Australia’s Pawsey Supercomputing Research Centre has unveiled plans to enhance its quantum computing capabilities by incorporating Nvidia’s Grace Hopper Superchips and CUDA Quantum platform. The announcement was made at the SupercomputingAsia 2024 event in Sydney.
Under the new plan, Pawsey will deploy eight Grace Hopper GH200 Superchip nodes, connected in a modular architecture, at its National Supercomputing and Quantum Computing Innovation Hub in Perth. These nodes will be equipped with Nvidia’s MGX modular architecture, combining the Arm-based Nvidia Grace CPU with an Nvidia H100 Tensor Core GPU in the same package.
The addition of Nvidia’s GH200 Superchips will significantly increase bandwidth by seven times between the CPU and GPU, compared to the latest PCIe technology. This leap in performance will enable Pawsey to handle applications that process terabytes of data, offering up to 10 times higher performance.
Furthermore, Pawsey researchers will utilize CUDA Quantum, an open-source hybrid quantum computing platform, that supports high-performance simulation and programming for hybrid CPU, GPU, and QPU systems. They will also leverage Nvidia’s cuQuantum software development kit, which includes optimized libraries and tools for accelerating quantum computing workflows.
By integrating quantum computing equipment from Australia’s Quantum Brilliance with traditional classical high-performance computing gear, Pawsey has established itself at the forefront of hybrid classical-quantum supercomputing. Nvidia’s GH200 Superchips and quantum software will further enhance their capabilities, enabling advanced simulations on a massive scale.
Tim Costa, director of HPC and quantum computing at Nvidia, highlighted the significance of high-performance simulation in addressing the challenges of quantum computing. Mark Stickells, executive director at the Pawsey Supercomputing Research Centre, expressed excitement about Nvidia’s CUDA Quantum platform and its potential to propel quantum computing research forward.
With this strategic partnership, Australia’s Pawsey Supercomputing Research Centre aims to push the boundaries of what is possible in quantum computing research and contribute to scientific exploration worldwide.
Frequently Asked Questions (FAQ) – Supercomputing Enhancements with Nvidia’s Grace Hopper Superchips and CUDA Quantum Platform
Q: What has Australia’s Pawsey Supercomputing Research Centre announced?
A: Pawsey Supercomputing Research Centre has unveiled plans to enhance its quantum computing capabilities by incorporating Nvidia’s Grace Hopper Superchips and CUDA Quantum platform.
Q: Where was the announcement made?
A: The announcement was made at the SupercomputingAsia 2024 event in Sydney.
Q: What will Pawsey deploy under the new plan?
A: Pawsey will deploy eight Grace Hopper GH200 Superchip nodes, connected in a modular architecture, at its National Supercomputing and Quantum Computing Innovation Hub in Perth.
Q: What does the MGX modular architecture combine?
A: The MGX modular architecture combines the Arm-based Nvidia Grace CPU with an Nvidia H100 Tensor Core GPU in the same package.
Q: How will Nvidia’s GH200 Superchips improve performance?
A: The GH200 Superchips will significantly increase bandwidth by seven times between the CPU and GPU, compared to the latest PCIe technology. This will offer up to 10 times higher performance, enabling the handling of applications that process terabytes of data.
Q: What is CUDA Quantum?
A: CUDA Quantum is an open-source hybrid quantum computing platform that supports high-performance simulation and programming for hybrid CPU, GPU, and QPU systems.
Q: What software development kit will Pawsey researchers utilize?
A: Pawsey researchers will leverage Nvidia’s cuQuantum software development kit, which includes optimized libraries and tools for accelerating quantum computing workflows.
Q: How will Pawsey utilize the quantum computing equipment from Quantum Brilliance?
A: By integrating quantum computing equipment from Quantum Brilliance with traditional classical high-performance computing gear, Pawsey aims to establish itself at the forefront of hybrid classical-quantum supercomputing.
Q: What significance does high-performance simulation have in quantum computing?
A: High-performance simulation plays a crucial role in addressing the challenges of quantum computing.
Q: What do Tim Costa and Mark Stickells say about the collaboration?
A: Tim Costa, director of HPC and quantum computing at Nvidia, highlighted the significance of high-performance simulation. Mark Stickells, executive director at the Pawsey Supercomputing Research Centre, expressed excitement about Nvidia’s CUDA Quantum platform and its potential to propel quantum computing research forward.
Q: What is the aim of Pawsey Supercomputing Research Centre with this partnership?
A: Pawsey aims to push the boundaries of what is possible in quantum computing research and contribute to scientific exploration worldwide through this strategic partnership.
Definitions:
– Supercomputing: High-performance computing using powerful computers to solve complex problems or perform intensive calculations.
– Quantum computing: A type of computing that uses the principles of quantum mechanics to perform calculations exponentially faster than classical computers.
– CUDA Quantum: An open-source hybrid quantum computing platform that supports high-performance simulation and programming for hybrid CPU, GPU, and QPU systems.
– GPU: Graphics Processing Unit, a specialized electronic circuit designed to rapidly manipulate and alter memory to accelerate the creation of images for display.
– CPU: Central Processing Unit, the primary component of a computer that performs most of the processing inside the system.
– QPU: Quantum Processing Unit, a device designed to perform quantum computations.
Related Links:
– Nvidia
– Pawsey Supercomputing Research Centre
– Quantum Brilliance
– Nvidia CUDA
The source of the article is from the blog smartphonemagazine.nl