| News digest November 2004 |
|
Advertisement
|
 |
 |  |
 | Industry
-
HPCN industry |
 |
 |
| Lawrence Livermore National Lab's new BlueGene/L re-establishes U.S. dominance in supercomputers |
|
IBM's BlueGene/L supercomputer, destined for delivery to the Lawrence Livermore National Laboratory (LLNL) starting in November, has surpassed NEC's Earth Simulator in Japan to become the world's most powerful supercomputer, according to IBM. Using the industry-standard LINPACK benchmark, the IBM Blue Gene/L system attained a sustained performance of 36.01 Teraflops, eclipsing the three-year-old top mark of 35.86 Teraflops for the Japanese Earth Simulator in Yokohama, Japan. The milestone was attained during internal testing at IBM's production facility in Rochester, Minnesota.
Read further... |
|
|
 |
| Fujitsu Siemens Computers offers mono server blades for the datacentre |
|
With the introduction of the PRIMERGY BX300 mono server blade, Fujitsu Siemens Computers is making outstanding reliability, performance and connectivity available to IT managers for a broad range of application areas. The exceptional performance and value of the BX300 was highlighted by a recent SAP SD Standard Application Benchmark, making it ideal for Web servers, terminal server farms, and particularly in the datacentre. The mono server blade, designed for the BX300 blade server chassis, is now available for prices starting at 1690 euro each in Germany (excl. VAT).
Read further... |
|
|
 |
| Cray's strategy for the XD1 rollout |
|
After the acquisition of OctigaBay by Cray, it has been quit for some time. Cray has used this time to test the system and a number of customers. Also Cray has set-up a marketing strategy for the system and figured out how to approach the use of the novel FPGA chips for applications. We discussed the rollout strategy with Cray's Adam Lorant.
Read further... |
|
|
 |
| NEC launches world's fastest vector supercomputer |
|
NEC Corporation has announced the worldwide launch and availability of the SX series model "SX-8", the world's most powerful vector supercomputer with a peak processing performance of 65TFLOPS (TFLOPS: one trillion floating point operations per second).
Read further... |
|
|
 |
| LBNLs Evaluation of Earth Simulator Performance Nominated for Best Paper Award at SC2004 Conference |
|
With the re-emergence of viable vector computing systems such as the Earth Simulator and the Cray X1, there is renewed debate about which architecture is best suited for running large-scale scientific applications. In order to cut through the conflicting claims of fastest, biggest, etc., a team led by Lenny Oliker of the U.S. Department of Energys Lawrence Berkeley National Laboratory put five different systems through their paces, running four different scientific applications key to DOE research programs.
Read further... |
|
|
 |
| Fireworks with new products at Cray - the XT3 |
|
After the announcement of the Cray XD1 the next supercomputer is on the list to be sold as a product, the XT3 based on Sandias Red Storm. The XT3 is the successor of the legendary Cray T3D and Cray T3E and is based on the AMD Opteron. It is starting in the price range of 1 million US$. A 6 cabinets system with 548 processors and 14 service PEs has a peak performance of 2.6 TeraFlop/s, it can be extended to an open end of peak performance.
Read further... |
|
|
 |
| HPC Community invited to U.S.-Europe Dialogue Meeting, 13 October 2004 at CERN |
|
The HPC User Forum invites members of Europe's HPC community to participate in the third annual U.S.-Europe dialogue meeting, to be held October 13, 2004 at CERN.
Read further... |
|
|
 |
| The Portland Group joins OpenMP Architecture Review Board |
|
The Portland Group, a wholly owned subsidiary of STMicroelectronics, has accepted an invitation to become a permanent member of the OpenMP Architecture Review Board (ARB). The non-profit OpenMP ARB owns and manages the freely available OpenMP application programming interface (API) specification. The OpenMP API is the de-facto standard for programming multi-processor, shared-memory parallel (SMP) computing systems. Example systems range from dual-processor workstations to multi-processor blade servers incorporated into the world's fastest supercomputers containing thousands of processors. SMP has emerged as the preferred building-block architecture in high-performance computing due to its relative cost-effectiveness and broad industry support. The OpenMP specification provides for simple, portable and scalable SMP programming.
Read further... |
|
|
 |
| Cray XD1 targeted for Linux cluster market |
|
Today Cray officially announces the OctigaBay based system Cray XD1. It is specifically designed for the lower end of the HPC market and lies in the range of less than 100.000 US Dollar up to 2 million US dollar. The system is based on the newest AMD Opteron processors. The main, innovative features are the Cray-specific interconnect, the management and reconfigure technologies, specific FPGAs (Field Programmable Gate Arrays) and the HPC Linux. Two months before schedule Cray delivered the first machines to its customers. In the 4th quarter 2004 Cray will install a Cray XD1 at the Helmut-Schmidt-Universität, Hamburg, Germany.
