In addition to high-performance computing resources managed by RCC, UQ researchers can gain access to a number of national computational resources.  

ARDC Nectar Research Cloud 

Loosely-coupled high-throughput  jobs 

The ARDC Nectar Research Cloud is an ideal platform for running loosely-coupled jobs.  

QCIF operates the Queensland node of the ARDC Nectar Research Cloud. The Queensland node is called QRIScloud, and its main data centre is located at the Polaris Data Centre in Springfield, Brisbane.   

UQ researchers can apply for access to a number of virtual machines through QCIF. 


National Computational Infrastructure (NCI)
  

The federally fundedNational Computational Infrastructure (NCI) operates Gadi, Australia’s most powerful central processing unit (CPU)-based research supercomputer.  

Gadi, first launched to NCI users in November 2019, contains more than 250,000 CPU cores, 930 terabytes of memory and 640 graphics processing units (GPUs). It is a 4,962 node supercomputer comprising Intel Sapphire Rapids, Cascade Lake, Skylake and Broadwell CPUs and NVIDIA V100 and DGX A100 GPUs. 

Gadi supports diverse workloads with well over 10 petaflops of peak performance.  

The supercomputer offers a seven-times increase in computational performance, and a significantly increased number of GPUs compared to its predecessor, Raijin. This provides significant benefits for the largest parallel codes in particular, and all users will benefit from shorter queues and higher throughput. 

 
 

Pawsey Supercomputing Research Centre 

The Pawsey Supercomputing Research Centre is one of two Tier-1 high-performance computing facilities in Australia whose primary function is to accelerate scientific research for the benefit of the nation.  

Pawsey operates Setonix, which is currently the most powerful research computer in the southern hemisphere, and the world’s fourth greenest supercomputer as ranked in the TOP500 and Green500 lists. 

Setonix is a hybrid system of CPUs and GPUs that are engineered to solve massively complex scientific problems. 

The system is built on the same architecture used in world-leading exascale supercomputer projects including Frontier at Oak Ridge National Laboratory and Lumi at CSC Finland. 

Access to Gadi and Setonix

The National Computational Merit Allocation Scheme (NCMAS) provides researchers with annual access to Australia’s major national computational facilities, namely NCI and the Pawsey Supercomputing Research Centre, through a merit-based selection process.
 
In total, NCMAS distributes around 700 million units of computing time to meritorious applicants from around Australia.
 
The main call for applications is made annually around August for allocations to start the following January for 12 months.
 
 

NCI's AI Flagship Scheme

NCI's AI Flagship Scheme provides access to cutting-edge Artificial Intelligence (AI) infrastructure at NCI, including GPUs, CPUs and specialised AI hardware accelerators.

The scheme aims to catalyse AI progress, address critical challenges, promote ethical AI development, foster collaboration, nurture talent, fuel economic growth, establish leadership, and make AI resources accessible to a broader audience.

This flagship acts as a driving force behind the positive impact that AI can have on society.
 

National Computational Merit Allocation Scheme

QCIF’s share of Gadi

UQ has access to about 4 million service units on NCI’s Gadi supercomputer from a dedicated QCIF allocation (shared between all QCIF members, including UQ) in addition to anything gained through the National Computational Merit Allocation Scheme.

The service units from QCIF’s share are allocated by Queensland researchers can use Gadi either by applying directly to NCI for an allocation of time under the NCMAS scheme (see above) or by applying for an allocation from QCIF’s partner share.

Please apply for QCIF’s share via the application form on the QRIScloud portal. (Please note: if you are a first-time user of the portal, you will be asked to create an account before you can create the request.)

Any problems or queries, please contact RCC/QCIF eResearch Analyst Dr Marlies Hankel: m.hankel@uq.edu.au.