insideHPC » New Installations

Boomer Super Comes Online at University of Oklahoma

Rich Brueckner — Thu, 24 May 2012 15:28:51 +0000

The University of Oklahoma powered up its new Boomer supercomputer today. The 109-Teraflop Dell system will power a variety of research with emphasis on weather forecasting, molecular dynamics and high-energy physics.

For the past decade, OU has been a national leader in supporting the computational research and education needs of local students, faculty and staff,” said Henry Neeman, Director of the OU Supercomputing Center for Education and Research. “We’re extremely proud to expand a great tradition with this fourth generation OU IT supercomputer, which will enhance research capabilities by connecting scientific collaborators throughout the state and nation.”

Read the Full Story.

ARCHIE Boosts Research at Scottish Universities

Rich Brueckner — Wed, 23 May 2012 17:50:40 +0000

A high-performance computer that can tackle complex calculations to solve major challenges in science and engineering, including drug development, energy systems and space technologies research, has been installed at the University of Strathclyde, UK.

The computer is at the core of a new £1.6 million regional Supercomputing Centre, funded by the Engineering and Physical Sciences Research Council (EPSRC), which will help academics further their research and support business and industry through the next generation of product design and development.

Professor David Littlejohn, associate deputy principal at the University of Strathclyde, said: ‘The new centre will make a step-change in high-performance computing provision for Scotland, helping researchers to work with industrial colleagues from around the world to develop and test innovative new products and technologies.

‘Our plans for the centre have received overwhelming support from industry, and we are delighted that the EPSRC has chosen to invest in our infrastructure and the work of our internationally leading scientists and engineers.’

The advanced computer is known as ARCHIE (Academic and Research Computer Hosting Industry and Enterprise), and was the result of a successful funding bid submitted by scientists Professor Littlejohn, Professor Maxim Federov and Dr Richard Martin, and engineers Professor Jason Reese and Dr Paul Mulheran.

The funding will enable multidisciplinary researchers at the Universities of Strathclyde, Glasgow, Glasgow Caledonian, Stirling and the University of the West of Scotland to access the Supercomputing Centre and link up with other supercomputing centres around the world.

They will work with public and private sector partners in a wide range of research areas, including the purification of seawater, renewable energy, the next generation of mobile communications and improved air transport systems.

This story originally appeared on HPC Projects. It appears here as part of a cross-publishing agreement with Scientific Computing World.

Podcast: Spectra to Deliver 380 Petabytes of Tape Storage to Blue Waters

Rich Brueckner — Tue, 22 May 2012 16:05:04 +0000

In this podcast, Michelle Butler from NCSA and Molly Rector from Spectra Logic discuss the massive tape storage system that is being deployed for the 10 Petaflop Blue Waters supercomputer. As announced this week, the Blue Waters system will be one of the world’s largest active file repositories stored on tape media and will scale to a capacity of 380 raw petabytes within the first two years of operation.

NCSA designed Blue Waters to be one of the largest, most powerful supercomputing ecosystems in the world,” said Bill Kramer deputy director of the Blue Waters project at the National Center for Supercomputing Applications at the University of Illinois at Urbana-Champaign. “The Spectra Logic T-Finity met our rigorous requirements with its high enterprise-level performance, ready data accessibility and massively scalable capacity. We are confident it will provide our user community with fast, reliable access to the massive volumes of critical data stored within Blue Waters’ Petascale near-line file repository.”

Spectra T-Finity tape libraries will provide the Blue Waters project with the ability to keep all near-line data accessible in an active repository, perform automated data integrity verification for the data store, and deliver high performance read/write rates of up to 2.2 PBs per hour utilizing enterprise TS1140 Technology tape drives.

Read the Full Story * Download the MP3 * Subscribe on iTunes * If Dropbox is blocked, download from this Google page.

