BeoShock HPC Condo Program
Program Overveiw
The BeoShock Condo Program allows research groups to contribute compute nodes to the BeoShock HPC cluster. In return, these groups receive priority access to their nodes and elevated priority across the cluster.
Benefits
- Priority access to contributed nodes
- Elevated scheduling priority across BeoShock
- Efficient use of idle compute time
How to Contribute
Contact the Director of HPC to discuss contributing nodes to the BeoShock cluster.
Contributions are managed under the Condo model, ensuring fair and prioritized access.
What is Slurm?
Slurm (Simple Linux Utility for Resource Management) is an open-source job scheduler
used by many high-performance computing (HPC) systems, including BeoShock. It manages
and allocates compute resources efficiently across a cluster.
Slurm handles job scheduling, resource allocation, queue management, and monitoring. It determines when and where jobs run based on priority, availability, and policies.
In the context of BeoShock’s Condo model, Slurm ensures priority access to contributed nodes. If another user’s job is running on your node, Slurm will halt and reschedule it to give your group access. It also allows unused time on your node to be shared with others.
Advantages (services provided by university)
- Cybersecurity
- secure physical space
- redundant power (including UPS and diesel generator)
- environment controlled
- rack (including rack power distribution)
- network infrastructure (including message passing network for distributed memory nodes)
- system administration and maintenance
- fairly distributed priority access to compute resources
- priority access to purchased hardware
- access to shared storage and file systems
- access to a university-funded licensed software*
- system and computational science support from HPC support team
University Advantages
- multiplies resources provided by university HPC investment
- increased HPC resource utilization yields more efficient use of university-wide research computing dollars
- scaling benefits reduce university-wide cost of HPC facilities (a few large power and cooling units vs. many small power and cooling units)
- scaling benefits reduce university-wide cost of HPC system support (incremental system administration and maintenance load for compatible hardware is very small - that is it takes nearly the same work to operate an 8-processor cluster as it does to operate a 100-processor cluster)