Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Jaguar Supercomputer Being Upgraded To Regain Fastest Cluster Crown

Unknown Lamer posted about 3 years ago | from the twenty-quadreeelon-laser-sharks dept.

Supercomputing 89

MrSeb writes with an article in Extreme Tech about the Titan supercomputer. From the article: "Cray, AMD, Nvidia, and the Department of Energy have announced that the Oak Ridge National Laboratory's Jaguar supercomputer will soon be upgraded to yet again become the fastest HPC installation in the world. The new, mighty-morphing computer will feature thousands of Cray XK6 blades, each one accommodating up to four 16-core AMD Opteron 6200 (Interlagos) chips and four Nvidia Tesla 20-series GCGPU coprocessors. The Jaguar name will be suitably inflated, too: the new behemoth will be called Titan. The exact specs of Titan haven't been revealed, but the Jaguar supercomputer currently sports 200 cabinets of Cray XT5 blades — and each cabinet, in theory, can be upgraded to hold 24 XK6 blades. That's a total of 4,800 servers, or 38,400 processors in total; 19,200 Opterons 6200s, and 19,200 Tesla GPUs. ... that's 307,200 CPU cores — and with 512 shaders in each Tesla chip that's 9,830,400 compute units. In other words, Titan should be capable of massive parallelism of more than one million concurrent operations. When the server is complete, towards the end of 2012, Titan will be capable of between 10 and 20 petaflops, and should recapture the crown of Fastest Supercomputer in the World from the Japanese 'K' computer."

cancel ×

89 comments

Sorry! There are no comments related to the filter you selected.

DOE projects (0)

ThorGod (456163) | about 3 years ago | (#37682068)

Makes me wonder what the DOE will run on that computer? Kind of makes another game of (insert your favorite FPS here) seem quaint.

Re:DOE projects (1)

slydder (549704) | about 3 years ago | (#37682098)

first step to the matrix maybe?

Re:DOE projects (1)

Surt (22457) | about 3 years ago | (#37682172)

They'll do nuclear weapon simulations as usual.

Re:DOE projects (0)

Anonymous Coward | about 3 years ago | (#37682202)

Oak Ridge is Office of Science, not NNSA (the nuke folks), and Titan is an open (non-classified) system. So no, they won't be doing weapons codes on these machines. More general science, like climate, weather, materials, combustion, astrophysics, etc...

Re:DOE projects (0)

Anonymous Coward | about 3 years ago | (#37682394)

And 'Hello World' obviously.

Re:DOE projects (1)

somersault (912633) | about 3 years ago | (#37682826)

More like "Hello Multiverse"

Re:DOE projects (0)

Anonymous Coward | about 3 years ago | (#37682708)

That's just the cover story.

Re:DOE projects (0)

Anonymous Coward | about 3 years ago | (#37683382)

Actually, no. Jaguar/Titan is part of the Office of Science, and is not used for classified work.

Re:DOE projects (1)

jd (1658) | about 3 years ago | (#37682286)

No idea, but that kind of monster is getting very close to the compute power needed to do full-blown raytracing (not shading sold as raytracing) for 3D movies in real-time. As in a cinema with one of these would only need the basic renderman files plus sound track.

If the US had shown any interest whatsoever in ITER (fat chance, after they lost the bidding war on who was going to house it), I'd say that a supercomputer on this kind of scale would be adequate for simulating the dynamics inside the fusion reactor. That would allow the design to be vastly tightened up, giving it a much better chance of exceeding the break-even point in a sustainable reaction.

It would also be very useful for crunching through the masses of data that CERN are producing, as it would be able to look for classes of event that could be interesting but fall outside the capacity of regular particle physicists to look at. (At present, less than 1% of the data available is processed because nobody has the means to process it. It's just dumped. A giant like this could make a far larger fraction of the events analyzable.) But, again, the US is too busy competing to cooperate. (Besides, cooperation is what those Pesky Socialists do. Pleh!) The idea of the DEA installing an ultra-fat pipe to the LHC for the purpose of helping CERN - not going to happen. The science be damned, egos are on the line!

