logo

EnterTheGrid - PrimeurWeekly

EnterTheGrid - PrimeurMagazine is the largest Grid and Supercomputer information source in the world. PrimeurWeekly delivers the news each week in your e-mail box.

>PrimeurMagazine
>PrimeurLive!
>EnterTheGrid
>Analysis
>Backissues
>Calendar
>Subscribe
>Advertise
>Contact
PrimeurWeekly 18 May 2009
>Special
>Amsterdam was supercomputing capital of Europe for three days
>European Commission puts emphasis on supercomputing eco-system
>Next-Generation Supercomputer project in Japan is becoming a challenge of its own
>Exaflops systems? We might never get there!
>Russia on the road to Pflop/s
>Focus
>The Top Trends in High Performance Computing
>EuroFlash
>European interoperable Grid infrastructure expanding further: SEE-GRID-SCI and EDGeS to connect Grids
>EDGeS helps us all talk to each other
>Mini-symposium on Networked Visualization for e-Science issues Call for Participation
>ISC'09 hits the record of its 24-year history
>FP7 Information Event on the Seventh Call for Proposals under the e-Infrastructures Activity
>European Commission to organize Information Day on Objective 1.2 "Internet of Services, Software and Virtualisation" Call 5
>HLRS selects Voltaire 40 Gb/s InfiniBand and Unified Fabric Manager Software for performance and management of new supercomputer
>Ipswich Borough Council secures data and reduces back-up times with ExaGrid Systems
>New PRIMERGY BX900 server system raises the stakes in virtualization and energy-efficiency
>Dolphin expands PCI Express Solid State Disk (SSD) storage product line
>USFlash
>NEC reviews participation in the MEXT Next-Generation Supercomputer Project but will continue its supercomputer business
>ASUS to introduce P6T7 WS SuperComputer workstation motherboard
>Cray appoints Quadrics co-founder Duncan Roweth to Principal Engineer, CTO Office
>Pittsburgh Supercomputing Center joins forces with Darkstrand to advance innovation and collaboration
>Altair and TARDEC emphasize need for increased modelling and simulation in the development of military ground vehicles
>AMD delivers the world's first 1 GHz graphics processor
>Cisco introduces Unified Service Delivery for service providers
>Crossroads Systems announces strategic alliance with Clearview's managed services
>Fujitsu simplifies unified data centre and Cloud computing management with Resource Coordinator VE
>IBM ushers in era of stream computing
>IntelePeer teams with Telx to offer hosted voice and rich media applications to colocation customers
>Oracle buys Virtual Iron
>Rackable Systems completes name change
PrimeurWeekly 18 May 2009
Advertisement
Special
Amsterdam was supercomputing capital of Europe for three days
The DEISA/PRACE supercomputing symposium in Amsterdam attracted about 200 attendees from Europe and abroad. There were main presentations on the current HPC policies in Europe, the USA, Japan, Russia and Australia. Overview presentations of main application areas, including astronomy and climate research. Insight into the technological developments around supercomputers, and many supercomputer application talks. In this Primeur Special we cover this event with several articles. Read further...
European Commission puts emphasis on supercomputing eco-system

The European Commission is stimulating the support for eScience with e-Infrastructures consisting of high-speed networking, Grid infrastructures, and data infrastructures. A relative new item is supercomputing. The DEISA project did and does combine a number of European supercomputers into a supercomputer Grid. With the funding of the PRACE project, the Commission funds the development of a European supercomputer strategy. The goal is to increase the number of Europe-based supercomputers in the upper regions of the TOP500. Also the European IT industry should be encouraged. At first, the ideas were a bit hardware system focused using a pyramid with at the top a few tier-0 systems, then a level with tier-1 country systems, etc. But now, Maria Ramalho Natário, from the European Commission explained at the DEISA/PRACE symposium in Amsterdam, that the focus is more on a complete eco-system, with also different machines or Grids at different levels, but accessible by a scientist through a workspace that hides as much as possible the complexity of the systems and the Grids, and can create work flows where different steps can use different system architectures or Grids when needed. The next funding call for projects, that will open in July and closes in November will support this complete eco-system.

