| News digest August 2004 |
|
Advertisement
|
 |
 |  |
 | Industry
-
HPCN industry |
 |
 |
| IDC HPC Market Update 2003 |
|
Recently IDC gave a market update on the technical servers, which it differentiates to capability, enterprise, divisional and departmental. Technical servers have been sold for a total of 5.4 billion US Dollars. The capability segment declined significantly, the departmental segment had the highest growth. 2003 includes estimates of tier 2 vendors with an additional revenue of 303 Mio. US Dollar.
Read further... |
|
|
 |
| Quant-X/Compusys group's 64-bit solutions: more than pie in the sky |
|
The development of computers powerful enough to perform billions of calculations per second and create realistic simulations to test theories of the universe's formation has led to the rapid development of Computational Astrophysics as a major field of research. One limitation of whole-universe supercomputer simulations is that they have failed to resolve the small-scale structure of the universe, individual galaxy clusters and galaxies. Frustratingly, the computational power simply hasnt been there and explanations of the universe have remained incomplete.
Read further... |
|
|
 |
| ClearSpeed Technology gains DTI funding to help advance nanotechnology |
|
Nanotechnology-based revenues are expected to grow towards $10 trillion per annum within the next ten years, but a significant obstacle for this new industry is the cost of computing. ClearSpeed Technology, a provider of high performance, low power chip-based solutions, has just been awarded an Exceptional Research and Development Grant of £427,800 by the British Department of Trade and Industry to address this problem.
Read further... |
|
|
 |
| Critical Software releases the first MPI implementation for Windows running on the Intel Itanium 2 Processor |
|
Critical Software has released WMPI II for the Itanium 2 processor family, the first Message Passing Interface (MPI-2) implementation which runs on Windows clusters based on the Intel Itanium 2 architecture.
Read further... |
|
|
 |
| Rocks cluster management toolkit rolls over new milestones |
|
The Rocks development team at the San Diego Supercomputer Center (SDSC) is celebrating two milestones: passing the 50 teraflops mark in aggregate computing power, and the release of version 3.2 of the cluster computer management software suite.
Read further... |
|
|
 |
| Bull reinforces its Escala range with four new AIXT servers based on Power5 technology |
|
Bull four new AIX servers, Escala PL250R/T, PL450R/T, PL850R, PL1650R, based on Power5 processor technology. Power5 technology features "micro-partitioning", which allows the dynamic creation of up to 10 partitions per physical processor. This fine level of granularity makes optimisation of server resources possible, and facilitates the consolidation of front-end and departmental servers.
Read further... |
|
|
 |
| Fujitsu Siemens Computers unveils new generation of Intel-based monoprocessor servers |
|
Fujitsu Siemens Computers is boosting the appeal of its entry-level monoprocessor servers with the new S2 generation of its PRIMERGY TX150 tower server and RX100 rack server. The PRIMERGY TX150 S2 has been enhanced to operate even more economically while offering better performance and reliability. Its sheer range of functionality and high performance is as convincing as the integration of quality future-oriented technology.
Read further... |
|
|
 |
| UMaine computer engineers helped lay foundation for new U.S. Army Apple Xserve supercomputer |
|
University of Maine computer engineers and employees of Applied Thermal Sciences of Sanford, Maine have bragging rights in a recent announcement that the U.S. Army will create what may be the second most powerful computer in the world. The Army decision to build the machine known as the MACH 5 (Multiple Advanced Computers for Hypersonic, G5) is based in part on UMaine research funded by the Army to develop more powerful and less expensive computing technology for military research.
Read further... |
|
|
 |
| NCSA to expand its high-performance computing woith 6 Tflop/s 1,024 SGI Altix system |
|
The US National Center for Supercomputing Applications (NCSA) has purchased an SGI Altix system, to be named Cobalt, will consist of 1,024 Intel Itanium 2 processors running the Linux operating system, 3 terabytes of globally accessible memory, and 370 terabytes of SGI InfiniteStorage.
Read further... |
|
|
 |
| Silicon Graphics and PCS Industries form alliance |
|
Silicon Graphics Systems has entered into a strategic alliance with India's premier IT company PCS Industries Ltd. wherein PCS will market SGI's entire hardware product range comprising servers and supercomputers, workstations, visualization systems and storage in India.
