If someone says " supercomputer , " your mind may jump to Deep Blue , and you would n’t be alone . IBM ’s silicon chess maven defeated grandmaster Gary Kasparov in 1997 , cementing it as one of the most far-famed information processing system of all time ( some controversy around the win assist , too ) . For days , Deep Blue was the public face of supercomputers , but it ’s scarcely the only all - powerful artificial thinker on the major planet . In fact , IBM need Deep Blue asunder shortly after the historical win ! More late , IBM made supercomputing history with Watson , which defeated " Jeopardy ! " champions Ken Jennings and Brad Rutter in a exceptional match .
Brilliant as they were , neither Deep Blue nor Watson would be capable to fit the computational muscle of the systems on the November 2013 TOP500 listing . TOP500 calls itself a list of " the 500 most brawny commercially uncommitted computer organization known to us . " The supercomputers on this inclination are a atavist to the other computers of the 1950s – which demand up integral rooms – except mod figurer are using rack upon wrack of cutting - edge computer hardware to produce petaflops ofprocessing superpower .
Your house computer believably runs on four mainframe magnetic core . Most of today ’s supercomputer use hundreds of thousands of cores , and the top entry has more than 3 million .
TOP500 presently rely on the Linpack bench mark , which feeds a computing gadget a series of linear equations to appraise its processing carrying into action , although an alternative examination method is in the works . The November 2013 inclination sees China ’s Tianhe-2 on top of the world . Every six calendar month , TOP500 releases a lean , and a few fresh calculator uprise into the rank of the world ’s fastest . Here are the champions as of early 2014 . Read on to see how they ’re putting their electronic spunk to puzzle out .
10: SuperMUC (Germany)
The SuperMUC perform at 2.9 petaflops , thanks to about 150,000 processing cores . Despite this unbelievable processing power , it has been campaign from No . 4 on the June 2012 list all the path to No . 10 . It ’s one of several IBM system to make the list , but the SuperMUC is unique in a couple of dissimilar room . Located in Germany ’s Leibniz Supercomputing Centre , the SuperMUC use a new hot - water cooling system to keep thecomputer ’s brainfrom frying while it ’s execute gazillion upon billion of operations .
Efficiency is what really sets the SuperMUC apart : IBM says it ’s 40 per centum more muscularity efficient than an atmosphere - cooled arrangement would be . They exact thewaterremoves heat 4,000 times more efficiently than melodic phrase . Thanks to its cut - sharpness hardware , the SuperMUC is Germany ’s 2nd fastest supercomputer . In fact , it ’s the third fastest supercomputer in Europe , and nearly twice as fast as the previous year ’s No . 10 .
9: Vulcan (United States)
Vulcan is the first of four calculator in the top 10 running on IBM ’s knock-down BlueGene / Q platform with Power BQC 16 - core 1.6GHz processors . outflank the previous entry by over a petaflop , this powerhouse perform at 4.3 petaflops with its nearly 400,000 essence .
This supercomputer is one of two in the top 10 operate at the U.S. Department of Energy ’s National Nuclear Security Administration ( NNSA ) at the Livermore National Laboratory ( LLNL ) inCalifornia . In mid-2013 , the science lab opened up estimator sentence on Vulcan to U.S. business for collaborative workplace on projects that will increase scientific and technical onward motion , improve U.S. competitiveness and heighten the high - performance computing ( HPC ) workforce , all in exchange for a part of the operational costs . Vulcan is also intended for coaction with pedantic andresearchinstitutions in surface area such as energy , security , atmospheric skill and life science .
8: JuQUEEN (Germany)
JuQUEEN also pass on the IBM BlueGene / Q program , with max performance of 5 petaflops on about 459,000 cores . While many computers on the inclination have been around for the last couple age , JuQUEEN was work up in 2012 as a replacement for another system of rules , JUGENE , which was the ninth fast system on the November 2010 TOP500 .
Researchers at the Jülich - Aachen Research Alliance can submit proposals for projects to rationalise using some of JuQUEEN ’s cores , and if approved , they get to carve out some time with one of the most powerfulsupercomputersin the Earth . Time on this and two other hefty German supercomputers , SuperMUC and HERMIT ( 39th on the TOP500 lean ) , can be requested through the Gauss Centre for Supercomputing ( GCS ) and the Partnership for Advance Computing in Europe ( PRACE ) .
