[工程科技]Terascale spectral element dynamical core for atmospheric general circulation models.pdf

TERASCALE SPECTRAL ELEMENT DYNAMICAL CORE FOR ATMOSPHERIC GENERAL CIRCULATION MODELS 1 Richard D. Loft, Stephen J. Thomas, John M. Dennis National Center for Atmospheric Research 1850 Table Mesa Drive, Boulder CO 80303, USA Abstract Climate modeling is a grand challenge problem where scientific progress is mea- sured not in terms of the largest problem that can be solved but by the highest achievable integration rate. These models have been notably absent in previous Gordon Bell competitions due to their inability to scale to large processor counts. A scalable and efficient spectral element atmospheric model is presented. A new semi-implicit time stepping scheme accelerates the integration rate relative to an explicit model by a factor of two, achieving 130 years per day at T63L30 equiva- lent resolution. Execution rates are reported for the standard shallow water and Held-Suarez climate benchmarks on IBM SP clusters. The explicit T170 equiva- lent multi-layer shallow water model sustains 343 Gflops at NERSC, 206 Gflops at NPACI (SDSC) and 127 Gflops at NCAR. An explicit Held-Suarez integration sustains 369 Gflops on 128 16-way IBM nodes at NERSC. 1. Introduction Climate simulation is a grand challenge problem requiring multiple, century long integra- tions of the equations governing the earth’s atmosphere. Consequently, grid resolutions in atmospheric climate models are coarser than in numerical weather models, where ac- curate predictions are limited to about ten days. Current climate models are typically run with a 300 km equatorial grid spacing (T42 spectral truncation), whereas global we