Bull has installed hundreds of Extreme Computing systems throughout the world. Here are some examples, by sector. View all
Bull helps AWE scientists push back the boundaries of science
To carry out their important work in support of the UK’s nuclear deterrent scientists at AWE need a vast amount of computing power. Until earlier this year, the organisation was reliant on one main supercomputer. However, this year, after a two year competitive tender process, AWE has accepted delivery of three supercomputers from Bull. All three are based on the award winning bullx platform. The first two, named ‘Willow’, were installed separately, one after the other, in the early part of the year before the most powerful of the three, named ‘Blackthorn’, was installed later in the year.
Tera 100: Europe’s first supercomputer to break the Petaflops barrier
• European Number One, with a performance of 1.05 Petaflops • One of the most efficient supercomputer in its category, with proven efficiency of almost 84% according to the LINPACK benchmark • A general-purpose supercomputer, designed to run the CEA-DAM’s Simulation program 24 hours a day Tera 100 has officially broken the Petaflops barrier, by recording a performance of 1.05 Petaflops in the LINPACK benchmark test, for a peak performance of 1.25 Petaflops. This performance means it ranked as the most powerful supercomputer in Europe, and as the 6th in the world, in the TOP 500 listing published in mid-November 2010 - and still number 1 in Europe in the June 2011 TOP 500 listing! Its 83.7% efficiency rating, one of the highest among all the supercomputers in its class, and its performance clearly demonstrate the quality of the design work carried out by the teams from Bull and CEA-DAM (the Military Applications Division of the French Alternative Energies and Atomi
University of Reims Romeo supercomputer ranked 5th of the Green500 list
The bullx supercomputer deployed at the ROMEO HPC Center of the University of Reims Champagne-Ardenne is now fully operational. Powered by NVIDIA Tesla K20X GPU accelerators, it is the most powerful GPU-accelerated cluster in France and also one of the greenest supercomputers in the world.
University of Reims to deploy France’s most powerful GPU-accelerated supercomputer
The University of Reims Champagne-Ardenne today announced plans to deploy a new BULL bullx high performance computing (HPC) cluster at its ROMEO HPC Center, powered by NVIDIA® Tesla® K20X GPU accelerators. Expected to be the most powerful GPU-accelerated cluster in France, and one of the most important Kepler installations in Europe, the “Romeo” system will be installed this summer. It will be available for both industrial and academic researchers in the region, along with an entire ecosystem of services, including secured storage, software and support, as well as an in-depth expertise in different engineering fields: HPC, applied mathematics, physics, biophysics and chemistry.
Bull Signs Strategic HPC Agreement with University of Liverpool
Bull has signed a strategic alliance deal, valued at around £800,000, with the University of Liverpool. Under the terms of the deal, which incorporates a five year partnership and support agreement, Bull will implement an integrated 40 Teraflop HPC system for the University based around its own ‘bullx’ blade hardware and bullx supercomputer software suite.
The Dresden University of Technology orders a Bull petaflops-scale supercomputer
Once the two phases of its installation are completed in 2013/14, the new supercomputer, which represents an investment of about 15 million Euros, will benefit the whole research community in Saxony. The Excellence University and the European high tech company also signed a cooperation agreement for the development of software solutions for the measurement and optimization of energy efficiency in high performance computing systems.
A mobull container for the University of Perpignan Via Domitia
The University of Perpignan Via Domitia (UPVD) has purchased a new modular data center for its campus in the South of France. The mobull modular data center - chosen by UPVD and supplied by ServiWare, a Bull Group company - will protect and store its computing data. It consists of a computing center in 'ISO45 container format'.
University of La Réunion orders a Bull supercomputer
The autonomous University of La Réunion, founded in 1982, has chosen Bull to supply a new computing cluster, to support the University’s research activities. The University nurtures research projects, both at a local level – looking at issues of sustainable development and the local economy, healthcare and bioinformatics, and tropical agriculture – and with an international remit. The Laboratory of Physics and Mathematical Engineering for Energy and the Environment (known as PIMENT) will be using the bullx™ supercomputer in particular to carry out computer simulations of fluid mechanics, designed to improve our understanding of thermo-convection phenomena relating to the natural ventilation of buildings in hot climates. Thanks to this work, consulting firms will have access to tools that let them adapt their proposals to suit tropical climates perfectly, with technical solutions that optimize both energy use and thermal comfort.
