Primeur weekly 2013-11-18

Special

Grid Engine celebrates its 20th anniversary this year ...

Exascale supercomputing

DataDirect Networks to preview groundbreaking new technology at SC13 ...

DOE awards $25.4 million in contracts for exascale supercomputer interconnect design ...

The Cloud

Leeds University selects CoolIT Systems to test benefits of liquid cooling on Cloud-based algorithms ...

Bright Computing previews next-generation Bright Cluster Manager at SC13 ...

Penguin Computing launches new HPC Cloud Appliance ...

IBM Watson's next venture: Fueling new era of cognitive apps built in the Cloud by developers ...

ConPaaS-1.3.1 is now available ...

Mainframe2 leverages new NVIDIA GRID G2 GPU instances from AWS to remotely run any application from a Web browser ...

Asigra introduces Cloud back-up Installation and Configuration Services (ICS) to speed deployments ...

Desktop Grids

Meliá Hotels International becomes a partner of the World Community Grid ...

EuroFlash

EGI in search of a new Director ...

"Piz Daint", the first supercomputer with sustained petaflops-scale performance in Switzerland ...

Fionn, Ireland's latest supercomputer, now launched ...

Quantum state world record smashed ...

Eurotech: CEA to test new Aurora Tigon water-cooled HPC system ...

Eurotech introduces their new divisional HPC systems at SC13 ...

USFlash

Four fastest supercomputers will lead Sino-US HPC dialogue in Denver ...

The recently released OpenMP 4.0 standard API will be showcased at SC13 ...

Cray extends its Cray Compiler Environment (CCE) to its line of cluster supercomputers ...

Cray Inc. reports third quarter 2013 results ...

NEC provides vector supercomputer with the world's fastest core performance ...

Improved ranking test for supercomputers to be released by Sandia ...

SC13 launches with weeklong look at new research and technologies that are changing the world ...

Designed for Big Data applications, AMD announces industry's first "supercomputing" server graphics card with 12GB memory ...

Wisdom Unbounded, the biggest global Student Supercomputer Challenge starts ...

SDSC uses Meteor Raspberry Pi cluster to teach parallel computing ...

Rice University method gives accurate picture of gas storage by microscopic cages ...

China's Tianhe-2 supercomputer maintains top spot on 42nd TOP500 list ...

Intel selects CoolIT Systems to liquid cool a Top500 cluster ...

Primeur magazine

Edition: weekly - Issue: 2013-11-18

Special

Grid Engine, now owned by Univa, has its origins in the CODINE project in 1993. The CODINE - COmputing in DIstributed Network Environments - project was focused on managing workloads in clusters of workstations. Primeur Magazine interviewed Univa members of the Board Fritz Ferstl, CTO & Business Development, EMEA, and Gary Tyreman, President & CEO. Read further...

Exascale supercomputing

DataDirect Networks (DDN) is heading to Supercomputing 2013 in Denver, Colorado where the company will host an exclusive analyst event - previewing technology that tackles the formerly impossible challenge of bringing high performance computing (HPC) customers within reach of the exascale 'Holy Grail'. Read further...
The Department of Energy's (DOE) Office of Science and the National Nuclear Security Administration (NNSA) have awarded $25.4 million in research and development contracts to five leading companies in high-performance computing (HPC) to accelerate the development of next-generation supercomputers. Read further...

The Cloud

A new collaboration between CoolIT Systems, Canada, and the Schools of Computing and Mechanical Engineering at University of Leeds, member of the prestigious Russell Group of 24 research-intensive universities, has been set up to analyse the influence of proximity liquid cooling on Cloud-based workload algorithms. The University has already received awards for analysis and development of Green IT solutions in the past couple of years. Read further...
Bright Computing will offer a preview of next-generation Bright Cluster Manager at SC13 featuring support for Hadoop clusters, OpenStack Clouds and more. Now, in addition to its leading HPC cluster management capabilities for data centres and AWS Clouds, Bright provisions, monitors and manages Big Data clusters and private Clouds making it an even more comprehensive management solution. Read further...
Penguin Computing, experts in high performance and enterprise computing solutions, have made available Scyld HCA, its new HPC Cloud Appliance. This appliance turns any HPC Linux cluster into a fully managed HPC hybrid Cloud environment, which adds the ease of use and automation of a public Cloud to an existing HPC cluster and has the added benefit of seamless hybrid access to Penguin Computing on Demand ("POD") to support burst out compute and storage capability. Read further...
For the first time, IBM will make its IBM Watson technology available as a development platform in the Cloud, to enable a worldwide community of software application providers to build a new generation of apps infused with Watson's cognitive computing intelligence. Read further...
The ConPaaS team has made available the release of ConPaaS-1.3.1: Platform-as-a-Service software. Read further...
Mainframe2, an innovator in Cloud computing, will support new NVIDIA GRID based Cloud instances at Amazon Web Services' annual re:Invent conference. The new instance types, launched by AWS on EC2, enable Mainframe2 to scale its customers' deployments to any size. The Mainframe2 technology has been optimized specifically for the new G2 instance type which features the powerful NVIDIA GRID GPUs. The combination of AWS, NVIDIA, and Mainframe2 technologies enables any browser-capable device to run even high-end 2D and 3D design software from the Cloud, on demand. Read further...
Asigra Inc., a Cloud back-up, recovery and restore software provider since 1986, has introduced world-class installation and configuration support to help service providers and the enterprises they serve to deploy Asigra Cloud Backup quickly and with minimal IT impact. The tiered professional service allows customers to select from basic set-up to full deployment of all Asigra software suite components to ensure end-to-end data recovery services and solution enablement. Read further...

