Category: Supercomputer

Facility built to support Blue Waters supercomputer 11 January 2012 by Yevgeniy Sverdlik Print The National Petascale Computing Facility at the University of Illinois The newly built data center at the University of Illinois that will soon support one of the world’s most powerful supercomputers received LEED Gold certification from the US Green Building Council. Even with 24MW of critical load, the Natio

The National Center for Supercomputing Applications (NCSA) announced that the National Petascale Computing Facility (NPCF) at the University of Illinois has been earned a Gold-level certification under the LEED (Leadership in Energy and Environmental Design) rating program for energy-efficient buildings. Blue Waters Constructed in 2010 the University of Illinois and NCSA opened the NPCF data center as the home to supercomputers and other high-performance systems operated by NCSA and used by scientists and engineers across the country. The Blue Waters project encompassed the NPCF and a 10 petaflop supercomputer, which was initially a venture with IBM. In 2011 NCSA and IBM determined that the project was too complex to proceed. IBM pulled the plug and NCSA later awarded they contract to Cray to build a XE6 system.

The Texas Advanced Computing Center (TACC) at The University of Texas at Austin announced that it is expanding the center’s current high performance computing data center to house the new Stampede supercomputer, which will be built in late 2012 and go into full production to the national science community in January 2013. The $56 million project will encompass a machine room and raised floor expansion, a separate building to include the transformer yard, a location to house the chillers, compressors and cooling towers, a tank for thermal energy storage, and an additional seminar room for training. The funds will also pay for the long-term upgrades to support the infrastructure of future projects. In this video Dan Stanzione, Deputy Director, Texas Advanced Computing Center talks about the power and cooling requirements of the expanded facility. Run time is about 2 minutes, 45 seconds.

Here’s our review of today’s noteworthy links for the High Performance Computing (HPC) industry: Cray delivers first Blue Waters Cabinet. On December 1 Cray delivered the first full cabinet for the NCSA Blue Waters system. A photo gallery of the installation day can be found on the NCSA Facebook album, where in the comments it is confirmed that the cabinets will be water-cooled. The National Science Foundation’s Blue Waters project was awarded to Cray last month after NCSA and IBM terminated the original contract last summer. Dell’s HPC Strategy. The Register reports on how Dell is going to engage the market to grow its HPC strategy. The primary focus for Dell’s HPC strategy is to concentrate on smaller HPC systems where projects are well-bounded with known workloads and customers they know and understand. Dell is putting together recipes for popular HPC apps in small, medium ...

NCSA and Cray announced that they have finalized a contract with the University of Illinois’ National Center for Supercomputing Applications (NCSA) to provide the supercomputer for the National Science Foundation’s Blue Waters project. Back in August NCSA and IBM jointly announced that IBM has terminated its contract with the University of Illinois. The Blue Waters Infrastructure The multi-phase, multi-year project was awarded to Cray for $188 million and will start with a Cray XE6 system, upgrading to the recently announced Cray XK6 with built-in GPU computing capability. Bill Kramer, deputy project director of the Blue Waters project at the NCSA at the University of Illinois, told The Register that Blue Waters was not a specific system, but rather a complete set of infrastructure, including a data center, plus computation, networking, and storage and, most importantly given the software goals of the NCSA, code that scales to real-world petaflops performance.

Airbus, one of the world’s largest aircraft manufacturers, has boosted its supercomputing power with the deployment of a high performance computing cluster housed in two containerized HP Performance Optimized Datacenters (PODs).

IBM has filed a patent for a massive supercomputing system that could reach 107 petaflops, more than 12 times the compute power of the current leader in the Top 500 supercomputer rankings. Powered by Blue Gene Last month IBM unveiled the Blue Gene/P and /Q systems that will use the A2 processing core and achieve upwards of 20 petaflops (quadrillion floating-point operations per second). The new patent describes the interconnected ASIC nodes using a five-dimensional torus network and is listed as being “capable of achieving 107 petaflop with up to 8,388,608 cores, or 524,288 nodes, or 512 racks is provided.”

Can a parking lot be transformed into a high-performance computing cluster in three months? That's what happened last year at the University of Colorado, which used a custom-built modular data center from Dell to deploy the Janus supercomputer, a 184 teraflop cluster on its Boulder campus. Check...

IBM lifted the curtain on its Blue Gene/Q SoC last week in Santa Clara and noted that it will soon be installed in two of the most powerful Blue Gene systems ever deployed. Power 7 vs. SoC With the plug pulled on the 10 petaflop Power7-based Blue Waters for NCSA, IBM is working with two Department of Energy labs for a 10 petaflop ‘Mira’ system at Argonne National Lab and a 20 petaflop “Sequoia” at Lawrence Livermore. The current top supercomputer in the world, the Japanese K, can sustain 8.162 petaflops. The Power-7 chip was set to perform at 256 gigaflops per 8 cores and consume 200 watts, where the Blue Gene/Q SoC will pull 204 gigaflops per processor, with an 18 core count, and consumes 55 watts at peak. With a significant increase in performance the Blue Gene/Q chip delivers 15 times as many peak ...

