The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Authors: Mark Taylor (Sandia National Laboratories); Peter M. Caldwell (Lawrence Livermore National Laboratory); Luca Bertagna and Conrad Clevenger (Sandia National Laboratories); Aaron S. Donahue (Lawrence Livermore National Laboratory); James G. Foucar, Oksana Guba, and Benjamin R. Hillman (Sandia National Laboratories); Noel Keen (Lawrence Berkeley National Laboratory (LBNL)); Jayesh Krishna (Argonne National Laboratory); Matthew R. Norman and Sarat Sreepathi (Oak Ridge National Laboratory (ORNL)); Christopher R. Terai (Lawrence Livermore National Laboratory); James B. White III (Hewlett Packard Enterprise (HPE)); Danqing Wu (Argonne National Laboratory (ANL)); Andrew G. Salinger (Sandia National Laboratories); Renata B. McCoy (Lawrence Livermore National Laboratory); L. Ruby Leung (Pacific Northwest National Laboratory (PNNL)); and David C. Bader (Lawrence Livermore National Laboratory)
Abstract: We present an efficient and performance portable implementation of the Simple Cloud Resolving E3SM Atmosphere Model (SCREAM). SCREAM is a full featured atmospheric global circulation model with a nonhydrostatic dynamical core and state-of-the-art parameterizations for microphysics, moist turbulence and radiation. It has been written from scratch in C++ with the Kokkos library used to abstract the on-node execution model for both CPUs and GPUs. SCREAM is one of only a few global atmosphere models to be ported to GPUs. As far as we know, SCREAM is the first such model to run on both AMD GPUs and NVIDIA GPUs, as well as the first to run on nearly an entire exascale system (Frontier). On Frontier, we obtained a record setting performance of 1.26 simulated years per day for a realistic cloud resolving simulation.
Back to Technical Papers Archive Listing