Re:DOE projects (1)

somersault (912633) | about 3 years ago | (#37682882)

"Hey guys, what do you want to do today.. analyze the deep mysteries of the universe, pushing science and technology 50 years further beyond what we were expecting to be able to do anytime soon, or watch Kung Fu Panda?"

"Quit joking around Tim - run Skynet.sh to hack into Pixar again and download Toy Story!"

Re:DOE projects (0)

Anonymous Coward | about 3 years ago | (#37683690)

I'd say that a supercomputer on this kind of scale would be adequate for simulating the dynamics inside the fusion reactor.

In fact, several of the codes run on Jaguar are used to simulate processes involved in fusion research.

Re:DOE projects (1)

rubycodez (864176) | about 3 years ago | (#37685874)

U.S. is funding efforts that might actually produce sustainable fusion, such as Bussard Polywell; not the money sewer that is ITER, which will not produce anything useful for decades even considering follow-on machine designs. Spend smarter, not bigger.

Re:DOE projects (0)

Anonymous Coward | about 3 years ago | (#37687204)

As someone who works in computational plasma physics and fusion research, I can't say I've heard someone working on tokamaks like ITER say, "If only I had a little bit more computing power, things would be so much better." Most of the problems come down to either, "If we want to make this better, we need an unrealistic amount of more computing power... so we should look into new algorithms," or some other form of needing more human creativity, theory work, and interpretation of results. Not to say more computing power wouldn't help make things go a little faster, but it is not like some barrier stopping everything from suddenly working easily.

Also I previously worked on the LHC Computing Grid, which as of at least a few years ago, the US contributes a lot of research and resources to. So we are helping CERN and their computations.

Re:DOE projects (1)

oh_my_080980980 (773867) | about 3 years ago | (#37682294)

All this for solitaire?

Re:DOE projects (3, Informative)

Raul654 (453029) | about 3 years ago | (#37682356)

The DOE categorizes their supercomputers into capacity machines and capability machines.

The capacity machines are the work horses - time-shared between lots of users doing a variety of applications (including material science, life science, nuclear simulation, etc). The spend pretty much their entire lives near maximum utilization.

The capability machines are the really big ones (Jaguar, Road Runner, etc) that are big enough to permit applications that are too large (require too much RAM or have absurdly long running times) to run on most systems. (Capability machines are also quite difficult to administer because none of the software they run has ever been tested at those scales)

Folding @ Home (0)

Anonymous Coward | about 3 years ago | (#37683988)

(Before we play Crysis on Windows8 on it) Put it to good use,
Folding. Cure Alzheimer's, ALS, Huntington's, Parkinson's disease, and many Cancers.

Ok, now who pays the electric bills...

Yeah, but how fast does it (1, Funny)

unassimilatible (225662) | about 3 years ago | (#37682084)

play Quake?

Re:Yeah, but how fast does it (1)

Joce640k (829181) | about 3 years ago | (#37682154)

What, no "beowolf cluster" joke yet?

Re:Yeah, but how fast does it (1)

SomePgmr (2021234) | about 3 years ago | (#37682734)

I was waiting for a Crysis joke.

Re:Yeah, but how fast does it (1)

seandiggity (992657) | about 3 years ago | (#37683754)

I'm waiting for the Gentoo joke, actually.

Re:Yeah, but how fast does it (1)

Shark (78448) | about 3 years ago | (#37684492)

It'll be done compiling any moment now... Just making sure the funny is fully optimized.

Re:Yeah, but how fast does it (1)

reubenavery (1047008) | about 3 years ago | (#37682168)

definitely play Quake

Re:Yeah, but how fast does it (0)

Anonymous Coward | about 3 years ago | (#37682252)

No, it doesn't play Quake. It drives a Koenigsegg.

Re:Yeah, but how fast does it (1)

ricky-road-flats (770129) | about 3 years ago | (#37682736)

play Quake?

A good question. I ran the numbers, and the answer is FUCKING quickly.

Re:Yeah, but how fast does it (1)

Megane (129182) | about 3 years ago | (#37682922)

I don't know, but it already plays Doom! [wikipedia.org]

Re:Yeah, but how fast does it (0)

Anonymous Coward | about 3 years ago | (#37684572)

No, iirc, Alien Vs. Predator is the flagship game for the Jaguar. In full 64bits too!