Kenya’s First Home-Grown Supercomputer

Rich Brueckner — Thu, 17 May 2012 16:36:48 +0000

Mbugua Njihia writes that a team of developers with financial backing from Google are working on Kenya’s first locally assembled supercomputer. And while the project has been underway for a while now, the potential benefits of HPC for the region are just beginning to sink in.

High performance computing can make money by doing the heavy lifting and thereby improving efficiencies across all sectors of the economy and this initiative will be one to keep an eye on; the spin-offs may just prove to be interesting.”

Read the Full Story.

Green Revolution Deploys Liquid-Submersion-Cooled Super for Oil & Gas

Rich Brueckner — Mon, 30 Apr 2012 15:51:44 +0000

Remember the CRAY-2? Heather Clancy over at ZDNet writes that liquid-submersion cooling is making a comeback in high-density computing.

Green Revolution Cooling, which develops fluid submersion cooling system for high-performance servers, has just finished the largest installation of its technology in Houston. The customer is CGGVeritas, which uses 1U dual-GPU SuperServers from Super Micro Computer to run data-intensive geophysical applications, such as seismic survey analysis. Each of the racks at CGGVeritas contains 40 servers, with 41K GPU cores. According to Green Cooling Revolution, the installation has helped reduce the power used in the data center by 40 percent.

Read the Full Story.

Containers Power Thor Datacenter in Iceland

Rich Brueckner — Fri, 27 Apr 2012 14:11:18 +0000

The Thor Data Center in Iceland is hosting a new container-based supercomputer. As a collaboration of National High Performance Computing organisations of Denmark, Norway, Sweden and Iceland, the new datacenter was designed with Green Computing in mind.

Due to growing power consumption, supercomputing costs are an increasing economic burden for researchers and their universities; however, Iceland is an attractive location, with powerful natural resources providing very low-cost electricity and cost-efficient cooling solutions.

Read the Full Story.

10 Petaflop Mira Super Coming to Argonne

Rich Brueckner — Fri, 27 Apr 2012 13:20:30 +0000

Mira is a red giant star estimated 200-400 light years away in the constellation Cetus. Closer to home, Mira is also a 10 Petaflop supercomputer that is due to arrive at Argonne National Lab during the second half of 2012.

David Bader, director of the Georgia Institute of Technology High Performance Computing Center, calls the Blue Gene/Q “revolutionary.” It’s impossible to watch a star explode in person, but Mira’s supercharged resolution could simulate a supernova “down to the sub-millimeter level,” Bader explains. “We’re talking about simulations even more detailed than the human eye can perceive.” His group will get in line to use Mira soon.

Read the Full Story.

Russia Turns to HPC to Revive National Defense Industry

Rich Brueckner — Sat, 21 Apr 2012 15:16:00 +0000

This week Russian HPC vendor T-Platforms announced it has launched the first phase of a new data center for the “Burevestnik” Central Research Institute designed for modeling samples of artillery weapons with the use of HPC technology. The institute will upgrade to a T-Platforms hybrid supercomputer with 50 Terflops of compute power powered by GPUS, multi-core X86 processors, Panasas storage, and integrated 10GbE technology.

Our Institute makes technically sophisticated products which will reliably serve our forces for many decades in the harshest conditions,” said Georgy I. Zakamennyh, DPhil, Professor, General Director of CNII “Burevestnik” JSC, and Russian Federation Artillery Armament Chief Designer. “Research and development work to design new types of weapons requires costly full-scale tests,” he added. “Over the last decade, CNII “Burevestnik” has created an integrated information framework providing automation of all business processes and information support for the full product life cycle. The use of information systems for enterprise resource planning and product information management has greatly improved the productivity and output.”

Read the Full Story.

Fujitsu Wins Hybrid Super Deal in Japan – Sparc, x86, and GPUs

Staff — Thu, 05 Apr 2012 12:00:03 +0000

By Timothy Prickett Morgan • Get more from this author

Japanese IT conglomerate Fujitsu has been pushing hard to peddle its Sparc and x86 supercomputer clusters to take on IBM, Cray, Silicon Graphics, and others, and not surprisingly Fujitsu it has scored some big deals in the home country. The company just took down a big hybrid Sparc-x86 cluster deal at Kyushu University, which is the dominant educational institution in the southern part of Japan.

