Slashdot Mirror
Japan's 8-petaflop K Computer Is Fastest On Earth
Stoobalou writes "An eight-petaflop Japanese supercomputer has grabbed the title of fastest computer on earth in the new Top 500 Supercomputing List to be officially unveiled at the International Supercomputing Conference in Hamburg today. The K Computer is based at the RIKEN Advanced Institute for Computational Science in Kobe, Japan, and smashes the previous supercomputing records with a processing power of more than 8 petaflop/s (quadrillion calculations per second) — three times that of its nearest rival."
640K cores is enough for anyone.
I imagine that their in-house fab churns out some very interesting niche designs; but it would be a real surprise if it has any terribly impressive capabilities in general-purpose compute applications. Staying on the bleeding edge of fabrication requires serious money, while just quietly gobbling up commodity stuff from Intel or Nvidia or whoever won't raise any eyebrows.
They probably have some cool specialized crypto-crunchers based on cryptoanalysis that hasn't officially been done yet, and I suspect that they are the chaps to talk to when you need a chip that absolutely hasn't been backdoored in china; but I suspect that their process density and clockspeed capabilities are middling at best.
I'm pretty sure that we've moved all our beowulf clusters to a cloud that runs linux in soviet russia...
Did you post that just to be able to use the word that is in your sig?
In other news, company announces the system will be used initially for Bitcoin mining. The Payback period is expected to range between three weeks an two hundred years, depending on market conditions....
Two things, your 4 year old desktop is nowhere near as fast as the new i7s. It just seems that way because you're not doing number crunching on it; for normal applications, you'd probably see a bigger boost by switching to a SSD then a new CPU. Second, these supercomputers are massively parallel, so while the procs themselves do get faster, the real increase in speed seen comes from adding lots more cores.
-- Let us endeavor so to live that when we pass even the undertaker shall be sorry. -- M. Twain
I agree, big numbers are a bit of a problem since the naming scheme isn't the same around the world.
There can be 6 orders of magnitude difference between trillion and trillion depending on where you are.
Danish for instance goes.
million, milliard, billion, billiard, trillion (10^18)
vs. US:
million, billion, trillion (10^12)
Peta on the other hand has a somewhat more unified meaning.
How many cores ? Have you considered the GPU as well ? These years, it is the form factor and the price that are halfed every year or so. It will continue until we find a use for the ridiculous power we have today.
smartphones are now dual-core, mainstream computers DO continue to improve.
The Wise adapts himself to the world. The Fool adapts the world to himself. Therefore, all progress depends on the Fool.
I'm not sure that you are being entirely fair to the desktops:
On the one hand, since a vast percentage of desktops are sold to budget-conscious users with fairly defined needs, the bottom end of the desktop market moves fairly sluggishly(of course, the bottom end of 'supercomputers' also moves more sluggishly; but nobody bothers to talk about the "250,000th fastest supercomputer!!"); but the top end has been moving at a reasonably steady clip.
Back in mid 2007, a Core2 quad was Pretty Serious Stuff, with maybe a Geforce 8800 or 9800 and 4-8 gigs of RAM if you were hardcore like that.
That will still go head to head with a contemporary budget to midrange box; but if you spent the same money today that you would have had to spend on that, you could be talking a high-end i7, a markedly more powerful graphics card(or 3 of them), and two or three times the RAM. Plus, the now-reasonably-cost-effective-even-when-large-enough-to-be-useful SSD that will have driven your I/O numbers through the roof.
Apathy and diminshing returns keep the desktop market boring; but if those are no object, you can still go nuts.
peace is not a static state of being. peace is a balanced state of tension between armed foes. war is a disruption in this equilibrium that is then restored. the goal of maintaining peace is to not have any sudden shocks to the status quo
you will never, ever, have a world where peace is simply a static state of being that requires no armed maintenance. why? human nature is why
show me a place where everyone is unarmed and peaceful, and i'll show you a warlord's pillaging grounds
sorry, but this is reality. stop asking for things that don't exist, and never will, as long as human beings are human beings
intellectual property law is philosophically incoherent. it is your moral duty to ignore it or sabotage it
Here are some images of the system, which currently uses 672 cabinets and uses about 10 megawatts of power. The K system is more powerful than the next 5 systems combined. It's a big-ass system.
Huh?
The K Computer was built by Fujitsu, and contains more than 80,000 2GHz SPARC64 VIIIfx CPUs, each with eight cores, to deliver a total of more than 640,000 processing cores.
That said I'm fairly surprised that it managed to be the 4th highest efficiency system, the SPARC64 isn't really known for being a hugely efficient and the low density of FLOPS/chip would normally mean it needs more support infrastructure further lowering the efficiency. Obviously the guys at Fujitsu have managed to do some great system engineering since Rmax is so close to Rpeak, kuddo's to them for making an awesome system around an ok chip!
There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
Anyone here who find that 'quadrillion' is more descriptive than peta? (or 1e15, for that matter?).
I would lean towards "brazillian!"
"I like to lick butts!" by MobileTatsu-NJG (#32700246) (Score:5, Informative)
Wasn't there an article recently about China's world's fastest supercomputer, and no competition in site for the next several years? Or did I fall asleep at my seak for several years?
Who would win this election: Andrew Weiner vs Andrew Weiner's weiner.
The K computer is able to do work more efficiently than GPUs because it uses a very power-efficient core, the Sun VIIIfx. If you peel the onion, it seems like the real reason for energy efficiency is special purpose units and the HPC-ACE instructions. I did a quick investigation of what this core has (and what it doesn't) to make it so energy efficient. It may be an interesting read for some of you guys so leaving a link here: http://bit.ly/kTvvDE
Soon you'll be able to take out one of those "nots", because the Americans have figured out that if they change the definition of a billion to the European one, it chops 3 places off the national debt.
The EU's Human Brain Project has an estimate of 1000 times the current fastest supercomputer (probably written about a year ago), so maybe around an exaflop.
"Today, simulating a single neuron requires the full power of a laptop computer. But the brain has billions of neurons and simulating all them simultaneously is a huge challenge. To get round this problem, the project will develop novel techniques of multi-level simulation in which only groups of neurons that are highly active are simulated in detail. But even in this way, simulating the complete human brain will require a computer a thousand times more powerful than the most powerful machine available today." (link)
That's 10 doublings, so if Moore's Law holds up this level of capability should be roughly 20 years away. I think it's interesting to note that this also suggests the feature size will halve 5 times to right around 1 nm: atomic scale. My rough understanding is that no matter what you may have heard from semiconductor physicists we are currently pretty clueless as to what, if anything, is going to drive the progress of Moore's Law beyond about 10 nm.
Keep in mind that one of the defining features of this CPU is 2 vector coprocessors per core, Intels offerings only have 1. For number crunching applications like matrix multiplication(which is what these benchmarks are based off of), the extra vector coprocessor makes a HUGE difference.
Monstar L