Desktop Grids

Meliá Hotels International has signed up to the World Community Grid and during its initial phase it will be contributing the potential capacity of 370 computers located in the company's headquarters in Palma de Mallorca and Madrid. A second phase will see the inclusion of the computers located in the hotels at national and international level. Read further...

EuroFlash

EGI.eu is now seeking to employ a Director to lead the EGI.eu organisation. The Director is an individual with a strong entrepreneurial flair to transform a competitive research oriented e-infrastructure into a sustainable future. The primary objectives of the Director are to further develop and implement the future EGI.eu strategy, to prepare the grounds for a long-term sustainability of the EGI federation and to build and maintain strong relationships with other e-infrastructure providers and existing and new research communities in Europe. A background in research-oriented e-infrastructures is desirable. Read further...
The upgraded Cray XC30 supercomputer "Piz Daint" has exceeded petaflops sustained performance in scientific production runs. At the same time "Piz Daint" demonstrates significant improvements in the energy efficiency. This important milestone will enable researchers to study more detailed models with higher accuracy. Read further...
Minister Seán Sherlock TD, Minister for Research and Innovation and the Irish Centre for High-End Computing have launched Ireland's latest supercomputer called Fionn at the Dunsink Observatory. The name, chosen by Oscar O'Donoghue, a student from DCU CoderDojo, stems from Fionnachtana - Irish for Discovery - and Fionn mac Cumhaill. It aptly reflects the size of the new machine and the new R&D that it will enable. Read further...
A normally fragile quantum state has been shown to survive at room temperature for a world record 39 minutes, overcoming a key barrier towards building ultrafast quantum computers. The research, published in the journalScience, was led by Mike Thewalt, Simon Fraser University, Canada, with involvement from researchers at University College London (UCL) and Oxford University, and material provided from collaborating institutes in Berlin. Read further...
Eurotech, a provider of embedded and supercomputing technologies, has reached an agreement to provide CEA, the French Alternative Energies and Atomic Energy Commission, a small module of the new Aurora Tigon hot water-cooled high performance computing (HPC) family. The unit will be hosted in the CEA Compute Complex in Bruyères-le-Châtel and will serve as an R&D platform in order to assess and develop software addressing the challenge of energy efficiency. Read further...
Eurotech, a provider of embedded and supercomputing technologies, will present their new concept of mini HPC system at SC13, the supercomputing conference in Denver, Colorado. In order to meet the growing demand for smaller HPC systems that cater SMEs and departments computational needs, as a way to bridge the gap between a $1000 workstation and a $10 million data centre, Eurotech presents to the market the Aurora G-Station, powered by NVIDIA Tesla GPU accelerators, and the Aurora Cube, the CPU-only version. Read further...

