When it comes to supercomputing and “green” energy, IBM is marking its spot. A new list shows Big Blue dominating when it comes to energy efficient supercomputers. It has built 90 percent of the Top 20 and 57 percent of the Top100.
The latest Supercomputing Green500 List, distributed by Green500.org, states IBM provides the broadest range of generally applicable supercomputers. A full 18 of the Top20 of the most energy efficient in the world are built on IBM technology, and those supercomputers are being used for everything from pharmaceutical research to climate prediction.
The top energy efficient system is — surprise, surprise — an IBM system built on the vendor’s BladeCenter QS22 being used at the Interdisciplinary Centre for Mathematical and Computational Modeling at the University of Warsaw in Poland. It produces more than 536 Mflops (millions of floating point operations per second) per watt of energy.
The fastest system is also IBM’s, in use at Los Alamos National Laboratories. It’s the fourth ranked energy efficient with 444Mflops per watt.
The second fastest is a Cray system, which ranks 90th on the Green500 List as it produces just 152 Mflops per watt.
An IBM release indicates that efficiency is nearly as important as speed these days when it comes to supercomputing. “Modern supercomputers can no longer focus only on raw performance,” said David Turek, vice president, deep computing, IBM. “To be commercially viable these systems most also be energy efficient. IBM has a rich history of innovation that has significantly increased energy efficiency of our systems at all levels of the system that are designed to simultaneously reduce data center costs and energy use.”
Green500 Rank
MFLOPS/W
Site*
Computer*
Total Power (kW)
TOP500 Rank*
1
536.24
Interdisciplinary Centre for Mathematical and Computational Modeling, University of Warsaw
BladeCenter QS22 Cluster, PowerXCell 8i 4.0 Ghz, Infiniband
34.63
422
2
458.33
DOE/NNSA/LANL
BladeCenter QS22/LS21 Cluster, PowerXCell 8i 3.2 Ghz / Opteron DC 1.8 GHz, Infiniband
138
61
2
458.33
IBM Poughkeepsie Benchmarking Center
BladeCenter QS22/LS21 Cluster, PowerXCell 8i 3.2 Ghz / Opteron DC 1.8 GHz, Infiniband
138
62
4
444.94
DOE/NNSA/LANL
BladeCenter QS22/LS21 Cluster, PowerXCell 8i 3.2 Ghz / Opteron DC 1.8 GHz, Voltaire Infiniband
2483.47
1
5
428.91
National Astronomical Observatory of Japan
GRAPE-DR accelerator Cluster, Infiniband
51.2
277