|
|
||
| 09 September 2002 |
EuroFlash no. 522
|
|
|
Advertisement
Primeur-EnterTheGrid is the premier news service on HPCN, supercomputing and The Grid in Europe. Primeur Weekly delivers the news each week in your e-mail box. Check out http://EnterTheGrid.com for all information on The Grid. Check out the Primeur HPCN web site for the Calendar, the Analysis section with background on the TOP500, the Monthly en Live! special issues, information on HPCN centres and industry.
Advertisement
|
||
Advertisement
While the first 3G networks have still to be rolled-out in Europe after the costly acquisition of UMTS licenses in most of the countries, preparations are already underway for the next generation after that. Dubbed 4G, it is envisioned to be an integrated IP based environment for all telecommunication functions, including speech, broadcast media and the Internet. 4G would use both wireless and wired infrastructure. In the Netherlands, an initiative has been started to advance knowledge in the 4G area. Research into 4G is done within two projects: "Research Programme for Telecommunications" and "Research Programme for Telecommunication applications". The first focuses on technology, the second on services.
Scali plans for making the ScaMPI MPI library available for the InfiniBand interconnect technology. The implementation will use an intermediate layer conforming to the DAT standard for enabling plug-and-play operation across different interconnects for high performance clustering. The DAT implementation will also enable ScaMPI to run over standard TCP/IP based socket layers on top of legacy interconnect
In a successful experiment that could help to benefit the way surgery is performed, surgeons have begun viewing and manipulating 3D medical images of the very patients on whom they are operating while the operation is in progress. Early results indicate the potential for improving success rates on such procedures as the removal of cancerous tumours.
WulfKit, the high-performance server clustering system developed by Dolphin Interconnect Solutions, now provides Message Passing Interface (MPI) communication libraries for server clusters based on the Intel Itanium 2 processor. Developed by Dolphin partner Scali AS of Oslo, Norway, the new MPI middleware supports data transfer rates in excess of 320 Mbytes/sec with less than 4 microseconds latency between user processes in different cluster nodes. The middleware is available immediately.
The First Workshop on Application Specific Processors (WASP 2002) will be held November 19th, 2002 in conjunction with MICRO-35 in Istanbul, Turkey. The deadline for paper submission is September 11th, 2002 with one week extension automatically.
The US National Center for Supercomputing Applications (NCSA) announced today that it will demonstrate the InfiniBand high-performance computing (HPC) interconnect at the Intel Developers Forum (IDF). The IDF starts today and runs through Thursday, Sept. 12.
The first European "Nanotechnology Meets Business" event will be held April 8-9, 2003. It is organised by the Institute of Nanotechnology and aims to promote the commercial potential of nanotechnology across Europe.
TurboGenomics, the life sciences industry expert in high-performance computing solutions, announced immediate availability of TurboBench 2.0, a revolutionary application software platform that delivers previously unattainable levels of speed and automation for computational work flows common in drug discovery and throughout the industry. TurboBench 2.0 enables users to exploit all the computing power available on heterogeneous mixtures of multiprocessor servers, clusters, networked desktops, and computational grids without rewriting their current applications. The parallel and distributed computing technology that underlies TurboBench 2.0 makes it possible for users to complete jobs in just a few minutes instead of the hours or days required previously.
Force10 Networks has launched the Force10 E-Series, a scalable and high performing Ethernet switch/router. The E-Series provides unmatched scalability, line-rate performance, and full L2 switching and L3 routing functionality for high-performance Ethernet applications. The E-Series has been selected by the National Center for Supercomputing Applications (NCSA) and the San Diego Supercomputer Center (SDSC) - both part of the National Science Foundation's TeraGrid Project - Lawrence Berkeley National Laboratory, and the London Internet Exchange (LINX).
Scientists from the National Center for Atmospheric Research (NCAR) have just completed a 1000-year run of a powerful new climate system model on a supercomputer at the U.S. Department of Energy's National Energy Research Scientific Computing Center (NERSC) at Lawrence Berkeley National Laboratory. Accurately predicting global climate change demands complex and comprehensive computer simulation codes, the fastest supercomputers available and the ability to run those simulations long enough to model century after century of the global climate.
Sistina Software is supporting a new high-performance clustering implementation unveiled at the University at Buffalo, the State University of New York (SUNY), one of the world's leading academic high-performance computing sites. The high performance computing cluster (HPCC) will be used in the Buffalo Center of Excellence in Bioinformatics at the University at Buffalo for human genome research, bio-informatics, protein structure prediction and large-scale computer simulations. In this cluster, Sistina's Global File System is providing enhanced data sharing functionality, managing data traffic amongst more than 2000 nodes.
Cray has raised $10 million from institutional investors in the form of common stock and warrants. These securities were sold under the company's shelf-registration statement. The company issued a total of 2,941,176 shares of Common Stock at $3.40 per share and four-year warrants covering 294,117 shares of Common Stock with an exercise price of $4.50 per share.
Avaki Corporation has signed a worldwide systems integration agreement with HP. Under the terms of the agreement, HP Services will resell the recently announced AVAKI 2.5 grid software to its prospects and customers around the globe. The AVAKI grid software will be available with HP's family of high-performance AlphaServer systems running Tru64 UNIX and industry-standard ProLiant servers running the Linux and Windows operating systems.
Platform Computing Inc. has launched Platform HPC for IBM, a new Grid-enabled job management solution for IBM high-performance computing (HPC) clusters. Platform HPC for IBM is designed specifically for midrange to high-end distributed HPC clusters running on IBM eServer xSeries and pSeries systems. This out-of-the box offering maximises the performance and capability of parallel workloads across AIX and Linux servers, enabling government, research, life sciences and manufacturing users complete compute-intensive tasks faster and more reliably at reduced costs.
