Primeur Monthly - December 2000


Advertisement

Primeur is the premier news service on on High Performance Computing and Networking (HPCN) in Europe. It is produced by an editorial team composed of professionals in publishing and HPCN. You can put the editorial team to work as well. Read about our services and advertising opportunities and find out about the friendly rates.

advertisement
Visit our sponsors

Breaking news - just a click away:


 
 

Contents December 2000 Issue

 
Atlantic
 
 SGI delivers first 256-processor Origin 3000 to Army Research Laboratory
 IBM SP used to search for satellite debris and other objects in space
 Challenge the Chinese chess supercomputer
 Eighteen Origin 3000 systems for US airforce
 SRC shocases forthcoming SRC-6 supercomputer
 
Country - DE
 
 Hitachi SR8000 workshop in Stuttgart
 Lectures on supercomputing in February 2001 in Karlsruhe
 Computer Centre of Karlsruhe University receives IBM's 425 000 euro SUR-Award
 
Country - NL
 
 New Dutch National Supercomputer inaugurated
 Simulation and visualization in the life sciences
 
Country - UK
 
 Veritas DGC installs third SX-5 supercomputer in London
 ECMWF hosts Workshop on Teracomputing for meteorology
 
Industry - Applications
 
 PeopleSoft Enterprise Performance Management Adds Analytics via Numerical Algorithms Group
 PV-WAVE Version 7.01 available
 Geophysical Fluid Dynamics Laboratory installs Origin 3000 clusters with 1,152 processors to for weather codes
 SAMPSON largest cluster based on AMD Athlon
 SUN buys more LSF licenses
 Duke University study mysteries behind the causes of heart attacks on IBM SP
 Saudi Aramco installs 92 node SP
 TRAIN-IT provides crash course on how towrite an investor winning business plan
 SGI and ANSYS collaborate on optimizing software and servers
 Digital River installs 15 Terabytes of Sun storage
 Artificial smart leg developed by Russion-American cooperation
 Prelease P-Suite - scientifc routines on top of MPI
 First call for Papers Euro-Par 2001 Manchester, UK August 2001 released
 Onyx 3000 graphics systems for U.S. Air Force F-22 pilot training devices
 2nd Workshop on Parallel and Distributed Scientific and Engineering Computing
 University of Waterloo gets 1 million CDN$ for IBM supercomputing
 BMW achieve 12 Gflop/s sustained with ESI PAM-CRASH on SGI Origin 3000
 Syrrx and MolSoft form strategic alliance
 hpcLine Application Software Status
 
Industry - HPCN industry
 
 API Networks introduces 140 Gflop/s rack cluster
 High-performance RAID subsystem from SGI
 Cray SV1ex supercomputer unveiled
 IDC's HPC Forum starts another Benchmark Initiative
 Synopsys' Physical Synthesis is used by Cray to tape out eight million-Gate, 450 Mhz, 1.8 Gflop/s Vector CPU ASIC for new SV1e
 Joint Supercomputer user meeting of Fujitsu Siemens Computers and Fujitsu
 Australian Bunyip wins Gordon Bell award
 Adaptec's high-performance RAID for Primergy servers from Fujitsu-Siemens
 Hitachi chooses TotalView to run on SR8000 supercomputers
 NEC receives several orders for its flagship SX-5 supercomputers
 Pentium 4 systems from Fujitu Siemens
 Solaris 8 trusted version available
 Cray posts loss
 hpcLine gains encouraging market acceptance - hardware and software aspects
 News from Scali
 Vectors - VPPs - are still alive
 
Industry - Linux
 
 SuSE Linux Database Server combines SuSE Linux 7.0 with IBM's DB2
 Japanese convenience store to build one of the largest Linux systems
 WebSphere on Linux
 SuSE Linux on S/390 available
 SuSE Linux 7.0 for PowerPC
 D.H. Brown rates VA Linux Systems as No. 1 in Linux strategy and solutions
 Bioinformatics company Bristol-Myers Squibb installs Linux clusters
 Star-hpc computational fluid dynamics on hpcLine
 
Industry - Media
 
 Fakespace opens European office
 New digital visualisation technology at Supercomputing 2000 Show
 AXS Technologies provider of the EyeSpy Image Server gets U.S. $3.2 million in funding from Swiss-based HPI
 IBM is shipping computer display 12-times sharper than current displays
 Third Virtual Reality International Conference
 Dell launches new workstation graphics cards
 Desh R. Urs vice president of Business Intelligence SGI
 Intergraph posts loss
 H.E.L.P.-VR
 
