| Contents October 2006 |
|
|
 |
| |
| Industry
-
HPCN industry |
|
|
| IBM to build world's first Cell Broadband Engine based supercomputer |
|
The U.S. Department of Energy's National Nuclear Security Administration (NNSA) has selected IBM to design and build the world's first supercomputer based on the Cell Broadband Engine (Cell B.E.) processor aiming to produce a machine capable of a sustained speed of up to 1 Pflop/s.
Read further... |
|
|
|
| Mercury Computer Systems announces the highest performing conduction-cooled COTS computer system |
|
Mercury Computer Systems Inc. has introduced the breakthrough PowerStream 6600 multicomputer, with 716 PowerPC GFLOPS of compute performance in a conduction-cooled enclosure, to enable powerful sensor computing on the move.
Read further... |
|
|
|
| ClearSpeed breaks Gflop/s per Watt performance barrier for supercomputing |
|
ClearSpeed Technology, specialized in double precision coprocessor acceleration technology, has issued Linpack benchmark results that set new standards for energy efficient computation for high performance computing (HPC) clusters. ClearSpeed Advance accelerator boards rated at only 25 Watts power consumption per board added 28.5 Gflop/s each to a cluster of Hewlett Packard Proliant DL380 G5 servers running the high performance Linpack benchmark.
Read further... |
|
|
|
| McGuinty Government supporting research Supercomputers |
|
The Candadian Ministry of Research and Innovation is investing $10.9 million in the University of Western Ontario's Shared Hierarchical Academic Research Computing Network (SHARCNET) to support 1200 researchers across the province,
Read further... |
|
|
|
| Rackable Systems to acquire Terrascale Technologies |
|
Rackable has signed a definitive agreement to acquire Terrascale Technologies Inc., a provider of a clustered file system solution enabling high performance I/O connectivity between servers and commodity-based storage subsystems.
Read further... |
|
|
|
| NCSA and SDSC collaborate on benchmarking project |
|
Staffers at the National Center for Supercomputing Applications (NCSA) and the San Diego Supercomputer Center (SDSC) have collaborated through the Cyberinfrastructure Partnership to test applications and kernels on the production compute systems at the two centres. This extensive benchmarking project was intended to serve as a reference for users when assessing the relative performance of new systems or deciding where to run a particular application in order to get optimal performance.
Read further... |
|
|
|
| NSF funds LSU $1 million for PetaShare development |
|
The National Science Foundation (NSF) recently funded Louisiana State University (LSU) $1 million for the development of PetaShare, which is seen as "a system that might become an important testbed for future Grids, and a leading site in next-generation petascale research". The unbounded increase in the size of data generated by scientific applications necessitates collaboration and sharing among the nation's education and research institutions.
Read further... |
|
|
|
| IBM opens Latin America's first specialized, high performance software and services lab in Brazil |
|
IBM has opened a multi-million dollar, high performance software and services laboratory in Sao Paulo, Brazil. The first of its kind on the continent, the High Performance On Demand Solutions Lab (HiPODS) is designed to support the growth of business across the emerging markets of Latin America by finding answers to the most vexing business and technology questions. The Brazil lab joins a global grid of six specialized IBM facilities to deliver a growing range of software lab services, including the recently opened HiPODS labs in China and India, as well as Japan, the UK and the United States.
Read further... |
|
|
|
| DMTF Technology spotlight the ROI Benefits of the DMTF’s CIM, WBEM and management standards in a Grid environment |
|
The Distributed Management Task Force, Inc. (DMTF), the industry organization for the development, adoption and promotion of interoperable management initiatives and standards will showcase via demonstrations, speaking sesions and its exhibit in the "Grid Ecosystem Pavilion" on how the Common Information Model (CIM) can form the backbone of an end-to- end management strategy in today's distributed grid infrastructures.
Read further... |
|
|
|
| Atipa adopts next-generation AMD Opteron processors in new line of Vision servers |
|
Supercomputer vendor Atipa Technologies, will be adding Next-Generation AMD Opteron processors to the Atipa Vision server line.
Read further... |
|
|
|
| IBM makes first Cell computer generally available |
|
IBM is making its first computing system based on the Cell Broadband Engine (Cell BE) generally available on a global basis, with early adopters such as University of Manchester, RapidMind Inc. and Fraunhofer Institute deploying compute-intensive applications on early ship versions.
