| Contents December 2006 |
|
|
 |
| |
| Industry
-
HPCN industry |
|
|
| Cray's new XMT - Data analysis and data mining large quantities of data |
|
Most supercomputers are designed to "compute" and perform large numbers of operations on more or less regular datasets. There is a complete different class of computing, however, that needs a computer with a completely different design. In data analysis and data mining large datasets, there is often no regularity in the data one can use: the goal is often to look for patterns. Also only part of the data set is of interest, however, it is not possible to separate the data to be used in a sensible way before the analysis starts. Hence these types of applications are data bound and not calculation bound as traditional supercomputing applications. With today's announcement of the XMT system, Cray has made available a special purpose system for analysing and mining large amounts of data.
Read further... |
|
|
|
| Cray on its way to Petaflop/s with the XT4 |
|
Cray has officially announced its new high end supercomputer: the Cray XT4. It is a scalar MPP system based on AMD Opteron processors. One of the largest configurations is a 288 cabinet system with 27.500 single sockets nodes with a peak of 1,15 Petaflop/s. The interconnect consists of a 32 x 36 x 24 Torus. The interconnect is capable of providing 0,385 bytes per flop of calculation power.
Read further... |
|
|
|
| AMD establishes University of Mannheim Center of Excellence to advance HyperTransport and supports FPGA research |
|
To expand industry adoption of the AMD Torrenza initiative and an open-standards approach to innovation, AMD announced today at Supercomputing 2006 it will be the inaugural sponsor for OpenFPGA. OpenFPGA is a non-profit consortium focused on accelerating the adoption and incorporation of reconfigurable computing solutions in high-performance and enterprise computing. OpenFPGA steering group members include many of today's leaders in high-performance computing including Cray, GE Research, Oak Ridge National Labs and Sandia National Labs.AMD also announced, in conjunction with the Computer Architecture Group at the University of Mannheim in Germany, the creation of the Mannheim Center of Excellence (COE), for research for HyperTransport technology.
Read further... |
|
|
|
| Cray signs $250 million agreement with DARPA to develop breakthrough adaptive supercomputer |
|
Cray has been awarded a $250 million agreement from the U.S. Defense Advanced Research Projects Agency (DARPA). Under this agreement, Cray will develop a revolutionary new supercomputer based on the company’s Adaptive Supercomputing vision, a phased approach to hybrid computing that integrates a range of processing technologies into a single scalable platform.
Read further... |
|
|
|
| IBM gets $244 Million DARPA HPCS Award for Supercomputing Grand Challenge |
|
The US Defense Advanced Research Projects Agency (DARPA) has awarded IBM a four-year $244 million award to develop a machine that provides 100 times the sustained performance of today's general purpose supercomputers and is dramatically simpler to program, administer and use. IBM expects the project to support DARPA's goals of increasing productivity and enabling the United States to achieve long-term technological leadership while opening up the complex world of supercomputing to a broader audience of scientists and businesses.
Read further... |
|
|
|
| Scali raises $3.5 million to drive continued growth and names Jack Kay CEO |
|
Scali, specialized in high performance clustering solutions for datacentres, has closed on $3.5 million in funding from investors Atlas Venture and Four Seasons Venture. The new round of funding will help fuel the company's continued growth and market share expansion.
Read further... |
|
|
|
| New HP cluster products at CSCS in Switzerland |
|
HP today announced enhancements to its Unified Cluster Portfolio for high-performance computing (HPC) at Supercomputing 2006. Product updates include support for new HP servers and workstations powered by Quad-Core Intel Xeon 5300 series processors. The HP Cluster Platform 3000 system now runs new Quad-Core processor-based HP ProLiant servers . "The HP Parallel Compositing Library and API will do for graphics clusters what the Message Passing Interface did for compute clusters – allow us to take advantage of the inherent performance scalability of clusters with network-based pixel compositing," said Jean M. Favre, chief scientist and leader of the scientific visualization group at CSCS, the Swiss national supercomputing centre. "Our new 16-node HP SVA cluster will be available remotely to the wide-area network of Swiss researchers and provide them with the advanced, cost-effective visualization capabilities they need to complement the supercomputing resources available at CSCS."
