Deep Thought - High Performance Computing (HPC)

Flinders University is home to Deep Thought, the University’s High-Performance Computing (HPC) platform. High Performance Computing (HPC) is the practice of aggregating computing power in a way that delivers much higher performance than one could get out of a typical desktop computer or workstation in order to solve large problems in science, medicine, engineering, or business.

The Deep Thought platform is based onsite, and is available to all research staff at the University to service your research computing needs 24 hours a day, 7 days a week.

Deep Thought specialises in workloads that require:

• High performance / large scale Central Processing Units (CPU)
• General Graphics Processing Units (GPU)
  
• High Rapid Access memory (RAM).

The Deep Thought HPC, built upon high-end Dell hardware, has the following resources available to use:

• 17 compute nodes, totalling 1376 cores and 6.28TB of RAM combined.
• 2 login nodes, with High-Availability failover
• 4 V100 Nvidia TESLA GPU’s with 32GB VRAM
• 25Gbps network connectivity.

We also host private nodes for dedicated resource usage.

Jobs are scheduled on the HPC using Simple Linux Usage Resource Manager (SLURM) and resources allocated using the “Fairshare” algorithm to ensure fair access and allocation of resources to each user and College.

Please note: These resources are only available to members of the Flinders University research community.