Primeur Weekly

02 July 2001

EuroFlash no. 464
USFlash no. 584


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.

 
 
EuroFlash
 
 Mercury Race for Alenia Radar systems
 World's fastest Mac-Based cluster in Portugal
 IBM delivers fastest unclassified 3.8 Tflop/s supercomputer
 Mercury ships multicomputer to UK Defens organisation
 Compaq and Intel collaboration on Itanium
 
Focus
 
 KEPLER, a selfmade Cluster in Tuebingen
 CLiC - Chemnitz Linux Cluster
 High Performance Scientific Computing Support by the BMBF
 
Special
 
 Terraspring launches data center-scale computing Grid architecture; Computing Grid
 EDA market ready for Sun Technical Compute Farm with Grid Engine
 GridEngine downloaded to over thousand sites in one year
 Grid company Terraspring appoints CEO
 Platform Computing launches P2P software for desktop distributed computing
 
USFlash
 
 Microsoft and Cornell Bring Supercomputing to the Financial Services Industry at a Fraction of the Cost of Proprietary Systems
 Auspex file server for Arlington compute farm
 TotalView 5 released adds thread debug support
 
EuroFlash
 
 Mercury Race for Alenia Radar systems
Marconi Systems will use Mercury s RACE++ PowerStream MP-510 systems for the European Multifunction Phased Array Radar (EMPAR). EMPAR will be deployed on the next generation of air defense frigates for the French and Italian navies. Orders received, valued at $7.4 million, are for development and production of initial systems. Future orders are anticipated.
 Full article...

 

 World's fastest Mac-Based cluster in Portugal
The world's fastest Mac-based cluster for plasma particle research is installed in Europe: epp. Researchers at Grupo de Lasers e Plasmas (GoLP) say the epp cluster is the first milestone of the GoLP simulation program in Extreme Plasma Physics. GoLP is located in the campus of Instituto Superior Tecnico (IST), Lisbon . The cluster is used for numerical simulation of plasmas, novel plasma particle acceleration schemes using ultra intense lasers, and relativistic shocks in astrophysics.
 Full article...

 

 IBM delivers fastest unclassified 3.8 Tflop/s supercomputer
IBM has delivered the world's most powerful unclassified supercomputer, which will conduct the basic scientific research that may lead to breakthroughs in fuel-efficient automobiles. The announcement came as IBM captured the number one ranking on an independent list of the world's fastest computers, issued at the Supercomputing 2001 Conference in Heidelberg, Germany.
 Full article...

 

 Mercury ships multicomputer to UK Defens organisation
Mercury Computer Systems has shipped high-performance RACE++ systems to the Defence Evaluation and Research Agency (DERA) in the United Kingdom. DERA will use Mercury's multicomputer systems, which incorporate PowerP G4processors, to perform advanced research for airborne electronic warfare.
 Full article...

 

 Compaq and Intel collaboration on Itanium
Compaq and Intel announced a multi-year agreement for next-generation enterprise servers based on the Intel Itanium processor family. Compaq will transfer key enterprise processor technology to Intel and consolidate its entire 64-bit
 Full article...

 

 
Focus
 
 KEPLER, a selfmade Cluster in Tuebingen
Harry Yserentant, University Tuebingen, presented some numerical applications that run on the Pentium Cluster KEPLER as well as its architecture. The users and the University has beneath PCs small compute servers, 4 processors and 8 GB memory, and can access the supercomputers in Stuttgart and Karlsruhe. Thus there is a gap which now is filled by a big PC cluster. It is equipped with dual Pentium III, 650 MHz, and 1 GB memory per node. They use BX motherboards and have 32 bit/33 MHz PCI bus. The nodes are connected with two networks. Ethernet, 100 Mbit, is used to start nodes and processors, while Myrinet is for the direct exchange of messages of the nodes.
 Full article...

