|
|
||
| 16 December 2002 |
EuroFlash no. 536
|
|
|
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
Each year, the Supercomputing event appears to go from strength to strength and SC2002 in Baltimore this November was no exception. Regrettably, I was unable to attend this year, but with over 7,000 participants and over 200 exhibitors, I was redundant to requirement. From reports I received, the HPC community was as usual buzzing with excitement not only about new product announcements from vendors, but more importantly about the many special recognition honours presented at this event. As HPC regulars know, these also include the prestigious Gordon Bell Awards. (Chris Lazou)
The seventh annual meeting of ScicomP, the IBM Scientific System User Group, will be held March 4-7, 2003 at the Max-Planck-Institute for biophysical chemistry in Göttingen, Germany. The meeting is hosted by the Gesellschaft für wissenschaftliche Datenverarbeitung Göttingen. The early registration deadline is February 7, 2003. Abstracts for user and vendor presentations are now being solicited.
The UK e-Science Institute unveiled its new Grid training room. The Swanston Training Room as it is called, will be used for providing workshops on for instance, "Advanced Java for Web Services" and a Globus 3 tutorial that will be organised early in the New Year.
The 18th International Teletraffic Congress (ITC) will be organised from 31 August to 5 September 2003 at the Haus am Köllnischen Park in Berlin, Germany. The theme of the Congress is "Providing QoS in Heterogeneous Environments". Deadline for paper submission is December 31, 2002.
ESI Group's first European Vibro-Acoustic User Conference will take place January 29-30, 2003 at the Bremberg Centrum Hotel in Leuven, Belgium. This conference represents a unique opportunity in Europe for technical exchange between experts of vibro-acoustic simulation.
At the Unicore symposium in Bonn, Mati Karelson from the Centre of Strategic Competence (CSC) of the University of Tartu, Estonia, explained the OpenMolGrid project goals. OpenMolGrid is one of the European Commission funded Grid projects. It is the first large scale European project with a project co-ordinator from Estonia. OpenMolGrid will make the OpenMol molecular design package running on the Grid, by creating a seamless interface to the Unicore Grid software. Then it will use the European-wide Grid platform EuroGrid to generate molecular structures with given chemical properties or biological activities.
"The Grid" as such does not exist. There are many small Grids, which sometimes can co-operate, but most of them are not even aware of each other. Hence "The Grid" can be considered as a worldwide conglomerate of small fractions that have dynamics of their own. Eventually, many of them will be connected to each other. One of the tools that are needed for this to happen is a universal brokerage mechanism. A Grid broker can take a request from a user to run, for instance, a computer job, get quotes from Grids and show the user the possibilities. At the Unicore Symposium in Bonn Germany, John Brooke, from the University of Manchester, shared his ideas on the fractal nature of the Grid, the need for brokerage, and the resource broker system that is being developed at the University of Manchester by Jon MacLaren and which is used in, for instance, EuroGrid.
Twice a year the Fujitsu Siemens Computers (FSC) users group Scientific Computing meets at different users locations. On December 5 and 6 the participants went to Castle Birlinghofen, St. Augustin. The former GMD (German Mathematics Research Centre) now belongs to the Fraunhofer Society. The Fraunhofer Institute for Algorithms and Scientific Computing (SCAI) hosted the event. About 50 participants in this busy pre-Christmas time followed the themes: roadmaps of hpcLine, Scali, Partec, AMD and Intel, site reports, cluster cooling, and different batch systems for clusters. In this special several of the topics will be discussed. (Uwe Harms)
Eric Schnepf, Fujitsu Siemens Computers (FSC), described the history and the future of the Linux-based IA-32 Intel and AMD cluster. End of December, FSC has delivered orders of 100 clusters with about 3000 processors. Interesting is the distribution in application areas and users. About 70% of the systems and processors are running in industry, the other 30% are installed in academia and research. Further on, Eric Schnepf discussed the hpcLine roadmap.
Fujitsu Siemens Computers partners with both companies in the field of System Area Networks, they presented new strategies. Scali for example will broaden its base for ScaMPI. Partec will start its ParaStation 4 in the first quarter next year.
In big clusters with lots of nodes, the air cooling can become a problem. As one of the DataGrid Centres, the Research Centre Karlsruhe (RCK) will run into these difficulties. Manfred Alef, RCK, presented a water cooling solution. Robert Gattereder, m + w Zander, discussed an industrial solution.
Again AMD and Intel entered the ring to discuss their approaches in new processor technology.
Dr. Linden from the well-known HPC Institute SCAI presented their activities.
As batch processing is essential, the organisers presented talks which covered the spectrum.
Fujitsu Siemens Computers today announced that its successful Linux Cluster series hpcLine can be equipped with 1U dual Xeon 2.8 GHz processor nodes, which use the Intel E7501 chipset with a 533 MHz front-side bus.
Linux NetworX is partnering with HP to expand each company's Linux cluster supercomputing solution offering. As part of the agreement, HP will now offer Linux NetworX ClusterWorX software as a cluster supercomputing management tool and Linux NetworX will offer HP Itanium 2-based systems running Linux to customers wanting 64-bit capability for meeting their high-performance technical computing needs. Linux NetworX will continue to offer its turnkey Evolocity Linux cluster solutions.
Simplifying cluster management, Platform Computing Inc. will offer a GBP 75-CPU, entry-level version of Platform Clusterware for small-scale Linux compute clusters. Platform Clusterware (On-line) can be deployed in a matter of minutes on smaller clusters of up to 64 CPUs running Linux on 32-bit hardware. With Platform Clusterware (On-line), small workgroups, start-up businesses or departments can roll out low-cost industry standards-based clusters faster, reduce operational costs, and improve computing productivity by managing the "cluster as server".
Based on the data warehouse industry standard TPC-H benchmark, IBM set the worldwide record, delivering a 10-terabyte business intelligence performance benchmark.
The 17th International Conference on Supercomputing (ICS 2003) will be held June 23-26, 2003 in San Francisco Bay Area, USA and is sponsored by ACM/SIGARCH. The paper submission deadline is February 10, 2003.
Delta Search Labs and Proteome Systems today announced a Memorandum of Understanding between the two companies to explore commercial opportunities at the intersection of computational engineering and proteomics.
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