RWTH Aachen University orders Bull supercomputer
The North Rhine-Westphalia Technical University (RWTH or Rheinisch-Westfälische Technische Hochschule) in Aachen - one of the nine German 'Universities of Excellence' with about 33 000 students - has chosen a bullx supercomputer. The new system, featuring over 28,000 processing cores, will deliver some 300 Teraflops of power and three Petabytes of disk storage, and will give the University a significant advantage when it comes to running computer simulations that reflect reality as closely as possible. In addition, the University's Center for Computing and Communication and Bull have signed a collaboration agreement aimed at optimizing applications that may be useful to industry in heterogeneous cluster environments and in the area of 'Green IT'.
BSC-CNS triples its calculation capacity
The Barcelona Supercomputing Center - Centro Nacional de Supercomputación (BSC-CNS) now has a new cluster with graphical accelerators which will be used to consolidate its research in programming models, tool development and application porting. This new Bull system, based on bullx nodes, each equipped with Intel processors and NVIDIA GPUs, would be ranked 90 in the world in the June 2011 Top500 list with its peak performance of 186 Teraflops. This cluster doubles MareNostrum's calculation capacity, consumes seven times less power and occupies 13 times less space. The combination of this new machine and the current MareNostrum system means that the public consortium has tripled the supercomputing resources provided to the Spanish scientific community.
University of Reims joins forces with Bull & Microsoft to make HPC more accessible to SMEs
The University of Reims Champagne-Ardenne, Bull and Microsoft have signed a partnership agreement to provide open access to the University’s new bullx® supercomputer to the widest possible range of users, both from higher education and industry. The new partnership will enable a new hybrid operating environment to be implemented across the entire bullx supercomputer recently acquired by the University of Reims Champagne-Ardenne. The supercomputer, which has been installed at the University’s Champagne-Ardenne Computing Center, delivers some 6 Teraflops of power. Known as 'Clovis', it has significantly increased the capacity of the Computing Center, and is destined to meet the intensive computing needs of researchers and businesses in the Champagne-Ardenne region.
A Bull cluster for Irish researchers
The National University of Ireland in Galway (NUIG) is one of Ireland’s foremost Universities. With over 15,000 students, it has a long established reputation of teaching and research excellence in each of its five Colleges – College of Arts, Social Sciences, & Celtic Studies; College of Medicine, Nursing, & Health Sciences; College of Business, Public Policy, & Law; College of Engineering & Informatics and the College of Science. NUIG decided in favour of a Bull solution for its new HPC system. To run its wide range of applications from different disciplines, with heterogeneous requirements, and runtimes of several hours to a few days, NUIG needed a system with "fat" nodes. They were also interested in developing their expertise in GPU computing.
Making the impossible possible: Cardiff’s High Performance Computer
Can we work out how the stars formed? How the earth’s crust moves? How to improve treatment for cancer patients? How to date an ancient burial site to within a decade? Cardiff University’s High Performance Computer does all of this – and more. Supplied by Bull, the computer is one of the most advanced in the UK academic sector, giving a whole new dimension to Cardiff University research. It is among the most powerful computers in British universities, enabling new research projects which previously were either impossible or would have taken too long to run.
Brazilian federal universities choose Bull supercomputers to host HPC applications
The Brazilian government has acquired two supercomputers for the federal universities, to form part of the National System of High-Performance Processing (Sinapad), encompassing eight supercomputers across Brazil. Bull's supercomputers - delivering some 6.1 teraflops of power - were deployed at the Universidade Federal de Pernambuco (UFPE) and Universidade Federal do Ceará (UFCE) towards the end of 2007. The main areas of scientific research involved are: · Simulations of petroleum reservoirs · Computational chemistry projects · Oceanographic research · Water resources and simulations of the impact of rain on rivers · Visualization projects · Studies on semi-arid climates · Biology and genome projects.
