HPCwire: ALCF Working to Get More Science Per Watt

King Abdullah University of Science and Technology

Since 1986 - Covering the Fastest Computers
in the World and the People Who Run Them

Translation Disclaimer

Subscribe | Sign In

Visit additional Tabor Communication Publications

Leading HPC
Solution Providers

April 14, 2009

ALCF Working to Get More Science Per Watt

ARGONNE, Ill., April 14 -- Cooling a supercomputer consumes more electricity than is required to run the machine, even machines as powerful as the IBM Blue Gene/P -- called Intrepid -- at the U.S. Department of Energy's (DOE) Argonne National Laboratory. Though Intrepid is one of the fastest and most energy-efficient computers in the world, researchers at Argonne's Leadership Computing Facility (ALCF) are continually looking for ways to further reduce the power needed to operate the machine.

"Electricity should never be wasted," said Pete Beckman, director of the ALCF. "Each improvement to our power efficiency makes us more environmentally friendly, reduces our carbon footprint and saves taxpayer dollars."

In the winter the ALCF saves as much as $25,000 every month in electricity costs by leveraging the Chicago area's cold climate to chill the water used to cool Intrepid for free. That is in addition to the millions of dollars saved by the energy-efficient architecture of the Blue Gene/P, which uses about one-third as much electricity as a comparable supercomputer.

The latest in a series of energy-efficient innovations at the ALCF focuses on cooling the machine itself. Varying the chilled water temperature to match the demand of the machine allows the chillers to use less energy. This effort involves mapping the optimum chilled water temperature to the machine load to determine the sweet spot for energy-efficient cooling.

"The trick," said Jeff Sims, ALCF project manager, "is to find the warmest chilled water temperature you can live with at a given machine load, thus reducing the electric load on the chillers and maximizing the free cooling period. While the energy consumed to cool the machine has been reduced, there has been no impact on Intrepid's performance."

It is still too early in the process to calculate the exact energy savings, but the change is noticeable. As data are collected and analyzed, the ALCF team will start experimenting with the temperature of the datacenter itself to see how far the temperature can be pushed without causing any degradation of the system.

Other enhancements include using smart power management functions to turn off chips and storage systems when they are not in use, as well as scheduling intensive compute jobs to run at night when the power grid has more capacity and temperatures are lower.

"Supporting breakthrough science is our main goal at the ALCF," added Sims. "We will not sacrifice performance for energy efficiency, but we will keep trying everything we can to reduce power consumption. Every little bit helps."

As Argonne continues to focus on energy-efficient enhancements today, it also has an eye to the future. Currently, Argonne is working with IBM and Lawrence Livermore National Laboratory in designing the next-generation supercomputer platform.

"Energy efficiency and computational power are not mutually exclusive," said Beckman. "Future supercomputers will push performance boundaries and deliver unprecedented design innovations that will use merely a trickle of the electricity that is required today."

The team successfully worked together in designing the initial Blue Gene system from the ground up specifically for scientific applications. The architecture of each supercomputer processor board was designed to reduce energy consumption, translating into its low-power, system-on-a-chip architecture and communications fabric. This approach enables science applications to efficiently scale to the highest performance by increasing the system's parallelism and using more power-efficient voltages and clock speeds.

The ALCF is a leadership-class computing facility that enables the research and development community to make innovative and high-impact science and engineering breakthroughs. Through the ALCF, researchers conduct computationally intensive projects on the largest possible scale. Argonne operates the ALCF for the DOE Office of Science as part of the larger DOE Leadership Computing Facility strategy. DOE leads the world in providing the most capable civilian supercomputers for science.

About Argonne National Laboratory

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.

-----

Source: Argonne National Laboratory

Share Options

Subscribe

Subscribe to HPCwire

Discussion

There are 0 discussion items posted.

Join the Discussion

Become a Registered User Today!

Registered Users Log in join the Discussion

RSS Feeds

Feeds by Topic

Feeds by Industry

Feeds by Content Type

Subscribe to All Content

All

May 23, 2012

May 22, 2012

May 21, 2012

May 18, 2012

May 17, 2012

May 16, 2012

May 15, 2012

May 14, 2012

May 11, 2012

Feature Articles

NVIDIA Works On CPU Co-Dependency Issues with Kepler GPU

NVIDIA is telling everyone that the GK110, its new Kepler GPU aimed at supercomputing, is all about improving performance per watt. But the other driving theme behind the new architecture is reducing the GPU's reliance on its CPU host. How well it accomplishes both these goals areas could determine the success of the new chip in high performance computing.
Read more...

OpenACC Starts to Gather Developer Mindshare

PGI, Cray, and CAPS enterprise are moving quickly to get their new OpenACC-supported compilers into the hands of GPGPU developers. At NVIDIA's GPU Technology Conference this week, there was plenty of discussion around the new HPC accelerator framework, and all three OpenACC compiler makers, as well as NVIDIA, were talking up the technology.
Read more...

NVIDIA Launches Kepler Into HPC

NVIDIA has introduced its first Kepler-generation GPU product for high performance computing, and revealed some of the inner working of the new architecture. The announcement took place at the kickoff of the company's GPU Technology Conference taking place this week in San Jose, California.
Read more...