Casper

The Casper cluster is a heterogeneous system of specialized data analysis and visualization resources and large-memory, multi-GPU nodes. Casper is the successor to the Geyser and Caldera clusters, which were decommissioned at the end of 2018.

NCAR's Casper system comprises 28 Supermicro nodes featuring Intel Skylake processors.

• 20 Supermicro SuperWorkstation nodes are used for data analysis and visualization jobs. Each node has 36 cores and up to 384 GB memory. Eight of the nodes also feature an NVIDIA Quadro class GPU.
• 6 additional nodes feature large-memory, dense GPU configurations to support explorations in machine learning (ML) and deep learning (DL) in atmospheric and related sciences.
• 2 serve as login nodes.

See the hardware summary table below for detailed specifications.

Job scheduler: Users submit jobs with the Slurm Workload Manager to run them on the Casper cluster.

Operating system: CentOS 7.4

Hardware