Industry - The Grid
 
 Entropia to donate 200 million CPU hours of computing time to US academics
  eGrid, Grid Forum unite to form Global Grid Forum, serving the world's Grid Communities
 NASA uses LSF Multicluster for production Grid computing
 The College of William and Mary installs 115 Gflop/s SUN cluster
 Parabon announces general availability of commercial Internet computing platform
 Atipa offering free online testing of Beowulf Clusters
 Industry initiative NPI aims at defining an open Distributed Resource Management standard API
 TurboLinux breaks NT passwords with EnFuzion
 DataSynapse announces premium benefits package for broadband users who join the company's distributed computing network
 NPACI releases Rocks open-source toolkit for clusters
 
Industry - TOP500
 
 Germany still Europe's number one in supercomputing
 There is a whole lot of shaking going on in the TOP500
 
Networking
 
 SC2000 Conference did house massive network connectivity Infrastructure
 QLogic launches high-end server and storage initiative
 
 

Leads December 2000 Issue

 
Atlantic
 
 SGI delivers first 256-processor Origin 3000 to Army Research Laboratory
The Army Research Laboratory (ARL) Major Shared Resource Center (MSRC) has installed a 256-processor SGI Origin 3800 system as part of the Department of Defense (DoD) High Performance Computing Modernization Program (HPCMP). The supercomputer is the largest SGI Origin 3000 series shared-memory system delivered to date.
 Full article...

 

 IBM SP used to search for satellite debris and other objects in space
The Maui High Performance Computing Center is using a 480 Gflop/s IBM SP supercomputer to identify objects in space, including old satellites, foreign spacecraft and unidentified objects.
 Full article...

 

 Challenge the Chinese chess supercomputer
Britain's Brain Games Network has agreed with the China Chess Institute exclusive rights to co-host and broadcast the World Chinese Chess (Xiangqi) Championships for the next five years. The winner of the upcoming tournament will go to challenge the world's most advanced Chinese Chess supercomputer.
 Full article...

 

 Eighteen Origin 3000 systems for US airforce
Aerojet has awarded SGI a contract to providetechnology to power mobile satellite stations for the U.S. Air Force's Space-Based Infrared System (SBIRS), the U.S.'s next-generation ballistic missile early warning system. Under the contract, SGI will provide 18 SGI Origin 3000 series servers and 27 SGI Onyx 3000 series visualization systems that will be colocated in the mobile satellite ground stations. The SGI Origin 3000 series servers will be used as the front-end of the mission for the ground stations from SBIRS satellites high above the earth. The SGI Onyx 3000 series systems will graphically display the data for U.S. military operators.
 Full article...

 

 SRC shocases forthcoming SRC-6 supercomputer
SRC Computers, the company founded by legendary computer architect Seymour R. Cray, will preview Serial Number 1 of its forthcoming SRC-6 computer at SC2000, showcasing the architecture that company officials say represents both Seymour Cray's final design and "the next big thing" in high performance computing (HPC).
 Full article...

 

 
Country - DE
 
 Hitachi SR8000 workshop in Stuttgart
HLRS in Stuttgart, organises a workshop on the use of the Hitachi SR3800 supercomputer on November 21st. The SR/800 in Stuttgart has a peak performance of 128 Gflop/s and 128 Gbyte of memory. The machine has 16 SMP-nodes, each with 8 processors. The SMP nodes can be used as a pseudo-vector unit with 8 Glop/s performance.
 Full article...

 

 Lectures on supercomputing in February 2001 in Karlsruhe
A general course on scientific supercomputing will by held in Karlsruhe, Germany, in February 2001. At the Universitaet Karlsruhe and the Forschungszentrum Karlsruhe an IBM RS/6000 SP and a Siemens/Fujitsu VPP300-5000 with totally 400 Gflop/s are installed. At LRZ Munich a Hitachi SR8000 with more than 1 Tflop/s is available for German scientists. Students will get acquainted with the usage of such supercomputers.
 Full article...

 

 Computer Centre of Karlsruhe University receives IBM's 425 000 euro SUR-Award
Professor Wilfried Juling and the Computer Centre of Karlsruhe University received IBM's SUR-award (Shared University Research) in Karlsruhe on October 4th for the extraordinary research in the field of high-performance computing. Primeur interviewed Prof. Juling, asking for the reasons and what he has done with this award. Furthermore he described the new machines and what will be done with the new computer power.
 Full article...