Read further... |
|
|
|
| Dr. Tadashi Watanabe awarded the Seymour Cray IEEE Prize |
|
Dr. Tadashi Watanabe, project manager of the Japanese petaflop/s Initiative, at the RIKEN research institute and a former Vice President of NEC, is the first Japanese citizen to be awarded the distinguished Seymour Cray prize for computer technology by the IEEE. This prestigious honour is for his life's work in High Performance Computer developments. (Chris Lazou)
Read further... |
|
|
|
| Panasas launches new ActiveStor Storage Cluster solutions with enhanced manageability, higher data availability and improved performance |
|
Panasas Inc., specialized in clustered storage solutions for the High Performance Computing (HPC) market, has launched two new families of storage clusters, the Panasas ActiveStor 5000 and Panasas ActiveStor 3000. Both ActiveStor 5000 and ActiveStor 3000 include the new ActiveScale 3.0 operating environment and Panasas PanFS Parallel File System. With the introduction of the ActiveStor Storage Clusters, in conjunction with the ActiveScale 3.0 operating environment, Panasas now offers the most comprehensive portfolio of storage solutions for HPC applications.
Read further... |
|
|
|
| Liquid Computing introduces Interconnect Driven Super Server |
|
Liquid Computing Corp., a developer of a new class of scalable computing system, announced the general availability of the world's first Interconnect Driven Server, LiquidIQ. LiquidIQ converges computing, networking and broadband to deliver unprecedented performance scalability and system control that is not available from today’s server and network equipment providers.
Read further... |
|
|
|
| 22nd Annual International Supercomputing Conference issues Call for Paoers |
|
The 22nd International Supercomputing Conference (ISC'07) will take place in Dresden, Germany on June 26-29, 2007. For ISC'07 the organisers are in the process of putting together 2 new elements: an Automotive Afternoon addressing the area "HPC for Automotive Engineering" and a Scientific Day. Innovative ISC activities from last year such as Bird-of-a-Feather Sessions and a Research Poster Session and Exhibitor forum will be organised again. Deadline for paper submissions is February 20, 2007.
Read further... |
|
|
|
| Etnus to offer TotalView debugger on IBM Deep Computing solutions |
|
Etnus has made available TotalView at IBM's Deep Computing Capacity On Demand Center in Rochester, Minnesota running on the IBM Blue Gene platform. Etnus is also announcing a remarketing agreement with IBM in which IBM and Etnus will develop a "go to market plan" to promote the use of TotalView for a number of IBM platforms, including AMD, Intel and Power-based Linux clusters, Power-based AIX systems, and IBM's powerful Blue Gene solution.
Read further... |
|
|
|
| Appro delivers the largest Linux Supercomputing Clusters to Lawrence Livermore National Labs based on AMD Opteron processors |
|
Appro has completed the first of four super compute Linux clusters for Lawrence Livermore National Laboratory (LLNL). Named "Rhea", the Infiniband interconnected cluster boasts 576 Next-Generation AMD Opteron 8000 Series processors with peak processing power of 22 teraflop/s (trillion floating operations per second). The Rhea server was brought on-line on October 23, 2006 and just completed its testing phase.
Read further... |
|
|
|
| Ohio Supercomputer Center uses NetEffect and Fujitsu for 10Gb iWARP Ethernet demonstration |
|
The Ohio Supercomputer Center (OSC) is featuring NetEffect's NE010e 10Gb iWARP Ethernet channel adapters (ECAs) in a demonstration of iWARP Ethernet at SC|06. OSC computer scientists will construct a high-speed iWARP Ethernet network with servers running Apache Web Server software and the Fujitsu XG1200 Low Latency 10Gb switch, connected by NetEffect 10Gb iWARP Ethernet adapters.
