petaflop
Latest
Desktop-sized laser supercomputers could be coming by 2020
Small, eco-friendly optical supercomputers may soon be crunching quadrillions of calculations per second (exaflops) if a company called Optalysys has its way. It claims to be months away from demonstrating a prototype optical computer that will run at 346 gigaflops to start with -- not as fast as the best supercomputers, but pretty good for a proof-of-concept. Here's how it works: low-intensity lasers are beamed through layers of liquid crystal grids, which change the light intensity based on user inputted data. The resulting interference patterns can be used to solve mathematical equations and perform other tasks. By splitting the beam through multiple grids, the system can compute in parallel much more efficiently than standard multi-processing supercomputers (as shown in the charming Heinz Wolff-hosted video below).
Tianhe-2 supercomputer claims the lead in Top 500 list, thanks its 3.1 million processor cores
As predicted, Chinese supercomputer Tianhe-2 (also known as the Milky Way-2) has now been crowned the most powerful supercomputer in the world. Arriving years ahead of schedule, and packing 32,000 Xeon processors alongside 48,000 Xeon Phi accelerator processors, the supercomputer can manage a quadrillion mathematical calculations per second (33.85 petaflops), double that of last year's king (and closest rival), the Titan. In this year's results, 80 percent of the Top 500 used Intel processors, while 67 percent had processors with eight or more cores -- as clock speeds stall, supercomputer development has now focused on processors running in parallel. Top 500 editor Jack Dongarra adds that "most of the features of the [Tianhe-2] system were developed in China, and they are only using Intel for the main compute part," meaning that you can expect to see more Chinese entrants (and possibly champions) over the next few years. For now, however, the US still claims the majority of the Top 500, with 253 top-ranking supercomputers.
China's Tianhe-2 supercomputer could hit 100 petaflops in 2015, may have a race on its hands
China's supercomputer development is as much driven by national reputation as by military prowess and science; the country chose to build the Sunway BlueLight MPP with domestic chips knowing that it wouldn't get the absolute performance crown. It won't be quite so modest the next time around. China's National University of Defense Technology wants the Tianhe-2 supercomputer due in 2015 to crack an extremely high 100 petaflops, or five times faster than the record-setting Titan over in the US and a whopping 40 times faster than the Tianhe-1A. Before we hand the crown over, though, Top 500 supercomputer chart keeper Jack Dongarra notes to ITworld that China might have to sprint if it wants the symbolic title: the EU, Japan and US are all striving for the same benchmark, and they're not backing off anytime soon. The nation's trump card may have to be long-term plans for an exaflop-strength supercomputer by 2018, at which point we suspect the bragging will simmer down. For awhile.
Cray's Jaguar supercomputer upgraded with NVIDIA Tesla GPUs, renamed Titan
Cray's Jaguar (or XK7) supercomputer at Oak Ridge National Laboratory has been loaded up with the first shipping NVIDIA Tesla K20 GPUs and renamed Titan. Loaded with 18,688 of the Kepler-based K20s, Titan's peak performance is more than 20 petaflops. Sure, the machine has an equal number of 16-core AMD Opteron 6274 processors as it does GPUs, but the Tesla hardware packs 90 percent of the entire processing punch. Titan is roughly ten times faster and five times more energy efficient than it was before the name change, yet it fits into the same 200 cabinets as its predecessor. Now that it's complete, the rig will analyze data and create simulations for scientific projects ranging from topics including climate change to nuclear energy. The hardware behind Titan isn't meant to power your gaming sessions, but the NVIDIA says lessons learned from supercomputer GPU development trickle back down to consumer-grade cards. For the full lowdown on the beefed-up supercomputer, hit the jump for a pair of press releases.
IBM's water-cooled supercomputer saves energy and helps with your heating bill (video)
IBM's SuperMuc has had a good week. Not only has the three petaflop machine been listed as Europe's fastest supercomputer, but it's also apparently the first high performance computer that's entirely water-cooled. Rather than filling rooms with air conditioning units, water is piped around veins in each component, removing heat 4,000 times more efficiently than air. The hot water is then used to heat the buildings of the Leibniz Supercomputing Centre where it lives, saving the facility $1.25 million per year. After the break we've got a video from Big Blue, unfortunately narrated by someone who's never learned how to pronounce the word "innovative."