 

 
Country - NL
 
 New Dutch National Supercomputer inaugurated
The new Dutch National Supercomputer, a 1024 processor SGI 3000, has been inaugurated. The Netherlands National Computing Facilities Foundation, a foundation under the umbrella of the Dutch National Science foundation and responsible for the selection of the machine, also did celebrate its tenth anniversary.
 Full article...

 

 Simulation and visualization in the life sciences
Sweden's main academic computing center, Parallelldatorcentrum, organises its annual conference on December 14 and 15. "Simulation and Visualization in the Life Sciences" will explore some of the life science fields in which the use of computer technology is steadily increasing. Topics will include bioinformatics, computational biology, the medical sector, neuroscience, and radiation therapy.
 Full article...

 

 
Country - UK
 
 Veritas DGC installs third SX-5 supercomputer in London
Veritas DGC (VDGC), has installed their third NEC SX-5 Series parallel vector supercomputer. The newest VDGC installation is located at their geophysical processing facility in London. The Company recently installed SX-5 supercomputers at both their Houston and Singapore centres. VDGC currently operates 21 seismic data processing centres in major oil and gas markets world wide.
 Full article...

 

 ECMWF hosts Workshop on Teracomputing for meteorology
13-17 November 2000: Some 150 meteorologists and HPC experts from 22 countries and four continents attended the 9th workshop on the use of HPC in meteorology at the European Centre for Medium-Range Weather Forecasts, (ECMWF), Reading, UK. This excellent workshop provided a tour de force in meteorological and computing techniques by active practitioners striving to maximise the latest HPC technology to refine and improve their weather forecasting models. This article provides a flavour of both weather modelling and the state-of-the-art Tera computing needed to achieve it.
 Full article...

 

 
Industry - Applications
 
 PeopleSoft Enterprise Performance Management Adds Analytics via Numerical Algorithms Group
PeopleSoft has embedded mathematical and statistical software components from NAG's C Library into PeopleSoft 8 Enterprise Performance Management products.
 Full article...

 

 PV-WAVE Version 7.01 available
PV-WAVE is a family of software products that let engineers, scientists, researchers and business analysts understand large and complex datasets using a wide variety of visual techniques. PV-WAVE's interactive, array-based scripting language allows users to rapidly develop platform-neutral applications for manipulating, analyzing and visualizing these datasets to detect and display trends, patterns and anomalies. The software includes hundreds of sophisticated mathematical and statistical functions from the company's IMSL . C Numerical Library (CNL), as well as image processing, signal processing and general mapping functionality.
 Full article...

 

 Geophysical Fluid Dynamics Laboratory installs Origin 3000 clusters with 1,152 processors to for weather codes
Raytheon Company will SGI Origin 3000 supercomputers at the Geophysical Fluid Dynamics Laboratory (GFDL) in Princeton, N. J. The upgrade is expected to improve the US climate prediction and weather forecasting capabilities. Eight 128-processor Origin 3800 systems will form a large-scale cluster and two 64-processor Origin 3800 systems will serve as an analysis cluster. The smaller analysis cluster will also serve GFDL's data archive that is stored in three robotic tape libraries and is expected to reach 2 Petabyte in size by September 2003.
 Full article...

 

 SAMPSON largest cluster based on AMD Athlon
olphin Interconnect announced the world's largest custom supercomputer cluster based on the Advanced Micro Devices (AMD) Athlon processor. The supercomputer physically comprises four standard racks containing 132 processor units in a parallel cluster architecture interconnected with high-speed WulfKit Scalable Coherent Interface (SCI) technology supplied by Dolphin Interconnect. The system, already christened "SAMPSON" will be installed at the Bartol Research Institute at the University of Delaware and is expected to rank among the world's top 100 supercomputers once its performance is benchmarked.
 Full article...

 

 SUN buys more LSF licenses
Sun recently purchased additional LSF server licenses for its Systems Product Group, which designs a wide range of computer systems including enterprise appliances, desktop workstations, workgroup, mid-range and high-end servers, making it one of the largest users of Platform's LSF technology.
 Full article...

 

 Duke University study mysteries behind the causes of heart attacks on IBM SP
Duke University researchers will use an IBM SP supercomputer to create models of the heart that they hope will lead to uncovering causes and developing treatments for life-threatening heart conditions. Dr. John Pormann and the Electro-physiology research team at Duke University are creating accurate and complex modeling of electrical currents flowing through the heart and nerve tissue.
 Full article...