Read further... |
|
|
|
| Liquid Computing raises US $27.7 million in Series B financing |
|
Liquid Computing has completed its Series B financing in the amount of US $27.7 million. The funding comes after the recent launch of Liquid Computing's Interconnect Driven Server, LiquidIQ. The financing will support Liquid Computing's commercial expansion in the North American and European Enterprise High Performance Computing and Service Provider (xSP) markets. The funding was led by Newbury Ventures, based in the San Francisco Bay Area.
Read further... |
|
|
|
| NCAR installs 12-Teraflop IBM supercomputer for improved climate and weather research |
|
The National Center for Atmospheric Research (NCAR) has installed a new IBM supercomputer known as blueice that nearly triples the centre's sustained computing capacity. With a peak speed of 12 Tflop/s the new machine will enable scientists to enhance the resolution and complexity of Earth system models, improve climate and weather research, and provide more accurate data to decision makers.
Read further... |
|
|
|
| Argonne extends advanced computing expertise to tackle scientific challenges with SciDAC2 |
|
Argonne National Laboratory has been awarded approximately $25 million over the next five years for more than a dozen projects under the Department of Energy's "Scientific Discovery through Advanced Computing” (SciDAC) programme. Designed to ensure that the United States maintains a leadership role in science and technology, these projects will bring together some of the nation's top researchers from national laboratories and universities to create the software and infrastructure needed to help scientists effectively use the next generation of supercomputers in tackling complex scientific challenges.
Read further... |
|
|
|
| 20th ORAP Forum calls for participation |
|
The 20th ORAP Forum will be held 13 December 2006 at the Ministery of Research, Amphithéatre Gay Lussac, 25 rue de la Montagne Sainte-Geneviève in Paris. The theme of the event is "The European Community Scene of HPC. Participation is free of charge but registration is requested.
Read further... |
|
|
|
| Fujitsu Siemens Computers raises the bar for data centre virtualization with vBlade software |
|
Fujitsu Siemens Computers has launched vBlade software, a new software add-on to the PRIMERGY BladeFrame system powered by Egenera. vBlade software introduces an entirely new way to manage both physical servers and virtual machines by providing a single environment for configuring, allocating, repurposing and managing both types of resources, and eliminating the complexities associated with virtual machine management.
Read further... |
|
|
|
| OSCAR 5.0 High Performance Computing Cluster Building Toolkit Released |
|
The OSCAR working group has released a new version of the Open Source Cluster Application Resources (OSCAR) toolkit, OSCAR 5.0. OSCAR is a software package that supports the use of high-performance computing by reducing the work of cluster configuration, installation, operation, and management. The infrastructure underlying OSCAR 5.0 has been completely reworked to include smart package managers, yum based image building and package installs, easier client updating by using a repository based approach, and optimized start ups to reduce build time. Another long anticipated feature added in 5.0 is the ability to support multiple Linux distributions and architectures on the same cluster
Read further... |
|
|
|
| Pittsburgh PSC oubles Capability of Cray XT3 BigBen |
|
The Pittsburgh Supercomputing Center (PSC) has announced that it will more than double the capability of its 10-Tflop/s Cray XT3 system, BigBen, to 21.5 Tflop/s, an increase that improves the ability of U.S. scientists and engineers to address the most large-scale, demanding computational science projects.
Read further... |
|
|
|
| HP unveils Blade for quick, efficient storage |
|
HP has launched its first dedicated storage blade. The company also introduced two offerings within the HP StorageWorks Enterprise Virtual Array (EVA) family to accelerate back-up and recovery, reduce costs and make storage area networks (SANs) simpler to manage.