Read further... |
|
|
 |
| StorCloud - a high bandwidth storage area network initiative for SC2004 |
|
A new initiative for SC2004 is to build a High Performance Computing (HPC) storage capability to showcase HPC storage technologies (topologies, devices, interconnects). This initiative, termed StorCloud, will comprise state-of-the-art heterogeneous devices and technology to build a virtual on-site "storage on request" area network capability to support researchers and demonstrate high bandwidth applications at the conference.
Read further... |
|
|
 |
| Bull NovaScale servers set a world record in performance |
|
Bull has set a world record by achieving the best performance in the 8-way server category, according to the Transaction Processing Council TPC-C benchmark: 175,366 transactions per minute (tpmC).
Read further... |
|
|
 |
| IBM establishes IBM eServer xSeries Taiwan Development Center |
|
IBM has established the IBM eServer xSeries Taiwan Development Center (xTDC), the first such centre opened by IBM outside the United States. The xSeries Taiwan Development Center will play a key role in connecting local vendors with IBM's global resources for Intel-based server development.
Read further... |
|
|
 |
| Bull announces the availability of the EMC CLARiiON AX100 on its Escala servers |
|
Bull announces the availability of entry-level storage EMC CLARiiON AX100 systems on its AIX servers. Integrated and validated by Bull in SAN environments, EMC CLARiiON AX100 simplifies the administration of the storage infrastructures and lowers storage costs.
Read further... |
|
|
 |
| IBM announces flexible On Demand server pricing for eServer i5 systems |
|
IBM will provide new pricing options for customers purchasing the IBM eServer i5.
Read further... |
|
|
 |
| Massively Parallel selects Metzger Associates for public and investor relations |
|
Massively Parallel Technologies (MPT) has hired Metzger Associates to assist in the development and execution of the company's public relations and investor relations programmes.
Read further... |
|
|
 |
| Cray announces professional services contract from Applied Technical Systems Inc. |
|
Cray Inc. has signed a 12-month professional services contract, valued at approximately $1 million, with Applied Technical Systems Inc. (ATS).
Read further... |
|
|
 |
| Fujitsu Siemens Computers launches new FUTRO S Series |
|
Fujitsu Siemens Computers has extended its range of thin client offerings with the new FUTRO S series. Taking up no more desk space than a medium-sized book (24.6 x 4.8 x 17.7 cm), these systems work with Transmeta processors. This means that despite having powerful graphics capabilities, they require only 25 watts, or 80 percent less power than consumed by the average PC.
Read further... |
|
|
 |
 |  |
 | Industry
-
The Grid |
 |
 |
| New EU-funded project NextGrid to set off in September 2004 |
|
NextGrid has been set up to develop architectural components that will lead to the emergence of the Next Generation Grid. This will prepare the way for the broader use of Grid technologies and their widespread adoption by organisations and individuals from the business and public domains. This widespread use will be a significant step towards meeting the vision of ERA and the goals of the e-Europe Action Plan. The project will start in September 2004.
Read further... |
|
|
 |
| European Grid Technology Days 2004 scheduled for September 2004 |
|
The IST-FP6 Grid Projects Launch and Concertation will take place during the European Grid Technology Days to be held September 15-17, 2004. The meeting will be held at the Crowne Plaza Brussels Europa Hotel, De Wetstraat 107, B-1040 Brussels, Belgium.
Read further... |
|
|
 |
| The old and the new |
|
Many of the early European IST Grid projects are now (nearly) finished. Of course, we are monitoring the project web sites, but they do not always provide up to date information. So we have to use personal contacts and look for demonstrations at events: demonstrations, of course, not presentations. At Heidelberg we saw a real demo of the OpenMolGrid project. Looked interesting enough to report in this week's Primeur. The latest round of European projects is now also known. A few weeks ago we did already report on a few of those projects. The European Commission is organising a day to introduce the new projects in September. Start memorizing the names of the new projects: NextGrid, Akogrimo, UniGrids, CoreGrid, Simdat, DataminingGrid, IntelliGrid, OntoGrid, K-WF Grid, Provenance, HPC4U, GridCoord. Difficult? Have a look at http://EnterTheGrid.com were we list all projects with short descriptions and links. We will update this with new information as it comes available. (AE)
|
|
|
 |
| From Grid to great? |
|
The Economist has released a survey on the uptake of commercial Grid computing. See elsewhere in this issue. What I do like about it is that they not only asked US persons, but also asked Europeans and people from Asia. What I do not like about these types of surveys is that the quality depends on the selection of the respondents. For instance in this case, they had two persons from Government/Public sector in the original survey phase. In the second detailed interview phase, these two where again interviewed, although the only represent a small percentage of the 177 respondents. Many citations of these two persons are mentioned in the report. Nevertheless it makes interesting reading. (AE)
|
|
|
 |
| OpenMolGrid automates 3D molecular structure search using Unicore |
|
Some of the European Grid projects are already running for a few years. Some have finished already. Did it work? At the Heidelberg supercomputer conference, results from the OpenMolGrid project were demonstrated. Using Unicore as Grid technology, what has been done is to automate the search for 3D molecular structures that could have a specific, looked for, behaviour.
