The standard compute nodes have 128GB of memory. Some work requires more memory than is available on these standard nodes, a need which is met by additional servers on BlueBEAR. These servers are considered as a scarce resource and are controlled as follows:
- registration on the general BlueBEAR service is a prerequisite for access to these nodes. See the BlueBEAR registration help page for details about registering on the general BlueBEAR service.
- experience of running work using the standard resources is required prior to requesting access to the Large Memory Service. Typically an example of a simulation that has failed due to insufficient memory is required prior to requesting access to this service.
- to request access to this service follow the instructions in the Registering a username for specialist BEAR services section of the BlueBEAR registration help page.
- IT Services will invite you to discuss your needs and identify the best way to meet your needs.
- approved users will be added to the bblargemem QoS in SLURM and will then be able to submit jobs to these nodes. See the help page for job submission for more details about submitting jobs.
- A job may only make use of one of the large memory nodes; it is not possible to run jobs across them.
Please contact the IT Service Desk with any questions about this large memory service.
Last modified: 3 August 2017