NVIDIA Tesla GPUs Used to Deploy New World's Fastest Supercomputer
Singapore – NVIDIA has just announced that the world’s premier open science computing facility for the U.S. Department of Energy, Oak Ridge National Laboratory (ORNL), will be using Tesla GPUs to deploy the new world’s fastest supercomputer.
Codenamed Titan, this Cray XK6 supercomputer will have the potential to deliver over 20 petaflops of peak performance, which is two times faster and three times more energy efficient than today’s fastest
supercomputer, the K Computer, located in Japan.
Once fully deployed, this new tool will be used for research in a broad range of fields, including material science, energy technology, medical research, geoscience, and others.
Currently, the first phase of Titan deployment is already underway, with the existing Jaguar supercomputer being upgraded with 960 Tesla M2090 Fermi GPUs, which will serve as companion processors to the multi-core CPUs. The second phase, which is expected to begin in 2012, will see ORNL deploying 18,000 Tesla GPUs that run on the next-generation architecture, Kepler.
“Oak Ridge’s decision to base Titan on Tesla GPUs underscores the growing belief that GPU-based heterogeneous computing is the best approach to reach exascale computing levels within the next decade,” said Steve Scott, Chief Technology Officer of Tesla Products at NVIDIA, referring to computing performance levels of 1,000 petaflops. “The Tesla GPUs will provide over 85 percent of the peak performance of Titan. You simply can’t get this level of performance in a power- and cost-efficient way with CPUs alone.”
For more information on Tesla offerings, please visit www.nvidia.com/object/tesla_computing_solutions.html.