"Titan"? (1)

N!k0N (883435) | about 3 years ago | (#37682100)

Would be more interesting if they named it "Joshua".

Re:"Titan"? (1)

PrescriptionWarning (932687) | about 3 years ago | (#37682170)

WOPR would be just as good. The only thing that concerns me about the name Titan is what happens when they need another name some years from now to indicate its even faster. Maybe they can go on to Gargantuan and then Colossus, but I think after that they're out of names to get bigger with!

Re:"Titan"? (1)

Rockoon (1252108) | about 3 years ago | (#37682260)

Super Titan

Re:"Titan"? (2)

Chris Burke (6130) | about 3 years ago | (#37682296)

The only thing that concerns me about the name Titan is what happens when they need another name some years from now to indicate its even faster.

Well, Olympian would be the obvious choice for a successor to Titan.

Re:"Titan"? (1)

Skarecrow77 (1714214) | about 3 years ago | (#37682616)

Just like the missile, you name it "Titan II" (aka "The Quickening" and/or "Electric Bugaloo")

Re:"Titan"? (0)

Anonymous Coward | about 3 years ago | (#37682620)

They wouldn't go with "bigger", they'd go with "better". At a blind guess: "Olympian".

Re:"Titan"? (2)

afidel (530433) | about 3 years ago | (#37683062)

I don't think they'll be using Colossus since the British WWII cryptographers used it first =)

Re:"Titan"? (0)

Anonymous Coward | about 3 years ago | (#37682732)

Joshua: "Would you like to play a game?"

Re:"Titan"? (0)

Anonymous Coward | about 3 years ago | (#37682878)

How about "Global Thermonuclear War"?

Now we know what Titan is... (0)

Anonymous Coward | about 3 years ago | (#37683532)

And it's Blizzard's Next MMORPG, and it will be Globalthermonuclear war!

Will it run Crysis? (0)

GameboyRMH (1153867) | about 3 years ago | (#37682158)

Will it run Crysis...on Flash?

Re:Will it run Crysis? (0)

Anonymous Coward | about 3 years ago | (#37682178)

Maybe, but what about... JavaScript?

Re:Will it run Crysis? (0)

Anonymous Coward | about 3 years ago | (#37682238)

Will it run Crysis on Wine on Linux on Javascript in Internet Explorer?

Re:Will it run Crysis? (1)

GameboyRMH (1153867) | about 3 years ago | (#37682448)

Crysis on Flash on Safari on Wine on Linux on Javascript on Internet Explorer on Vista

Now we've got a proper benchmark!

Re:Will it run Crysis? (0)

Anonymous Coward | about 3 years ago | (#37682254)

Will it run Crysis... on multithreaded Python?

hmmm.... (0)

Anonymous Coward | about 3 years ago | (#37682232)

Can it render the world as we see it in real time?

Re:hmmm.... (1)

erroneus (253617) | about 3 years ago | (#37682496)

No, but I think it will be able to run Vista.

Re:hmmm.... (1)

game kid (805301) | about 3 years ago | (#37682524)

Yes, but all people are rendered as instances of Kim Kardashian to save time. She funds a few more processors if it uses her instead of stick figures.

It also replaces billboards with ads for her latest perfume, Ass ("It's What I Use(TM)") and runs at half frame rate with a two-hour delay on the US West Coast (because it costs more to send the frames to Oregon for some reason).

If it doesn't get outrun by Blue Gene/Q... (2)

gentryx (759438) | about 3 years ago | (#37682266)

LLNL will receive their 20 PF machine dubbed Sequoia [wikipedia.org] later this year. IBM's Blue Genes are known for their good ratio of CPU performance/network performance. This allows the MPI codes to scale well. The same is true for vanilla Cray XT5 and XE6 machines, but if upgraded with GPUs then each node receives a significant boost in computational power without increasing the network performance. This leaves the individual nodes bandwidth starved and makes it next to impossible to achieve peak performance in production code. The abysmal ratio of peak performance to actual production performance of China's Tianhe-1A tells the same story.

