NVIDIA has announced that the Pawsey Supercomputing Research Centre in Australia will be incorporating NVIDIA CUDA Quantum platform and NVIDIA Grace Hopper Superchips into its National Supercomputing and Quantum Computing Innovation Hub. This integration will propel the centre’s existing initiatives in advancing quantum computing.
The Perth-based research centre is set to utilise CUDA Quantum, an open-source hybrid quantum computing platform characterised by powerful simulation tools and the capabilities to program hybrid CPU, GPU, and QPU systems. Alongside this, researchers will also be implementing the NVIDIA cuQuantum software development kit of optimised libraries and tools, all designed to streamline quantum computing workflows.
The NVIDIA Grace Hopper Superchip brings together the NVIDIA Grace CPU and Hopper GPU architectures to produce an extreme performance setup to run highly accurate, scalable quantum simulations on accelerators. This advanced product also allows for seamless interfacing with future quantum hardware infrastructure.
NVIDIA's director of HPC and quantum computing, Tim Costa, stated, "High-performance simulation is essential for researchers to address the biggest challenges in quantum computing – from algorithm discovery and device design to the invention of powerful methods for error correction, calibration and control. CUDA Quantum, together with the NVIDIA Grace Hopper Superchip, enables innovators like Pawsey Supercomputing Research Centre to achieve these essential breakthroughs and accelerate the timeline to useful quantum-integrated supercomputing."
According to Mark Stickells, executive director at the Pawsey Supercomputing Research Centre, "NVIDIA’s CUDA Quantum platform will allow our scientists to push the boundaries of what’s achievable in quantum computing research." Furthermore, the Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia's national science agency, estimates that the domestic market from quantum computing could generate $2.5 billion in annual revenue, potentially creating 10,000 new jobs by 2040. Realising this goal will require quantum computing to be incorporated across various scientific domains, such as astronomy, life sciences, medicine, and finance.
Pawsey plans to deploy the system to run quantum workloads from traditional high-performance computing systems, harnessing their processing power while developing new hybrid algorithms. This innovative approach uses the quantum device to enhance computing efficiency, boosting research capabilities in various fields, including quantum machine learning, chemistry simulations, image processing for radio astronomy, financial analysis, bioinformatics and specialised quantum simulators. The cutting-edge exploration will commence using various quantum variational algorithms.
Eight NVIDIA Grace Hopper Superchip nodes based on NVIDIA MGX modular architecture will be used in the system deployment. These GH200 Superchips eliminate the necessity for a traditional CPU-to-GPU PCIe connection, combining an Arm-based NVIDIA Grace CPU with an NVIDIA H100 Tensor Core GPU in the same package, using NVIDIA NVLink-C2C chip interconnects. This innovative design increases the bandwidth between the GPU and CPU by seven times compared with the latest PCIe technology and delivers up to ten times higher performance for applications running terabytes of data.
In a final note, it was announced that Pawsey plans to make the NVIDIA Grace Hopper platform accessible to the wider Australian quantum community, as well as its international partners, further advocating for the advancement of quantum computing research and development.