Read further... |
|
|
 |
| USDA Forest Service selects Cray XD1 supercomputer to improve wildfire smoke plume path prediction and tracking |
|
The United States Department of Agriculture Forest Service has selected the new Cray XD1 supercomputer to help improve the Forest Service's ability to predict and track the paths of smoke plumes from wildfires. Financial details were not disclosed.
Read further... |
|
|
 |
| Bull NovaScale servers at the heart of a world first in cryptography |
|
A team of French researchers from the Central Office for Information Systems Security (DCSSI) and the University of Versailles-Saint Quentin en Yvelines has computed a collision for "SHA-0" code, a hash algorithm developed in the 1990s by the National Security Agency. The computation was performed on TeraNova, a supercomputer clustering Bull NovaScale servers. TeraNova demonstrated its power and reliability by breaking SHA-0 in three weeks and 80,000 CPU hours.
Read further... |
|
|
 |
| Cray begins shipping of Cray XT3 supercomputer |
|
Global supercomputer leader Cray Inc. (Nasdaq NM: CRAY) today reported that it has begun shipping the Cray XT3 supercomputer, an industry standard massively parallel processing (MPP) system that strongly advances the record-setting scalability and sustained application performance of the renowned Cray T3D and Cray T3E systems. U.S. list pricing for the Cray XT3 supercomputer begins at about $2 million.
Read further... |
|
|
 |
| Cray announces 'Red Storm' contract with Pittsburgh Supercomputing Center |
|
The Pittsburgh Supercomputing Center (PSC) has received a $9.7 million grant from the National Science Foundation that will be applied toward the contract for a Cray Red Storm-based supercomputer.
Read further... |
|
|
 |
| BlueGene/L comes to Lawrence Livermore National Laboratory in November |
|
Theres a new world heavyweight supercomputer coming to town, courtesy of the Department of Energy. BlueGene/L is the latest jewel in DOE's crown of high-performance computers that dates back to the agency's formation during the Cold War. At present, five of the worlds top 10 fastest computers are hard at work at DOE facilities. Delivery of BlueGene/L at the DOEs Lawrence Livermore National Laboratory should begin this November.
Read further... |
|
|
 |
| ClearSpeed announces its first commercial processor, the CSX600 |
|
ClearSpeed Technology has announced details of its first commercial microprocessor, the CSX600. In a presentation at the Fall Processor Forum in San Jose, California, one of the world's key semiconductor industry conferences, the company will be presenting performance data showing the new processor to be the highest performing product of its kind. The new chip, which delivers up to 50 GFLOPS for just 5 watts power consumption, is expected to become available by the end of Q1 2005.
Read further... |
|
|
 |
| ClusterVision expands UK team with new sales staff |
|
ClusterVision, specialist in Linux supercomputer clusters, have expanded their UK sales team with the recent arrival of Dr. ir. Gerdjan Busker as UK Manager and Georgina Gibbs as Senior Sales Executive. The new expansion follows two successful sales quarters in the UK with several large installations of compute, storage and database clusters at UK universities, research institutes and companies.
Read further... |
|
|
 |
| PathScale Product Suite to be offered with Hewlett Packard servers |
|
PathScale has announced that its product suite will be available to users and resellers of industry-standard HP ProLiant servers based on both AMD Opteron and Intel Xeon-based processors.
Read further... |
|
|
 |
| Cray reports order for 144-processor Cray XD1 system from Alabama Supercomputer Authority |
|
Cray Inc. has received an order for a 12-chassis Cray XD1 supercomputer system for the Alabama Supercomputer Authority (ASA). Financial terms were not disclosed.
Read further... |
|
|
 |
| Fujitsu Siemens Computers introduces new FibreCAT N20i storage system with iSCSI |
|
Fujitsu Siemens Computers has launched the new FibreCAT N20i entry-level NAS (Network Attached Storage) system with iSCSI) support. The new system addresses the growing storage needs of small and medium-sized enterprises (SME) by providing 1 Terabyte of easy-to-install storage capacity using hot-swap SATA disks.
Read further... |
|
|
 |
| Dot Hill releases RIO Xtreme storage solutions for high-bandwidth applications |
|
Dot Hill has released its RIO Xtreme storage solutions, which are optimized for very high sequential bandwidth applications such as streaming audio/video, data acquisition and high performance computing. Built with enterprise-class fault tolerance, RIO Xtreme storage solutions deliver high availability with redundant, hot-swappable components.
