UQ supercomputer Bunya was launched in December 2022 after a successful user testing phase. 

Bunya, procured from Dell Technologies and named after the native South-East Queensland tree, uses novel methods of software deployment and management to allow for flexibility and ease of operation for researchers. 

The HPC can perform across a wide range of research domains, from the sciences to the humanities, and is available for UQ researchers and QCIF member researchers.  

The HPC was funded by UQ with other contributions from UQ organisational units and QCIF. 

Bunya has been co-located with cloud computer QRIScloud(the QCIF-managed Queensland node of the ARDC Nectar Research Cloud) and uses QRIScloud's identity management system to ensure interoperability with RCC's other HPCs and storage infrastructure. Bunya is optimised for local users and campus infrastructure but has the flexibility to extend to UQ and QCIF partners. 

The HPC started out as a traditional central processing unit (CPU)-based supercomputer with a number of high-memory capacity nodes for special uses. 

Subsequent upgrades of Bunya have added different node types, such as high-performance accelerators, including GPUs. 

RCC’s Metropolitan Data Caching Infrastructure (MeDiCI) data fabric enables research data collections to be accessed transparently via all UQ HPCs, including Bunya. 

Getting a Bunya account 

Researchers wishing to use Bunya need to complete an application form before being granted access.  

It is important to note that there are eight questions on the application form, and all are mandatory. Please scroll all the way up the application form to see all the questions. 

Please try and copy the questions into the box on the form and answer each one. You will need to provide current 2020 six-digit FoR (Field of Research) code(s). If you do not know what a FoR code is, or do not have one, please contact your supervisor. The list of current ANZSRC 2020 FoR codes can be found here.   

Please note: Incomplete applications will be rejected, and applicants will have to fill in a new form.  

Bunya training 

RCC conducts regular 'Introduction to HPC' training, usually on the last Friday of each month. Please visit RCC's training webpage for further information. 

Please send enquiries via email to rcc-support@uq.edu.au for further information or to register your interest in future 'Introduction to HPC' training sessions. 
 

onBunya

onBunya is for all Bunya users, providing researchers with an easily accessible graphical user interface (GUI) and remote web access to the powerful hardware Bunya has to offer. It is an easier introduction to high-performance computing for people unfamiliar with the technology.

Please see our onBunya webpage for more information.
 

Bunya User Guide 

The Bunya User Guide provides more information on user spaces, software, Slurm, how to submit jobs and how to use Bunya.   
 

Bunya support 

If you have any questions or concerns that are not addressed in the Bunya User Guide, please contact your relevant support team or person. 

UQ users of Bunya should submit support requests to the RCC Service Desk: rcc-support@uq.edu.au. 

Non-UQ users should contact their local HPC/eResearch team for help. 
 

Bunya technical specifications 

The Bunya high-performance computer: 

  • was provided by Dell EMC Technologies Australia Pty Ltd 

  • features ~10000 AMD EPYC Milan and Genoa series cores, 96 physical cores per node  

  • features between 1.5 and 2 terabytes of memory per node on a standard compute node 

  • features 4 terabytes of memory per node on each of the three high-memory capability nodes 

  • features a blocking topology Nvidia Infiniband HDR cluster interconnect, running at a native 200 Gbit/sec per port, per node 

  • includes AMD Instinct MI2xx series GPU accelerators 

  • includes a fleet of Nvidia H100 GPU enabled nodes for AI/ML and high performance accelerated supercomputing workloads. 

  • includes a fleet of Nvidia L40 GPU enabled nodes for OpenOnDemand visualisation and graphical interactive computing workloads. 

  • runs a current generation RHEL-type Linux distribution.