A new bullx supercomputer at the University of Cologne
The Regional Computing Center based at the University of Cologne has acquired a bullx supercomputer dedicated mainly to chemistry, physics and bioscience applications. It has the processing power needed to run numerous new simulations, and also enables many existing simulations to be refined. This bullx system, based on bullx blades, will ultimately provide 100 Teraflops of computing power. In the first phase of this project, the bullx supercomputer consists of 215 computing nodes, equipped with Intel® Xeon® 5500 'Nehalem EP' quad-core processors, and linked via an ultra-fast InfiniBand QDR network. In 2010, Bull will install 602 additional computing nodes. For extremely memory-hungry shared memory applications, four high-end bullx supernodes – each with 128 cores –will also be added.
The University of Münster acquires a 27-teraflops supercomputer from Bull
For the Wilhelms University of Westphalia, based in Münster (Germany), the supersystem marks the “entry into a new era of scientific computing”. When the system reaches its final stage, it will be a hundred times faster than the University’s previous high performance system. In its first phase, installed by Bull in 2009, the University’s supercomputer includes 36 nodes. In its final stage, this high-powered system will be composed of 230 bullx compute blades and a bullx SMP (Symmetric Multi Processing) system. The cluster will then deliver a performance of exactly 27.5 teraflops. Bull won the order for this Extreme Computing system after a European-wide tendering process and careful scrutiny by the University of Münster of the proposals issued by several renowned manufacturers. What made the difference – besides the energy efficiency of the supercomputer – was its high degree of flexibility, which allows it to meet the varied requirements of the different fields of application.
Institute of Cosmos Sciences chooses Bull to create Spain's most powerful Datacenter for cosmology
The Institute of Cosmos Sciences at the University of Barcelona has purchased a Bull supercomputer that will provide it with maximum computing power dedicated to the study of cosmology. The new cluster will enable this center for physical cosmology – led by Professor Licia Verde and Professor Raúl Jiménez – to carry out simulations of the Universe and analyze the cosmology mapping data that it produces. According to Prof. Raúl Jiménez: “The new simulations of the Universe and the data that we will be able to produce using the new Bull supercomputer will enable us to respond to fundamental questions about the origin and evolution of the Universe, and the nature of the dark matter and energy which is speeding up its expansion.”
BBVA relies on a new Bull supercomputer
BBVA's bullx supercomputer will be the fifth most powerful in Spain, and is said to be the country's leading system in the banking sector BBVA will reduce the time taken to run models of complex trend scenarios and financial forecasts by up to three times
Power on demand for Société Générale
Financial services require powerful analysis and modeling tools. To answer these needs, Extreme Computing helps organizations constantly push back the boundaries of computer simulation, modeling and digital analysis. SG CIB, Société Générale Corporate and Investment Banking, was looking for a solution that would give it both the performance it needed and great flexibility of use. So SG CIB turned to Bull, whose HPC-on-demand offering corresponded to its demands: power, flexibility, responsiveness, high levels of security, commitment and cost control. Bull not only provides servers but also network infrastructure, security, hosting and associated services. Not only the architecture itself, but also the way the services are delivered, are set up to absorb Société Générale’s extra demands and respond to peaks in workload, to meet their changing needs, especially when they are carrying out complex calculations around share derivatives or risk management.
Big Data for DNA Sequencing
Leids Universitair Medisch Centrum (LUMC) in the Netherlands retained Bull to help design a Big Data storage environment. Bull assisted LUMC in finding, designing and testing the best storage architecture: the Isilon storage systems, now part of EMC. Bull and LUMC deployed the Isilon cluster, which consists of four 72NL-series nodes. This configuration allows LUMC to address almost 200TB of net storage capacity.
High Performance Computing plays its role in the fight against cancer
New techniques for calculating planned radiation doses delivered in the course of external radiotherapy cancer treatments bring a tremendous increase in precision. However a large amount of compute power is needed to achieve enough precision in an acceptable calculation time for clinical application. This is precisely the issue addressed by Bull’s HPC Centre of Expertise, which studied the problem and delivered a supercomputer adapted to the task in hand. Since it would be impractical for every radiotherapy center to install this kind of computer, it was decided to set up a service that can be supplied on demand to hospitals.