Read further... |
|
|
 |
| Fujitsu Siemens Comouters releases "cool" servers for hot performance |
|
Fujitsu Siemens Computers has released its PRIMERGY S2 rack and tower servers, which will offer IT managers greater flexibility and performance for their server farms, while ensuring 'peace of mind by protecting application investment and providing easier server management.
Read further... |
|
|
 |
| Lenovo, the first Chinese IT player, will market Bull NovaScale servers |
|
Bull and Lenovo are launching a five-year co-operation based on the following terms. Bull will provide Lenovo with NovaScale 5000 and 6000 server series based on Intel Itanium 2 processors and its FAME (Flexible Architecture for Multiple Environments) technology. Lenovo will actively market these servers throughout China, for Enterprise Database and Business Intelligence applications, Enterprise Resource Planning (ERP), Internet-based application servers and HPC.
Read further... |
|
|
 |
| OptimaNumerics delivers higher performance on IBM eServer BladeCenter JS20 |
|
OptimaNumerics, specialized in high performance technical and scientific computing software, has introduced OptimaNumerics Libraries for IBM eServer BladeCenter JS20, providing customers with the highest performance numerical software tools to enable efficient technical and scientific computations.
Read further... |
|
|
 |
| SAN health check-up from Brocade helps keep storage networks at peak performance |
|
Brocade Communications Systems a provider of Storage Area Network (SAN) infrastructure solutions, has introduced an expanded set of tools, utilities, and educational offerings designed to help its customers and partners to better design, administer, and manage SANs. Led by Brocade SAN Health, a powerful and innovative new SAN management tool that Brocade is providing free of charge to its customers and partners, these new offerings combine technical depth with practical advice on how to optimize new and existing SANs.
Read further... |
|
|
 |
| Thom Dunning to lead NCSA |
|
Thom H. Dunning Jr. will be the new director of the National Center for Supercomputing Applications (NCSA), pending the approval of the University of Illinois Board of Trustees. Dunning will officially assume his new position shortly after January 1, 2005. He also has been recommended for an endowed position as Distinguished Chair for Research Excellence in Chemistry and professor in the department of chemistry.
Read further... |
|
|
 |
| Appro launches high-performance storage systems, cluster technology and Compute On Demand Service |
|
Appro, a provider of high-performance enterprise computing systems demonstrated its cluster technology and its new Storage Systems working with the Appro HyperBlade Cluster solution at SEG in Denver, Colorado. The company also has shipped seven Appro HyperBlade Linux clusters consisting of 500 nodes/1000 AMD Opteron processors to Staag Imaging, L.P., a provider of high-quality imaging solutions for the Oil and Gas Industry, located in Houston, Texas. In addition, Appro launched its new Compute On Demand Service designed to address the increasing demand for supercomputing power in the oil and gas industry.
Read further... |
|
|
 |
| Verari Systems recognized as one of the fastest growing technology companies in North America |
|
Verari Systems has been selected to Deloitte's annual listing of the 500 fastest growing technology companies in North America based on percentage revenue growth over five years. The company ranked #184 on this year's list.
Read further... |
|
|
 |
| SGI reports first quarter financial results |
|
Silicon Graphics has announced results for its first fiscal quarter which ended September 24, 2004. Revenue for the first quarter was $175 million, in line with the preliminary results announced October 5, 2004. Gross margin from continuing operations was 35.8% compared with 40.1% in the same quarter one year ago. SGI's first-quarter operating loss from continuing operations was $27 million, compared with an operating loss of $44 million for the first quarter fiscal 2004. The first-quarter net loss was $28 million or $0.11 per share, compared with a net loss of $48 million or $0.23 per share one year ago.
Read further... |
|
|
 |
| Hinditron secures first order in India for new Cray XD1 supercomputer, from Saha Institute of Nuclear Physics |
|
Hinditron, Cray Inc.'s representative in India, has secured the first order in that country for the new Cray XD1 supercomputer product. A Cray XD1 system with 96 compute processors and more than 422 billion calculations per second (gigaflops) of peak performance will be installed in late 2004 at the Saha Institute of Nuclear Physics in Kolkata (Calcutta). Financial terms were not disclosed.
Read further... |
|
|
 |
| Bull enhances its Express5800 range of servers with four mid-range servers |
|
Bull announces four new mid-range systems within its family of Express5800 servers.