Read further... |
|
|
|
| Etnus collaborates with Cisco Systems and Argonne National Laboratory on development of MPI2 debugging interface |
|
Etnus s working with partners including Cisco Systems and Argonne National Laboratory to develop a debugging interface for MPI2. This interface builds upon the current MPI-1 TotalView process acquisition interface, which is currently used by almost all MPI vendors. The new interface will be supported in a future TotalView release.
Read further... |
|
|
|
| SilverStorm Technologies' InfiniBand DDR shipments reach 10,000 port milestone |
|
SilverStorm Technologies, specialized in high performance interconnect solutions for clustered computing, has shipped over 10,000 ports of 20Gb/s InfiniBand DDR in its award winning portfolio of interconnect products since reaching general availability in June of this year. DDR shipments have been made to over 25 different customers including Chevron, NASA, Sandia National Laboratories, and the US Department of Defense in support of a variety of supercomputing applications, including the setting of a new world record visualization rendering rate of 1.5 billion polygons per second by a Linux Networx system currently being delivered to the Army Research Laboratory (ARL).
Read further... |
|
|
|
| DOE SC provides 800,000 hours of supercomputing time to U.S. Army Corps of Engineers to improve Gulf Coast hurricane defenses |
|
In 2006, the Department of Engergy's Office of Science made two separate allocations of 400,000 processor hours of supercomputing time at the National Energy Research Scientific Computing Center (NERSC) to the U.S. Army Corps of Engineers for studying ways to improve hurricane defenses along the Gulf Coast. The research is being done in co-operation with the Federal Emergency Management Agency (FEMA).
Read further... |
|
|
|
| HP enhances server portfolio with latest Intel dual-core technology |
|
HP has made new additions to its x86 server line-up that are powered by the latest Dual-Core Intel Xeon 7100 series processors.
Read further... |
|
|
|
| Louisiana Immersive Technologies Enterprise (LITE) installs one of world's largest supercomputers with 4.1- Tbyte SGI Altix 4700 system |
|
The Louisiana Immersive Technologies Enterprise (LITE) recently installed a massive computing component to its already world-leading SGI-powered visualization capabilities with the purchase of a 160-processor SGI Altix 4700 supercomputer with 4.1 Tbytes of memory.
Read further... |
|
|
|
| Virginia Tech adds SGI Altix 4700 for large-scale chemistry applications |
|
To primarily run Gaussian for chemistry research and development, among other code, Virginia Tech selected technology from SGI. After using the shared memory architecture of an SGI Altix system for a year, the university purchased a new SGI Altix 4700 and upgraded their existing system by doubling the amount of processors. Approximately 80 percent of the CPU cycles on the new SGI Altix system will run Gaussian calculations.
Read further... |
|
|
|
| Bull appoints Philippe Miltin Vice-President of the Products and Systems Division |
|
Philippe Miltin has been appointed Vice-President of Bull's Products and Systems Division. Having started his career in 1988 in sales with Rank Xerox, Philippe Miltin joined Altos in 1990 where he spent three years developing the sales network.
Read further... |
|
|
|
| IBM launches Blade Migration Center |
|
IBM has developed a Blade Migration Center aimed at helping clients escape the complexity of multiple incompatible architectures by migrating to a smarter IT platform, IBM BladeCenter. The programme is backed by a global team of more than 300 consultants and technologists to help make it easy for clients to consolidate workloads onto the slim IT footprint of the blade server platform. IBM will also offer existing HP blade clients a US$1000 incentive to make the switch.
Read further... |
|
|
|
| HP helps Philippine National Bank retool for global banking |
|
The Philippine National Bank (PNB) is leveraging HP's Core Banking Hardware infrastructure and systems management as it transforms its global IT banking environment over the next three years. To service all of PNB's branches worldwide, HP will supply a complete hardware platform for the bank's transition from a combined mainframe and minicomputer (AS/400) environment.
Read further... |
|
|
|
| Registration opens for SC06 Conference |
|
Registration opens for SC06, the annual conference of high-performance computing, networking, storage and analysis. This year's meeting, with the theme "Powerful Beyond Imagination", will convene November 11-17 at the Tampa Convention Center in Florida.
Read further... |
|
|
|
| NetApp certifies CentricStor for Network Data Management Protocol (NDMP) back-up |
|
Fujitsu Siemens Computers' CentricStor Virtual Tape Appliance has been certified by close partner Network Appliance for NDMP-back-up of its unified storage solutions. With the interoperability of CentricStor and NetApp solutions already laboratory-tested by Fujitsu Siemens Computers and widely used, this completes two-way ratification.