Asco opts for a bullx supercomputer from Bull
Asco – the Belgium-based company that has specialized for almost 60 years in manufacturing spare parts and materials for the aeronautical industry – has chosen a bullx supercomputer to run its simulations. For Bull, this represents its third HPC customer in the Belgian aerospace industry, along with Sonaca and Cenaero. Serviware – Bull’s subsidiary specializing in High-Performance Computing (HPC) solutions – is responsible for the installation and maintenance of the bullx system.
CCRT acquires a new bullx supercomputer to support industrial innovation
AIRAIN, a 200 Teraflops massively parallel supercomputer, was officially unveiled on October 9, 2012 at the Research and Technology Computing Centre CCRT) hosted by CEA near Paris, France. This supercomputer is available to all industry partners members of CCRT, a unique organisation created specifically to support partnerships between research and industry in high performance digital simulation.
Bull to Deliver State-of-the-Art HPC Capability for New MTC Innovation Centre
Bull has been awarded an important contract by the Manufacturing Technology Centre (MTC) to deliver and implement state-of-the-art high performance computing (HPC) equipment and provide associated consultancy and support. The MTC is a non-profit distributing research and technology organisation focused on transferring knowledge to industrial companies and their supply chains in order to help drive the UK’s manufacturing competitiveness. MTC has acquired a HPC facility designed to help develop a comprehensive capability in manufacturing simulation. To support this new focus, MTC needed a partner and provider capable of providing direct access to the component (hardware and software) HPC technology and possessing associated skills in deploying and developing it.
Wirth Research set to race into the future with Bull High Performance Computing
Innovative engineering consultancy group, Wirth Research has signed a partnership agreement with Bull, which will help streamline its engineering design and development capabilities. Under the terms of this long term contract, Bull will deliver high performance computing (HPC) solutions; Panasas ActiveStor™ storage and services to Wirth Research. Bull will also provide consultancy, enabling Wirth to optimise its use of computational fluid dynamics (CFD) within the Bull HPC environment and streamline the design process. Wirth pioneers the use of advanced virtual engineering technologies, developed in-house, and, as part of a partnership with Honda Performance Development Inc (HPD), uses CFD for the design, development and manufacture of its multi championship winning ARX sports cars.
Cenaero has acquired a Bull supercomputer of about 3300 cores
A specialist in modelling methodologies and software for complex industrial problems in various areas of applied mechanics, Cenaero required a new HPC platform to match their rapidly increasing computing needs. Cenaero awarded a public supply contract to ServiWare, a Bull Group company, for the installation of a supercomputer of about 3300 cores supplying a computing power of close to 40 TFLOPS. This supercomputer is housed in a mobile data centre based on the mobull solution developed by Bull, namely a 14 meter-long container able to host eventually 15 IT racks.
Dassault Aviation uses bullx to boost computer simulation
For cutting-edge aeronautical companies, the age of wooden mock-ups and innumerable prototypes is long gone. Nowadays, designing an aircraft is an extremely hi-tech process, and computer simulation is at the very heart of the process. As a major player in both civil and military aeronautics, and a first-rate enterprise in terms of its computerization, Dassault Aviation has a very sophisticated Data Center for its intensive computing. The constant search for greater and greater levels of precision in the simulation of physical properties – these days, several million points are mapped when modeling the structure of an aircraft – requires ever more processing power. Dassault Aviation is constantly upgrading its HPC environment to meet these demands. Most recently, it has been further strengthened with the addition of two bullx clusters.
Bull and AVL together help to reduce the effects of vehicle emissions
AVL, the Austrian automotive software vendor and expert partner to the automotive industry, has chosen a Bull cluster to create a wide range of simulation tools to optimize engine combustion and reduce emissions. AVL is the world's largest privately-owned and independent company for the development of powertrain systems with internal combustion engines as well as instrumentation and test systems. The pressure on the automotive industry to increase both the efficiency and the mileage of their vehicles while reducing the environmental impact of vehicles, especially in the area of emissions, has led AVL to strengthen its business partnership with Bull in the area of advanced simulations.