Maybe they'll achieve peak performance in Linpack, but for everything else Blue Gene/Q will be a much nicer system than Titan. Plus, on Blue Gene you don't have to deal with the heterogeneous system design, which already gave hell to coders on Roadrunner.

BTW: GCGPU should be corrected to GPGPU.

Re:If it doesn't get outrun by Blue Gene/Q... (1)

loufoque (1400831) | about 3 years ago | (#37683914)

No real application gets close to peak performance on such a supercomputer.

And if you're limited by I/O, it just means you don't have a big enough workload. I/O and computation time should be overlapped so that you only pay for latency.

Re:If it doesn't get outrun by Blue Gene/Q... (1)

gentryx (759438) | about 3 years ago | (#37684062)

Who's talking about disk I/O? I'm talking about network bandwidth, which is required for synchronization, e.g. to update ghost zones in stencil codes [wikipedia.org] . The required bandwidth is proportional to the computational power of the nodes. Latency can actually be hidden, too, by overlapping computation and communication -- at least for the afore mentioned stencil codes, which represent the largest fraction of simulation codes out there. That said, disk I/O is still vital [lbl.gov] , at least if you want to actually see what your super computer has computed. Of course peak performance is never actually achieved, but a 10 PFLOPS machine is useless if production codes all run at 10 TFLOPS. That's why Blue Waters did target 1 PFLOPS application performance -- that meant more to them than 10 PFLOPS Linpack throughput.

Re:If it doesn't get outrun by Blue Gene/Q... (1)

loufoque (1400831) | about 3 years ago | (#37707212)

I wasn't talking about disk I/O, but network I/O.
Stencils are computed by replicating the borders during tiling. Doing a communication every time a node needs to access that zone is doing it wrong.

Re:If it doesn't get outrun by Blue Gene/Q... (1)

gentryx (759438) | about 3 years ago | (#37707370)

Yes. And in every time step you'll have to sync the ghost zones (or halos). And if the time step is computed faster (because your CPU/GPU has been upgraded), and your network hasn't been equally accelerated, then, at some point, you'll be bandwidth limited. Overlapping of calculation and communication only hides communication time if t_send = (t_latency + size / bandwidth) is smaller than t_compute. Speeding up the CPU/GPU will reduce t_compute. t_send will remain constant.

That said, of course there are algorithms which don't have to sync in every time step because they'll communicate a wider halo, e.g. an halo of width 4 and communication only every fourth step, but those algorithms only reduce the influence of the network latency, not the bandwidth limit.

Justification. (1)

geekmux (1040042) | about 3 years ago | (#37682348)

"...being upgraded to regain fastest cluster crown"

"...a total of 4,800 servers, or 38,400 processors in total; 19,200 Opterons 6200s, and 19,200 Tesla GPUs..."

Gee, that sounds cheap. And all for a "crown"...Hell of a financial justification there...especially considering by the time they upgrade the last rack of blades, someone else will have plans for a bigger, faster one.

Re:Justification. (1)

Baloroth (2370816) | about 3 years ago | (#37682798)

Gee, that sounds cheap. And all for a "crown"...Hell of a financial justification there...especially considering by the time they upgrade the last rack of blades, someone else will have plans for a bigger, faster one.

Welcome to the wonderful world of technological progress, brought to you today by the Law of Moore!

Re:Justification. (2)

gentryx (759438) | about 3 years ago | (#37682862)

Regaining the #1 spot on the Top500 is merely a convenient side effect. The real reason for building these machines is that they are a key enabler for numerous science projects ranging from astrophysics to climate modeling to atomic phasefield simulation of crystal growth [supercomputing.org] . This type of research can only be done on machines which offer Petabytes of RAM and Petaflops of performance. They cost hundreds of millions to build and operate. And if you can cut this cost down to a fraction by reusing Jaguar's existing housing, cooling and networking facilities, then this is financially a very clever move.

