Chipmaker NVIDIA will be equipping Pawsey Supercomputing Research Centre with NVIDIA CUDA Quantum. This move is set to accelerate quantum innovation within its National Supercomputing and Quantum Computing Innovation Hub based in Perth, Australia.
NVIDIA’s CUDA Quantum, operating on NVIDIA Grace Hopper Superchips, stands as an open-source hybrid quantum computing platform. It offers robust simulation tools and the capability to program hybrid CPU, GPU, and QPU systems. It features the NVIDIA cuQuantum software development kit, comprising optimized libraries and tools for expediting quantum computing workflows.
“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,” said Tim Costa, director of HPC and quantum computing at NVIDIA.
READ:
Alliance seeks to advance post-quantum cryptography
IBM: Enabling a quantum-safe environment
Costa noted that CUDA Quantum, together with the NVIDIA Grace Hopper Superchip, will allow innovators to achieve these essential breakthroughs and accelerate the timeline to useful quantum-integrated supercomputing.
Superchips
Australia’s national science agency, CSIRO (Commonwealth Scientific and Industrial Research Organisation) projects that the quantum computing market could reach $2.5 billion by 2040, potentially generating 10,000 jobs. This advancement not only impacts quantum computing but also paves the way for innovations across various scientific domains like astronomy, life sciences, medicine, and finance.
Pawsey is set to deploy eight nodes equipped with NVIDIA Grace Hopper Superchips based on NVIDIA MGX modular architecture. These GH200 Superchips boast an Arm-based NVIDIA Grace CPU paired with an NVIDIA H100 Tensor Core GPU within the same package, connected via NVIDIA NVLink-C2C chip interconnects. This design eliminates the need for traditional CPU-to-GPU PCIe connections, increasing bandwidth between GPU and CPU by 7x compared to the latest PCIe technology. It promises up to 10x higher performance for applications handling terabytes of data, empowering quantum-classical researchers to tackle complex problems.
“NVIDIA’s CUDA Quantum platform will allow our scientists to push the boundaries of what’s possible in quantum computing research,” said Mark Stickells, executive director at the Pawsey Supercomputing Research Centre.
The system will enable Pawsey to run quantum workloads directly from traditional high-performance computing systems, leveraging their processing power. They’ll develop hybrid algorithms dividing calculations into classical and quantum kernels, optimizing computing efficiency with the quantum device. Various applications, including quantum machine learning, chemistry simulations, radio astronomy image processing, financial analysis, bioinformatics, and specialized quantum simulators, will be explored, starting with different quantum variational algorithms.