 

 Saudi Aramco installs 92 node SP
Saudi Aramco, a leading global petroleum company, has completed the installation of 92 node IBM SP supercomputer. It is based at the company's headquarters in Dhahran, Saudi Arabia.
 Full article...

 

 TRAIN-IT provides crash course on how towrite an investor winning business plan
TRAIN-IT has been restarted as an Accompanying Measure in the IST Programme, after finishing its very successful piloting phase.
 Full article...

 

 SGI and ANSYS collaborate on optimizing software and servers
ANSYS and SGI are collaborating to optimize the performance of larger, faster and more complex simulations through multiprocessor technology.
 Full article...

 

 Digital River installs 15 Terabytes of Sun storage
Digital River, a Commerce Service Provider (CSP) that builds, hosts and manages e-commerce sites for thousands of clients, has selected 15 terabytes of Sun StorEdge arrays an Sun Enterprise servers to provide exceptional performance for those clients.
 Full article...

 

 Artificial smart leg developed by Russion-American cooperation
Former Russian nuclear scientists are working together with the US Sandia lab on a project to research, design and develop an advanced 'smart leg.' Using a combination of microprocessors, hydraulic joints and electric motors, the leg will simulate a human leg on a wide range of terrain. The plan is to have the new prosthetic device available for use within 2 years.
 Full article...

 

 Prelease P-Suite - scientifc routines on top of MPI
Pedro Diaz Jimenez announced a prerelease of P-Suite: an effort to build a suite of scientific parallel programmes using the MPI standard.
 Full article...

 

 First call for Papers Euro-Par 2001 Manchester, UK August 2001 released
A first call for papers for Euro-Par 2001 Manchester, UK August 28 - 31, 2001 One topic deals with all subjects concerning automatic parallelization and technology for compilation of programs for high performance systems, including, optimizing the utilization of system resources such as power consumption, code size, and memory requirements.
 Full article...

 

 Onyx 3000 graphics systems for U.S. Air Force F-22 pilot training devices
Link Simulation and Training, a division of L-3 Communications (NYSE: LLL) in Arlington, Texas, has purchased two SGI Onyx 3000 series high-performance graphics systems to power the U.S. Air Force's F-22 pilot training devices.
 Full article...

 

 2nd Workshop on Parallel and Distributed Scientific and Engineering Computing
The 2nd Workshop on Parallel and Distributed Scientific and Engineering Computing with Applications to be held in San Francisco April 23-27, 2001 has released a call for papers.
 Full article...

 

 University of Waterloo gets 1 million CDN$ for IBM supercomputing
The University of Waterloo in Canada has been selected by IBM as a recipient of a Shared University Research (SUR) grant to help establish the UW/IBM Facility for Scientific and Deep Computing. This Facility will enable the university to pursue leading-edge research in the area of large scale parallel computing by providing researchers and students alike with access to IBM's RS/6000 SP technology.
 Full article...

 

 BMW achieve 12 Gflop/s sustained with ESI PAM-CRASH on SGI Origin 3000
An SGI and ESI team was able to achieve sustained performance of more than 12 Gflop/s using the SGI Origin 3000 series with 96 processors and 400 MHz MIPS processors. This marks the highest level of performance ever achieved in a crash simulation.
 Full article...

 

 Syrrx and MolSoft form strategic alliance
Syrrx and MolSoft, have entered into a 10-year strategic alliance to accelerate structure-guided drug discovery through the combination of MolSoft's Virtual Ligand Screening (VLS) technology with Syrrx's high-throughput structural proteomics platform.
 Full article...

 

 hpcLine Application Software Status
Application software is the most important issue on new hardware platforms. With the hpcLine parallelised engineering applications are extremely important. In the meantime more ISVs (Independent Software Vendors) ported their software on hpcLine.
 Full article...

 

 
Industry - HPCN industry
 
 API Networks introduces 140 Gflop/s rack cluster
API NetWorks introduced the CS20 at SC2000, the world's most powerful server in a 1U package and the company's most advanced platform for computer clustering. The CS20 is a rack-optimized, 1U, dual-processor Alpha server and gives the high-performance computing (HPC) and Internet community the ability to scale clusters into state-of-the-art supercomputer facilities, providing the most economic solution with the minimum computer room footprint.
 Full article...