Eyes-on the innards of Fujitsu's K supercomputer (updated)
Fujitsu's K supercomputer was on our radar before it was even completed, and naturally, we let you know when it smoked the competition and became the supercomputing speed king. So, when we had the opportunity to see a piece of K at Fujitsu's North America Technology Forum today, we couldn't pass it up. In case you forgot, K is a massive machine powered by 864 racks with 24 boards per rack housing SPARC64 CPUs. We got to see one of those boards, and Yuichiro Ajima -- who designed the inter-connection chips (ICC) on them -- was gracious enough to give us some more info on this most super of supercomputers.As you can see in the gallery above, each board has extensive plumbing to keep the SPARC silicon running at a manageable 32 - 35 degrees Celsius (90 - 95 Fahrenheit) under load. Underneath that copper cooling system lies four processors interspersed between 32 memory modules (with 2GB per module) and four ICCs lined up next to the board's rack interconnect ports. Currently, the system takes 30 megawatts to do its thing, though Ajima informed us that K's theoretical max electricity consumption is about double that -- for perspective, that means K could consume the entire output of some solar power plants. When asked if there were plans to add more racks should Fujitsu's supercomputer lose its crown, Ajima-san said that while possible, there are no plans to do so -- we'll see if that changes should a worthy opponent present itself.Update: Turns out the K's power consumption resides around 13 megawatts, with a max consumption of 16MW at its current configuration. The facility in Kobe, Japan where K resides can deliver up to 24 megawatts, so expansion is possible, but none is currently planned.
Fujitsu's 10.51 petaflop K supercomputer is fastest in the world
Fujitsu, sweaty palmed from the construction of the K supercomputer, swore the colossal machine would manage a speed of ten petaflops by the year 2012. The effort has paid off handsomely: the hangar-sized machine has a top speed of 10.51. If you wanted to duplicate that setup at home, you'd only need 864 racks, 88,128 processors and enough cash in your back pocket to front an annual electricity bill of $10 million a year. The company will be spilling all at November's SC11 conference in Seattle, where the K will cement its position as the fastest computer in the world. One last thing -- we have a hunch that this machine can just about play Crysis.
China debuts homegrown supercomputer, hits one petaflop mark
China has already, however briefly, sat atop the Top500 list of supercomputers, but that was using silicon designed by American companies like Intel and NVIDIA. The country's latest contestant though, is sure to be a much bigger point of national pride. The Sunway BlueLight MPP, which was installed at the National Supercomputer Center in Jinan this September, is powered by 8,700 ShenWei SW1600 CPUs -- the homegrown chips that come out of Shanghai. The Sunway's one petaflop performance isn't enough to make it the new king of the hill, but it should get it into the top 20. More impressively, the machine only consumes about one megawatt of electricity -- roughly a quarter of the 2.5 petaflop Tianhe-1A. Now it's up to researchers to crank these ShenWei cores up to a 11 and make a run at that 50 petaflop Cray.
IBM and NCSA end their Blue Waters affair, go back to just being supercomputing friends
It seems that IBM and the National Center for Supercomputing Applications at the University of Illinois have hit a snag in their once fruitful relationship. After nearly four years of partnering for the Blue Waters petascale supercomputer, the NCSA's recently released a joint statement explaining that IBM's "terminated" its involvement with the project. If you'll recall, IBM was supplying its latest Power7 rigs to get all that data flowing, but the company's now decided that Ol' Blue will require more resources than initially anticipated. Apparently, there were talks to try and keep the spark alive, but since those fell through both have decided to return each others CDs and hoodies assets involved with the project (per contract terms): IBM gives back the money, while the NCSA returns any hardware supplied. The two plan on remaining in touch for future endeavours, and the NCSA doesn't appear to be too down either as it'll be consulting with the National Science Foundation to keep Blue Waters afloat. You'll find the official statement in the source link below, but we've included a video rendition of how we'd like to imagine it past the break. [Photo credit: kosheahan]
Fujitsu K supercomputer now ranked fastest in the world, dethrones China's Tianhe-1A
Remember the K -- the Fujitsu supercomputer that promised to do a whopping ten petaflops by the year 2012? Well, it hasn't reached that threshold just yet, but according to the latest Top 500 supercomputer list, it's still faster than any other machine on Earth. In fact, the top-ranked beast is more powerful than the next five supercomputers combined, consumes enough electricity to power about 10,000 homes for a full year, and is capable of churning out about 8.2 quadrillion calculations per second -- three times as many as what runner-up (and former number-one) Tianhe-1A can process. Today's announcement marks the first time since 2004 that a Japanese creation sits atop Top500.org's rankings, but Fujitsu isn't exactly resting on its laurels. Before deploying it next year, engineers at the Riken Advanced Institute for Computational Science are aiming to add about 100,000 cores to the K's collection of 548,352, which would provide it with even more computational muscle, and likely spell doom for all of humanity. Find out more in the PR after the break.