The NSA's new High Performance Computing Center, slated to be complete by December 2015, will be designed to with energy efficiency, security, and lots of "state-of-the-art" computing horsepower in mind, according to unclassified specs found in the documents, which detail numerous military construction project budgets, including several NSA efforts. NSA has long been a supercomputing powerhouse. The secretive signals intelligence agency purchased the first Cray supercomputer in 1976, and even keeps two Cray supercomputers on display at its National Cryptologic Museum alongside spy gadgets such as centuries-old code books and a working German Enigma machine from World War II. The specs for the new supercomputing center read much like the NSA is building a massive data center, with typical requirements for raised flooring, chilled water systems, fire suppression, and alarms. Power requirements are 60 megawatts, equivalent to the power requirements of Microsoft's recently completed 700,000 square foot ...

We’ve seen a lot of videos that look at various aspects of data center construction, including many time-lapse videos providing an accelerated view of the process. Here’s a new one: a video that focuses on the construction of the data center roof for the new Swiss National Supercomputing Centre (CSCS) in Lugano. This 1-minute clip provides a sense of the infrastructure for a strong roof, which is an important consideration in buildings where heavy equipment will be stored on the rooftop. Each roof beam is 35 meters long and weights 50 tons, and are moved into place by a mobile crane that weighs 380 tons.

Follow Reuters Facebook Twitter RSS YouTube READ Special Report: STD fears sparked case against WikiLeaks boss 07 Dec 20101Spain gets debt warning before EU summit 10:43am EST2Murdered Alabama children were tortured: documents 09 Dec 20103UPDATE 4-Greek police clash with anti-austerity protesters 8:10am EST4Time names Mark Zuckerberg 2010 Person of the Year 9:58am EST5 DISCUSSED 62 WikiLeaks backers hit MasterCard and Visa in cyberstrike 58 Tax deal moves forward despite doubts 56 Democrats defy Obama, oppose tax deal WATCHED The year in 60 seconds Tue, Dec 14 2010 Bejeweled bra exposed in NY Thu, Oct 21 2010 U.S. Navy breaks railgun record Mon, Dec 13 2010 BROKER CENTER Special Advertising Feature Trade Now at Fidelity Biggest Problem for Exascale Computing: Power Tweet This Share on LinkedIn Share on Facebook Digg More from Earth2Tech Abound Solar Snags Ample Funding for 775 MW of Factories 14 Dec 2010 Smart ...

Protecting the world’s forests will be a crucial way to fight climate change, given deforestation contributes to more carbon emissions than all vehicles combined. Now Google has emerged as a key warrior in the deforestation battle. On Thursday morning in Cancun, Mexico at the COP 16 U.N. climate negotiations, the search engine giant unveiled Google Earth Engine, a product which combines an open API, a computing platform and 25 years of satellite imagery available to researchers, scientists, organizations and government agencies. While the software and satellite imagery in Google Earth are already being used to look at world climate change data, Google Earth Engine offers tools and parallel processing computing power to groups to be able to use satellite imagery to analyze environmental conditions in order to make sustainability decisions.

The world's most powerful supercomputer could be the size of a sugar cube and more energy efficient than you might ever imagine. Researchers at IBM's Zurich Labs have developed a prototype supercomputer called the Aquasar that uses a water-cooling principle to keep the system from overheating. The Aquasar is a normal-sized computer; there's nothing tiny about it. But IBM thinks that the water-cooling technology that's proven effective in this supercomputer could work just as well in a vastly smaller machine. The processors in today's computers get very hot, and they have to be cooled off, usually by air. IBM found that using water to cool off a computer's processors is 4,000 times more efficient than using air.

A system from IBM Research is the most energy efficient supercomputer in the world, finishing atop the Green 500 list released today at the SC10 supercomputing conference in New Orleans. The Green 500 list recognizes the systems with the best performance-per-watt to raise awareness about the power consumption of high-performance clusters and “ensure that supercomputers only simulate climate change, not create it.” The IBM Research system proved more efficient than the more powerful Tsubame 2.0 from the Tokyo Institute of Technology, which placed second. The Chinese Tianhe-1A system, which took the top spot in the Top 500 rankings for overall supercomputing power, finished 10th in the Green 500. IBM’s system had a Linpack benchmark of 653 teraflops, but got 1,684 mflops of performance from every watt, easily outdistance Tsubame 2.0′s efficiency of 948Mflops per watt.