Like the 1.13 petaflops “Oakleaf-FX” machine that was just fired up this week at the University of Tokyo, the new machine going into Kyushu University will be compatible with the 10.5 petaflops massively parallel Sparc64 machine known as K that was built by the Japanese government and that has been the most powerful machine in the world for the past year. And like the University of Tokyo, Kyushu University was also a user of IBM’s parallel clusters, in this case a Power6-based system based on Power6 processors that is resold by Hitachi as the SR16000 rated at 25.3 teraflops.

Kyushu University also had a 64-engine VPP5000/64 vector supercomputer made by Fujitsu rated at a comparatively tiny 563 gigaflops and an old PrimeQuest Itanium cluster rated at 10.9 teraflops. The largest machine in its data center is a cluster of Primergy RX200 S6 rack servers with 4,704 Xeon cores that is rated at 50.2 teraflops. Add it all up and this is no big deal in today’s petaflops era.

But Japan, like the United States, China, and Europe, is on an upgrade wave in the HPC data center, and the hybrid Kyushu University machine, which has not yet been nicknamed, will weigh in at a combined 691.7 teraflops across the Sparc and Xeon nodes used for computation, and that is perfectly respectable.

On the Sparc side of the system, Kyushu University is getting eight racks of the PrimeHPC FX10 system, which is a modified version of the K super that uses a 16-core Sparc64-IXfx processor instead of the older eight-core Sparc64-VIIIfx used in the K machine. The Sparc side of the machine will have 768 server nodes with a total of 24TB of main memory and will of course use the “Tofu” 6D mesh/torus interconnect to link those nodes together.

The PrimeHPC FX10 setup will be back-ended with 44 of Fujitsu’s Eternus storage arrays with a total of 576TB of capacity and running the Fujitsu Exabyte File System (FEFS), a variant of the Lustre cluster file system that was designed to span 100,000 nodes. The machine is front end-end by 22 Primergy x86 servers that are used as log-in and management nodes. This part of the hybrid machine will have a peak theoretical performance of 181.8 teraflops.

The bulk of the raw math in the Kyushu University system comes from a cluster of Fujitsu density-optimized CX1000 machines, which were first announced two years ago with the Xeon 5600s. The CX1000 machines were updated in March with CX400 enclosures sporting Intel’s new Xeon E5-2600 processors, and the system has 1,476 two-socket nodes that together have 184.5TB of main memory and deliver 510.1 teraflops of peak performance on double-precision math. This machine is also using FEFS on a cluster of 74 Eternus storage units with a total of 4PB of capacity and is front-ended with 44 Primergy rack servers used to manage access to the cluster.

The whole shebang will presumably run Linux – Kyushu University didn’t say – but there is obviously the option of running Solaris on the Sparc side and Windows HPC Server 2008 on the x86 side.

Later this year, when the machine has been up and running for a bit, Kyushu University will be slapping some GPU coprocessors into the box to boost its performance, very likely through the petaflops barrier and possibly as high as many petaflops. If the university waits for the “Kepler” Tesla GPUs from Nvidia – and those CX400 enclosures have room – then Kyushu University could be sitting near the top of the Top 500 supercomputer rankings by the fall, instead of near the bottom as it is with its current Primergy cluster. ®

This article originally appeared in The Register. It appears here in its entirety as part of a cross-publishing agreement.

First Simulation Images from Blue Waters Super

Ralph — Thu, 05 Apr 2012 11:00:01 +0000

While the Blue Waters Cray XK6 system won’t come fully online until later this year, NCSA staff members are already performing application tests to ascertain Blue Waters’ system and application performance.