ORNL energy harvester turns heat waste into electricity, converts hot machines into cool customers
We've heard of turning yesterday's lunch into tomorrow's electricity, but a new energy converter coming out of Oak Ridge National Laboratory harnesses the power of a different type of hot waste. The as-of-yet unnamed thermal waste-heat converter has the potential to cool electronic devices, solar cells, and computers while generating electricity from excess heat. Its creators see the new conversion process being used to reduce the massive amounts of heat generated by petaflop computers. The converter employs up to one thousand tiny cantilevers attached to a one square inch surface (e.g. a computer chip) to produce between one and ten milliwatts of electricity -- admittedly a very small amount of energy. However, it's creators are quick to point out that a slew of these converters could generate enough power to perform small tasks in the heat-generating device -- things like sensing when a server room gets too hot for comfort. Sure it's a small step, but if they can get this stuff to save our future babies from cooking, we're all in. Full PR after the break.
Tokyo Institute of Technology announces SSD-packing, 2.39 petaflop supercomputer
IBM has announced plans to start using SandForce SSDs in its enterprise machines, and now it looks like the Tokyo Institute of Technology is doing one better, working with NEC and HP to produce Tsubame 2.0. This next-gen supercomputer will reportedly operate at 2.39 petaflops (that's a lot of flops!) and uses a new multilevel storage architecture consisting of DRAM as well as SSDs. Not only will this bad boy have thirty times the computing capacity of Tsubame 1.0 (due in part to its some 2,816 Intel Westmere microprocessors and 4,224 NVIDIA Tesla M2050 GPUs), its power draw should be some 1/25th of its predecessor's. If all goes according to plan, it should be in operation this fall, at a cost of ¥3.2 billion (approx $35.5 million). [Thanks, Dylan]
Cray Jaguar leaps past IBM Roadrunner as world's fastest supercomputer and pun generator (video)
Cray has finally clawed IBM back from the lead position on the Top500 Supercomputer chip-measuring contest. After just missing out on the title to IBM's Roadrunner last year, Cray's XT5 supercomputer (aka, Jaguar) at Oak Ridge National Lab in Tennessee received an update from quad- to six-core Opteron processors to boast a 2.3 petaflop per second performance peak (theoretical) and 1.75 petaflops as measured by the Linpack benchmark; a feat requiring almost a quarter million AMD cores. IBM's Roadrunner, the very first supercomputer to race past the petaflop per second threshold, managed just 1.042 petaflops by comparison. Remember, one petaflop per second is equivalent to one quadrillion calculations per second. Of course, chip makers put their own spins on the list by noting that 4 of the top 5 systems depend on AMD for performance while Intel can be found powering 402 of the Top500. Video of the AMD processor upgrade procedure can be found after the break.
World's fastest: IBM's Roadrunner supercomputer breaks petaflop barrier using Cell and Opteron processors
When you're looking to set a record this is how you do it. Not only has IBM's Roadrunner supercomputer come on-line, it's now the world's fastest -- twice as fast as the old BluGene/L champ -- and churning through 1.026 quadrillion calculations per second. The $133 million supercomputer achieved the milestone with the help of 12,960 "improved" Cell processors (yes, like those powering your PS3) and a smaller number of AMD Opteron processors -- 116,640 processor cores in total. Unfortunately (or fortunately depending upon your perspective), Roadrunner is for military use only so you'll have to solve the traveling salesman problem on your own time. While not quite into Exaflop territory, we're definitely on the way.[Thanks, Chris S.]