Fluent has made available Airpak/RSF, a new service that significantly reduces the entry cost for using engineering simulation software in the design of buildings and other facilities. This new subscription-based service delivers Airpak airflow modelling software through a secure internet portal. The user pays for simulation time, rather than having to purchase additional hardware and software.
Sun Microsystems announced the successful deployment of Java Card technology and Sun network solutions by the Bureau of National Health Insurance of Taiwan (BNHI). The BNHI has started to roll out 22 million Java Card technology-powered Integrated Circuit (IC) health cards to Taiwan citizens in July, replacing its original paper-based system. This new smart card will bring substantive time and cost savings to the BNHI.
TurboGenomics Inc. and IBM have signed an agreement that paves the way for new solutions that will provide improvements in the performance of life sciences computing clusters and grids. The collaboration brings together, for the first time, IBM infrastructure software for managing diverse life sciences data with high-performance TurboGenomics tools for distributing application workloads and managing work flows across large computing clusters and grids.
Platform and HP Services will provide consulting and integration services to deliver Linux, Windows, HP-UX, and Tru64 UNIX Grid computing and clustering solutions to joint customers around the world. Under the agreement, Platform's full portfolio of software solutions, including the newly released Platform Clusterware, will be available across HP's entire server line.
At the Fall 2002 Intel Developers' Forum, SGI announced it has attained linear scalability on a 64-processor Itanium 2-based system and world-record results among microprocessor-based systems on the STREAM Triad benchmark, which tests memory bandwidth performance. Demonstrating linear scalability from 2 to 64 processors, the Itanium 2-based prototype system from SGI exceeded 120 GB per second on a single system image.
IBM Taiwan has launched a life sciences centre at the Nankang software park in Taipei, the first IBM research and development facility of its kind in the Asia Pacific region. The centre will offer information technology solutions and services to help accelerate life sciences research and development, according to IBM Taiwan country general manager Jason Hsu.
Trimension Systems, a division of SEOS, and SGI have just completed installation of an SGI Reality Center facility in the Executive Briefing Center at the Houston, Texas, headquarters of Landmark Graphics Corporation. The new immersive visualisation system, powered by a 16-processor SGI Onyx 3400 graphics supercomputer with three InfiniteReality3 subsystems, is the first-ever front-projected installation using Digital Light Processing (DLP) projectors on a curved screen with active stereo, not only in the energy industry, but at any commercial site internationally.
Dell announced the Dell Centers for Research Excellence, a programme recognising the use of Dell high performance computing clusters (HPCC) for groundbreaking commercial research and projects that ultimately can greatly benefit society. Michael Dell presented the first such award to the University at Buffalo, the State University of New York, for its innovative research that could eventually help speed drugs to market to combat cancer, Alzheimer's, AIDS and a variety of other diseases.
Platform debuted the beta version of a new Enterprise Grid solution called Platform Symphony for use by financial institutions to process compute and time-sensitive applications, such as trading, pricing, risk analysis, profit and loss reporting and trade settlement, in real time across an Enterprise Grid computing infrastructure. Platform Symphony has been adopted by a major investment bank, JP Morgan, as the cornerstone of its globally distributed technology infrastructure.
The 36th Annual Simulation Symposium will be organised March 30 - April 2, 2003 in Orlando, Florida, USA. The event is sponsored by the Society for Modeling and Simulation International in co-operation with the IEEE Computer Society's Association for Computing Machinery (ACM). Deadline for paper submission is October 15th, 2002.
Force10 Networks Inc.'s E1200, which was introduced as part of the Force10 E-Series, has been tested by the independent laboratory The Tolly Group in Manasquan, New Jersey. The tests confirmed that the E1200 delivers non-blocking, line-rate forwarding across all 28 ports of 10G Ethernet with extended access control lists (ACLs) applied when tested with large frame sizes greater than 512 bytes. Tests that hammered the E1200 with smaller, more processing-intensive frame sizes yielded zero-loss throughput ranging from 98% to 99%.
Xilinx Inc. and Ignis Optics announced full hardware interoperability of a 2.5 Gbps serial optical interface between the Ignis IGP-2000 Series fiber optic transceivers and the Xilinx Virtex-II Pro FPGA with Rocket I/O multi-gigabit transceivers. The proven interoperability will be demonstrated at the National Fiber Optic Engineers Conference (NFOEC) on September 15-19, 2002 in Dallas, Texas.
Xilinx and Paxonet Communications, a Xilinx AllianceCORE member and leading telecommunications IP and Silicon provider, have made available Paxonet's 10 Gigabit Physical Coding Sublayer (PCS) and Media Access Controller (MAC) cores for use in Xilinx Virtex-II and Virtex-II Pro FPGAs.
Metis Technologies specializing in Web Services grid computing, has signed a partnership with Data Junction Corporation addressing new Web services integration issues. This partnership will enable applications to be built with access to many different sources with little or no programming. With Data Junction, the Metis Collaboration Platform (MCP 5) assists enterprises in building applications quickly and easily and provides access to any data type in real time, resulting in lower development cost and the capability to dynamically deploy applications.
Primeur Weekly is published per e-mail. Check out the subscription information for more details how to subscribe. You can find the back issues on the Primeur web site. The EuroFlash! and USflash! are published together with ESIS - European Supercomputing Information Service.
© 2002, Genias Benelux