 

 High-performance RAID subsystem from SGI
SGI launched the Total Performance 9400 (TP9400) RAID storage array, a full-fiber storage solution that offers the highest throughput RAID storage subsystem in its class, the company says.
 Full article...

 

 Cray SV1ex supercomputer unveiled
Cray unveiled the Cray SV1ex supercomputer product line at SC2000, the annual high-performance computing conference. The new line strongly enhances the performance and price/performance of the current Cray SV1 series. The air-cooled Cray SV1ex vector systems are slated for availability in the first half of 2001, at U.S. list pricing from $700,000.
 Full article...

 

 IDC's HPC Forum starts another Benchmark Initiative
Many tried, but to date all efforts failed to define benchmarks that go beyond the Linpack used in the TOP500 and have wide acceptance by users. Eurobench, Parbench, the NAS kernels, and many others. But, nevertheless, the HPC User Forum organised by IDC, representing leading supercomputer users in government, industry and academia, reported progress on a plan to create better performance tests for this most powerful class of computers. Speaking at the SC2000 supercomputing conference in Dallas, HPC User Forum officials said improved tests are needed to advance scientific research, industrial engineering and classified government work, all of which rely heavily on supercomputers. It would be too easy to predict that also this very US oriented benchmark initiative will fail, but the approach, identifying a set of "representative" benchmarks is not different from earlier attempts. Supercomputer architectures from different vendors evolving into the same direction, could, however, help this initiative.
 Full article...

 

 Synopsys' Physical Synthesis is used by Cray to tape out eight million-Gate, 450 Mhz, 1.8 Gflop/s Vector CPU ASIC for new SV1e
Synopsys announced that Cray has successfully taped out an eight million-gate, 450 MHz, vector processor ASIC using Synopsys' Physical Compiler. The design was implemented using a copper-based 0.12-micron process technology. The chip, code named Processor Vector Cache (PVC), is being used in the new Cray SV1e scalable-vector supercomputer, which was announced today at the IEEE Supercomputing 2000 conference in Dallas, Texas.
 Full article...

 

 Joint Supercomputer user meeting of Fujitsu Siemens Computers and Fujitsu
This year's fall meeting of the different Fujitsu Siemens high-end computer users took place in the Munich facilities in Neu-Perlach South from October 9th to October 11, 2000. There, the Fujitsu International Supercomputer Users (FISUM) met the 9th, the SAVE Working Group Scientific Computing the 13th and the VPP Special Interest Group the 8th time. Users from all over the world, Japan and Australia as well as Europe, came together to discuss their experiences and the requirements with Fujitsu Siemens representatives too. This special report will cover first experiences with the Intel Pentium-based hpcLine, new developments, the porting of application packages on this architecture, virtual reality on hpcLine and some remarks from vector computer centers.
 Full article...

 

 Australian Bunyip wins Gordon Bell award
The Australian National University (ANU) won the Gordon Bell Prize for best price/performance at SC2000 in Texas. The machine, Australian-designed and built, called "Bunyip" is a Beowulf style parallel supercomputer.
 Full article...

 

 Adaptec's high-performance RAID for Primergy servers from Fujitsu-Siemens
Fujitsu-Siemens Computers has selected Adaptec's new 3200S and 2100S high-performance Ultra160 SCSI RAID controllers for use in its entire line of Intel based Primergy servers.
 Full article...

 

 Hitachi chooses TotalView to run on SR8000 supercomputers
The TotalView debugger/analyzer from ETNUS was selected for use on Hitachi SR8000 high performance computing systems, three of which are ranked in the top ten on the TOP500 list: the highest ranking at Leibniz Rechenzentrum in Munich.
 Full article...

 

 NEC receives several orders for its flagship SX-5 supercomputers
NEC has received two new orders for its flagship SX-5 supercomputers from universities in Japan and installed a system at the Australian Center for Advanced Computing and Communications. The recent orders show the demand for vector supercomputers for tackling ever-complex computational problems is steadily increasing. NEC received an order for a 1.28 Tflop/s scalable parallel vector (PVP) SX-5 Series MultiNode supercomputer from Osaka University. The system, which employs 128 processors, will be one of the largest systems to be installed in Japan.
 Full article...

 

 Pentium 4 systems from Fujitu Siemens
Fujitsu Siemens Computers announced its next generation of 1.5 GHz based Intel Pentium 4 processor based systems, called SCENIC L professional PC and CELSIUS 460.
 Full article...