Re:Justification. (1)

geekmux (1040042) | about 3 years ago | (#37688882)

Regaining the #1 spot on the Top500 is merely a convenient side effect. The real reason for building these machines is that they are a key enabler for numerous science projects ranging from astrophysics to climate modeling to atomic phasefield simulation of crystal growth [supercomputing.org] . This type of research can only be done on machines which offer Petabytes of RAM and Petaflops of performance. They cost hundreds of millions to build and operate. And if you can cut this cost down to a fraction by reusing Jaguar's existing housing, cooling and networking facilities, then this is financially a very clever move.

I would be willing to agree with you 110% here on your justification model here, save for one tiny little thing. We also happen to hold the #1 spot in the world regarding debt, which tends to question the overall benefit of building systems that cost "hundreds of millions to build and operate", regardless of the use.

I DO understand and respect the advances we've made and will continue to make in science due to these types of systems, but the title of this article tends to scream a childish "king of the hill" statement as to the underlying justification, and I keep reading it over and over again as entire countries fight to regain the top spot about every six months.

Re:Justification. (1)

Chris Burke (6130) | about 3 years ago | (#37696226)

I would be willing to agree with you 110% here on your justification model here, save for one tiny little thing. We also happen to hold the #1 spot in the world regarding debt, which tends to question the overall benefit of building systems that cost "hundreds of millions to build and operate", regardless of the use.

Yeah! I'm hugely in debt because I over-bought on my summer home, so I'd better stop paying for the bus tokens I use to get to work! That'll really help my situation!

Hundreds of millions is nothing compared to the debt problem at issue, super-computer purchasing is not a significant contributor to that issue, however scientific advances that can only be achieved via such computers can provide returns far above what was spent and do orders of magnitude more to resolve our debt issues than it is contributing to them.

Being in debt doesn't mean you stop spending money. It means you have to spend money wiser -- on things that can provide dividends. This is a perfect example of the kind of spending that should not be stopped exactly because of the debt problem.

Re:Justification. (1)

geekmux (1040042) | about 3 years ago | (#37709422)

...Being in debt doesn't mean you stop spending money. It means you have to spend money wiser -- on things that can provide dividends. This is a perfect example of the kind of spending that should not be stopped exactly because of the debt problem.

And as I said, I agree completely on the purpose and validation of these systems. Now, how about taking a look at some statistical analysis both before and after the top500.org website was established, and validate that overall spending on these massive supercomputers, as well as average upgrade timelines, is NOT somehow tied to the "king of the hill" theory.

Let's not be ignorant and think that greed and corruption somehow cannot infiltrate organizations building these systems. I agree that their dividends can and will eventually pay off, but this is a perfect example of the kind of spending that needs to be justified well, and I'm afraid we would find a correlation with the top500 website. As I said before, waaaay too many times reading about these systems, the underlying theme has been "#1 spot".

Re:Justification. (1)

Chris Burke (6130) | about 3 years ago | (#37713012)

And as I said, I agree completely on the purpose and validation of these systems. Now, how about taking a look at some statistical analysis both before and after the top500.org website was established, and validate that overall spending on these massive supercomputers, as well as average upgrade timelines, is NOT somehow tied to the "king of the hill" theory.

So what if it the keeping of a Top 500 list of supercomputers spurs governments and other organizations to compete to produce the most powerful computers? The problems these supercomputers are solving are problems where you can always throw more computational power at them to get better answers. You agree that this purpose is worth while.

I go back to what I said before. This is a tiny portion of the budget, a tiny portion of our debt problem. It's something that pays dividends. It's part of our spending that makes no sense to cut. Not because we're competing over who can produce the most data-crunching, the most science, the most dividends. This is a good thing.

Might as well complain that runners compete for the top spot rather than simply trying to achieve the fastest times. Or complain about spending on the Apollo programs because the space race was a political pissing match between superpowers, after agreeing that the Apollo missions were worth it!

2012 will be a big year for supercomputers. (2)

flaming-opus (8186) | about 3 years ago | (#37682440)

Titan will be a hugely powerful computer. However, fastest supercomputer might be just out of reach. 2012 is also the year that Lawrence Livermore labs, also part of the Department of Energy, is planning to unveil their 20 petaflop BlueGene/Q computer name Seqoia. [http://www.hpcwire.com/hpcwire/2009-02-03/lawrence_livermore_prepares_for_20_petaflop_blue_gene_q.html]

That said, Seqoia will be a classified system for nuclear stockpile simulations. Titan will be a comparatively open system for wide ranging scientific discovery: government, academic, and industrial.

