Welcome to the DeepThought HPC

The Flinders University High Performance Computing (HPC) cluster is called DeepThought and runs on RedHat Enterprise Linux 10.

Tip

If you’ve never used Linux before or are a bit rusty with the command line interface and would like a refresher we have a new Intro to Linux page that may be helpful

DeepThought is available to all Researchers at Flinders University including Staff, HDR Students, Full Academic Status holders and Emeritus Professors.

Note

Staff and Students falling outside of the classifications above may still request access to DeepThought but we’ll need appropriate justification and sponsorship/authorisation. Please contact the IDS Research Success team via Service One if you don’t have access but require it

DeepThought is primarily intended to be used by our HDR Students and Early/Middle-Career Researchers as a way to familiarise themselves with the tools that they will likely be using during their Research Projects and to allow access to computational services prior to working on projects that would be eligible for schemes like NCMAS.

Having a local compute cluster also allows us to cater for other Research-active Staff who have specific requirements for grants and projects, including those that are working with UNCLASSIFIED Defence-related materials and DEIDENTIFIED health data. We also have enough capacity to cater for more experienced Researchers, with many preferring to prototype their designs and pipelines using DeepThought before moving them to other providers for their final compute run.

DeepThought is intended as a stepping stone towards the use of the larger HPC providers (such as our partners at NCI and Pawsey as Researchers progressing through their career will find that their requirements eventually outstrip what we can provide locally at the University. Pawsey in particular uses much of the same tooling as DeepThought and allows for a relatively seamless transition when the extra compute power is needed.

Attention

These pages are currently a Work In Progress while we update them to include information about the upgraded HPC Cluster. Please email researchsupport@flinders.edu.au if you require assistance and we also welcome user contributions to this documentation

Attribution

If you use the HPC to form a part of your research, you should attribute your usage.

Flinders has minted a DOI that points to this documentation, specific for the HPC Service. It will also allow for tracking the research outputs that the HPC has contributed to.

Text Citation

The below text citation follows the standard Australian Research Data Commons (ARDC) format for attributing data and software. For more information on this type of attribution, visit the ARDC Data Citation page.

Flinders University (2021). DeepThought (HPC). Retrieved from https://doi.org/10.25957/FLINDERS.HPC.DEEPTHOUGHT

Reference Managers

The following files are provided for integration into your reference manager of choice. To save the file, ‘Right Click -> Save Link As..’.

• BibTex

• EndNote

• RIS

Table of Contents

Getting Started

• Connecting to DeepThought
• Using the Web Portal
• Working with Files
• Software and the Module System
• Running Jobs
• Introduction to Linux
• Moving from Legacy DeepThought

FAQ & Known Issues

• Frequently Asked Questions
• Known Issues

System Information

• Deepthought: System Specifications
• Storage Overview & Usage Guidelines
• Software and Modules
• SLURM
• HPC Job Data Flow
• HPC Research Data Flow
• Deepthought: Legacy System Specifications

Software

• Software Overview
• Open OnDemand Web Portal
• EasyBuild and Software Modules
• Containers
• EPI2ME
• Gaussian
• Large Language Models
• Miniconda3
• WRF with WPS

Software & Support Policies

• Fair Usage Guidelines
• Storage Usage Guidelines
• Software Support Guidelines
• Upgrade Cycles
• HPC Etiquette

Legacy Software

• ANSYS Engineering Suite
• CST Studio Suite
• Delft3D
• GROMACS
• Jupyter Hub
• LAMMPS
• Mathworks MATLAB
• VASP
• Open Data Cube

The legacy DeepThought cluster has a time-series based visual statistics dashboard that be viewed via a web-browser while on campus.

The ‘Default’ and ‘Public’ URL’s are using an Alpha Release feature set, and may not display correctly. In that case, please use the ‘Full Version’ link, and any display strangeness will be resolved.

The following URLS all link to the dashboard.

1. Default URL

2. Public Dashboard

3. Full Version

The ‘Full Version’ has the capability to change the time-period viewed, and will be removed when the ‘Public’ and ‘Default’ feature set reach maturity.

A screen shot of a small portion of the Dashboard is below.

Acknowledgements

We recognise the respect the trademarks of all third-party providers referenced in this documentation. Please see the respective EULAs for software packages used in configuring your own environment based on this knowledgebase.

License

This documentation is released under the Creative-Commons: Attribution-ShareAlike 4.0 International license.