“Slurm is the industry standard workload manager trusted by institutions across the globe. It queues and schedules jobs for small, large, and exascale clusters allocating resources based on the computational needs of your application.” – SchedMD
The Slurm job scheduler allows researchers to request HPC resources on the Andromeda cluster for batch and interactive workloads. Leveraging a multi-factor priority system and the backfill plugin to provide fair and equitable access to Andromeda’s resources that are freely available to the BC Research Community. The Research Computing Services team manages and maintains the HPC cluster environment, which is built on RedHat Enterprise Linux, so researchers can focus on their projects without having to worry about security patches, hardware failures or network connectivity issues.