April 23, 2012
MOSCOW, April 18 -- T-Platforms, a global developer and supplier of supercomputers and a full range of solutions and services for high-performance computing, today announced it has launched the first phase of a new data center for the “Burevestnik” Central Research Institute (CNII “Burevestnik” JSC), designed for modeling samples of artillery weapons with the use of high-performance computing technology.
The “Burevestnik Central Research Institute (CNII)” Joint Stock Company was founded in 1970 as a lead organization engaged in the design of barreled artillery weapons for the Army and Navy. The Institute has design, scientific, manufacturing and test resources that support the complete artillery weapon making cycle including creation of the R&D specimens and preproduction prototypes, design optimization on test benches, and firing ranges and large-scale production.
According to Alexey Komkov, Chief Products and Technology Officer for T-Platforms, “Information technology has become a key tool for improving the effectiveness of engineering and manufacturing processes at foreign enterprises including the military-industrial complex, aerospace, and many other high-tech industries. By carefully evaluating the experiences of these organizations, Russian enterprises are able to increasingly adopt information technology to improve their business processes.”
Leaders of CNII “Burevestnik” specializing in the development of artillery weapons for the Russian Army, Navy, and Airborne troops, made a decision to fund the data center based along with the “Minin” computing cluster as part of an expanded enterprise IT complex. The system, being created by T-Platforms, will enable the Institute to make optimal use of its scientific and technical potential to reduce development time and cost while improving product quality.
“Our Institute makes technically sophisticated products which will reliably serve our forces for many decades in the harshest conditions,” said Georgy I. Zakamennyh, DPhil, Professor, General Director of CNII “Burevestnik” JSC, and Russian Federation Artillery Armament Chief Designer. “Research and development work to design new types of weapons requires costly full-scale tests,” he added. “Over the last decade, CNII “Burevestnik” has created an integrated information framework providing automation of all business processes and information support for the full product life cycle. The use of information systems for enterprise resource planning and product information management has greatly improved the productivity and output.”
“The experience of many Western companies clearly demonstrates that the use of high-performance computing in product design and testing enables new levels of analytical design, shorter time to market and improved quality of manufactured products. Therefore, we are creating a data center based on high performance computing technologies for the Institute. Its deployment will allow us to effectively meet the challenges of multi-parameter optimization of products, while solving problems of hydro-gaz-dinamics, dynamics of mechanisms and systems, strength, and other functional problems of our products. And thanks to the integration of the data center into a single enterprise information environment, we can make optimal use of scientific and technical potential of the Institute, which in turn will boost the gross profit."
A hybrid-architecture computational subsystem has been chosen as the basis of the data center being created at CNII “Burevestnik.” At present, its peak performance is 15 teraflops, and upon completion of the project it will exceed 50 teraflops. The use of compute nodes with integrated graphics accelerators helps to reduce the time required to solve the most demanding tasks related to engineering analysis of the product’s functioning processes. The Panasas Active Store 12 Storage System is included in the data center infrastructure. This storage system is a fourth-generation DSS with a blade architecture that takes full advantage of Panasas PanFS, the last-generation parallel file system, in combination with multi-core processors and integrated 10GbE technology. This system has a maximum performance among all DSS with a parallel architecture which makes it an ideal solution for demanding applications being used by science and manufacturing enterprises. Data center uninterrupted operation is provided by the infrastructure that includes cooling, automatic fire-suppression and uninterruptible power supply systems.
“Foreign enterprises of various military-industrial complexes, aerospace industries, heavy manufacturing industries, and other economic sectors have constantly shown us the effectiveness of computing clusters in new product development,” said Vsevolod Opanasenko, CEO of T-Platforms. “For example, the developers of the U.S. missile defense system successfully use computing systems for modeling missile interceptor trajectories, and Boeing engineers, thanks to a supercomputer, could increase the Boeing-787 aircraft’s commercial load by 45%. In so doing, the company has reduced fuel consumption by 25% relative to the closest competitors in the long- and medium-haul airliners market. The experience of these companies is not ignored by domestic developers who adopt the practice of using supercomputing technology to improve their designs and create fundamentally new types of weapons. When commissioning the first phase of the CNII “Burevestnik” data center, we have taken an important step towards creating a solid foundation tor the revival of the national defense industry.”
T-Platforms (www.t-platforms.ru) is a global supercomputer developer and a supplier of the full range of solutions and services for high performance computing. Founded in 2002, T-Platforms maintains headquarters in Moscow (Russia) and regional offices in Hanover (Germany), Kiev (Ukraine), Taipei (Taiwan), and Hong Kong (China). The company has implemented more than 200 integrated projects, six of which are included in the Top500 list of the world’s most powerful supercomputers. T-Platforms owns patents on a number of supercomputer technologies and electronic components. Solutions of T-Platforms are used for academic and applied research in various fields of science, including life sciences, nuclear physics, chemistry, mathematics, as well as for highly calculation-intensive tasks in engineering, computer graphics and much more. In 2011, HPCWire named Vsevolod Opanasenko, CEO of T-Platforms, one of 12 most famous and respected people of the HPC global community.
About CNII “Burevestnik”
The “Burevestnik Central Research Institute (CNII)” Joint Stock Company was founded in 1970 as a head enterprise engaged in design of barreled artillery weapons for the Army and Navy. The Institute has design, scientific, manufacturing and test resources that provide the complete artillery weapon making cycle including creating of R&D specimen and preproduction prototypes, design optimization on test benches, and firing ranges and large-scale production. For more than 40 years of practical work, the Institute has implemented more than 400 research and development projects including manufacturing and demonstration of a number of naval and field artillery, as well as the maintenance and support for the artillery weapons.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?