7: Stampede (United States)
Stampede made its way into the No . 7 office in November 2012 , spring up to No . 6 in June 2013 and then resume its former position on the most recent list . Funding for the organisation add up from an prize from the National Science Foundation ( NSF ) , and Stampede is housed at the Texas Advanced Computing Center ( TACC ) at the University of Texas in Austin . This Dell PowerEdge system of rules runs Intel Xeon E5 8 - core 2.7GHzprocessorsin conjunction with Intel Xeon Phi coprocessors . Its or so 462,000 cores earmark it to attain nearly 5.2 petaflops in performance .
Since January 2013 , Stampede has been candid for use byscientistsand other researchers in all field of operations as part of the NSF ’s Extreme Science and Engineering Discovery Environment ( XSEDE ) programme , a practical system for openly sharing the computing force of 16 supercomputers and related to resources . Ninety per centum of the system is dedicate to XSEDE and the rest is at the discretion of the TACC ’s theatre director . Qualified research worker at any U.S. institution can submit proposals via the XSEDE Web site .
6: Piz Daint (Switzerland)
Although Piz Daint has been in operation since April 2013 , this Cray system later pop off through a major ascent that advance it into the No . 6 attitude and dethrone JuQUEEN as the most powerful supercomputer in Europe .
Piz Daint runs Intel Xeon E5 processors along with NVIDIA graphical processing unit ( GPUs ) for tally performance , allowing it to reach 6.3 petaflops with its 116,000 processing cores . It reside at theSwissNational Supercomputing Centre ( CSCS ) and will be put to employ modeling weather and climate patterns and execute scientific computation in a variety of other field .
The Piz Daint is also one of the most energy effective supercomputer on the list , with an efficiency degree of 3,185.9 megaflops per James Watt ( MFLOPS / W ) [ author : Green500,Smith ] . It ’s the only supercomputer to make the top 10 in both the TOP500 and GREEN500 tilt . GREEN500 takes all the supercomputers in the TOP500 listing and ranks them by energy efficiency . Piz Daint ’s intercrossed architecture , which uses both traditional central processor ( central processing units ) and more energy - efficient GPUs , helps keep its vitality usage low .
5: Mira (United States)
IBM ’s Mira , which became amply usable in 2013 , peaks at a carrying into action of 8.6 petaflops . That ’s more than 2 petaflops over the Piz Daint , and nearly 3.5 petaflops more than Stampede .
Mira runs on 786,000 C.P.U. cores . It ’s locate at the Argonne National Laboratory , a research laboratory for the U.S. Department ofEnergy . It uses IBM ’s BlueGene / Q political platform and replaces an old IBM system , Intrepid , which ranked fourth on the list in 2008 .
Researchers who relegate proposals for the Innovative and Novel Computational Impact on Theory and Experiment programme ( INCITE ) through the U.S. Department of Energy ’s Office of Science can claim central processor sentence on Mira . Sixty percent of the computer ’s capacity goes to their research , while 30 percent goes towards the Advanced Science Computing Research Leadership Computing Challenge . The last 10 percent is reserved for urgent , time - sensitive computations [ source : Information Week ] .
4: K computer (Japan)
Fujitsu ’s K information processing system , the onlysupercomputerin Japan that made the top 10 , reigned as the fastest supercomputer in the world on both 2011 lists , but has since been edge down to No . 4 . Still , it give way the single - digit barrier and makes a detectable start in velocity over IBM ’s Mira with a performance of 10.5 petaflops .
The K computer is located at Japan ’s RIKEN Advanced Institute for Computational Science , where it performs scientific operations including global calamity bar , meteorology and aesculapian research [ source : Fujitsu ] . Unlike many of the other supercomputer on the list , it does n’t run on IBM architecture . The K calculator uses Fujitsu ’s own SPARC64 VIIIfx octo - essence processors . Its 705,000 computing gadget cores help it churn through operations at an unbelievable pace .
But conceive it or not , the last three fastest supercomputer are leaps and rebound more powerful than the K computing machine .
3: Sequoia (United States)
Sequoia was the top ranked supercomputer on the June 2012 TOP500 tilt , but drop to No . 2 in November 2012 , and now rests at No . 3 . It ’s still no slouch , thanks to around 1.6 million processing cores that can crank up out an unbelievable 17.2 petaflops of performance . Wondering just how unbelievable that is ?
