Quantum computing promises to shorten the path to solving some of the world’s biggest computational challenges, from scaling in-silico drug design to optimizing otherwise impossibly complex, large-scale logistics problems.
Integrating quantum hardware into state-of-the-art AI supercomputers — forming accelerated quantum supercomputers — helps speed the scaling of today’s quantum processors into helpful devices for solving these complex challenges.
At the COMPUTEX trade show, NVIDIA underscored how its work with partners across the Taiwan supercomputing ecosystem is advancing quantum computing toward accelerated quantum supercomputers.
Leading hardware developers are working with NVIDIA to equip quantum researchers with tools to make significant contributions in the field.
Atlantic Quantum, the University of Edinburgh,, the University of Oxford, Quantum Circuits Inc., QuEra Computing and Yale University anticipate receiving NVIDIA Grace Hopper Superchips from Supermicro to explore and refine the intersections between AI supercomputing and quantum computing.
Compal announced its CGA-QX platform, built using the NVIDIA CUDA-Q platform, to accelerate the simulation of quantum optimization problems. The platform has been adopted by the Taiwanese National Science and Technology Council and made available to researchers from universities across Taiwan.
Quanta has employed NVIDIA CUDA-Q to experiment with physical quantum hardware, using the platform’s state vector simulations to verify and validate existing quantum processors. This allows Quanta to understand the details of noise in its systems and assess how well they work for use cases of interest.
NVIDIA is also working with supercomputing centers to advance accelerated quantum supercomputing.
Taiwan’s National Center for High-Performance Computing (NCHC) announced a new supercomputer for quantum research. Built by ASUS, the AI supercomputer at NCHC will feature NVIDIA HGX H200 systems with over 1,700 GPUs, two NVIDIA GB200 NVL72 rack-scale systems and an NVIDIA HGX B300 system built on the next-generation NVIDIA Blackwell Ultra platform — interconnected by NVIDIA Quantum InfiniBand networking. Announced today at COMPUTEX, it’s expected to go live later this year.
NCHC is enabling over 20 companies working in quantum computing — collaborating under what’s known as the National Quantum Team. NVIDIA CUDA-Q is being used at the center to explore quantum solutions for applications ranging from machine learning to chemistry.
In Japan, AIST’s ABCI-Q — the world’s most powerful supercomputer dedicated to quantum workloads — integrates an NVIDIA supercomputer with more than 2,000 NVIDIA H100 GPUs with quantum processors from Fujitsu, QuEra Computing and OptQC.
Increased availability of these quantum-AI platforms is poised to accelerate the breakthroughs researchers can make in quantum computing — including developing new error correcting codes, integrating quantum processors within AI supercomputing and simulating low noise designs of quantum hardware.
Learn more about NVIDIA’s work advancing accelerated quantum supercomputing at NVIDIA GTC Taipei, running May 21-22.
