The Research Computing Center of Lomonosov Moscow State University and the RAS Joint Supercomputer Center – the creators of Supercomputers.ru web portal - have announced the publication of the 10th edition of the CIS Top 50 most powerful computers rating. For the first time ever the average peak performance of the systems represented in the rating has exceeded 10 TFlop/s.
The 10th anniversary edition of the Top 50 rating was officially announced on the 31st of March at the International Science Conference 'Parallel Computer Technologies’ in Nizhni Novgorod organized with the assistance of the Russian Fundamental Research Foundation. The recent edition of the rating is available at Supercomputers.ru.
The 10th edition of the rating has demonstrated further performance growth of the supercomputer systems in the CIS. Since the latest publication the total peak performance of such systems has grown by 14.95% and reached 510 TFlop/s (trillions floating-point operations per second). The total performance tested by Linpack has also grown by 15.33% and reached 382.6 TFlop/s within half-year. Thus, the average peak performance has for the first time exceeded 10 TFlop/s and amounts to 7.65 TFlop/s as tested by Linpack.
It should be noted that this year’s total performance growth is one of the lowest throughout history of the Top 50 rating. However, this rate showed its lowest value in the 5th edition, when the peak performance growth amounted to 2.2%. But on the average, performance was growing by 30-80% a year, and in the 8th edition a record performance growth of over 200% was achieved.
Saturday, May 2, 2009
Wednesday, April 29, 2009
Timeline of supercomputers
This is a list of the record-holders for fastest general-purpose supercomputer in the world, and the year each one set the record. For entries prior to 1993, this list refers to various sources[19][citation needed]. From 1993 to present, the list reflects the Top500 listing[20], and the "Peak speed" is given as the "Rmax" rating.
Research and development
IBM is developing the Cyclops64 architecture, intended to create a "supercomputer on a chip".
Other PFLOPS projects include one by Narendra Karmarkar in India,[12] a CDAC effort targeted for 2010,[13] and the Blue Waters Petascale Computing System funded by the NSF ($200 million) that is being built by the NCSA at the University of Illinois at Urbana-Champaign (slated to be completed by 2011).[14]
In May 2008 a collaboration was announced between NASA, SGI and Intel to build a 1 petaflops computer, Pleiades, in 2009, scaling up to 10 PFLOPs by 2012.[15]
Given the current speed of progress, supercomputers are projected to reach 1 exaflops (1018) in 2019.[16] Futurist Ray Kurzweil expects supercomputers capable of human brain neural simulations, for which according to Kurzweil 10 exaflops (1019) would be required, in 2025.
Erik P. DeBenedictis of Sandia National Laboratories theorizes that a zettaflops (1021) computer is required to accomplish full weather modeling, which could cover a two week time span accurately.[17] Such systems might be built around 2030Quasi-supercomputing
Some types of large-scale distributed computing for embarrassingly parallel problems take the clustered supercomputing concept to an extreme. The fastest, Folding@home, reported over 8.1 petaflops of processing power as of April 8, 2009. Of this, 2.5 petaflops of this processing power is contributed by clients running on PlayStation 3 systems and another 5.3 petaflops is contributed by their newly released GPU2 client.[4] Another distributed computing project BOINC platform, a host for a number of distributed computing projects. As of February 2009[update], BOINC recorded a processing power of over 1.7 petaflops through over 530,000 active computers on the network.[5] One such project, SETI@home, reported processing power of over 508 teraflops through almost 317,000 active computers.[6] As of May 2008[update], GIMPS's distributed Mersenne Prime search achieves currently 29 teraflops.[citation needed] Also a “quasi-supercomputer” is Google's search engine system with estimated total processing power of between 126 and 316 teraflops, as of April 2004.[7] In June 2006 the New York Times estimated that the Googleplex and its server farms contain 450,000 servers.[8] According to recent estimations, the processing power of Google's cluster might reach from 20 to 100 petaflops.[9] The PlayStation 3 Gravity Grid uses a network of 16 machines, and exploits the Cell processor for the intended application which is binary black hole coalescence using perturbation theory.[10][11] The Cell processor has a main CPU and 6 floating-point vector processors, giving the machine a net of 16 general-purpose machines and 96 vector processors. The machine has a one-time cost of $9,000 to build and is adequate for black-hole simulations which would otherwise cost $6,000 per run on a conventional supercomputer. The black hole calculations are not memory-intensive and are highly localizable, and so are well-suited to this architecture.
Current fastest supercomputer system
On June 8, 2008, the Cell/AMD Opteron-based IBM Roadrunner at the Los Alamos National Laboratory (LANL) was announced as the fastest operational supercomputer, with a sustained processing rate of 1.026 PFLOPS.[2] The Roadrunner hardware and software was then optimized and the benchmark was re-run and submitted for the November 2008 TOP500 with an Rmax of 1.105 PFLOPS, barely surviving a challenge from the Cray XT5 Jaguar to remain the fastest computer on the "official" list.
The Top500 list
Since 1993, the fastest supercomputers have been ranked on the Top500 list according to their LINPACK benchmark results. The list does not claim to be unbiased or definitive, but it is a widely cited current definition of the "fastest" supercomputer available at any given time.
Subscribe to:
Posts (Atom)