Re:2012 will be a big year for supercomputers. (1)

gentryx (759438) | about 3 years ago | (#37683162)

Not just Sequoia, but also Mira [hpcwire.com] (10 PFLOPS BG/Q @Argone), Hermit [inside.hlrs.de] (4-5 PFLOPS Cray CE6 @HLRS, Germany) and... well Blue Waters seems to have silted up [slashdot.org] .

Re:2012 will be a big year for supercomputers. (1)

Junta (36770) | about 3 years ago | (#37686102)

Not to mention the likelihood of the arrival of Sandy Bridge systems, Kepler and Southern Islands GPUs providing competitors that aren't big in the news at the moment.

By the end of 2012, even the optimistic end of the scale at 20 petaflops probably won't be #1. If #1 is a BlueGene, it will probably use less electricity than Titan while still getting higher numbers, though either way programmers will have a bit of a struggle vs. big traditional CPU based systems.

Re:2012 will be a big year for supercomputers. (0)

Anonymous Coward | about 3 years ago | (#37689234)

>Seqoia will be a classified system for nuclear stockpile simulations

When a supercomputer arrives it's usually left on the unclassified side
for months, 'cause there's lots of testing to be done, and figuring out
how to run codes at a larger scale than ever before. Then it goes
to the classified side -- or sometimes is broken into pieces, one classified
and one not.

But will it run Android? (0)

Anonymous Coward | about 3 years ago | (#37682456)

Sorry to borrow the old meme "but will it run Linux?" but I was wondering how long before that level of performance will be available on a hand held mobile device. :)

Re:But will it run Android? (1)

erroneus (253617) | about 3 years ago | (#37682478)

Damnit, I just realized I wasn't logged in... oh well.

Re:But will it run Android? (1)

Yvan256 (722131) | about 3 years ago | (#37682504)

"Within 5 to 10 years", of course.

Re:But will it run Android? (1)

Meeni (1815694) | about 3 years ago | (#37683300)

Usually, current laptop computer would have appeared in top5000 (top500.org) of 7 years ago. iPad 2 would have been the most powerful supercomputer in 1985.

Re:But will it run Android? (1)

mattr (78516) | about 3 years ago | (#37686384)

1M instances...

Or they could call it (0)

Anonymous Coward | about 3 years ago | (#37682482)

titanic - for when the weather simulation predicts freezing in the north atlantic...

I couldn't resist.

Great, but... (1)

wjcofkc (964165) | about 3 years ago | (#37682484)

Can I play Iron Soldier 2 on it?

Yeah! (2)

Yvan256 (722131) | about 3 years ago | (#37682486)

Go Atari!

Re:Yeah! (0)

Anonymous Coward | about 3 years ago | (#37683298)

Yeah! 64-bits FTW!

Re:Yeah! (0)

Anonymous Coward | about 3 years ago | (#37683886)

Yeah! I still own one of those... hopefully they come up with a better controller this time.

Re:Yeah! (1)

ogdenk (712300) | about 3 years ago | (#37686752)

You jest but Atari really was working on a deskside "supercomputer"....

http://en.wikipedia.org/wiki/Atari_Abaq [wikipedia.org]

AKA The Atari ATW800.... based on INMOS Transputer RISC CPU's. Very cool, really wanted one when I was a kid. Figured they were vapor until years later when a few started popping up here and there on eBay.

Never had a Jaguar but always wanted one. I grew up with the Atari XL/XE-series and the ST though.

Wait.... (1)

aggspball3r (1190479) | about 3 years ago | (#37682500)

inb4 "S" Jokes next up the launch of the Japanese "K S" computer.

Jaguar (3, Funny)

Ukab the Great (87152) | about 3 years ago | (#37682528)

I would have thought that the world's fastest cluster would something a little more modern than OS X 10.2.