Read further...
Next-Generation Supercomputer project in Japan is becoming a challenge of its own
At the PRACE/DEISA Symposium in Amsterdam, Ryutaro Himeno explained the Japanese supercomputer development progress in a presentation: "Next-Generation Supercomputer R&D Project in Japan and Grand Challenges in Life Sciences". Later during the conference the news came from Japan that NEC stepped out of the Next-Generation Supercomputer R&D Project. This will be a serious set-back for the project, as NEC was providing the vector part of the supercomputer system, the part that can boost performance of the supercomputer system for many large-scale applications. However, Ryutaro Himeno's presentation gave a nice overview of the achievements of the Next-Generation Supercomputer project thus far. Read further...
Exaflops systems? We might never get there!
At the DEISA/PRACE symposium in Amsterdam, Horst Simon gave an overview of the current supercomputing developments in the USA. With two supercomputers currently running over a Pflop/s (petaflops), and studies underway on exascale systems that are a thousand times faster, many people are confident we will get there in a few years. That is too optimistic, said Horst Simon. We do not know how to build Eflop/s (exaflops) systems, we do not know how to operate them, and we do not know how to program them. Read further...
Russia on the road to Pflop/s
At the DEISA/PRACE supercomputing symposium in Amsterdam, Vladimir Voevodin, from the Research Computing Center, Moscow State University (MSU), gave an overview of the Russian supercomputing activities on the road to Pflop/s systems. Currently the fastest system in Russia is on position 35 in the TOP500 with 70 tflop/s performance. Vladimir Voevodin, expects that by next year a machine with 0.5 Pflop/s performance will be operational. Read further...
Advertisement
Visit our sponsors
Focus
The Top Trends in High Performance Computing

Horst Gietl, Executive Consultant, Prometeus GmbH & Hans Meuer, General Chair of ISC'09 in Hamburg, Prometeus GmbH

If we calculate the performance predictions for the TOP500 list, then we will see a 100 Petaflops system most likely in the year 2016. In the past we had a performance increase within 11 years from Gigaflops (Cray2 in 1986), via Teraflops (Intel ASCI Red in 1997) up to the Petaflops (IBM Roadrunner in 2008) by a factor of 1000.

Despite these performance improvements the HPC arena will more and more be defined indirectly via the highly compute-intensive applications. They are coming from a variety of areas, involving quantum mechanical physics, weather forecasting, climate research, molecular modeling (computing the structures and properties of chemical compounds, biological macromolecules, polymers, and crystals), physical simulations (such as simulation of airplanes in wind tunnels and research into nuclear fusion), cryptanalysis, and improved seismic processing for oil exploration for continued supply. For most of these applications detailed results may only be achieved with systems in the Petaflops range. And hopefully Exascale Systems will be seen first in 2019.