 

 Solaris 8 trusted version available
Sun introduced the Trusted Solaris 8 Operating Environment: Solaris 8 with added security, control and capabilities of a trusted environment.
 Full article...

 

 Cray posts loss
For the third quarter ended September 30, 2000, Cray Inc. reported revenues of $33.7 million, compared to revenues of $850,000 for the third quarter of 1999. Exclusive of imputed interest and amortization of expenses related to the acquisition of the Cray business unit assets, the company reported a net loss of $3.9 million, compared to a net loss of $13.9 million in the year ago period. Including the $2.2 million in imputed interest and amortization expenses, the net loss for the third quarter of 2000 was $6.1 million
 Full article...

 

 hpcLine gains encouraging market acceptance - hardware and software aspects
The hpcLine is installed at 18 sites in research, academic institutes and industrial research and development. Eric Schnepf gave an overview on the application areas, new hardware developments and the interconnect - system area network.
 Full article...

 

 News from Scali
Hakon Bugge from Scali gave an outlook on the actual situation and coming products as a scheduled ScaSAN architecture, MPI2 and MPICH.
 Full article...

 

 Vectors - VPPs - are still alive
The second day opened with the FISUM session, where VPP sites reported on their experiences. As the Japanese sites showed their structure and users, it was quite interesting to see, what they are doing.
 Full article...

 

 
Industry - Linux
 
 SuSE Linux Database Server combines SuSE Linux 7.0 with IBM's DB2
SuSE Linux and IBM bring DB2 Universal Database to Linux SuSE Linux Database Server provides companies with a basis for their e-business that expands with their growing demands and success.
 Full article...

 

 Japanese convenience store to build one of the largest Linux systems
Lawson, Inc., the Japanese convenience store chain, will run Linux on the IBM eServer xSeries to allow customers to download music, movies and other Web content from multimedia terminals throughout its stores. The terminals also will provide timely information collected from Internet feeds and communications satellites. Customers already can book airline reservations and order concert tickets from the existing terminals. Armonk will install more than 15,000 IBM eServer xSeries servers, running Linux, making it one of the largest IBM Linux-based installations to date.
 Full article...

 

 WebSphere on Linux
IBM's WebSphere Commerce Suite Start version 4.1 is now available on Linux. It can be used to provide customers the functionality to buy and sell products and services in a personalised manner on the open Linux platform, while extending their e-commerce applications to any server.
 Full article...

 

 SuSE Linux on S/390 available
SuSE Linux announced the general availability of SuSE Linux Enterprise Server for S/390. SuSE's Linux distribution for the mainframe allows enterprise customers to scale Linux from PC clients to host systems.
 Full article...

 

 SuSE Linux 7.0 for PowerPC
SuSE Linux announced the release of SuSE Linux 7.0 PowerPC Edition.
 Full article...

 

 D.H. Brown rates VA Linux Systems as No. 1 in Linux strategy and solutions
D.H. Brown Associates (DHBA), has rated VA as No. 1 in overall Linux strategy in DHBA's recently released multi-client study on "Linux Strategies and Solutions." In a comparison with Dell, HP, Compaq and IBM, VA Linux Systems was ranked highest in overall vendor positioning, value added and Linux community leadership.
 Full article...

 

 Bioinformatics company Bristol-Myers Squibb installs Linux clusters
SGI installed a Linux based bioinformatics computing system at Bristol-Myers Squibb Company, a health and personal care company. Bristol-Myers Squibb will use the Linux to conduct research for genomics projects, including DNA and protein sequence analysis, transcriptional profiling, and proteomics, one of the fastest growing segments of bioinformatics research.
 Full article...

 

 Star-hpc computational fluid dynamics on hpcLine
Dr. Roesler from Computational Dynamics discussed first experiences and benchmark results of Star-hpc on the Fujitsu Siemens hpcLine. One year ago, industry was not heavily interested in Linux clusters. Most of the ISVs started a Linux strategy, but today Mr. Roessler ran big benchmarks on Linux clusters for leading companies.
 Full article...

 

 
Industry - Media
 
 Fakespace opens European office
Fakespace Systems opened its first European development office, and appointed industry veteran Richard Cashmore, as Business Development Representative. The new office, located in Leicestershire, United Kingdom (UK), will enable Fakespace Systems to better support its current customers and aggressively expand its sales and marketing programs in key European markets.
 Full article...

