Darwin

Overview

Darwin cluster is available to qualified faculty, graduate students (under faculty supervision), and researchers from the Computer Science Faculty.

Introduction to the Darwin Computing

The cluster consists of login node and a larger number of compute nodes. On a Darwin cluster, login node are only used for preparing and submitting batch jobs.

In batch mode the tasks are described in a script and submitted to the job scheduler to be run on one of the compute nodes without further user intervention.

The compute nodes provide around 1232 CPU cores and for serial and parallel batch jobs. When justified by the project requirements, it is also possible to use a compute node allocation for interactive processing.

Typically users rely on home directories for small storage needs and use Datasets and private labs volumes for large storage requirements.

For detailed hardware information, see: Darwin Hardware Specifications