Resources overview

Cheyenne | Data analysis and visualization | GLADE | Campaign Storage | HPSS

These NCAR supercomputing, data storage, and archive systems support the development of climate models, weather forecasting, and other critical research.

Access to these resources is available through several allocation opportunities. In general, researchers who are supported by the National Science Foundation to pursue work in the atmospheric sciences or computational science in support of the atmospheric sciences are eligible to apply.


Cheyenne: High-performance computing resource

Cheyenne is a new 5.34-petaflops, high-performance computer built for NCAR by SGI. The hardware was delivered in September 2016 at the NCAR-Wyoming Supercomputing Center (NWSC) and became operational at the beginning of 2017. An SGI ICE XA Cluster, the Cheyenne supercomputer features 145,152 latest-generation Intel Xeon processor cores in 4,032 dual-socket nodes (36 cores/node) and 313 TB of total memory. It is a critical tool for researchers across the country studying climate change, severe weather, geomagnetic storms, seismic activity, air quality, wildfires, and other important geoscience topics.

See Cheyenne system documentation.


Data analysis and visualization systems

The data analysis and visualization (DAV) resource comprises multiple systems. Geyser offers large-memory nodes (1 TB in each node) and is used for large-scale analysis and post-processing tasks, including 3D visualization. Caldera is designed to run distributed-memory parallel applications and for development and testing of general-purpose GPU (GPGPU) code.

The Casper cluster is a new, heterogeneous system of specialized DAV resources and large-memory, multi-GPU nodes. In addition to 20 nodes for analysis and visualization, it includes four nodes that feature large-memory, dense GPU configurations to support explorations in machine learning (ML) and deep learning (DL) in atmospheric and related sciences.

See the Geyser and Caldera documentation and the Casper documentation.


GLADE: Centralized file systems and data storage

This central file and data storage resource consists of file system servers and storage devices with 52.7 PB of usable capacity. It is shared by the Cheyenne system and the Geyser and Caldera analysis and visualization clusters. The centralized file systems allow scientists to generate model output on the supercomputer, then analyze or visualize it on the other clusters without needing to move data between separate systems.

See GLADE system documentation.


Campaign Storage

The NCAR Campaign Storage file system is intended for use by the NCAR labs and universities as archival space for storing project data on publication timescales. As a disk-based storage system, it is the preferred alternative to the older, tape-based High Performance Storage System (HPSS).

See Campaign Storage.


HPSS: NCAR data archive

The High Performance Storage System (HPSS) consists of tape libraries with storage capacity of more than 320 petabytes at the NCAR-Wyoming Supercomputing Center (NWSC) and more than 15 petabytes of disaster-recovery data storage at the Mesa Lab in Boulder.

See HPSS documentation.