 

 New digital visualisation technology at Supercomputing 2000 Show
High-performance projection technologies Christie Digital System did present a technology demonstration of the world's first stereoscopic 3-D digital projector, based on 3-chip DLP technology, at the Supercomputing Show in Dallas. Sponsored by Fakespace the demonstration will feature a single large-screen display in regular show-level lighting with interactive applications.
 Full article...

 

 AXS Technologies provider of the EyeSpy Image Server gets U.S. $3.2 million in funding from Swiss-based HPI
EyeSpy is the first digital imagery server to utilize parallel processing, offer multi-platform flexibility and operate in a pure HTML environment. EyeSpy also offers chacheability and is fully scalable. HPI has chosen to invest in AXS Technologies because they have developed and patented a brand new parallel processing technique that has far-reaching implications throughout business and government today and in the future.
 Full article...

 

 IBM is shipping computer display 12-times sharper than current displays
The U.S. Department of Energy's Lawrence Livermore National Laboratory in California is the first customer to use this breakthrough display. The Livermore Lab will use the displays to study the operation and aging of nuclear weapons using 3-D model simulations that are crunched by the world's fastest supercomputer, the ASCI White machine IBM shipped to the Lab in July. IBM plans to ship the displays to other customers in 2001 and license the patented technologies to other manufacturers. With 200 pixels per inch and more than 9 million pixels in total on its 22-inch screen, the new display is as clear as an original photograph and 4.5-times sharper than top-of-the-line high-definition television screens.
 Full article...

 

 Third Virtual Reality International Conference
The Third Virtual Reality International Conference will be held Laval, France 17 - 18th May 2001. Call for papers is now open.
 Full article...

 

 Dell launches new workstation graphics cards
Dell is one of the first workstation vendors to offer the Fire GL2 graphics adapter from FGL Graphics, a division of S3 Inc. The 64 MB Fire GL2 offers high-end performance and supports both analog and digital outputs. Dell today also introduced "Dell Graphics Plus" for workstation customers who need specialized graphics products.
 Full article...

 

 Desh R. Urs vice president of Business Intelligence SGI
Desh R. Urs has been appointed vice president of Business Intelligence, SGI. He will report to Kenneth L. Coleman, executive vice president of Global Sales, Service and Marketing, SGI.
 Full article...

 

 Intergraph posts loss
For the last quarter, Intergraph incurred a net loss of $5.3 million,, on revenues of $159 million. The 15% decline in revenue from the second quarter level and the net loss were largely attributable to the Company's exit from hardware, which was completed this quarter with the sale of the Intense3D graphics card business to 3Dlabs Inc., and the sale of the high-end workstation business to Silicon Graphics Inc.
 Full article...

 

 H.E.L.P.-VR
High End Low Price Virtual Reality is an affordable high-end virtual reality system. Usual VR labs cost about US$ 10 to 15 million. Thus Siemens ZT decided to port VR on PC platforms.
 Full article...

 

 
Industry - The Grid
 
 Entropia to donate 200 million CPU hours of computing time to US academics
At the Supercomputing2000 conference this week in Dallas, Texas, Entropia CTO Andrew Chien announced this morning that his company has signed agreements with both the National Computational Science Alliance ("Alliance") and the National Partnership for Advanced Computational Infrastructure (NPACI). As part of the agreements, Entropia, an Internet and enterprise computing services company, will donate an unprecedented 200 million CPU hours to the PACI program, creating the largest computing platform ever offered to its national academic user community. The Alliance and NPACI are both part of the National Science Foundation's Partnerships for Advanced Computational Infrastructure Program.
 Full article...

 

  eGrid, Grid Forum unite to form Global Grid Forum, serving the world's Grid Communities
eGrid - the European Grid Forum, has combined with Grid Forum, a primarily U.S.-based organisation of individuals developing, deploying, or using grid technologies, and leaders from Asia Pacific to create Global Grid Forum (GGF)
 Full article...

 

 NASA uses LSF Multicluster for production Grid computing
NASA has acquired Platform's LSF MultiCluster software to manage the combined scientific and engineering computing workloads at the Glenn Research Centre in Cleveland, OH and the Langley Research Centre in Hampton, VA. LSF MultiCluster extends the reach of Platform's market leading Load Sharing Facility (LSF) distributed resource management (DRM) capabilities by coordinating the scheduling of the computing resources between the NASA centres in a fail safe, lights-out, peer-to-peer operational relationship, without requiring the addition of new hardware and without having to learn or implement any new job submission language or queuing system syntax.
 Full article...