Read further... |
|
|
|
| Panasas lauches next generation ActiveScale operating environment |
|
Panasas Inc. has introduced the third generation of the company's operating environment, ActiveScale 3.0. The ActiveScale 3.0 operating environment adds several new features to the established PanFS parallel file system that Panasas has deployed in top companies and scientific organizations around the world. The ActiveScale 3.0 enhancements provide large-scale reliability and manageability, including new predictive self-management capabilities and an increase in client performance by a factor of 3X to over 500MB/s per client, and up to 10GB/s in aggregate.
Read further... |
|
|
|
| HP to support Windows Compute Cluster Server 2003 for High-performance Computing |
|
The HP Unified Cluster Portfolio now includes a certified original equipment manufacturer version of Microsoft Windows Compute Cluster Server (CCS) 2003 and a new HP Cluster Management Utility option. Additionally available is HP Message Passing Interface on Windows CCS.
Read further... |
|
|
|
| Dell launches removable hard drive to ease back-up pain |
|
Dell has introduced the PowerVault RD1000, a removable disk-based storage device for data back-up and restore that combines the speed of a hard disk with the portability of tape. Designed for small and medium-sized businesses, branch offices and individual power users, the PowerVault RD1000 is a removable disk drive that makes it easy, convenient and fast to back-up and protect critical data. Industry research estimates that one in five small businesses owns at least one PC-related data protection device.
Read further... |
|
|
|
| IBM unleashes new breed of hybrid supercomputers with System Cluster 1350 |
|
IBM has launched a new line-up of next-generation processor systems and blades, high speed connectivity and coprocessor acceleration technology for the IBM System Cluster 1350. With its improved ability to handle a broad range of application environments and capability to scale up to 1024 nodes, the System Cluster 1350 is a primary choice for building supercomputing solutions for a variety of industries including financial services, industrial, petroleum and life sciences.
Read further... |
|
|
|
| IBM revs up performance of x86 servers with new quad-core processors |
|
IBM is enhancing its line of x86 servers with the introduction of four, quad-core IBM systems and a new blade utilizing the quad-core Intel Xeon 5300 processor. System x servers provide a whole new level of value for clients, delivering three to four times performance of systems that IBM offered less than 12 months ago, enhanced systems management capabilities, expanded memory and I/O. When combined with the built-in virtualization and power management from IBM, these new systems enable clients to consolidate applications onto fewer, more powerful servers and keep control over energy spending in the datacentre.
Read further... |
|
|
|
| Platform expands Platform Open Cluster Stack with first AMD-based hardware from Dell |
|
AMD processors are now officially supported as a component of Platform Open Cluster Stack's (OCS) certification programme. Dell, which recently launched its first AMD-based PowerEdge servers, is the first vendor to join the programme. The certification of Dell's products further drives the two companies' long-standing commitment to simplify the deployment and management of HPC clusters.
Read further... |
|
|
|
| Fujitsu Siemens Computers launches its new FibreCAT NX storage solutions for SMEs |
|
Fujitsu Siemens Computers has introduced two new disk storage systems (file and print servers) for small and medium-sized enterprises (SMEs). Even the most exacting demands in terms of reliability, speed and availability will present no problems to the FibreCAT NX20 and FibreCAT NX40 models.
Read further... |
|
|
|
| DRC announces new coprocessor platform and development system for accelerated supercomputing |
|
DRC Computer Corporation, a provider of coprocessor systems, has launched its new Reconfigurable Processor Unit (RPU), and new development platform for modifying application subroutines to run in hardware. DRC’s new coprocessor system, the RPU110, is the second family in a series of dynamically reconfigurable coprocessors designed specifically for AMD Opteron systems. The DRC Development System, the DS2000, is the first complete development environment for large clusters using Opteron CPUs, DRC RPUs, and the Message Passing Interface (MPI) environment to emulate arrays of mixed processing elements.