USFlash

On November 20th, the HPC connection workshop @SC13 - HPCC 2013 will be held in Denver along with the SC13. The HPC scientists from ORNL, LLNL, NUDT and NSCC-TJ which have built the most famous supercomputers at present such as Tianhe-1A, Tianhe-2, Titan and Sequoia will share their knowledge on the development of HPC applications. Read further...
The OpenMP Consortium has recently released OpenMP 4.0, a major upgrade of the OpenMP standard language specifications. The Consortium will be showcasing it at the SC13 exhibition. Read further...
Cray Inc. has now made available the latest release of the Cray Compiler Environment (CCE) on the Cray CS300 line of cluster supercomputers. As a result of years of use in the world's most demanding high performance computing (HPC) centres, the CCE provides customers with a proven, familiar and HPC-optimized compiler for highly parallel environments. Read further...
Cray Inc. has issued financial results for the third quarter ended September 30, 2013. Revenue for the quarter was $54.4 million compared to $35.7 million in the prior year period. Cray reported a net loss for the quarter of $11.0 million or $0.29 per share compared to $5.2 million or $0.14 per share in the third quarter of 2012. Non-GAAP net loss, which adjusts for selected unusual and non-cash items, was $13.5 million or $0.35 per share for the third quarter of 2013, compared to a non-GAAP net loss of $5.7 million or $0.15 per share for the third quarter of 2012. Read further...
NEC Corporation has made available worldwide the SX-ACE supercomputer, the latest model in NEC's SX Series of vector supercomputers, featuring the fastest processor core performance in the world. Read further...
Sandia National Laboratories researcher Mike Heroux has helped craft a new benchmark that more accurately measures the power of modern supercomputers for scientific and engineering applications. Mike Heroux collaborated with the creator of the widely used LINPACK benchmark, Jack Dongarra, and his colleagues at the University of Tennessee and Oak Ridge National Laboratory. Read further...
SC13, the 25th conference in the SC series, welcomes high performance computing researchers, practitioners, and industry leaders from around the world. SC is an international conference on high performance computing (HPC), networking, storage and analysis, and provides the premier forum for the exchange of information in the global high performance computing community. The conference will be held at the Colorado Convention Center, Denver, from Sunday, November 17 to Friday, November 22. Read further...
AMD has launched the new AMD FirePro S10000 12GB Edition graphics card, designed for Big Data high-performance computing (HPC) workloads for single precision and double precision performance. With full support for PCI Express 3.0 and optimized for use with the OpenCL compute programming language, the AMD FirePro S10000 12GB Edition GPU features ECC memory plus DirectGMA support allowing developers working with large models and assemblies to take advantage of the massively parallel processing capabilities of AMD GPUs based on the latest AMD Graphics Core Next (GCN) architecture. AMD FirePro S10000 12GB Edition GPU is slated for availability in Spring 2014. Read further...
The ASC14 student supercomputer challenge - ASC14 - will be held in China, and the registration has opened already. ASC14 is initiated by Asia and accepts the registration from all academic organisations in the five continents. As introduced by the ASC14 committee, this event has fruitfully achieved the world's biggest student supercomputer challenge in 2013, per registration teams' amount. Read further...
Researchers at the San Diego Supercomputer Center (SDSC) at the University of California, San Diego, have built a Linux cluster using 16 Raspberry Pi computers as part of a programme to teach children and adults the basics of parallel computing using a simple model that demonstrates how computers leverage their capacity when working together. Read further...
A computational method to quantify the adsorption of gas by porous zeolites should help labs know what to expect before they embark upon slow, costly experiments, according to researchers at Rice University. The new method created by engineers in Rice's Multiscale Materials Modelling Lab accurately calculated the ability of two zeolites, small cage-like molecules with enormous surface area, to trap and store gas molecules. Among other possibilities, the work could help in the race to meet Department of Energy (DOE) standards that call for the creation by 2015 of materials that can hold 5.5 percent of their weight in hydrogen to fuel vehicles. Read further...
Tianhe-2, a supercomputer developed by China's National University of Defense Technology, retained its position as the world's no. 1 system with a performance of 33.86 petaflop/s (quadrillions of calculations per second) on the Linpack benchmark, according to the 42nd edition of the twice-yearly TOP500 list of the world’s most powerful supercomputers. The list was announced November 18 at the SC13 conference in Denver, Colorado. Read further...
Intel has selected CoolIT Systems, to liquid cool a high performance compute cluster that will showcase Intel's latest technology at SuperCompute'13 in Denver. CoolIT's Direct Contact Liquid Cooling (DCLC) System has enabled Intel to deploy a High Performance Compute cluster that will run live at Intel's Booth #2701. Read further...

Primeur weekly 2013-11-18

Special

Grid Engine celebrates its 20th anniversary this year ...

Exascale supercomputing

DataDirect Networks to preview groundbreaking new technology at SC13 ...

DOE awards $25.4 million in contracts for exascale supercomputer interconnect design ...

The Cloud

Leeds University selects CoolIT Systems to test benefits of liquid cooling on Cloud-based algorithms ...

Bright Computing previews next-generation Bright Cluster Manager at SC13 ...

Penguin Computing launches new HPC Cloud Appliance ...

IBM Watson's next venture: Fueling new era of cognitive apps built in the Cloud by developers ...

ConPaaS-1.3.1 is now available ...

Mainframe2 leverages new NVIDIA GRID G2 GPU instances from AWS to remotely run any application from a Web browser ...

Asigra introduces Cloud back-up Installation and Configuration Services (ICS) to speed deployments ...

Desktop Grids

Meliá Hotels International becomes a partner of the World Community Grid ...

EuroFlash

EGI in search of a new Director ...

"Piz Daint", the first supercomputer with sustained petaflops-scale performance in Switzerland ...

Fionn, Ireland's latest supercomputer, now launched ...

Quantum state world record smashed ...

Eurotech: CEA to test new Aurora Tigon water-cooled HPC system ...

Eurotech introduces their new divisional HPC systems at SC13 ...

USFlash

Four fastest supercomputers will lead Sino-US HPC dialogue in Denver ...

The recently released OpenMP 4.0 standard API will be showcased at SC13 ...

Cray extends its Cray Compiler Environment (CCE) to its line of cluster supercomputers ...

Cray Inc. reports third quarter 2013 results ...

NEC provides vector supercomputer with the world's fastest core performance ...

Improved ranking test for supercomputers to be released by Sandia ...

SC13 launches with weeklong look at new research and technologies that are changing the world ...

Designed for Big Data applications, AMD announces industry's first "supercomputing" server graphics card with 12GB memory ...

Wisdom Unbounded, the biggest global Student Supercomputer Challenge starts ...

SDSC uses Meteor Raspberry Pi cluster to teach parallel computing ...

Rice University method gives accurate picture of gas storage by microscopic cages ...

China's Tianhe-2 supercomputer maintains top spot on 42nd TOP500 list ...

Intel selects CoolIT Systems to liquid cool a Top500 cluster ...