Exascale computing: it's the new terascale
Anybody remember when a gigaflop was a big deal? Oh, how far we've come. Researchers are now talking about exascale computing, which means systems that can handle a million trillion calculations per second. To put that in perspective, IBM's BlueGene/L (pictured), the fastest machine running, has a peak performance of 596 teraflops. A petaflop is 1000 times faster than a teraflop, and an exaflop is 1000 times faster than a petaflop. Yeah, that's a lot of flops. Right now researchers are sorting out the most preliminary of groundwork, such as how do you get data to tens of thousands of processors at a time for crunching, but we're sure before a few decades are up they'll finally have built a machine that is powerful enough to cure all human diseases -- or, you know, maybe even play Crysis at 60fps.
Folding@Home recognized by Guinness World Records
Finally getting the street cred that its creators have so long desired, the multi-platform, distributed computing network known as Folding@Home is to be recognized by Guinness World Records. According to the group, the network is now the most powerful distributed computing cluster in the world. The system, which utilizes the power of more than 670,000 PS3s, PCs, and lawnmower motors to crunch data, has overall computational capabilities greater than a petaflop (which is a ton of flops). The linked consoles tackle a number of tasks, and scientists harnessing the network's power are able to study complex medical problems -- such as Parkinson's and Alzheimer's -- much more quickly. Vijay Pande, Associate Professor of Chemistry at Stanford University and head of the Folding@home project says, "Without them [the Folding@Home users] we would not be able to make the advancements we have made in our studies of several different diseases." Now that Guinness has recognized the system, it can proudly stand next to luminaries such as the man with the longest fingernails, and fastest land animal.
IBM unveils one-petaflop Blue Gene/P supercomputer
It was but two years ago that we all sat in awe of IBM's beautiful 280.6-teraflop masterpiece, and it's finally safe to call that workhorse a thing of the past. Today, Big Blue announced the second-generation of its famed supercomputer (dubbed Blue Gene/P), which reportedly comes close to "tripling the performance of its predecessor." In an attempt to showcase its might, IBM suggested that 27 million clinical trials could be computed "in just one afternoon using a sliver of its full power." Additionally, the engineers went the extra mile by crafting a highly scalable system that comes in "at least seven times more energy efficient than any other supercomputer," but we're sure those 294,912 processors (each touting four PowerPC 450 CPUs) can churn through some energy when utilizing the whole petaflop. And just think, Sun probably thought the 500 or so teraflop production from its forthcoming Ranger would be the (momentary) top dog.Read - IBM's Blue Gene/P, via CNETRead - Sun's Ranger, via Wired
IBM building world's fastest supercomputer using Opteron and Cell processors
One reason there's so much fuss (and delay) over the upcoming PlayStation 3 platform is the fact that it sports those new Cell processors jointly developed with Sony and Toshiba. Now those Cell procs are about to find themselves pumping away at the heart of a new $35 million supercomputer for Los Alamos National Laboratory. But this won't be just supercomputer mind you, IBM is hoping to reclaim the title of the world's fastest once completed in 2007. Dubbed Roadrunner, ACME IBM plans to jump from 280-teraflops to a full petaflop performance by combining AMD Opteron blade servers and Cell-based accelerator systems. A performance threshold achieved earlier this year by NEC's MDGrape-3, the supercomputer behind new pharmaceutical drugs and the curious taste and powerful punch of Mad Dog's 20/20 Red Grape Malt beverage. Mmm, grape.
Japanese supercomputer breaks the petaflop barrier
Japan, which once topped the list of world's fastest supercomputers with NEC's Earth Simulator, has seen its position deteriorate in recent years in the face of faster machines like IBM's 280-teraflop BlueGene/L. Well now it looks like a new Japanese rig is poised to regain the top of the charts, and the most amazing thing about Riken's MDGrape-3 -- besides its claimed 1 petaflop performance -- is the fact that it cost only $9 million to build, giving it a per-gigaflop pricetag of just $15 (compared to the $140/gigaflop cost of IBM's top dog). Developed in conjunction with Hitachi, Intel, and NEC subsidiary SGI Japan, MDGrape-3 is being tasked with helping the pharmaceutical industry model new drugs, as it can calculate the chemical bonding properties of a proposed drug-protein combo in mere seconds. While BlueGene/L contains a whopping 130,000 processors distributed over 65,000 nodes, Riken's closet-sized machine needs only 4,808 chips to achieve four times its speed for certain applications. Oh, and despite the impressive-sounding performance, due to the specialized nature of its design, its unlikely that you'll see MDGrape-3 rocking a game of Doom anytime soon.[Via Slashdot]
