CISL computing and data services

Overview | Computing | Software | Data collections | Facilities

Image in the VisLab

Overview

CISL provides state-of-the-art supercomputing services and resources to more than 1,800 users in the atmospheric and related Earth system science community. Our suite of computational resources, specialized software, data analysis, and visualization resources allows today’s Earth system models to simulate atmospheric, ocean, sea ice, land surface processes, and others with increasing fidelity.

We have provided world-class supercomputing and data management services to our community for decades, as you can see at this link to a page about our supercomputing history.

Below is an overview of our current services for the science community.


Computing

CISL provides computing, data storage, data analysis, visualization, networking, and other systems customized to support the atmospheric and related sciences.

  • Cheyenne – Cheyenne is a 5.34-petaflops, high-performance computing system (HPC) built for NCAR by SGI. The supercomputer was installed at the NCAR-Wyoming Supercomputing Center in the second half of 2016 and became operational in January 2017.
  • Casper – The Casper cluster is a heterogeneous system of specialized data analysis and visualization resources and large-memory, multi-GPU nodes. In addition to its analysis and visualization capabilities, it supports explorations in machine learning and deep learning in atmospheric and related sciences.
  • GLADE – This centralized file system allows HPC users to access their data from the Cheyenne and Casper systems and to transfer data to internal or external storage and archive systems as needed.
     

Software

CISL and NCAR have developed and support a number of freely available software packages for data assimilation, analysis, visualization, and high-performance computation. These include:

  • Data Assimilation Research Testbed (DART) is a community resource that gives modelers, observational scientists, and geophysicists powerful, flexible data assimilation tools; a software environment; and a framework for ensemble data assimilation research and applications.
  • Geoscience Community Analysis Toolkit (GeoCAT) is a collection of tools for scientific visualization, file input/output, and data analysis. The collection includes the GeoCAT computational library (GeoCAT-Comp) and the PyNGL and PyNIO Python packages.
  • Visualization and Analysis Platform for Ocean, Atmosphere, and Solar Researchers (VAPOR) provides an interactive 3D visualization environment that can also produce animations and still frame images.

Data collections

CISL develops and curates research data sets and maintains user-centered online access to these collections, which include meteorological and oceanographic observations, operational and reanalysis model outputs, and remote sensing data sets supporting atmospheric and geosciences research.

  • The Digital Asset Services Hub (DASH) provides services for open access digital assets from NCAR labs and UCAR Community Programs members, including support, engagement, and training resources for managing, sharing and working with data sets, publications, software, and models.
  • The Research Data Archive (RDA) contains a large, diverse collection of meteorological and oceanographic observations, operational and reanalysis model outputs, and remote sensing data sets to support atmospheric and geosciences research, along with ancillary data sets, such as topography/bathymetry, vegetation, and land use.
  • The Climate Data Gateway integrates supercomputers with large-scale data and analysis servers located at numerous national labs and research centers to create a powerful environment for next-generation climate research.

Facilities

CISL deploys and operates these physical facilities in support of the science community.

  • NCAR-Wyoming Supercomputing Center – The NWSC opened in October 2012 in Cheyenne, Wyoming. As a world-class center for high-performance scientific computing in the atmospheric sciences, it houses the Cheyenne computational and data storage resources.
  • Visualization Laboratory – The VisLab supports an immersive environment for visualizing complex data sets at very high resolution and for collaborating across sites via high-definition video teleconferencing. It typically supports 2,000 to 3,000 users and visitors per year and is used in many of CISL’s education and outreach efforts.
  • Mesa Lab Data Center – The data center at the Mesa Lab serves as a centralized colocation facility for other NCAR labs and institutions in the Boulder area.