Read further... |
|
|
 |
| More energy exploration firms turn to SGI Altix to maximize output from oil and gas discoveries |
|
British Gas Exploration and Production India Ltd., (BGEPIL) and Instituto Venezolano del Petroleo SA (INTEVEP) have invested in SGI Altix servers and supercomputers to maximize production from some of the world's largest deposits of oil and gas. The companies join other energy industry leaders including BP, Marathon Oil Company, Saudi Aramco, and Total in using scalable SGI Altix systems for their E&P business. Based on industry-standard 64-bit Linux and Intel Itanium 2 processors, Altix systems are crucial in helping many of these companies gain a sharper understanding of oilfields located miles below the earth's surfac
Read further... |
|
|
 |
| French energy giant Total adds to SGI deployment to accelerate exploration decisions |
|
In a global effort to extract the greatest value from subsurface oil and gas reservoirs, the Exploration and Production Branch at French energy giant Total recently expanded its already extensive capabilities provided by servers and storage solutions from Silicon Graphics. The move is expected to allow Total to maximize its return on drilling investments made throughout the world by strategically approaching each discovery for optimal output.
Read further... |
|
|
 |
| Supermicro launches Pentium 4 EM64T single-processor server solutions |
|
Supermicro Computer has released its latest single-processor serverboards, the SUPER P8SC8/i and SUPER P8SCT, based on the Intel E7221 (Copper River) chipset. Combining EM64T, PCI-Express, and DDR2 memory performance with impeccable quality in the most cost-effective package available today, these new P4 solutions are optimized for entry-level server platforms.
Read further... |
|
|
 |
| Cray elects Stephen C. Richards to Board of Directors |
|
Cray Inc.'s Board of Directors has elected Stephen C. Richards as a member of the Board. He will serve on the Board's Audit Committee.
Read further... |
|
|
 |
| Cray and LSTC team to exploit scalability of LS-DYNA engineering software and new Cray XD1 supercomputer |
|
Cray and Livermore Software Technology Corporation (LSTC) established a collaboration to exploit the scalable designs of LSTC's LS-DYNA engineering software and Cray's new Cray XD1 supercomputer. Cray and LSTC are aggressively optimizing the Cray communications libraries to enable LS-DYNA to fully exploit the scalability and performance of the Cray XD1 system's innovative interconnect technology.
Read further... |
|
|
 |
| Cray targets CAE market with new Cray XD1 supercomputer |
|
Cray Inc. is targeting computer-aided engineering (CAE) as a primary market for its new Cray XD1 Opteron/Linux-based supercomputer. The Cray XD1 product is "purpose-built" for high performance computing (HPC) applications, including CAE problems, and features breakthrough innovations in interconnect technology, high availability and ease of management. Cray is working with Independent Software Vendors (ISVs) to exploit the Cray XD1 system's advantages on widely used CAE applications. With U.S. list pricing starting at under $100,000, the Cray XD1 system promises to substantially outperform conventional Linux clusters in the same price range.
Read further... |
|
|
 |
| Fujitsu Siemens Computers goes a siginificant step towards Information Lifecyle Management with CentricStor |
|
Under the umbrella of TRIOLE the company's strategy for an optimized IT - Fujitsu Siemens Computers has realised far reaching enhancements of its unique CentricStor Virtual Tape Appliance. Through the additional support of Service Level Agreements (SLA), CentricStor addresses comprehensive capabilities towards Information Lifecycle Management (ILM).
Read further... |
|
|
 |
| Fujitsu Siemens Computers automates Quality of Service management with Adaptive Services Control Center |
|
At its international trade fair, VISIT 2004, Fujitsu Siemens Computers has announced its Adaptive Services Control Center (ASCC), which is designed to help customers to build service-centric IT management solutions that automate the fulfilment of Service Level Agreements (SLA). As a key element of Fujitsu Siemens Computers TRIOLE strategy for an optimized IT, this product is designed to minimize the need for manual administration of diverse IT systems to maintain the highest quality of service (QoS).
Read further... |
|
|
 |
| IBM takes aim at midmarket with new power-based Express Unix and Intel-based servers |
|
IBM has announced the industry's first high-performance Express UNIX servers and a new security solution for mid-sized business clients. These Express servers, based on the IBM POWER5 microprocessor, introduce mainframe-inspired technology and performance to customers at prices and configurations that fit the budgets of even the smallest mid-size firms.
Read further... |
|
|
 |
| IBM extends Open Blade server into the mainstream datacentre with new enterprise features |
|
IBM announced the early success of opening the IBM eServer BladeCenter specification and new models packed with technology breakthroughs to further extend the system's enterprise capabilities. Forty-nine companies have received the BladeCenter open specification since Intel and IBM's joint announcement on September 2.
Read further... |
|
|
 |
| Sun unveils new set of reference architectures designed to help customers address coming explosion of data management needs |
| |