This article was accepted into the corpus but its outbound wikilinks were never NER-processed — typical at the deepest BFS hop or when the run's entity cap was reached. No expansion funnel to show.
| NCAR Cheyenne | |
|---|---|
| Name | Cheyenne |
| Operator | National Center for Atmospheric Research |
| Location | Cheyenne, Wyoming |
| Architecture | SGI ICE XA |
| Cores | 4,032 compute nodes, 18,432 compute cores |
| Peak | 5.34 petaflops (single precision) |
| Date operational | 2013 |
NCAR Cheyenne Cheyenne is a high-performance computing system deployed by the National Center for Atmospheric Research for climate and weather simulation, providing substantial capacity for researchers from the National Science Foundation, University Corporation for Atmospheric Research, and collaborating institutions such as the National Oceanic and Atmospheric Administration, United States Geological Survey, and numerous universities. The system supports large-scale simulations used by investigators affiliated with centers like the Earth System Modeling Framework, NOAA Geophysical Fluid Dynamics Laboratory, and regional consortia involving University of Colorado Boulder and Colorado State University.
Cheyenne serves as a computational resource for projects including initiatives led by the Intergovernmental Panel on Climate Change, Princeton University, Massachusetts Institute of Technology, and the Scripps Institution of Oceanography. It integrates workflows originating from research groups at Lamont–Doherty Earth Observatory, National Renewable Energy Laboratory, Lawrence Berkeley National Laboratory, and Argonne National Laboratory. Users include teams associated with programs such as the World Climate Research Programme, Coupled Model Intercomparison Project, and Integrated Research on Disaster Risk.
The system is based on the SGI ICE XA architecture supplied by Silicon Graphics International and employs processors from Intel families similar to those used in systems at Oak Ridge National Laboratory and National Energy Research Scientific Computing Center. Storage arrays provided by companies like DataDirect Networks integrate with parallel file systems used in centers such as NERSC and Texas Advanced Computing Center. Networking relies on high-speed interconnects comparable to technologies from InfiniBand Trade Association vendors used at Lawrence Livermore National Laboratory and Los Alamos National Laboratory facilities.
At commissioning, Cheyenne ranked among the top systems monitored by the TOP500 list and was featured in performance analyses alongside machines at Oak Ridge Leadership Computing Facility, Argonne Leadership Computing Facility, and NERSC. Benchmark comparisons reference suites used by the High Performance Computing Modernization Program and performance metrics considered by agencies such as the United States Department of Energy. The system’s capability supports experiments comparable to those undertaken at Met Office and European Centre for Medium-Range Weather Forecasts research centers.
Cheyenne’s software stack includes climate and weather codes shared across institutions like NOAA labs, NASA Goddard Space Flight Center, and university groups at Columbia University and University of Washington. Common packages in the environment mirror tools used at Princeton University and University of Oxford research groups: community models such as Community Earth System Model, libraries like NetCDF, and parallel frameworks similar to those employed by MPI Forum and OpenMP Architecture Review Board initiatives. Data management workflows align with standards championed by World Data System and repositories like Earth System Grid Federation.
Researchers from Stanford University, Harvard University, Yale University, University of Michigan, and Cornell University use Cheyenne for studies spanning atmospheric chemistry, hydrology, and cryosphere modeling. Projects connect to observational programs at NOAA National Centers for Environmental Information, National Snow and Ice Data Center, and Palisade Observatory-style campaigns. Collaborations include efforts with Environmental Protection Agency scientists, United Nations Environment Programme partners, and interdisciplinary teams from Johns Hopkins University and University of California, Berkeley.
Development drew on partnerships among NCAR, NSF, and vendor communities including Hewlett Packard Enterprise and Cray Inc. earlier procurement cycles. The system followed predecessors and complementary resources at institutions like NCAR-Wyoming Supercomputing Center and reflected design influences from projects at NERSC and leadership systems at Argonne and Oak Ridge. Program oversight involved committees similar to those formed at National Academies of Sciences, Engineering, and Medicine and coordination with federal labs such as Sandia National Laboratories.
Cheyenne operates within data center facilities associated with NCAR, employing facility management practices aligned with standards from Uptime Institute and energy-efficiency considerations invoked by American Society of Heating, Refrigerating and Air-Conditioning Engineers. User support and allocations follow procedures comparable to those at Extreme Science and Engineering Discovery Environment and peer allocation programs at XSEDE and PRACE institutions. Training and outreach have included workshops co-hosted with AGU and AMS events and collaborations with regional research networks like Front Range GigaPOP.