High-Performance Computing takes off at SONACA with Bull
Belgian aerospace manufacturer SONACA is to use bullx® supercomputers from Bull for its sizing calculations on aeronautical and space structures. More than ever, this makes Bull the strategic IT partner for this hi-tech company, based at Gosselies in the town of Charleroi.
ATEME and Bull partner for extreme performance in transcoding
The combined expertise enables large scale transcoding of video content for multiple screens. ATEME, a world leader in video compression solutions for the broadcast and broadband market, and Bull announced a broadening of their cooperation to market ATEME video processing solutions on bullx blade systems. Introduced by ATEME in 2009, TITAN is a scalable video processing platform, based on bullx blades, that enables massively parallel content transcoding into multiple at a very high degree of fidelity to the original source. It is increasingly popular with content providers and already deployed to deliver linear channels, Video On Demand or Catch Up TV services to the TV sets, PCs, tablets and smartphones of more than 70 million subscribers worldwide.
Planet 51 designed by Ilion Animation Studios on a Bull supercomputer
The design of a 3D animated movie is one of the most intensive computer-aided tasks, both in terms of computing power and hardware ressources. The Planet 51 movie project was born in 2002. Since then, Ilion Animation Studios has created an entire parallel universe around Planet 51 using leading-edge technologies. The result is an incredible visual experience which cannot be compared with any other animated film. Over 350 people from more than 20 countries have worked on Planet 51 – including designers, developers, engineers and many other professionals – with a budget of some $70 million. Ilion Animation Studios, which has designed the 3D animation of Planet 51, has chosen Bull to design and upgrade its server farm dedicated to graphics rendering. “We were impressed by Bull’s remarkable ability to design and configure solutions in extremely critical situations, involving a multitude of systems and, above all, very strict deadlines,” explains Gonzalo Rueda, IT Director at Ilion.
IFP updates its central HPC resources
IFP – a world-class public sector research and training center in France – has recently updated its High-Performance Computing (HPC) resources, in a project which follows the pattern seen in the HPC world since 2003: replacing vector computers with Linux clusters to address all the various needs of research and development. Bull subsidiary Serviware responded to an invitation to tender published by IFP at the end of 2007, to provide significant pre-sales assistance needed to put together a comprehensive solution that met the institute’s needs and was competitive in terms of both price and performance.
Bull supplies a new supercomputer for Petrobras
Petrobras is the leader in the Brazilian petrochemical sector. It operates in the sectors of exploration and production, refining, commerce, transport and distribution of petrochemical products, natural gas, bio-fuel and other renewable energy sources, and ambitions to be among the five biggest integrated energy companies in the world by 2020. CENPES, its Research and Development Centre, has chosen a bullx supercomputer equiped with GPU accelerator technology to develop its of new subsurface imaging techniques using geophysical methods to support oil exploration and production. This supercomputer, with over 250 Teraflops of computing power, will be one of the largest and most powerful computers in Latin America.
DKRZ chooses Bull for its first Pflops-scale supercomputer and for cooperation on climate research
The German computing center for climate research DKRZ (Deutsches Klimarechenzentrum) and Bull have signed a contract for the delivery of a petaflops-scale supercomputer, as well as cooperation on climate research simulation. The contract worth 26 million euro covers the delivery of all the key computing and storage components of the new system.
CSC deploys an energy-efficient Bull supercomputer
CSC- IT Center for Science is deploying a highly energy-efficient supercomputer. The system is built by Bull and co-funded by the European PRACE project. It will be installed in CSC's datacenter in Kajaani. CSC will use the system in collaboration with Finnish researchers and the PRACE community to leverage the latest processing technologies from Intel and Nvidia. These new technologies promise significant improvements in cost-effectiveness and energy-efficiency compared to traditional processors.