Read further... |  OpenMolGrid automates the workflow of 3-D selection of molecules with the use of Unicore Grid infrastructure
|
|
|
 |
| Grid computing is breaking out |
|
The "Economist Intelligence Unit" (EIU) branch of the magazine "The Economist", has published a study with the title "From grid to great? Grid computing's corporate prospects". The Oracle sponsored study published in June is based on a survey in of 177 senior executives on the topic of Grid computing and concludes that Grid computing is breaking out.
Read further... |
|
|
 |
| German Grid project VIOLA to create a Vertically Integrated Optical test bed for Large Applications |
|
The German Grid project VIOLA (Vertically Integrated Optical test bed for Large Applications will be supported by the governement with 10.5 million Euro. Through the VIOLA project that is led by DFN, the German research network provider, a computer Grid will be developed to link research centre computers as well as to help generate new ideas for advanced applications and services. VIOLA will be a multi vendor and multi layer, integrated data and optical network. VIOLA will run from 2004-2007. The project has 10 partners, including research centres, universities, and industry. Initially it will run a 10 Gigabit Ethernet in North-Rhine Westfalia and Bavaria. The work will be done on four applications areas and there is one middleware work package. Unicore and MetaMPI are among the technologies deployed.
Read further... |
|
|
 |
| The state of Grid research in Europe |
|
The European Commission has published a booklet called "Changing the way research is done - The user perspective on eInfrastructures". eInfrastructures includes both the high-speed research network in Europe, Geant and the Grid infrastructure. Although the book is dated December 2003, it has just become available recently. The booklet contains high-level, introductory articles about Grid applications, most FP5 projects, and a part on status of Geant and Grids. Each item is written by a researcher involved in the project or area. This leads to a large difference in quality: the worst are only quoting from their project proposal or describing their own contribution to the Grid as the evolution of Grid technology. Other items, for instance on the activities in Japan, the overview of test beds and most of the application stories are quit nice. Keeping that all in mind the booklet is interesting if you want to get fast an introductory overview of what is/was happening. Each item has a small photograph of the author(s). If you do not know those people, I can reassure you that in real live they are much nicer than the impression you could get from their photograph in the booklet which is availabe from the European Commission. ISBN 92-894-6592-1.
|
|
|
 |
| Let us know |
|
Dissemination, although obliged by contract, is not a strong part of most European (Grid) projects. SeLeNe is no exception. The project, that is already finished, was working on looking at self-organising learning objects with relation to Grid and P2P. I was not sure what they did exactly mean with that. Recently, I noticed the SeLeNe website, which in itself is not an easy one to find - now includes updated project deliverables. An interested part was the description of the proposed architecture. This is an example of a knowledge Grid architecture, in a time were computational and datagrid are still dominating. I wonder what other useful developments have been done by Grid research projects that we do not know about.
|
|
|
 |
| SeLeNe architecture for supporting Learning Objects in a knowledge Grid |
|
SeLeNe's goal was to investigate into self learning networks, using metadata technology and Grid/P2P technology. As such it was an investigation into semantic Grids or Knowledge Grids technology. One part of the SeLeNe study was to investigate a possible architecture. SeLeNe designed a service based architecture. See the figure. It also did comparisons with OGSA and Globus to see whether there was functionality available or missing.
Read further... |  SeLeNe Grid Service architecture for Learning Objects
|
|
|
 |
| NEC develops Grid middleware for commercial IT systems |
|
NEC Corporation has announced Grid middleware, which enables autonomous resource allocation of services in response to dynamic changes in service workloads. The middleware mainly focuses on commercial enterprise IT systems, e.g. data centres, consisting of several resources, such as servers, networks and services.