Read further... |
|
|
|
| Fujitsu Siemens Computers' CentricStor extends integration |
|
Fujitsu Siemens Computers' CentricStor virtual tape solution has achieved "Ready for IBM Tivoli software" and "IBM System Storage Proven". CentricStor - the flagship of storage solutions from Fujitsu Siemens Computers - can be seamlessly integrated with Tivoli Storage Manager (TSM). Compatibility of the virtual tape appliance with the IBM System Storage TS3500 Tape Library in combination with the IBM System Storage TS1120 tape drive was also confirmed.
Read further... |
|
|
|
| Fujitsu Siemens Computers, McDATA and Decru launch joint solution for secure, distributed data protection |
|
Fujitsu Siemens Computers, McDATA Corporation, and Decru, a NetApp company, have released a joint wide-area replication solution designed to simplify the back-up process and improve security for tape vaulting. The companies have worked together to integrate Fujitsu Siemens Computers' market-leading CentricStor Virtual Tape Appliance with McDATA's high performance Edge3000 Storage Routers and Decru DataFort storage security appliances to help enterprise customers with backup and disaster recovery operations that frequently span hundreds or thousands of kilometers.
Read further... |
|
|
|
| World's first OpenSolaris Center of Excellence opens in Italy |
|
Sun Microsystems Italy and the Department of Physics at the University of Pisa have reached an agreement to create the world's first Center of Excellence for the OpenSolaris technology platform. The goal of the centre is to provide technological expertise and support to academic institutions, businesses and developers.
Read further... |
|
|
|
| RENCI partners on two DOE SciDAC Awards |
|
The Renaissance Computing Institute will play a key role in two national research projects that are among 30 computational science projects being supported by the Department of Energy's Scientific Discovery (SciDAC) programme. The SciDAC awards were announced September 7. RENCI will receive more than $1.6 million over the next five years for SciDAC-funded research designed to improve the performance of very large-scale computing systems and the scientific codes that run on them.
Read further... |
|
|
|
| Altair Engineering's PBS Professional enhances efficiency and ease-of-use at LITE, host of one of the world's largest shared-memory supercomputers |
|
Altair Engineering Inc.'s PBS Professional software is the workload management solution driving the Louisiana Immersive Technologies Enterprise (LITE) system, one of the world's largest shared-memory supercomputers available to private sector and commercial users. In managing the HPC capabilities of the 4.1 terabyte (TB) system from SGI , PBS Professional facilitates the ability to apply the entire system to one complex problem or multiple projects at the same time.
Read further... |
|
|
|
| AMD announces socket compatibility plans to drive industry collaboration |
|
AMD's Torrenza Initiative is serving as a collaborative force toward achieving future processor socket compatibility in the server industry. By leveraging the advantages of AMD64 with Direct Connect Architecture and HyperTransport technology, OEMs will be able to standardize on a Torrenza Innovation Socket for many of their current and future server platforms.
Read further... |
|
|
|
| |
| Industry
-
The Grid |
|
|
| Sun Grid Compute Utility Infrastructure delivers cost savings and flexibility for electronic design automation |
|
AMD selected the Sun Grid Compute Utility for processor design and simulation to decrease time-to-market for new products, avoid costly infrastructure additions and gain more flexibility in scheduling testing during peak production cycles. The Sun Grid Compute Utility delivers affordable, easy and secure access to high-performance computing resources on a pay-for-use basis for $1/CPU-hour. Leveraging the Sun Grid Compute Utility for electronic design provides AMD with an additional tool for making efficient use of compute resources and continuing to deliver reliable products on time.
Read further... |
|
|
|
| Digipede Technologies adds new power to Grid computing software |
|
Digipede Technologies, a provider of distributed computing solutions for the Microsoft Windows platform, has introduced the Digipede Network version 1.3, featuring seamless integration with Microsoft Windows Compute Cluster Server; an expanded API for independent software vendors (ISVs) and enterprise developers, finer control of IT resources, and other new features.
Read further... |
|
|
|
| Second wave of EU-funded Grid technology projects officially launched |
|
During the European Grid Technology Days in Brussels last week, the second wave of Grid technology projects have been launched publicly at the Grid Concertation Meeting. Next week, Primeur/EntertheGrid will devote a special to the newly launched Grid projects. So please, do not miss that issue and watch this space.
