The Leading Source for Global News and Information Covering the Ecosystem of High Productivity Computing
April 11, 2008
MOSCOW, March 27 -- The Research Computing Centre of the Lomonosov Moscow State University and the Joint Supercomputer Centre of the Russian academy of science announce the release of the 8th edition of the Top 50 list of the most powerful computers in Russia and CIS (former Soviet Union countries). The new list can be found at http://www.supercomputers.ru/?page=rating.
The 8th edition of the list shows a skyrocketing increase of performance of the most powerful computers in Russia and CIS. Total Linpack performance has increased from 61.6 TFlops to 197.3 TFlops (by 220.3 percent) within half a year -- an unparalleled increase for the entire life of the list. New systems, including those upgraded over the last half a year, comprise 56 percent of the list (28 out of 50 installations).
The most significant changes as compared to the previous edition affected the top section of the list. The top five of the most powerful supercomputers in CIS are all completely new. As a result, total Linpack performance of Top5 has increased from 31.2 TFlops up to 117.1 TFlops (by 275.4 percent).
The top position of the list is occupied by the SKIF MSU supercomputer delivered by T-Platforms for the Lomonosov Moscow State University within the frames of the SKIF-GRID supercomputer program of Russia & Belarus. The Linpack performance of this computer deployed in the MSU Research Computing Centre is 47.14 TFlops (78.5 percent of peak performance).
The second position of the new list edition is taken by the MBC-100K supercomputer delivered by HP with Linpack performance of 33.9 TFlops. The 3rd and 5th positions are occupied by two IBM systems deployed in the Ufa State Aviation Technical University and the Siberian Federal University with Linpack performance of 14.6 TFlops and 9.3 TFlops respectively. The 4th position goes to SKIF Ural supercomputer by T-Platforms deployed in the South-Ural State University with Linpack performance of 12.2 TFlops.
The 6th position of the list is taken by the leader of two previous editions of Top50 -- the T-Platforms SKIF Cyberia supercomputer for Tomsk State University with Linpack performance of 9 TFlops. Only two systems from the previous edition remained in the top ten -- it is the most significant change during the whole history of the Top50 list.
The number of computers with real performance over 1 TFlops in CIS has actually doubled from 13 to 25, and the entry level to top ten moved from 1.3 TFlops to 5.2 TFlops (by 300 percent). The entry level to the entire Top50 is now 432 GFlops on the Lipack benchmark as compared to 253.6 GFlops half a year ago.
The number of systems in the academic segment increased from 38 percent to 58 percent, while the share of HPC systems used for applied research stayed on the same level of 28 percent as compared to the previous edition. At the same time, the share of powerful computers in the industrial and financial segments decreased from 16 percent to 10 percent and from 18 percent to 4 percent respectively.
Most of Top50 computers are based on Intel processors (38 systems as compared to 31 half a year ago). The list also includes six AMD processor-based systems (nine in the previous edition), five IBM processor-based systems (unchanged from the previous edition) and one HP processor-based system (five in September). The number of computers based on Gigabit Ethernet interconnect significantly decreased -- from 20 to nine during six months. High-speed communication technologies are used more widely: InfiniBand (up from 20 to 31 systems) and Myrinet (up from six to eight systems). SCI and HyperPlex communication technologies are each used in one system.
T-Platforms improves its leading positions among Top50 system vendors with an increase of its share from 30 percent to 46 percent (including SKIF supercomputers developed and delivered by the company). The share of systems sold by Hewlett-Packard and IBM slightly decreased from 26 percent to 20 percent and from 22 percent to 14 percent respectively.
Page: 1 of 2(Digg, Technorati, more)
PGI Accelerator™ Fortran 95/03 and C99 compilers for x64+NVIDIA
Accelerate applications on x64+GPU platforms by adding OpenMP-like compiler directives to existing Fortran and C programs. Available now for Linux, MacOS and Windows. Download a free 15 day trial.
Platform HPC Workgroup Manager
Platform HPC Workgroup Manager integrates all the cluster productivity tools you need to deploy, run and manage your HPC environment.
The Moscow State University supercomputer, Lomonosov, has been selected for a high-performance makeover, with the goal of tripling its processing power to achieve petaflop-level performance in 2010. T-Platforms, who developed and manufactured the supercomputer, is the odds-on favorite to lead the project.
Read More...
Right on schedule, Intel has launched its Xeon 5600 processors, codenamed "Westmere EP." The 5600 represents the 32nm sequel to the Xeon 5500 (Nehalem EP) for dual-socket servers. Intel is touting better performance and energy efficiency, along with new security features, as the big selling points of the new Xeons.
Read More...
The ACM Turing Award goes to the creator of the modern personal computer; and Voltaire announces a mid-range InfiniBand switch and new technology that accelerates distributed applications. We recap those stories and more in our weekly wrapup.
Read More...
Mar 17 | The Register | But what about the tier ones? Read more...
Mar 17 | Cadalyst Magazine | A new generation of workstations is changing the nature of technical computing. Read more...
Mar 17 | Linux Magazine | Latest iteration of Sun Grid Engine able to tap into Cloud. Read more...
Mar 16 | Bio-IT World | Biotech firm builds genetic models from patient data. Read more...
Mar 15 | The Register | EMC's grand vision for unified global storage. Read more...
Jan 12 | | In-depth look at vSMP Foundation server virtualization technology, technical implementation, use cases and capabilities. The technical whitepaper provides an architectural overview and details on the three vSMP Foundation products: vSMP Foundation for SMP, vSMP Foundation for Cluster and vSMP Foundation for Cloud.
Jan 18 | | This white paper discusses Gore’s copper cable assemblies, and how they continue to exceed the standards for providing reliable, cost-effective solutions for high-performance computer applications.
Join this online panel discussion for live Q&A with leading industry experts, analysts, and end-users to discuss the latest innovations, best practices, barriers to implementation, and measurable benefits of server virtualization with a particular focus on today's real world solutions.
Learn about scalable fault-tolerant architectures and examples of energy efficient and scalable supercomputing clusters using dual QDR InfiniBand to combine capacity computing with network failover capabilities with the help of programming languages such as MPI and a robust Linux cluster management package.
LIVE@SCO9: The IBM team discusses new innovations in hardware, software and services that help clients better understand their workloads and get insight from their R&D efforts. Technology demonstrations include the soon-to-be-released Power7 HPC processor, the DCS990 system with 2.4 petabytes of storage, the xCAT management tool, secure HPC cloud computing and more. Winners of two HPCwire Readers' and Editors’ Choice Awards! Take the IBM virtual tour at SC09 or more information go online to: http://www-03.ibm.com/systems/deepcomputing/sc09.html