 

 CLiC - Chemnitz Linux Cluster
CLiC is a large Beowulf-style cluster, which was installed in autumn 2000 at the Chemnitz University of Technology. It is built from 528 off the shelf commodity PC nodes running Linux, plus some server and management nodes. Professor Uwe Huebner gave an overview of the current system. The University was supported by the Chemnitz based company Megware computer, which was found in the exhibition of Supercomputer 2001. The system consists of 528 Pentium III, 800 MHz, with 512 MB RAM and 30 GB hard disk as computing nodes. This sums up to 264 GB memory and 15 TByte disk space.
 Full article...

 

 High Performance Scientific Computing Support by the BMBF
The well known Ministerialrat Bernd Reuse, Federal Ministry of Education and Research (BMBF), gave an overview of the actual activities of BMBF in this field. He mentioned the National Coordination Committee for the Procurement of HPC for the Scientific Council which started its operation 31. May 2001. A detailed description will be given in an other article in Primeur. Reuse mentioned that HPC installations have to fast, to save time, as in about 5.5 years the number 500 performance of the top500 will be reached by a PC.
 Full article...

 

 
Special
 
 Terraspring launches data center-scale computing Grid architecture; Computing Grid
Terraspring announced both its launch and the completion of a new round of funding totalling more than $28 million. Accel Partners, EMC Corporation, Hewlett-Packard Company, and Mohr Davidow Ventures participated in the round. Terraspring has raised equity of $54.5 million to date. Terraspring's Grid Computing Architecture allows for flexible growth and rapid re-purposing of resources resulting in control of massive computing infrastructures.
 Full article...

 

 EDA market ready for Sun Technical Compute Farm with Grid Engine
A growing number of companies looking to improve their production and speed their time to market in the electronic design automation space are looking at the Sun Technical Compute Farm (Sun TCF) solution for their compute-intensive EDA needs. Roughly 80 percent of Sun TCF sales have been logged in the EDA market segment since the hardware and software solution was announced at DAC last year.
 Full article...

 

 GridEngine downloaded to over thousand sites in one year
Sun Grid Engine software has been embraced by many EDA companies as their distributed resource management (DRM) tool to improve their design cycles and time to market. Sun also used the DAC event to announce new product support programs as well as its latest version of Sun Grid Engine 5.2.3 software, available for free download.
 Full article...

 

 Grid company Terraspring appoints CEO
Terraspring, a grid computing software company, appointed Ian Bonner to the position of president and chief executive officer. Bonner, a 22-year veteran of the computing industry and former IBM vice president, is responsible for leading the company to deliver and implement software and technologies in the IT market space.
 Full article...

 

 Platform Computing launches P2P software for desktop distributed computing
Platform Computing launched software that allows enterprises to harness the unused processing power of their desktop computers. LSF ActiveCluster extends Platform's core Load Sharing Facility (LSF) product line.
 Full article...

 

 
USFlash
 
 Microsoft and Cornell Bring Supercomputing to the Financial Services Industry at a Fraction of the Cost of Proprietary Systems
The Cornell Theory Center (CTC) and Microsoft Corporation launched an expanded services for the finance industry through CTC's new role as a Windows Cluster Solutions Provider. Focused at CTC-Manhattan at 55 Broad St., these services will help the finance industry to take advantage of Window-based enterprise scale computing solutions, including the option to scale up new applications on servers with up to 32 processors and mainframe-like reliability and to scale out networked applications through component clustering services. CTC-Manhattan will offer consulting, software development, education and training, and special events for finance industry professionals and also will serve as a showcase and testbed for Windows High-Performance Computing clusters.
 Full article...

 

 Auspex file server for Arlington compute farm
The University of Texas at Arlington has purchased and installed an Auspex NetServer to store and serve files for 28 Compaq nodes in a new supercomputing farm utilized by the college's research community.
 Full article...

 

 TotalView 5 released adds thread debug support
Etnus announced a major new release of its TotalView debugger, Etnus TotalView 5, with new capabilities for threaded-code debugging, making it the only debugger in the market able to efficiently assist in the debugging of today's complex, business-critical application software.
 Full article...

 

 

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.

© 2001, Genias Benelux

Go to top