Read further... |
|
|
|
| e-Infrastructures to support eScience in Europe with Grid and HPC is taking shape |
|
Science is an international business. To support scientific cross-border collaboration, national research networks in Europe have collaborated since many years, aided by the European Commission, to set up fast pan-European connections. During the recent years, Grid infrastructures have been explored too, and even more recently, discussions about collaboration on supercomputers Europe wide have also been started. However, in international European collaborations, it are not so much the technical problems that have to be solved, but one has to agree on the funding, sharing of resources, policy and legal issues. In the e-Infrastructures Reflection Group representatives from national science foundations of most European countries participate to develop a strategy for e-Infrastructures. The Group recently published an "e-Infrastructures Roadmap" and a version of its regularly updated whitepaper.
Read further... |
|
|
|
| Lofar sensor Grid expanded with first weather station |
|
On September 6, Dr. Eugene de Geus, manager of the LOFAR sensor Grid project at Astron in Dwingeloo, The Netherlands, has handed over a first Grid attached weather station to the president of the board of directors at the Regional Community of Schools Wolfsbos, Nel Frederix, on the roof of the location Groene Driehoek.
Read further... |
|
|
|
| Desktop Grid Experience Workshop organisers call for participation |
|
At the occasion of the offical opening of AlmereGrid, a workshop/mini-symposium will be organised on September 28, 2006 in Almere, The Netherlands. The workshop will discuss the technical possibilities and problems of Desktop Grids. In the morning, the experiences with AlmereGrid will be discussed. In the afternoon a number of other Desktop Grid projects, especially in the Netherlands will be presented.
Read further... |
|
|
|
| Open Science Grid receives $30 Million from NSF and DOE Office of Science |
|
A five-year, $30 million award to the US Open Science Grid Consortium, announced by the National Science Foundation and the U.S. Department of Energy‚s Office of Science, will operate and expand the Open Science Grid, a computing environment used by scientists to harness computing resources and scientific data from around the world.
Read further... |
|
|
|
| Helping computers identify real meaning |
|
The lightning rise of the internet and the development of advanced search technologies have created the greatest storehouse of information ever seen. Yet the very speed of this growth has brought its own problems. Which content is the wheat, and which the chaff? The METOKIS project aimed to help. A major obstacle stands astride the road to advanced internet search and services. To a computer, words or pictures on a page are just the 1s and 0s of binary language. The meaning, context, purpose and authority of the words are completely lost in the binary field. Computers cannot thresh the semantic, or meaningful, wheat from all the binary chaff.
Read further... |
|
|
|
| DOE announces $60 million in projects to accelerate scientific discovery through advanced computing |
|
The U.S. Department of Energy's (DOE) Office of Science has granted approximately $60 million in new awards annually for 30 computational science projects over the next three to five years. The projects are aimed at accelerating research in designing new materials, developing future energy sources, studying global climate change, improving environmental clean-up methods and understanding physics from the tiniest particles to the massive explosions of supernovae.
Read further... |
|
|
|
| Researchers tackle problem of data storage for next-generation supercomputers |
|
The U.S. Department of Energy (DOE) has awarded a five-year, $11 million grant to researchers at three universities and five national laboratories to find new ways of managing the torrent of data that will be produced by the coming generation of supercomputers.
Read further... |
|
|
|
| BIG GRID funding of 28.8 million euro officially approved by Dutch Science Foundation |
|
After the project had been submitted more than six months ago on December 7, 2005, the Dutch Organisation for Scientific Research (NWO) has officially granted the funding for the BIG GRID project. The three submitting organisations including the National Dutch Computing Facilities (NCF), the Netherlands Bioinfomatics Centre (NBIC), and the Dutch National Institute for Nuclear Physics and High Energy Physics (NIKHEF) will receive 28,8 million euro to set up a national Grid infrastructure for scientific research in The Netherlands.
Read further... |
|
|
|
| World's largest scientific Grid sustains a million jobs per month |
|
A milestone for scientific Grid computing was announced at the launch of EGEE'06, a major conference on scientific Grids hosted by CERN and held in Geneva this week. The Enabling Grids for E-sciencE (EGEE) project maintains a global Grid infrastructure that has been able to sustain more than 30000 jobs a day - over a million per month - for a period of six months this year. These computing tasks were submitted by scientists from diverse fields of research, and range from simulations of molecular drug docking for neglected diseases to geophysical analysis of oil and gas fields. Clusters of hundreds and even thousands of PCs, in institutes and universities around the world, have been executing these calculations - in total over 25000 central processor units (CPUs) are involved. Several million gigabytes of data storage in disk and tape facilities also contribute to make EGEE the world's largest scientific Grid infrastructure.
Read further... |
|
|
|
| University of Ulster Science Info-Sharing Project may help curb animal tests |
|
| |