But what are the trends in the nearest future which will form the basis for all these performance predictions. The major challenges to all processor requirements for HPC systems now and in the future will be: low cost, low power consumption, availability of support for parallel programming, and efficient porting of existing codes. Read further...
Advertisement
Visit our sponsors
EuroFlash
European interoperable Grid infrastructure expanding further: SEE-GRID-SCI and EDGeS to connect Grids
The EDGeS and SEE-GRID-SCI projects have signed a Memorandum of Understanding (MoU) to connect the SEE-GRID infrastructure to other Grids using the EDGeS Bridge technology. EDGeS already connects Desktop Grids in several European countries, with the EGEE and EELA Grids. SEE-GRID-SCI project is a collaboration of Grids covering South-East Europe. Under the agreement, SEE-GRID-SCI and EDGeS will further collaborate on application porting and dissemination and training activities. Read further...
EDGeS helps us all talk to each other
Like Bill Murray adrift in Japan in the movie "Lost in Translation", things can go awry when service grids and volunteer grids try to talk to each other. Service grids, such as EGEE, often involve large institutions whose work method is centered around collaboration - to the point where participants often know each other personally. To ensure security, resources and users pass through an accreditation process, and the resulting "certificate" provides proof that this occurred successfully. The certificate is key to allowing jobs to be submitted and completed. (Danielle Venton, EGEE) Read further...
Mini-symposium on Networked Visualization for e-Science issues Call for Participation
The University of Amsterdam is organizing a small symposium/theme-afternoon on Friday afternoon June 19, 2009 on the occasion of the visit of Professor Thomas DeFanti to the University of Amsterdam. Professor DeFanti is well known for his groundbreaking work in computer graphics and visualisation and is one of the inventors of the CAVE. The symposium will be held at Science Park Watergraafsmeer, CWI, Auditorium Z11, Kruislaan 413, Amsterdam. Read further...
ISC'09 hits the record of its 24-year history
Over 30% more attendees have registered for the 24th International Supercomputing Conference - ISC'09 - to be held in Hamburg 23-26 June, 2009, in comparison with the same time in 2008. Every June, many of the world's leading experts in high-performance computing convene in Germany to discuss the latest advances in supercomputing and to get a glimpse of what the future holds. Read further...
FP7 Information Event on the Seventh Call for Proposals under the e-Infrastructures Activity
The information event on the seventh call for proposals under the e-Infrastructures topic of the FP7 "Capacities" Specific Programme will be held in Brussels on 18 June 2009. Read further...
European Commission to organize Information Day on Objective 1.2 "Internet of Services, Software and Virtualisation" Call 5
The European Commission is organizing an Information Day on Objective 1.2 "Internet of Services, Software and Virtualisation" Call 5 on 9 June 2009 at the Charlemagne building, Room Alcide de Gasperi, Rue de la Loi, 170, 1040 Brussels. The objective of this meeting will be to inform the audience about the scope of Objective 1.2, the procedure for preparing a proposal and to allow networking among the participants. Read further...
HLRS selects Voltaire 40 Gb/s InfiniBand and Unified Fabric Manager Software for performance and management of new supercomputer
The High Performance Computing Center Stuttgart (HLRS) has selected Voltaire 40 Gb/s InfiniBand and Unified Fabric Manager (UFM) software for a supercomputer dedicated to providing HPC services to multiple customers. HLRS chose the Voltaire scale-out fabric solution to help them achieve peak performance, low communication latency and efficient management to deliver services to their end users primarily from the automotive and aerospace industries. Read further...
Ipswich Borough Council secures data and reduces back-up times with ExaGrid Systems
Ipswich Borough Council has chosen the ExaGrid system to achieve faster back-ups, improve security of data and save taxpayers' money in the future with built-in scalability. Ipswich BC is a regional centre for business, culture, entertainment and sport and has more than 130.000 residents. Read further...
New PRIMERGY BX900 server system raises the stakes in virtualization and energy-efficiency
Fujitsu has achieved a key foundation stone in its global market growth programme for x86 servers, with the introduction of the Dynamic Cube - the new-generation PRIMERGY BX900 blade server system. Read further...
Dolphin expands PCI Express Solid State Disk (SSD) storage product line
Dolphin has unveiled new higher capacity members of its StorExpress storage product line. With leading edge PCI Express flash memory technology (PCIe SSD); StorExpress breaks new ground for capacity and performance for data intensive financial, eCommerce, defense, and entertainment applications. Read further...
Advertisement
Visit our sponsors
USFlash
NEC reviews participation in the MEXT Next-Generation Supercomputer Project but will continue its supercomputer business
NEC Corporation will not extend its current contract into the manufacturing phase of the Japanese "Development and Use of an Advanced, High-Performance, General-Purpose Supercomputer" project (Next-Generation Supercomputer Project) by the Ministry of Education, Culture, Sports, Science and Technology (MEXT), following the completion of its role as a co-development partner in the detail design phase. NEC will continue to contribute to various aspects of the project, including architectural research for fast computing, and development support for application software, in cooperation with a range of research institutions. Read further...
ASUS to introduce P6T7 WS SuperComputer workstation motherboard
ASUS, a producer and innovator of motherboards, has launched the ASUS P6T7 WS SuperComputer motherboard. Equipped with 7 PCI-E Gen2 x16 slots, the P6T7 WS SuperComputer has been certified for NVIDIA Tesla GPU computing which is based on the NVIDIA CUDA parallel computing architecture, supporting up to three NVIDIA Tesla cards and one NVIDIA Quadro card. This amounts to a total of 960 parallel processing cores providing 4 Tflop/s of processing power. The ASUS P6T7 WS SuperComputer also provides users with flexible high speed I/O, graphics and computing options. Read further...
Cray appoints Quadrics co-founder Duncan Roweth to Principal Engineer, CTO Office
Cray has appointed Duncan Roweth as principal engineer in the CTO office. With 20 years of experience in the high performance computing (HPC) industry, Duncan Roweth will work on Cray's future interconnect R&D and will also be in charge of the company's research activities across Europe. Read further...
Pittsburgh Supercomputing Center joins forces with Darkstrand to advance innovation and collaboration
Darkstrand has signed a collaborative agreement with the Pittsburgh Supercomputing Center (PSC). This agreement enables corporations connected anywhere on the Darkstrand Network to collaborate in real time with PSC on high-performance computing projects leading to product development. Read further...
Altair and TARDEC emphasize need for increased modelling and simulation in the development of military ground vehicles
The role of modelling and simulation in tomorrow's defense engineering industry was a focal point for some of the top experts in military and software engineering at the Advanced Innovative Methods for Improved Reliability & Efficiency (AIM FIRE) Military Day, a programme co-hosted by the global technology provider Altair Engineering Inc. and the U.S. Army Tank Automotive Research, Development and Engineering Center (TARDEC). Read further...
AMD delivers the world's first 1 GHz graphics processor
Building on the recently launched ATI Radeon HD 4890 graphics card AMD has made available a factory overclocked graphics processor that is the first to break the 1 Gigahertz (GHz) barrier using standard air-cooling solutions. Read further...
Cisco introduces Unified Service Delivery for service providers

