."
Hmmm...the ORNL web site lists the phone number for the Help Line. I think someone should call them up and ask them to reboot the server because the Internet is running slow.
To clarify myself, I do not have a particular stance on global warming itself. I do not know climatology. I do believe however that
a) Appeal to consensus are irrelevant, scientific truth comes from repeated and verified experiments, not consensus.
b) Whether it is man made or not is an ethical puppet to distract attention. What's done done.
c) Most of the politics and economics surrounding global warming are flawed. That much I can tell. Even the worst prediction of the IPCC are quite tame compared to other disasters likely to happen, and they are dwarfed by the difference that even 0.5% of growth and technological progress a year makes on the same timescale.
Most of the global warming debate is really an attack on industrialization and global trade under the guise of environmentalism.
(And no it doesn't mean there's no global warming, and no it doesn't mean we shouldn't do something about it, but so far the debate has been mostly a trojan horse for political ideology).
\u262D = \u5350
That is a lot of SETI@home power!
The worst IPCC scenario (A1FI) gives a worst case of 6.4 C (11.5 F) global warming in less than 100 years. I don't know if it's the worst thing that is likely to happen, but that's not that tame (especially when you consider that land warms faster than the global average, and northern latitudes even faster than that). As for the economics, Nordhaus's book A Question of Balance is a good place to start. Nordhaus isn't ideological. It's economically worth mitigating some CO2 emissions to insure against the more severe outcomes. Not cutting them to zero instantly, but reducing them. Even the so-called Copenhagen Consensus, which concluded that a marginal investment in other disasters is more cost effective than pure CO2 abatement for global warming, ended up recommending CO2 abatement (in combination with adaptation and tech R&D).
And frankly, I don't particularly care whether certain parties find global warming ideologically convenient. The problem still exists.
I think I'll wait for Leopard.
Someone care to explain why this uses Opterons instead of something Xeony? What does an AMD chip do for supercomputers that it can't seem to do for games and desktop machines?
Lucas Electronics are crap for Jaguar and MG electrical systems. /Jaguar XJ owner
Who run Barter Town?
Los Alamos are jealous since they just got a 1.026 petaflop supercomputer installed earlier this year by IBM called RoadRunner. It was featured in last month's Linux Journal.
this nation, under God, shall have a new birth of freedom. -- Lincoln, Gettysburg Address
Ouch
I hate to even ask, but ...
What operating system does this thing run?
I find myself hoping that's it's Linux with a Beowulf cluster, but ...
-- thanks,
David Small
It depends on the context.
If you are searching the whole Local Group, it seems reasonable.
In June the Jaguar had 30,000 Quad Core Opterons, and now it has 45,000. The previous machine was an XT4, but the most recent update shows that 200 XT5 cabinets have been added to it. I have been unable to find how many cabinets the Jaguar has in total, but it seems that in June it had 313 (30,000 Opterons and 96 Opterons per cabinet). To me, the Jaguar seems to be two machines: the Cray XT4, and the Cray XT5. I'm also wary how increasing the number of processors by 50% yeilds an 800% performance increase. I'm going to wait until the official figures have been released on the 18th, when the next Top500 list comes out.
If the Jaguar has had a performance increase, then I'd say the IBM machine would have had one too. It seems Cray are just fighting a war of attrition, trying to win back the supercomputing crown they held for so long (in the company's previous incarnations). They seem to be throwing processors at the problem. Yes there is more to supercomputers than processors (interconnects, switching, and memory management design are also vital ), but a 45,000 processor beast taking up 500+ cabinets is not a very elegant solution compared to a machine with 18,800 processors taking up only 278 cabinets (and arguably using far less power).
In the not too distant future, we shall see a new Top 500 list. It just seems like yesterday that RoadRunner cracked the Petaflops barrier, and the whole world seems to have fallen on its ass in the interim. Banking failures, government bailouts, people losing their retirement portfolios. The irony is too much. Even as the computers get better, the answers that people need don't come fast enough.
Then the light turned on for me. People in general, the people you see on the street going on their busy way to whatever, are mostly relying on "someone else" to come up with the answers. Most people have little confidence in their own ability to answer hard questions.
Well, maybe things will turn around because of the power of supercomputers. It would be about time, wouldn't it? Here's how it may play out. Supercomputers so far, good as they are, serve up expensive results, so they are applied to difficult problems that are useful but far removed from everyday life.
As supercomputer clock cycles become more abundant, researchers can apply them to do more mundane things that the unwashed can relate to. The result could be revolutionary. People who have always aspired to some inconsequential achievement that requires some expertise or training may suddenly have access to highly instructive supercomputer-generated procedures that explain both how and why. Not only will people become more expert do-it-yourselfers, but robots will become far versatile, with amazing repertoires.
Crossing the petaflops barrier may be sufficient psychological incentive for people to request that governments begin to make supercomputing infrastructure available for public consumption, like roads and other services. Certainly, exciting times are comiing.
Know your pads. One time pad: good for cryptography. Two timing pad: where to take your mistress.
Will it run Cybermorph?
So, let me get this straight: If someone writes something you think is not true he or she is an 'idiot', whereas if you write something that you admit wasn't true you 'have been misled' ?
MP3 Search Engine
creating better algorithms? Or at least educating a little bit all non-CS scientists about performance and optimization? If you go over the climate-prediction loop many many times, you should consider some caching..
Heh. Worlds fastest computer runs Linux.
Yes! But the XJ isn't made of Unobtanium!
"Flyin' in just a sweet place,
Never been known to fail..."
Whether it's man made or not is quite important, actually. If it's not (a scenario that's looking pretty damned unlikely) then doing something to halt or slow it becomes difficult as we have to find out what the hell IS causing the problem.
Yeah, but can it run Duke Nukem?
Just five months after IBM's hybrid Roadrunner became the first supercomputer to break the lofty petaflop barrier, a second, more traditional machine has made the same leap .And at least one industry watcher said the move of Cray's XT Jaguar supercomputer -- with the help of a $100 million upgrade -- into the petaflop realm is swinging the doors wide open for other systems that are on the verge of following it to a new level of power and speed.
---------------
Tonnywilliams
Your DUI News
I'm amazed.. I mean this is Slashdot, How could an article about some kind of computer get posted without the obligatory: Imagine a Beowolf cluster of these things.. :)
That would be my program if I had a chance to run something on it. I would make sure it ran on every core too.