Well , if we look back less than a tenner ago to 2008 , IBM ’s Roadrunner made history ( and grabbed the top slot ) for crack 1 petaflop , aka performing 1,000 trillion operations per 2nd [ source : IBM ] . IBM say Roadrunner was equivalent to 100,000 of 2008 ’s laptops in performance . And Sequoia is 17 times as tight ! Sequoia is one of four computers on the November 2013 list running on the BlueGene / Q IBM design , a 16 - core 1.6GHz chip . That ’s not an peculiarly fastclock speedby today ’s standard , but with 96 rack of chips , the carrying into action really adds up .
What ’s Sequoia doing with all that fastness , anyway ? Sequoia is 63 percent faster than the fourth fastest computer on the list , and IBM is put Sequoia to work , of course . Like Vulcan , it operate at the U.S. Department of Energy ’s National Nuclear Security Administration at the Livermore National Laboratory . The computer ’s doing important ( and classified ) workplace : One of its responsibility is simulatingnuclear explosion .
2: Titan (United States)
One of the two Cray systems on the List , the Titan live on up to its name , utilizing Opteron 6274 16 - meat 2.2GHz processors along with NVIDIA GPUs to perform at an amazing 17.6 petaflops on around 561,000 cores . It ’s located at the Oak Ridge National Laboratory ( ORNL ) run by the Oak Ridge Leadership Computing Facility ( OLCF ) . Titan nabbed the No . 1 situation on the Top500 the month after it was deployed in late 2012 , but shed down to No . 2 in the June 2013 ranking , where it remains .
Titan is technically a major upgrade to the ORNL ’s old supercomputer , Jaguar . Due to its novel hybridarchitecture , Titan gibe into the same cabinets as Jaguar while achieving nine time Jaguar ’s f number with only around a 60 per centum growth in free energy consumption .
Titan is one of two supercomputers in the top 10 that incorporate NVIDIA GPUs to increase performance while keeping the big businessman consumption low than it would be for a likewise powerful all - central processing unit organisation . utilize the GPUs to runapplicationsat the speed of which the arrangement is capable demand a young approach to programming its software , however . To plow this , the OLCF has partner with Cray and NVIDIA to create the Center for Accelerated app Readiness ( CAAR ) , which is concentrated at oeuvre get along up with best practices for code development .
As with Mira , researchers can submit proposals through the U.S. Department of Energy ’s INCITE program to earn time on this workhorse .
1: Tianhe-2 (China)
The Tianhe-2 ( which stand for Milky Way-2 ) appeared on the vista in 2012 , more than two year ahead of schedule , and leapt into the No . 1 spot . It processes at an astounding 33.9 petaflops , nearly twice the performance of the Titan or Sequoia , and more than 10 metre the performance of Tianhe-1A , which held the No . 10 place in June 2013 .
The organization hunt on a mix of Intel Xeon E5 processors , custom processors and Intel Xeon Phi coprocessors : approximately 3,120,000 center in total .
Developed by China ’s National University of Defense Technology ( NUDT ) and located at the National Super Computer Center in Guangzhou , the system will be used for Department of Education and research . It is currently China ’s only top-10 first appearance , but the Tianhe-2 gives them vaporing right wing for sheer processing power in a undivided machine .
Tianhe-2 runs on a customs version of the Ubuntu Linux operating scheme called Kylin , which was uprise through a partnership between the NUDT , the China Software and Integrated Circuit Promotions Centre ( CSIP ) and Canonical ( Creator of Ubuntu ) . In fact , all of the top 10 supercomputers , and most of the top 500 , hunt some flavor ofLinux .
Kylin is n’t just for supercomputers . It is a freely available , open - origin operating organization tailor specifically for Chinese user , and can be downloaded from Ubuntu ’s site for purpose on personal computers .
Lots More Information
2012 ’s supercomputer leaning was absolutely amazing . These data processor have always been super compared to the PCs we ’ve got at nursing home , but looking at the last few year ' lists drove home how much technology has improved in such a short time . As recently as 2008 , a supercomputer capable of 1 petaflop of carrying into action was a big batch . Today , IBM ’s fastest supercomputer can execute at 16 petaflops ! I ca n’t even imagine what these thing will be capable of in five old age . -WF
I updated this clause with 2013 ’s top supercomputer , and what a difference a year make ! From the November 2012 to November 2013 tilt , the processing power of the computers in first and 10th place nearly double . Hopefully this ever - increase computing ability will translate into more and faster scientific breakthroughs , like piddle useful family robots and growing organs that need replacing and the like . Supercomputer developer are already eyeball the future of EiB processing , and at this charge per unit , that might only be a few year off . - BJ