Read further... |
|
|
|
| Intel shows supercomputing updates in Tampa |
|
Intel Corporation revealed new products and technology building blocks for system manufacturers, system builders and software developers to more easily create high-performance supercomputers that run faster and save space. New Intel-based server products introduced this year are delivering breakthroughs in technical computing. As a point of reference, 10 years ago, a supercomputer with 9000 Intel Pentium Pro processors took up 1,500 square feet, delivered 1.80 teraflops of peak performance and consumed some 800,000 watts of power. Today, the same level of performance can be achieved by a server cluster with 44 Quad-Core Intel Xeon processor 5300 series, codenamed "Clovertown" and due to ship shortly, while taking up just 16 square feet and consuming less than 10,000 watts.
Read further... |
|
|
|
| New energy-efficient HP servers and workstations power up performance |
|
HP has introduced new server and workstation systems designed to maintain power efficiency while meeting the needs of high-throughput, data-intensive applications. The new platforms, based on the Quad-Core Intel Xeon 5300 series processors, include HP ProLiant servers, HP BladeSystem server blades and HP Workstations and can improve certain enterprise application performance by 48 percent.
Read further... |
|
|
|
| Cluster Resources' Moab - most selected on Top500 supercomputers |
|
With the new Top500 supercomputers list released November 14, Cluster Resources Inc.'s Moab has been selected to run on 50 percent of the top ten systems and now more than 48 percent of the top 100 systems' total CPU count. Leading sites that have selected Moab include the numbers 1,2,4,6 and 10 systems. Cluster Resources has experienced consistent year-over-year growth in Top500 adoption over the previous five years.
Read further... |
|
|
|
| Sandia and Cray boost Sandia's "Red Storm" supercomputer performance to 125 Tflop/s |
|
Sandia National Laboratories has upgraded its "Red Storm" supercomputer by boosting performance from 40 Tflop/s to 125 Tflop/s , further establishing Cray's Red Storm as one of the highest performing supercomputers in the world.
Read further... |
|
|
|
| Supercomputer Center boosts storage capacity to 25 Petabytes |
|
SDSC already has six storage silos, each of which holds about 6000 tapes. With the new tape drives and media - IBM System Storage TS1120 tape drives with the new industry-leading 700-gigabyte tape media, Richard Moore ( director of Production Systems) and his colleagues can now store 25 Petabytes - that's 25 million billion bytes - an upgrade from SDSC's previously phenomenal storage capacity of six Petabytes.
Read further... |
|
|
|
| Altair Engineering's PBS Professional 8.0 released for IBM Blue Gene architecture |
|
Altair Engineering Inc.'s PBS Professional 8.0 is now generally available for the IBM System Blue Gene Solution. PBS Professional 8.0 adds support for massive IBM Blue Gene systems through new virtual node functionality. Blue Gene customers can now have one common workload management solution across their entire high-performance computing (HPC) infrastructure.
Read further... |
|
|
|
| Appro announces support for dual-core/quad-core Intel Xeon processor 3000, 5100 and 5300 series |
|
Appro, a provider of high-performance enterprise computing systems, has launched support for Dual-Core Intel Xeon processor 3000 and 5100 series and the new Quad-Core Intel Xeon processor 5300 series.
Read further... |
|
|
|
| Quadrics to expand its line of 10-Gigabit Ethernet interconnects for massively parallel computing |
|
Quadrics has launched its latest member of the QsTenG family designed for smaller networks. Quadrics is offering the 24-port QsTenG-TG2 1U, a one rack-unit solution also based on the FM2224, which comes in CX-4 copper and XFP optics versions. Quadrics QsTenG is a chassis-based 10-Gigabit Ethernet solution that can scale from 24 ports to 96 ports. The switch will use the company's own switch federation software to build hierarchical "fat tree" interconnect networks of up to 3456 ports.
Read further... |
|
|
|
| German-Japanese servers based on Intel's Quad-Processors are front runners in the footrace of industry standard servers |
|
| |
