Attention: Confluence is not suitable for the storage of highly confidential data. Please ensure that any data classified as Highly Protected is stored using a more secure platform.
If you have any questions, please refer to the University's data classification guide or contact ict.askcyber@sydney.edu.au
NCI-Sydney Scheme
Sydney purchases bulk Service Units each Quarter via the Sydney Research Cloud initiative to distribute to researchers needing computing on the National Computational Infrastructure (NCI) facilities.
If you require a new Project or a new NCI Account visit https://my.nci.org.au/ to get started. Select “University of Sydney” when Choosing an Allocation Scheme. New projects will automatically be allocated 1 KSU by default unless specified in the project request form.
Read the docs at https://opus.nci.org.au/ for details on the types of workloads you can run on NCI facilities.
For Service Units beyond the Sydney Scheme, consider alternate methods of access at: https://nci.org.au/users/how-access-nci
Additional Service Unit Requests
If you exhaust your allocation or anticipate requiring more computing time, you may request additional Service Units in the management portal: http://nci.sydney.edu.au
Note: you must be on the Sydney University network to access the portal.
Projects can request additional SU for the current and next Quarter. The amount available for request may fluctuate between Quarters depending on overall demand. Excessive unused KSU will be reclaimed and redistributed in the final month of each Quarter.
A Service Unit (SU) is the currency of NCI. Different computational requirements (large memory, gpu, cpu, etc) charge different amounts. SU are often reported as KSU (1,000 SU) and MSU (1,000,000 SU). 1 SU ~ 1 cpu-hour.
Please contact nci-sydney.scheme@sydney.edu.au with any issues or questions.
NCI Facilities
Gadi
The national High Performance Computer similar to Sydney’s former Artemis HPC.
Nirin
Self-provision “virtual machine” service, “cloud” computing using “OpenStack”.
Australian Research Environment (ARE)
Allows for one-click compute “Virtual Research Desktop” resources using “Open OnDemand”. Provides Jupyter and RStudio instances.