National Energy Technology Laboratory

Setting records in computational fluid dynamics

The U.S. Department of Energy’s National Energy Technology Laboratory focuses on applied research for the clean production and use of domestic energy resources. They partnered with Cerebras to help solve a large, sparse, structured system of linear equations that could be beneficial for weather forecasting, finding the best shape for an airplane’s wing, predicting temperatures and radiation levels in a nuclear power plant and more. Together we achieved performance with a CS-1 that was beyond what CPUs or GPUs could achieve and 200 times faster than the Joule supercomputer.

This work at the intersection of supercomputing and AI will extend our understanding of fundamental scientific phenomena, including combustion and how to make combustion more efficient. Together, NETL and Cerebras are using innovative new computer architectures to further the NETL Mission and benefit the United States.

Dr. Brian J. Anderson

Director @ National Energy Technology Laboratory

  • At SC21, NETL joined us for a panel discussion on the role of AI and HPC in delivering solutions for an environmentally sustainable future

    Watch Now
  • A technical overview of NETL’s work and early results with our CS system

    Watch Now
  • We can solve this problem in an amount of time that no number of GPUs or CPUs can achieve,” startup Cerebras tells supercomputing conference

    Read News Article
  • Beyond AI for Wafer Scale Compute: Setting Records in Computational Fluid Dynamics

    Read Blog
  • Fast Stencil-Code Computation on a Wafer-Scale Processor

    Read Research Paper
Cerebras Systems and National Energy Technology Laboratory (NETL) Panel at SC21

Tech talk with NETL: First Engineering Problem on Cerebras Wafer-Scale Engine

Tech talk with NETL: First Engineering Problem on Cerebras Wafer-Scale Engine