 

 The College of William and Mary installs 115 Gflop/s SUN cluster
The College of William and Mary installed one of the largest academic computing clusters world wide. The "SciClone" HPC cluster is actually a grid of four sub-clusters that consists of 160 processors and offers a theoretical peak performance of 115 Gflop/s. The grid-like environment will allow faculty and students to research the issues facing users of larger distributed systems utilizing the Internet.
 Full article...

 

 Parabon announces general availability of commercial Internet computing platform
Parabon Computation announced general availability of its commercial distributed computing platform, Frontier. Any organization can now benefit from distributed computing via the Internet, the company claims. Shipment of Frontier will begin on November 15, 2000.
 Full article...

 

 Atipa offering free online testing of Beowulf Clusters
Linux provider Atipa Corporation is now offering prospective customers free on-line testing of its new Ascendance Beowulf clusters.
 Full article...

 

 Industry initiative NPI aims at defining an open Distributed Resource Management standard API
One of the foundations of the Grid is to connect resources from all kinds of providers, running all kinds of software. Most Grid initiatives use Globus services, or for instance in Germany Unicore, to provide a connectivity layer. With NPI - the New Productivity Initiative - this could change. Eleven companies have taken the initiative to define and open standard API for distributed resource management. When it is a success, it can accelerate the take-up of Grid services in commercial settings.
 Full article...

 

 TurboLinux breaks NT passwords with EnFuzion
Turbolinux demonstrated the power of its EnFuzion software by breaking Microsoft NT passwords at product demonstrations during Linux Business Expo at Comdex in Las Vegas last week.
 Full article...

 

 DataSynapse announces premium benefits package for broadband users who join the company's distributed computing network
US home broadband users who visit the DataSynapse Web site and sign in will be able to profit from the time their computers sit idle by joining the company's premium distributed computing platform. DataSynapse says it currently has five beta clients in the financial services sector, an industry with an ever present need for speed.
 Full article...

 

 NPACI releases Rocks open-source toolkit for clusters
The USA based National Partnership for Advanced Computational Infrastructure (NPACI) has released version 1.0 of its NPACI Rocks software, a set of open-source enhancements for istalling and managing large Linux-based clusters, called Rocks.
 Full article...

 

 
Industry - TOP500
 
 Germany still Europe's number one in supercomputing
The most powerful supercomputer in Europe, is located at LRZ in Munich. In number of systems, Germany leads Europe with 55 systems in the TOP500 of the most powerful systems in the world, followed by the UK (34) and France (29). As usual, Europeans by both Japanese and US machines at the same distribution as world wide: 10% Japanese and 90% USA made supercomputers. In the USA almost 100% of the machines is mad-in-the-USA. while in Japan it is 50% Japanese and 50% US manufactured systems. Again, Luxembourg has the largest number of supercomputers per person: one for each 150.000 inhabitants.
 Full article...

 

 There is a whole lot of shaking going on in the TOP500
A new number one, about half of the machines are new entries. IBM almost dominating the list, Europe is growing USA fall below 50%. It sure has a lot of news in it, the most recent TOP500 list of the world's most powerful supercomputers. At last, a new number one in this November 2000 version of the list, although it is specifically build for the ASCI programme, the IBM ASCI White system with 4.9 Tflop/s of Linpack performance installed at the Lawrence Livermore National Laboratory (LLNL) in the USA. Numbers 2,3 and for are also ASCI machines. The Intel ASCI Red at Sandia, the former number one; the IBM ASCI Blue Pacific at LLNL, the SGI ASCI Blue Mountain at Los Alamos National Laboratory. The performance of these for ASCI machines is the same as that of all the Japanese TOP500 supercomputer power combined, and half of Europe's combined performance.
 Full article...

 

 
Networking
 
 SC2000 Conference did house massive network connectivity Infrastructure
Many people who attend conferences say they go for the networking. But the 5,000 computing and networking experts at the SC2000 conference did have access to one of largest, most complex communications networks in the USA offering a combined capacity more than 196,000 times faster than a typical residential Internet connection and 200 times as fast as the connections used by many universities.
 Full article...

 

 QLogic launches high-end server and storage initiative
QLogic announced the general availability of its host bus adapter (HBA) High Availability Package, a software module that provides complete data path redundancy in clusters and storage area networks (SANs) incorporating servers running Windows NT. The QLogic HBA High Availability Package also complements storage subsystem failover software by eliminating performance degradation associated.
 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.

© 2000, Genias Benelux

Go to top