A Bull supercomputer for the new Czech national Center of Excellence IT4Innovations
The VSB-Technical University of Ostrava and Bull signed a contract for the supply of a bullx supercomputer, which represents the first step in the creation of the Ostrava-based national supercomputing center. The system, code-named "small cluster", will be delivered at the end of March 2013 and will be available for production starting in May. With this system, Czech science and industry will have at their disposal a machine with a theoretical peak performance of 82.54 TFLOPS. It will help advance development in areas such as nanotechnology, engineering and the transportation industry.
SARA selects Bull for delivery of new petascale national Dutch supercomputer
SARA provides in the Netherlands an integrated national ICT research infrastructure including expertise, services and support in the field of high performance computing. The new system, which will be operational in the first half of 2013, replaces the current IBM system Huygens at SARA. Bull was selected as supplier of the new supercomputer by means of a European tender procedure. The main criteria for the selection of the new system were a performance benchmark with key user applications, efficient energy utilization and cooling, a user-friendly environment and opportunities for flexible, on-demand growth.
French weather forecasting agency orders from Bull its new supercomputers: 5 Pflops by 2016
French weather forecasting agency Météo-France placed a €30.5 M order for Bull’s new-generation supercomputers to deliver total peak power in excess of 5 Petaflops by 2016. bullx supercomputers will be used for weather forecasting and climate research. Featuring a highly innovative liquid cooling system, the bullx B700 DLC supercomputers chosen by Météo-France will have a very limited carbon footprint. The supercomputers will be installed at Météo-France’s site in Toulouse from the first quarter of 2013 onwards, and then at the Espace Clément Ader in Autumn 2013. Equipped with an innovative, high-performance cooling system and the latest generation of Intel® Xeon® processors, the bullx supercomputers will initially deliver processing power of around 1 Petaflops (in 2013-2014), with a total performance of over 5 Petaflops due to be available by 2016.
The Valencia Board of Health, the PFCI and Bull create a Chair in Computational Genomics
The Board of Health in the Spanish region of Valencia, the PFCI (Prince Felipe Research Center) and Bull have signed a collaborative agreement to establish a Chair in Computational Genomics (Study of the genome informations), with the aim of encouraging teaching, research and technology transfer in this area. The aim of the new Chair in Computational Genomics is to develop, produce, apply, innovate and disseminate knowledge and activities related to research in life sciences and computational biology.
New Bull supercomputer powers weather and climate research at Royal Netherlands Meteorological Insti
KNMI, the Dutch national institute for weather, climate research and seismology, has aquired a new Bull supercomputer that is is forty times more powerful than their current system. This offers KNMI more opportunities to issue early warnings in case of extreme weather. It also enhances KNMI's capabilities for climate research. According to Frits Brouwer, KNMI director, KNMI has selected Bull for its comprehensive solution: "The hardware, combined with Bull's knowledge support, gives us confidence in our cooperation. With Bull, we expect to have found the right partner who is able to address our computing needs for the coming years."
Bull, CEA, F4E and JAEA inaugurate the Helios supercomputer dedicated to the Nuclear Fusion program
The supercomputer, installed in Rokkasho (Japan) and delivering over 1.5 Petaflops, will provide the computer modeling and simulation capabilities needed for the 'Broader Approach' program, linked to the ITER initiative. The Helios supercomputer is the third Petascale supercomputer designed and developed by Bull to go into operational production in the past 18 months. In April 2011, the CEA (the French Alternative Energies and Atomic Energy Commission), acting on behalf of F4E (Fusion For Energy), chose Bull to equip the new data center being built at Rokkasho in Japan, under the auspices of the International Fusion Energy Research Center (IFERC). The data center is one of the key components of the 'Broader Approach'; a research program designed to complement ITER and launched in November 2006 as part of a cooperation between Japan and Europe.
