NERSC-led Team Named 2018 Gordon Bell Prize Finalist for Deep Learning Achievement
September 20, 2018
A team from Lawrence Berkeley National Laboratory's (Berkeley Lab) National Energy Research Scientific Computing Center (NERSC), Oak Ridge National Laboratory (ORNL) and NVIDIA has, for the first time, demonstrated an exascale-class deep learning application that has broken the exaop barrier. Their achievement earned them a spot as one of the six finalists for the 2018 ACM Gordon Bell Prize, which will be announced at the SC18 conference in Dallas in November.
Working with a climate dataset from Berkeley Lab and ORNL's Summit supercomputer, the NERSC-led collaboration trained a deep neural network to identify extreme weather patterns from high-resolution climate simulations, leveraging specialized tensor cores built into Summit’s NVIDIA GPUs to achieve a performance of 1.13 exaflops - the fastest deep learning algorithm reported to date. It is also the first example of a deep learning architecture able to solve segmentation problems in climate data, according to Prabhat, who leads the Data & Analytics Services team at NERSC and is a co-author on the Gordon Bell submission.
Summit, an IBM AC922 system powered by more than 27,000 NVIDIA GPUs, was recently named the fastest supercomputer in the world.
About Computing Sciences at Berkeley Lab
The Lawrence Berkeley National Laboratory (Berkeley Lab) Computing Sciences organization provides the computing and networking resources and expertise critical to advancing the Department of Energy's research missions: developing new energy sources, improving energy efficiency, developing new materials and increasing our understanding of ourselves, our world and our universe.
ESnet, the Energy Sciences Network, provides the high-bandwidth, reliable connections that link scientists at 40 DOE research sites to each other and to experimental facilities and supercomputing centers around the country. The National Energy Research Scientific Computing Center (NERSC) powers the discoveries of 7,000-plus scientists at national laboratories and universities, including those at Berkeley Lab's Computational Research Division (CRD). CRD conducts research and development in mathematical modeling and simulation, algorithm design, data storage, management and analysis, computer system architecture and high-performance software implementation. NERSC and ESnet are Department of Energy Office of Science User Facilities.
Lawrence Berkeley National Laboratory addresses the world's most urgent scientific challenges by advancing sustainable energy, protecting human health, creating new materials, and revealing the origin and fate of the universe. Founded in 1931, Berkeley Lab's scientific expertise has been recognized with 13 Nobel prizes. The University of California manages Berkeley Lab for the DOE’s Office of Science.
DOE’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States, and is working to address some of the most pressing challenges of our time. For more information, please visit science.energy.gov.