Naming... (1)

damn_registrars (1103043) | about 3 years ago | (#37682576)

So the system called Jaguar was powered by multiple XK6 engines. If they're upgrading it to take the title of world's fastest, they should have stuck with that pattern and called the new system the XJ220 [wikipedia.org] .

Bitcoin mining (0)

Anonymous Coward | about 3 years ago | (#37682994)

This is, of course, to shore up the DOE's budget in light of looming cuts...

Bitcoins? (0)

Anonymous Coward | about 3 years ago | (#37683258)

The problem is that they chose NVIDIA, and any SERIOUS bitcoin miner knows to use AMD ;-) They just blew the whole project!

End of 2012 you say? (0)

Anonymous Coward | about 3 years ago | (#37683260)

I fear an army of Arnolds

All kidding aside for Crysis and Quake (1)

Commontwist (2452418) | about 3 years ago | (#37683420)

What kind of gaming server WOULD this kind of processing power allow? Imagine the AIs, physics, and real-time geographical updates something like this could support. I know that EVE has a rather massive server and database for their universe but this should kick that server's behind.

Communications with clients would likely be the main bottleneck to keep up with all this but imagine some nifty in-house gaming consoles.

Jaguar? That sounds old (0)

Anonymous Coward | about 3 years ago | (#37683502)

I'm pretty sure they're up to Snow Leopard now.

I was mistaken... (1)

Pionar (620916) | about 3 years ago | (#37683520)

I was expecting a supercomputer made out of a beowulf cluster of Atari Jaguars.

Slickdeal? (1)

whatme (997566) | about 3 years ago | (#37684052)

That's a total of 4,800 servers, or 38,400 processors in total; 19,200 Opterons 6200s, and 19,200 Tesla GPUs. ... that's 307,200 CPU cores — and with 512 shaders in each Tesla chip that's 9,830,400 compute units.

Fail. No HDMI. :)

Re:Slickdeal? (0)

Anonymous Coward | about 3 years ago | (#37686482)

But it's not $99.

And the Software/OS will be? (0)

Anonymous Coward | about 3 years ago | (#37685410)

Once again the news media goes ape over the hardware specs of the computer and leaves off any mention of the OS.
Got to believe it is some form of Linux though isn't it?
pgmer6809

Re:And the Software/OS will be? (1)

Stax (13864) | about 3 years ago | (#37685560)

http://www.nccs.gov/computing-resources/jaguar/

Cray linux, which as I understand is a derivative of SuSE

Re:And the Software/OS will be? (0)

Anonymous Coward | about 3 years ago | (#37686438)

It's full-blown SuSE 11 for service nodes (CPUs that handle interactive login, job scheduling, and I/O) and a barebones ramdisk with Busybox, libraries, and management daemons on the compute nodes (CPUs that do nothing but run jobs)

LFTR (1)

drwho (4190) | about 3 years ago | (#37686660)

Mandatory LFTR comment here. Yes, it would be nice if this fancy tool were to be used in the effort towards solving problems with Liquid Fluoride Thorium Reactors, such as cutting down on the tritium production, but ORNL doesn't seem to be interested in its child any more. But, perhaps some funding will be found in the future for creation of modeling software and purchase of CPU time on this Jaguar or the next. Is Stephen Chu the bottleneck?

Obviously Capcom vs SNK (0)

Anonymous Coward | about 3 years ago | (#37687454)

Jaguar is obviously a thinly veiled reference to Adon, so it's K' vs. Adon. I'm thinking K' dash wins, since he was top tier in both KOF 99 and 2003.

Difference between a supercomputer and a cluster? (1)

BlueCoder (223005) | about 3 years ago | (#37690450)

Seems to me this supposed supercomputer is just a cluster of quad processor motherboards with coprocessors.

And why isn't it liquid cooled in refined mineral oil on cabinets on their back? It cuts the power requirements for cooling and makes the boards as a whole more reliable. Don't have to worry about cooling fans going down and you can have redundant heat exchanging pumps.

This is research? (1)

doston (2372830) | about 3 years ago | (#37691734)

Why can't these little penis types just stick to monster trucks? I know it looks dumber, but it's a lot less expensive.
Check for New Comments
Slashdot Login

Need an Account?

Forgot your password?