Read further... |
|
|
 |
| IDA and Oracle announce S$25 million initiative to help local companies lead in the adoption of enterprise Grid technology |
|
The Infocomm Development Authority of Singapore (IDA) and Oracle Singapore announced a S$25 million initiative on enterprise Grid technology. The collaboration, 'Enterprise-g @ Singapore', will help more than 30 local companies develop enterprise Grid solutions and train some 300 Infocomm professionals. In addition, the collaboration will also establish other cluster projects in key verticals, such as manufacturing, transportation and health care. To achieve these goals, IDA and Oracle will set up a nerve centre, called the Enterprise-g Centre, to drive activities under the collaboration. The nerve centre also serves as a one-stop resource for vendors, enterprises and developers seeking to undertake enterprise Grid development, software development, testing, integration, standards compliance and Grid awareness activities.
Read further... |
|
|
 |
| ScotGrid clocks up 1 million CPU hours |
|
The ScotGrid system was first deployed on June 25th 2002. Today marks the second anniversary of deployment. Two years on, the total CPU usage is more than 1,000,000 CPU hours and the total number of jobs processed is more than 100,000. This represents a major landmark in terms of deployment of the system.
Read further... |
|
|
 |
| HPC4U - HPC clusters for Grids |
|
One of the newly funded European projects is HPC4U. It is the only project that is focussing on building hardware and not only software. The acronym is an abbreviation of Highly Predictable Clusters for Intranet Grids. The objectives of the HPC4U project are to expand the potential of the Grid approach to complex problems solving by means of deploying Grids that are able to meet specified Service Level Agreement (SLA), based on commodity-based clusters.
Read further... |
|
|
 |
| CERN openlab adds a new dimension to Grid computing |
|
The CERN openlab for DataGrid applications, a partnership between CERN , the European Organization for Nuclear Research, and five leading IT companies Enterasys Networks, HP, IBM, Intel and Oracle has announced a series of server and storage technical results regarding the first global science Grid the Large Hadron Collider Computing Grid project, LCG. The announcement was made at the recent annual sponsors meeting of the CERN openlab.
Read further... |
|
|
 |
| Distributed and dependable computing systems: a vision of the future |
|
A compilation of ideas on future research directions in distributed and dependable computing systems has been published by the IST project CaberNet in its Vision-2004 document.
Read further... |
|
|
 |
| T-Com chooses Bull Evidian software to deploy a Single-Sign-On infrastructure for 100,000 users |
|
Bull Evidian has been chosen to provide the secure access management and single sign-on (SSO) infrastructure for T-Com. Serving 100,000 users, this infrastructure will be among the world's largest SSO implementations for heterogeneous environments - from legacy to web.
Read further... |
|
|
 |
| Workshop on Grid Applications Programming issues Call for Participation |
|
The EPCC and the EU funded projects GridStart and GridLab invite participation in a 3-day workshop on "Grid Applications Programming" on July 2004, 19-21 in Edinburgh, United Kingdom. Registration and use case submission deadline is July 7, 2004.
Read further... |
|
|
 |
| Scali secures $ 7.5 million in series C financing to advance growth in new clustering and Grid markets |
|
Scali AS, a provider of high performance clustering solutions, has secured an additional $ 7.5 million in venture capital funding. New investor Atlas Venture led the round with participation from existing investor Four Seasons Venture. The new round of funding will be used to extend the company's presence in the US market, fund product development and continue to build relationships with key strategic partners such as Dell, HP and IBM. As part of the investment, Atlas Venture Senior Partner Alexander Bruehl will join the Scali board of directors.
Read further... |
|
|
 |
| i3ARCHIVE adopts Grid standards into National Digital Mammography Archive |
|
i3ARCHIVE Inc., a provider of systems for managing digital mammography information, will become the first company to adopt the OGSA standards for Grid Computing in a medical offering. i3ARCHIVE will integrate the standards into its National Digital Mammography Archive, the largest archive of digital mammography images and patient data, setting the stage for its growth nationwide. The project, which will be completed in 2005, is being funded through a grant from the National Institutes of Health and the National Cancer Institute.
Read further... |
|
|
 |
| Grid Computing adoption rises by 75% in six months |
|
Survey findings from Evans Data Corporation new Database Development Survey Summer 2004 show that Grid computing has risen by more than 75% in the past six months. Thirty seven percent of database developers are implementing or planning to implement a Grid computing architecture.