These tests, done in collaboration with the early science users, have produced datasets that are in turn being used by the Blue Waters visualization staff to test scalable visualization tools. Such tools enable science teams to explore the very large volumes of data they will produce on the full Blue Waters system. While the early visualization work is mostly concerned with software functionality, it is providing tantalizing glimpses of the early science.

Read the Full Story.

Petaflop Fujitsu Sparc Super Delivers Extreme Efficiency at University of Tokyo

Rich Brueckner — Mon, 02 Apr 2012 18:00:27 +0000

Today Fujutisu announced that the new Oakleaf-FX supercomputer has begun opeation at the University of Tokyo’s Information Technology Center. Based on the SPARC64 IXfx processor (an enhanced version of the SPARC processor used in the #1 K Supercomputer), the 1.13 Petaflop system achieves high energy efficiency with just 1.4 MW overall system power consumption.

The PRIMEHPC FX10 supercomputer system will contribute to advancements in various types of research and development activities by users from both academia and industry,” said Kengo Nakajima, Director, Supercomputing Division, Information Technology Center, The University of Tokyo. “Oakleaf-FX will be used for the HPC education program in the Graduate School of the University of Tokyo for future computational scientists. Oakleaf-FX will be operated so that priority is given to larger-scale jobs. Furthermore, a new project, called “Large-Scale HPC Challenge” is also starting. Members of a group whose proposal has been accepted can occupy all computing nodes (4,800 nodes, 1.13 PFLOPS) of the FX10 system for 24 hours. One proposal is selected per month.”

Read the Full Story.

260 Tflop Abel Supercomputer Coming to University of Oslo

Rich Brueckner — Fri, 30 Mar 2012 16:46:43 +0000

Today the University of Oslo announced that it will install a 260 Teraflop supercomputer named after famed Mathematician Niel Henrick Abel. The system will be provided by Megware and will be used for a wide range of research with demanding data handling applications.

The Abel system will strengthen the University of Oslo’s position as a leading European research university”, says UiO IT-director Lars Oftedal. “Abel is designed for running a large number of concurrent tasks with large datasets and/or memory requirements. Such applications are found in an increasing number of research disciplines, but in particular in life sciences (bioinformatics), climate research and high-energy physics.”

The Abel system is to be installed in June 2012. Read the Full Story.

Rutgers Launches HPC Center for Big Data

Rich Brueckner — Tue, 27 Mar 2012 11:57:41 +0000

Today Rutgers launched a new HPC center at the university focused on the application of Big Data analytics in life sciences, finance, and other industries. As part of the newly created Rutgers Discovery Informatics Institute, the new HPC center will utilize supercomputing equipment and software provided by IBM.

There is immense potential here because Rutgers and IBM have some of the best minds in high-performance computing,” said Michael J. Pazzani, vice president for research and economic development and professor of computer science at Rutgers. “The ability to conduct data analysis on a large scale, leveraging the power of ‘big data,’ has become increasingly essential to research and development.”

www.youtube.com/watch?v=zYxnuznv0cc

Read the Full Story.

OSC Oakley Cluster Gets its Guns

Rich Brueckner — Tue, 20 Mar 2012 10:40:32 +0000

After 25 years of service, the Ohio Supercomputer Center has fired up a powerful new supercomputer named after the famous American sharpshooter, Annie Oakley. The 154 Teraflop Oakley Cluster is a hybrid HP system powered by 8328 Xeon x5650 cores, 128 Tesla M2070 GPUs, and the Lustre file system.

The new system provides nearly twice the memory per core (4 gigabytes) and three times the number of graphic processing units or ‘GPUs’ (128). The Oakley Cluster also provides researchers with one and a half times the performance of the Glenn Cluster at just 60 percent of Glenn’s power consumption and will expand OSC storage to nearly two petabytes with the addition of 600 terabytes of new DataDirect Lustre storage.

Read the Full Story.

