From Deep Blue, the computer that defeated Garry Kasparov in a 1997 chess match, to the new Blue Gene® line of high-performance computers created by IBM, a single color has traditionally been associated with advanced computing.
With the recent opening of the Argonne Leadership Computing Facility (ALCF) at the U.S. Department of Energy's Argonne National Laboratory, however, high-performance computing has taken on a different hue: green. Several innovative steps designed to maximize the efficiency of Argonne's new Blue Gene/P high-performance computer have saved many taxpayer dollars while reducing the laboratory's environmental footprint.
While similar computing centers at other laboratories and institutions often require several megawatts of electricity – enough to meet the energy demands a small town – the ALCF needs only a little more than one megawatt of power. "Because the ALCF can effectively meet the demands of this world-class computer, the laboratory ends up saving taxpayers more than a million dollars a year," said Paul Messina, director of science at the ALCF.
The Blue Gene/P currently runs at a speed of more than 557 teraflops, which means that it can complete more than 557 trillion calculations per second. While several high-performance computing facilities recently established or upgraded at some of Argonne's sister laboratories have surpassed that mark, only one exceeds the efficiency of Argonne's Blue Gene/P. "The Blue Gene/P uses about a third as much electricity as a machine of comparable size built with more conventional parts," Messina said.
While a megawatt of electricity might seem like a lot of power, the massive number of computations that the Blue Gene/P can do puts it in perspective. Energy efficiency of high-performance computers is measured in flops per watt – how many calculations per second the computer can do for every watt of electricity it uses.
According to the November 2008 Green500 ranking of supercomputers, the Blue Gene/P's energy efficiency averages out to more than 350 million calculations a second per watt. By contrast, a common household light bulb frequently uses between 50 and 100 watts of electricity. Among the top 20 supercomputers in the world, the Blue Gene/P is the second-most energy-efficient. "The fact that we are running such a powerful computer so efficiently shows that we can simultaneously respond to the demands of the advanced simulation and modeling community and the environmental concerns of today's society," Messina said.
Much of the electricity that the Blue Gene/P requires is used not to actually process the computations, but rather to cool the machinery. Without any cooling at all, the room that houses the computer would reach 100 degrees within ten minutes after the computers started running.
To keep the facility cool and safe, six air handlers move 300,000 cubic feet of air per minute under the floor, keeping the room chilled to 64 degrees Fahrenheit. These air handlers, according to Messina, cool more cost-effectively than large air conditioners used at other facilities. "Many other high-performance computing centers require as much electricity to cool their computers as they do to operate them, but here at Argonne we need only an additional 60 percent," he said. "We not only have a green computer, we have an entire green facility."
Argonne National Laboratory seeks solutions to pressing national problems in science and technology. The nation's first national laboratory, Argonne conducts leading-edge basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of companies, universities, and federal, state and municipal agencies to help them solve their specific problems, advance America 's scientific leadership and prepare the nation for a better future. With employees from more than 60 nations, Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy's Office of Science.
Eleanor Taylor | Newswise Science News
Dispersal of Fish Eggs by Water Birds – Just a Myth?
19.02.2018 | Universität Basel
Removing fossil fuel subsidies will not reduce CO2 emissions as much as hoped
08.02.2018 | International Institute for Applied Systems Analysis (IIASA)
Animal photoreceptors capture light with photopigments. Researchers from the University of Göttingen have now discovered that these photopigments fulfill an...
On 15 March, the AWI research aeroplane Polar 5 will depart for Greenland. Concentrating on the furthest northeast region of the island, an international team...
The world’s second-largest ice shelf was the destination for a Polarstern expedition that ended in Punta Arenas, Chile on 14th March 2018. Oceanographers from...
At the 2018 ILA Berlin Air Show from April 25–29, the Fraunhofer Institute for Laser Technology ILT is showcasing extreme high-speed Laser Material Deposition (EHLA): A video documents how for metal components that are highly loaded, EHLA has already proved itself as an alternative to hard chrome plating, which is now allowed only under special conditions.
When the EU restricted the use of hexavalent chromium compounds to special applications requiring authorization, the move prompted a rethink in the surface...
At the ILA Berlin, hall 4, booth 202, Fraunhofer FHR will present two radar sensors for navigation support of drones. The sensors are valuable components in the implementation of autonomous flying drones: they function as obstacle detectors to prevent collisions. Radar sensors also operate reliably in restricted visibility, e.g. in foggy or dusty conditions. Due to their ability to measure distances with high precision, the radar sensors can also be used as altimeters when other sources of information such as barometers or GPS are not available or cannot operate optimally.
Drones play an increasingly important role in the area of logistics and services. Well-known logistic companies place great hope in these compact, aerial...
16.03.2018 | Event News
13.03.2018 | Event News
08.03.2018 | Event News
16.03.2018 | Earth Sciences
16.03.2018 | Physics and Astronomy
16.03.2018 | Life Sciences