Read further... |
|
|
 |
| Ohio Supercomputer Center orders Cray X1 and Cray XD1 systems |
|
The Ohio Supercomputer Center (OSC) has ordered a Cray X1 supercomputer and a Cray XD1 high-performance computing system. An air-cooled Cray X1 supercomputer will be installed in the third quarter at OSC's new data center facility in Springfield, Ohio. The system will support scientific researchers throughout Ohio and beyond, especially in the fields of chemistry, materials science and life science. A Cray XD1 system is also scheduled to be installed in the third quarter at OSC-Springfield. The Cray XD1 system will be used for scientific research and to exploit the system's reconfigurable computing capability.
Read further... |
|
|
 |
| GridIron Software launches X-Factor reseller programme |
|
GridIron Software, a developer of Grid computing solutions, has launched its Value Added Reseller (VAR) Programme for X-Factor by GridIron. The programme enables GridIron and its partners to support the strong initial demand for X-Factor, the productivity extension for Adobe After Effects Professional 6.5 that speeds the creation of motion graphics and effects for film, video, DVD and the Web.
Read further... |
|
|
 |
| Globus Alliance announces change in the delivery schedule of the Globus Toolkit version 4.0 (GT4) |
|
The Globus Alliance has decided to move the release date of 4.0 Final to January 2005. This move is designed to affect a major advance in terms of toolkit stability, ease-of-use and documentation.
Read further... |
|
|
 |
| Enterprise Grid Alliance establishes foothold in Japan with regional operations |
|
The Enterprise Grid Alliance (EGA) has initiated regional activity with the formation of the Japan Regional Steering Committee (JRSC) to promote Grid adoption in Asia-Pacific.
Read further... |
|
|
 |
| Customers embrace EqualLogic's self-managing approach to IP SAN consolidation |
|
EqualLogic Inc., a provider of iSCSI-based, self-managing networked storage solutions, has surpassed the 100th customer deployment of its award-winning PeerStorage Array 100E.
Read further... |
|
|
 |
| Oracle Application Server 10g enhances integration with certification of leading business-to-business standards |
|
Oracle Application Server 10g is certified to support all leading business-to-business (B2B) standards, enabling organisations to easily comply with industry mandates required by companies such as Cisco, Intel, Wal-Mart, Home Depot and Lowe's.
Read further... |
|
|
 |
| Petrobras to use Linux, Grid and IBM BladeCenter for oil exploration |
|
Petrobras, one of the largest oil companies in the world, has chosen a Linux-based Grid comprised of IBM eServer BladeCenter systems to speed deep-sea oil exploration in the state of Espirito Santo. This is the largest collection of BladeCenter servers implemented by IBM Brazil and one of the largest in Latin America.
Read further... |
|
|
 |
 |  |
 | Industry
-
Applications |
 |
 |
| Critical Sotware signs contract with Microsoft Portugal and University of Coimbra |
|
Critical Software announces the signature of a three-way co-operation protocol involving Microsoft Portugal and the University of Coimbra aimed at fostering university-industry relationship through co-operation and R&D. Critical expects to contribute as an independent software company with its solid track-record working with Microsoft platforms, namely in the HPC market.
|
|
|
 |
| US Department of Energy Office of Science INCITE Programme seeking proposals for large-scale scientific computing |
|
Secretary of Energy Spencer Abraham has announced that proposals are being accepted for a Department of Energy (DOE) Office of Science programme to support innovative, large-scale computational science projects which will allow for high-impact scientific advances through the use of a substantial allocation of computer time and data storage at the department's scientific computing centere in Berkeley, California.
Read further... |
|
|
 |
| European Weather Forecast Center installs Linux Networx cluster system |
|
The European Centre for Medium-Range Weather Forecasts (ECMWF) has installed an Evolocity II Linux Networx cluster computing system. The system will be used to evaluate the suitability of cluster technology for broader deployment within ECMWFs high performance production environment.
Read further... |
|
|
 |
| 64-bit applications infrastructure continues to build using latest release of PGI compilers and tools |
|
The Portland Group, a wholly-owned subsidiary of STMicroelectronics, has made available version 5.2 of PGI Workstation, a suite of Fortran, C, and C++ compilers and development tools for scientists and engineers. The PGI compilers and tools are widely used on Linux workstations, servers, and clusters based on AMD64 and IA32 processors to build high-performance computing (HPC) applications for complex modelling and simulations | | |