Interview: Michael Resch on the Hermit Super at HLRS

Rich Brueckner — Tue, 13 Mar 2012 07:01:38 +0000

A few weeks ago, Stuttgart’s Center for High Performance Computing (HLRS) held an inauguration ceremony for Hermit, the fastest supercomputer in Germany. With over 1 Petaflop of performance, this “industrial supercomputer” will be also used for health, energy, environment and mobility research.

To learn more, I caught up with Prof. Michael Resch from HLRS.

insideHPC: The stunning graphical images painted on the front of Hermit suggest that machine is all about industrial simulation. What was the thinking behind that effort?

Michael Resch: The machine has two sides. One of them shows the industry related applications the other one shows the more scientific ones. It is because of the better light on the industrial side that photographers always pick the industrial one. The thinking behind out design was to show on the outside of the machine what is going inside the machine. Given our focus on engineering applications we ended up with a lot of applications from engineering that are by nature also industrial applications.

insideHPC: Hermit is the largest civil computer in Europe. What is its primary mission?

Michael Resch: The primary mission of Hermit is to provide researchers all over Europe with access to a new platform. The system was chosen specifically with engineering applications in mind. This is where HLRS has a well established reputation in Europe.

insideHPC: Does the Hermit name have something to tell us about that mission?

Michael Resch: The name Hermit does have a history. It actually has a double meaning. First it stands for the hermit beetle which is a symbol for the environmental problems the region of Stuttgart is facing. The system will contribute to an ecological turn around in the field of energy supply and mobility and hence we gave it a name of an endangered species which can be found in the region of Stuttgart. On the other hand the name naturally suggests that our Cray XE6 is a hermit-like installation. Most of its time running in the dark but spending time on “thinking” about the most important problems in the world.

insideHPC: Proposing, procuring, and deploying a supercomputer of this scale is undoubtedly a monumental task, but does the hard work really begin now that the system is operational?

Michael Resch: That is a discussion that we always have during such procurements. The procurement is just a part of the overall hard task. We do not see operation and procurement as separate activities. These things have to go hand in hand – both for users and ourselves. The hard part that comes after the installation is the work on the user applications. We have established a Cray Center of Development at Stuttgart such that we will have a lot of support for our users.

insideHPC: As one of the premier supercomputer centers in Europe, what will HRLS be looking to accomplish at ISC’12 this year?

Michael Resch: ISC 2012 is the place for us to showcase our achievements in Europe. This year we will focus on success stories of Hermit. There are already some exciting results that will draw your attention. So make sure to join us at Hamburg.

2 Petaflop FERMI Super to Power CINECA Consortium

Ralph — Thu, 08 Mar 2012 15:28:50 +0000

Based on IBM BG/Q architecture, the new supercomputing system in CINECA, the Italian supercomputing centre, will replace the IBM SP6 supercomputer when it is installed this spring, becoming fully operational in August 2012. Dubbed FERMI, this new system is composed of 10.240 PowerA2 sockets running at 1.6GHz, with 16 cores each, totalling 163.840 compute cores and a system peak performance of 2.1 petaflops. Each processor comes with 16Gbyte of RAM (1Gbyte per core). The BG/Q system will be equipped with a high-performance scratch storage system with a capacity of 2 Pbyte and a bandwidth in excess of 100 Gbyte/s.

From the mandate of the Italian Ministry of Education University and Research, CINECA represents Italy in PRACE (the Partnership for Advanced Computing in Europe). CINECA becomes a Tier-0 site as described in the PRACE roadmap. Access to FERMI will be on the basis of national and European calls for proposals. ISCRA (Italian Super Computing Resources Allocation) and PRACE will manage the access to the Tier-0 supercomputer by the way of international peer-review procedures ensuring world-class research is carried out that will be competitive worldwide.

Marco Lanzarini, director of CINECA, commented: ‘As director of CINECA I am extremely proud that this impressively large Italian supercomputer will represent an effective reply to the growing demand from national and European academia, research institutions and industries for petascale computing capabilities. The installation of this new powerful Italian infrastructure will strengthen the position of the PRACE consortium and reinforce Europe’s competitiveness in the race to exascale.’

