The Department of Energy says the $40 million it is investing in nearly two dozen multi-year projects will result in exascale computing systems that perform calculations on data 50 to 100 times faster than today's most powerful supercomputers.
The DoE Exascale Computing Project says such high-performance computing systems can make at least a billion billion calculations per second, and will be used to process data for applications such as energy security, economic security, scientific discovery, healthcare and climate/environmental science. The U.S. is shooting to attain such powerful systems by the mid-2020s and China is aiming for 2020.
The project fits with President Obama's overall National Strategic Computing Initiative, which is also being undertaken by the Department of Defense and the National Science Foundation.
Leading the Exascale Computing Project will be six DoE labs, including Argonne, Lawrence Berkeley, Oak Ridge, Los Alamos, Lawerence Livermore and Sandia.
A sampling of projects (15 fully funded, 7 with seed funding):
*Exascale Deep Learning and Simulation Enabled Precision Medicine for Cancer
*Data Analytics at the Exascale for Free Electron Lasers
* Computing the Sky at Extreme Scales
Sign up for Computerworld eNewsletters.