HPC NEWS
Student wins award for distributed computing cloud
Pierre Riteau, a student from the University of Rennes, has won the Grid5000 Large Scale Deployment Challenge award for creating one of the largest-ever distributed computing ‘clouds’. At the Grid5000 conference, held in Lille, France, Riteau used the Nimbus toolkit to deploy Nimbus over hundreds of nodes at three different Grid5000 sites and to create a distributed virtual cluster, a technique that makes multiple physical systems appear to function as a single logical system.
HPC Products
SGI has released SGI InfiniteStorage Server 3500, a fully-integrated storage server that offers high density and power efficiency in a cost-effective package. With support for low latency protocols including iSER for iSCSI over InfiniBand, ISS3500 is a perfect target for HPC clusters, such as SGI Altix ICE.
www.sgi.com
Eurotech has introduced the Aurora Au-5600, a next-generation green supercomputer that takes advantage of the new Intel Xeon 5600 series. The Aurora Au-5600 brings the efficiency and power of the 32nm architecture to the HPC domain.
www.eurotech.com
Bull has launched its Bullx supernodes. These quad-core SMP (Symmetric Multi-Processing) servers – which can be extended to 8, 12 or 16 processors – offer a powerful compute node in their maximum configuration, with up to 128 cores and 2TB of memory.
www.bull.com
Cray, has expanded its range of HPC solutions with the addition of the CX1000, a supercomputing solution featuring a hybrid supercomputing architecture built on Intel Xeon processors. Configurable with Microsoft Windows HPC Server 2008 and Linux, the Cray CX1000 supports three different compute architectures within one product family.
www.cray.com
Altair Engineering has announced
that version 10.1 of its PBS Professional HPC job-scheduling software has achieved Common Criteria EAL3+ certification. Common Criteria is the international standard for certifying software technology conforms to stringent security requirements, internationally recognised under the Common Criteria Recognition Agreement (CCRA).
www.altair.com
The Portland Group has added
support for the latest Nvidia GPUs
to its entire line of PGI Accelerator compiler products, including the PGI 10.4 release. Nvidia Cuda-enabled GPUs are used to accelerate the performance of appropriate HPC applications
www.pgroup.com
Matrox Imaging has announced its Supersight e2 HPC imaging platform is compatible with the latest Intel Xeon processor – the 5600 series. System host boards (SHBs) based on the processors are now available for the company’s imaging platform. The 32nm-architecture Intel Xeon processor 5600 series includes a 12MB shared L3 cache.
www.matrox.com
Microsoft’s High Performance Computing Group has
launched Windows HPC Server 2008 R2 Beta 2, available for download. Improvements to scalability have been made through regularly testing on the 1,000 node cluster in Microsoft Research.
www.microsoft.com
Nema Labs has introduced
FASThread, a parallel programming tool that enables easy and reliable parallelisation of code running on multicore platforms. FASThread integrates into IDEs (Integrated Development Environments) and provides programmers the tools to get maximum performance from code, processors and computers.
www.nemalabs.com
Numerical Algorithms Group
(NAG) has released a new NAG Library for SMP and Multicore, which will help scientists to make better use of the processing power of multicore computer systems. The NAG Library for SMP and Multicore contains more than 1,600 routines.
www.nag.com
Platform Computing has launched
Platform HPC Enterprise Edition, a comprehensive cluster management solution to help set up and use a cluster with more power and simplicity for technical application users.
www.platform.com
Grid5000 is a highly reconfigurable testbed for studying large-scale parallel and distributed systems and comprises thousands of nodes geographically distributed over nine sites in France and one site in Brazil. Distributed computing allows scientists to divide computational problems into many tasks across multiple computers to solve problems more quickly and efficiently. The Nimbus toolkit, developed by researchers at the US Department of Energy’s (DOE) Argonne
National Laboratory and the University of Chicago, provides an infrastructure-as-a-service cloud computing solution that includes an extensible architecture, specifically designed for scientists, enabling them to customise components to meet large-scale project needs.
Each cloud provides
computing cycles and storage resources to support real-time demands. The paradigm of cloud computing has long generated interest in the scientific community.
Russian Top50 list topped by Lomonosov
The 12th edition of Russia’s Top50 list of the most powerful HPC systems has been released at the annual ‘Parallel computing technologies’ international conference. The new list is topped by the ‘Lomonosov’ supercomputer, which features a peak performance of 414Tflops, and Linpack-measured performance of 350Tflops. The system is deployed at Moscow State University (MSU), and is ranked 12th on the current TOP500 list of the world’s most powerful supercomputers. The Lomonosov
supercomputer was manufactured by Russian HPC vendor T-Platforms.
20
SCIENTIFIC COMPUTING WORLD JUNE/JULY 2010
www.scientific-computing.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60