This article originally appeard in Scientific Computing World’s HPC Projects. It appears here in its entirety as part of cross-publishing agreement.

Video: Blue Waters Completes Early Science System Installation Phase

Rich Brueckner — Sat, 03 Mar 2012 17:42:38 +0000

UI Blue Waters Supercomputer from UI-7 News on Vimeo.

In this video, Sam Kargol from UI-7 News interviews Klaus Schulten and about “early science system” deployment of the Blue Waters supercomputer at NCSA. Cray has installed approximately 15 percent of the hardware for the system, which is expected to be fully deployed in late 2012.

Blue Waters will be composed of more than 235 Cray XE6 cabinets based on the recently announced AMD Opteron™ 6200 Series processor (formerly code-named “Interlagos”) and more than 30 cabinets of a future version of the recently announced Cray XK6 supercomputer with Nvidia Tesla GPU computing capability.

Jaguar Jumps to 3.3 Petaflops with Phase 1 Titan Upgrade

Rich Brueckner — Fri, 02 Mar 2012 16:58:51 +0000

The most powerful supercomputer in the U.S. just got a lot faster. ORNL has completed the first phase of Titan supercomputer transition with its upgrade of Jaguar to 3.3 Petaflops. When the upgrade process is completed this autumn, the system will be renamed Titan and will be capable of 10 to 20 petaflops.

Completed ahead of schedule, the Jaguar upgrade included new AMD Opteron processors (now totaling 299,008 cores), an upgraded Gemini system interconnect, and a doubling of system memory to 600 Terabytes. In addition, 960 of Jaguar’s 18,688 compute nodes now contain an Nvidia GPU in anticipation of a much larger GPU installation later in the year.

This is going to be an exciting year in Oak Ridge as our users take advantage of our new XK6 architecture and get ready for the new NVIDIA Kepler GPUs in the fall,” Wells said. “A lot of work by many people is beginning to pay off.”

Read the Full Story.

Hermit Fires Up as Fastest Civil Supercomputer in Europe

Rich Brueckner — Fri, 24 Feb 2012 16:33:01 +0000

This week Stuttgart’s Center for High Performance Computing (HLRS) held an inauguration ceremony for Hermit, the fastest supercomputer in Germany. With over 1 Petaflop of performance, this “industrial supercomputer” will be also used for health, energy, environment and mobility research.

Supercomputers like Hermit contribute to strengthening Germany’s position as a research pole. Computer simulations have evolved to be the third pillar of science, together with theory and experimentation. Many research areas can no longer do without it; a good example being health, energy, environment protection, and mobility. Those are themes which the federal government supports inside the high-tech strategy,” says, Prof. Dr. Annette Schavan, Federal Minister of Education and Research. “Great computer resources have also become an important means for the industry for the ability of shortening development time. With the commissioning of the supercomputer Hermit in Stuttgart, we continue the expansion of the national high performance computing centre, the ‘Gauss Centre for Supercomputing’, which is already a big success. Germany will maintain a leading position in supercomputing and become more attractive to excellent scientists from all over the world.“

Read the Full Story.

PRACE Boosts Bull’s CURIE Supercomputer to 2 Petaflops

Rich Brueckner — Thu, 16 Feb 2012 18:37:24 +0000

This week European PRACE Research Infrastructure announced that the 2 Petaflop CURIE supercomputer is now fully operational with 92,000 processor cores. An open house event will celebrate the deployment of the system, which will be completely opened to scientists on March 1st, 2012.

Thanks to CURIE, the European HPC capacity available through PRACE is now doubled. This capacity will help Europe lead the world in the quest for suitable solutions to societal challenges such as population ageing, climate change and energy efficiency”, said Nellie Kroes, Vice-president of the European Commission for the Digital Agenda.

Europe is definitely stepping up on the world stage for HPC. This week the European Commission announced plans to double its funding of high-performance computing. Read the Full Story.