Cisco has unveiled Cisco Unified Service Delivery, a solution to help service providers build a foundation for Cloud services, while they transform the delivery of consumer and business applications to any place and device.

Read further...
Crossroads Systems announces strategic alliance with Clearview's managed services
Crossroads Systems has signed a strategic alliance with Texas-Based Clearview. Clearview will deploy several Crossroads products starting with Crossroads' ReadVerify Appliance (RVA) technology and RVA Services at its Waco Information Technology Gateway (ITG) data centre. Read further...
Fujitsu simplifies unified data centre and Cloud computing management with Resource Coordinator VE
Fujitsu launched ServerView Resource Coordinator VE harnesses all physical and virtual resources within complex IT server topologies - including Cloud computing environments - providing simplified, unified management and ensuring that resources are dynamically optimized to deliver best performance at all times. Read further...
IBM ushers in era of stream computing
At its annual investor briefing, IBM has made available its unique "stream computing" software that enables massive amounts of data to be analysed in real time, delivering extremely fast, accurate insights to enable smarter business decision-making. The new software is called IBM System S. Read further...
IntelePeer teams with Telx to offer hosted voice and rich media applications to colocation customers
IntelePeer, an expert in hosted on-demand rich media communications, has signed a partnership with Telx, one of the largest North American providers of network-neutral colocation and interconnection services. IntelePeer will offer ReachSuite-hosted voice and rich media applications that allow Telx customers to quickly roll out new, high-margin voice and telecommunications services while avoiding up-front capital costs. Read further...
Oracle buys Virtual Iron
Oracle has agreed to acquire Virtual Iron Software, a provider of server virtualization management software that enables dynamic resource and capacity management in virtualized data centres. Read further...
Rackable Systems completes name change
Rackable Systems Inc. has completed its legal name change to "Silicon Graphics International Corp." The company also will change its NASDAQ stock ticker symbol from "RACK" to "SGI." The stock ticker change has gone into effect for the trading community on Monday, May 18, 2009. Read further...

EnterTheGrid - Primeur

James Stewartstraat 248

1325 JN Almere

The Netherlands

http://enterthegrid.com/primeur

mailto:primeur [AT] enterthegrid [DOT] com

© EnterTheGrid - PrimeurWeekly