CURIE speeds up European research
GENCI's CURIE supercomputer - designed by Bull - opens up unprecedented new possibilities for academic and industrial research in Europe. The equivalent of reading two billion books in just one second: that's the level of performance which the CURIE supercomputer - designed by Bull for GENCI (the French National High-Performance Computing Organization) and now being made available research purposes - is capable of. Over the past two decades, supercomputers have become essential tools for researchers, helping them to model and simulate complex phenomena, in ever more detail, in a way that traditional experimentation could never achieve. The greater the performance and capacity of supercomputers, the more precise and realistic the computer models and simulations become. CURIE - which is capable of up to 2 Petaflop/s - consists of more than 92,000 processing cores, linked to a system that can store 15 Petabytes at a speed of 250Gbit/s.
The Forschungszentrum Jülich chooses Bull to deliver a 200-Tflops supercomputer for JuRoPa
The Forschungszentrum Jülich, Germany's leading HPC center and the instigator of the JuRoPa project, aimed at accelerating the development of high performance cluster computing in Europe, has acquired from Bull a supercomputer with a performance of 200 Teraflops, deployed in 2009 and integrated within the Jülich's datacenter network. The JUROPA project (which stands for "Jülich Research on Petaflops Architectures") was set up by the Forschungszentrum Jülich to investigate emerging cluster technologies and achieve a new class of cost-efficient supercomputers for peta-scale computing.
Catalan high-performance computing center chooses Bull to facilitate research
Since mid-May 2009, users at CESCA (the Catalan intensive computing center) have had access to a new Bull supercomputer for calculation and computer simulation. The installation, code-named Prades, includes 240 processing cores. The system has significantly enhanced CESCA’s computing capacity. Thanks to the new supercomputer, users have an ultra-fast cluster system at their disposal, with shared memory, and featuring an InfiniBand network. Once the installation and benchmarking were completed, even before the system went into full production users were able to see for themselves how the actual system performed. In total, the 14 research groups used over 130,000 hours of computing time in areas including chemical engineering, materials science, astrophysics and pharmacology.
CURIE: the first large scale hybrid system available in PRACE
PRACE welcomes the expansion of the French Tier-0 system, CURIE, with a hybrid fraction. Installed in France at the Très Grand Centre de Calcul (TGCC) operated by CEA near Paris, CURIE is the second PRACE Tier-0 system. Funded by GENCI, as the French representative in PRACE, designed and built by Bull, CURIE has general purpose modular architecture, based on a mix of thin and fat nodes. During the summer of 2011, it was extended with a hybrid fraction. This upgrade was realised by adding 192 Teraflop/s (DP) peak performance provided by 288 nVIDIA M2090 GPUs fitted into 144 Bull B505 blades.
Bull provides supercomputing power to European research into nuclear fusion
Thanks to the Bull supercomputer for the Jülich Research Center, research into nuclear fusion has access to European computer simulation resources for the first time. The Bull HPC-FF supercomputer with 100 Teraflops-capacity hosts applications for the European Union Fusion community. Alongside the Bull JuRoPA supercomputer ordered in 2008, it forms an integrated computing platform delivering more than 300 Teraflops of processing power, taking a lead-position among Europe's supercomputers. HPC-FF will help speed up research into nuclear fusion, and put Europe in the lead when it comes to providing scientific support to the ITER project.
CAPS launches CAPS Compute Lab with BULL and NVIDIA
CAPS Entreprise, the industry leader in development tools for high performance applications, relies on Bull servers for its CAPS Compute Lab, a first and exclusive EMEA solution center for hybrid computing with both BULL and NVIDIA as partners. As the industry is shifting toward hybrid computation technologies, the need for a solution enabling to rapidly and successfully evaluate the performance of software applications has become crucial. CAPS' initiative will help hybrid computing gain momentum, by offering developers an easy and fast way to evaluate and port their applications on a fully operational hybrid system.
German Federal Waterways Institute (BAW) optimizes waterways using a Bull supercomputer
Performance and operating reliability are central to the mission of the Bundesanstalt für Wasserbau (BAW), responsible for one of the most complex tasks in the German High-Performance Computing (HPC) sphere. BAW operates on behalf of the federal administration for navigable waterways and navigation (WSV) in the areas of research and computing. The BAW Institute carries out 2D and 3D modeling of the flows in rivers and canals, models structures that generate currents and analyses the reliability of morphodynamic models.