NVIDIA wants to replicate CUDA success with Quantum Computing

Analogous to when CUDA opened up a new type of hardware and programming paradigm, we expect software builders to help develop an ecosystem of hybrid quantum applications running on top of QODA.
NVIDIA wants to replicate CUDA success with Quantum Computing
Listen to this story

In July 2022, NVIDIA announced the launch of its open, unified computing platform, ‘QODA’ (quantum optimised device architecture), to accelerate breakthroughs in quantum research and development across various areas, including AI, HPC, health, finance and others. 

With this, NVIDIA aims to make quantum computing more accessible by creating a coherent hybrid quantum-classical programming model. Its platform is currently being used by the most powerful computers and quantum processors, improving scientific productivity and enabling greater scale in quantum research. 

Accelerating quantum computing research 

Contemporary quantum computers are programmed in equivalence with assembly code, which has an extremely steep learning curve for researchers who are not already quantum engineers incorporating quantum computing into their workflows. NVIDIA looks to remove that barrier to entry by enabling the programming of hybrid quantum systems in a model familiar to scientific computing developers, interoperable with the best of today’s classical computing applications.

THE BELAMY

Sign up for your weekly dose of what's up in emerging technology.

NVIDIA revealed that this allows the development of the first quantum-accelerated applications by enabling incremental quantum acceleration to scientific computing applications where it makes sense, alongside using the best classical resources within the same applications.

The team noted that QODA is the only unified platform that makes it possible to add quantum computing to the existing applications. It enables HPC and AI domain experts to easily add quantum computing to existing applications, similar to how one would typically operate classical computing. 

Betting big on quantum computing 

In 1993, NVIDIA founder Jensen Huang started the company thinking that the PC would one day become a consumer device for enjoying games and multimedia. Cut to 2022, the company’s work in AI is transforming 100 trillion dollars of industries—from gaming to healthcare to transportation—and impacting society profoundly. 

Now, NVIDIA seems to be chasing quantum computing dreams.

NVIDIA said that it had built the tools to democratise new computing technology and empower researchers and developers for decades. “Quantum computing holds great promise to help solve some of the most important challenges of our time. We see a great need for a unified platform to make useful quantum computing possible”, shares NVIDIA. 

However, this brings us to the question—if it would affect its GPU business? “No. We are at the forefront and will continue to push the boundaries of what’s possible in computing”, says team NVIDIA, stating that hybrid quantum-classical computing would be around for decades. 

Tim Costa, director of HPC and quantum computing products at NVIDIA, said that with hybrid solutions combining classical computing and quantum computing, there would be scientific breakthroughs in the near term. He said QODA would revolutionise quantum computing by giving developers a powerful and productive programming model. 

How QODA works

QODA enables scientific developers to integrate quantum computing acceleration directly into their existing applications. It also allows them to fully develop hybrid applications, putting the best classical and quantum resources together for the tasks they are best suited to perform.

NVIDIA envisions algorithms and applications that benefit from both GPU and QPU processing. QODA would enable the efficient interoperability of these computational accelerators. Domains that would likely require classical parallel processing in tandem with quantum co-processing include machine learning, optimisation in financial portfolios, and novel quantum chemistry algorithms and frameworks.

The team revealed that HPC and AI domain experts can leverage today’s quantum processors and simulate future quantum machines using NVIDIA DGX systems and a large installed base of NVIDIA GPUs available in scientific supercomputing centres and public clouds.

However, this brings us to question if NVIDIA would launch its quantum processors or QPUs? “No. We are not”, says the team, explaining that they are looking to enable the ecosystem with a programming model that they can use to add quantum computing to the existing applications with ease.

Quantum computing versus hybrid quantum-classical computing 

For those unaware, quantum computing runs full applications on computing systems with quantum processing units (QPUs), leveraging the possible performance advantages for specific types of problems. Most industry experts recognise that current quantum technology is limited in practical use due to challenges with scale, noise, reliability and expense.

On the other hand, hybrid quantum-classical computing synthesises existing applications that can now successfully add quantum architectures with GPU-accelerated classical compute architectures. GPU acceleration can help simulate QPU systems for early algorithm research and work with hardware QPUs to offload or otherwise distribute parts of a larger application where GPUs are a more appropriate compute element.

Advantages 

Illuminating the benefits, NVIDIA revealed that QODA connects quantum hardware makers to a massive new class of developers who can now easily incorporate quantum computing into their applications. 

Simultaneously, hardware makers could contribute different types of quantum processors. Software makers, on the other hand, could gain the ability to programme and develop applications for a wide variety of hybrid quantum systems in the same languages and using the same tools as the leading scientific computing applications of today. 

Analogous to when CUDA opened up a new type of hardware and programming paradigm, we expect software builders to help develop an ecosystem of hybrid quantum applications running on top of QODA in application areas like pharmaceuticals, energy, finance, logistics, and more.”

—NVIDIA 

CUDA ≠ QODA 

While the company looks to boost the quantum tech ecosystem, another question that comes to mind is—will QODA cannibalise CUDA or other parts of its business? 

The team responds that interoperability is a core design priority. They emphasise that “QODA will work in concert with CUDA, standard language parallelism, OpenACC, OpenMP, and more”. Further, they explained that this would enable domain scientists, who will be able to incrementally introduce quantum acceleration while complementing support of the programming platform across GPU/CPU and hard/simulated QPUs.

What will NVIDIA get out of this? 

NVIDIA said its existing customers are already using NVIDIA GPUs and highly specialised software—NVIDIA cuQuantum—to develop individual quantum circuits. With QODA, developers can now build complete quantum applications simulated with NVIDIA cuQuantum on GPU-accelerated supercomputers. 

In addition, NVIDIA revealed that many types of organisations are investing in quantum approaches currently, with investments coming from government agencies, education institutions and industry. 

NVIDIA believes that partnering across ecosystems and democratising software and hardware innovation would help increase the amount of hardware, software and ISVs working on quantum solutions. 

Boosting the quantum computing partner ecosystem 

The company recently collaborated with quantum hardware providers. This includes IQM Quantum Computers, Pasqal, Quantinuum, Quantum Brilliance, and Xanadu; software providers QC Ware and Zapata; and supercomputing centres—Forschungszentrum Jülich, Lawrence Berkeley National Laboratory (JUNIQ) and Oak Ridge National Laboratory.

Alex Chernoguzov, the chief engineer at Quantinuum, said that it partnered with NVIDIA to enable users of Quantinnum’s H-series quantum processors, powered by Honeywell, to program and develop the next gen of hybrid quantum-classical applications with QODA. He further revealed that the partnership brings together the best performing classical computers with their world-class quantum processors. 

Zapata’s CTO, Yudong Cao, said that QODA would enable HPC developers to accelerate their existing applications by providing an efficient way to program quantum and classical resources in a consolidated environment. He further explained that near-term applications in chemistry, drug discovery, material science and more could be seamlessly integrated with quantum computing. 

Kristel Michielsen said that QODA would help bring quantum computing closer to the HPC and AI communities. “It will speed up how they get things done without them needing to do all the low-level programming, so it makes their life much easier”, she adds, explaining that many researchers would be using QODA to try out hybrid quantum-classical computers—over the coming year and beyond.

More Great AIM Stories

Amit Raja Naik
Amit Raja Naik is a seasoned technology journalist who covers everything from data science to machine learning and artificial intelligence for Analytics India Magazine, where he examines the trends, challenges, ideas, and transformations across the industry.

Our Upcoming Events

Conference, in-person (Bangalore)
Machine Learning Developers Summit (MLDS) 2023
19-20th Jan, 2023

Conference, in-person (Bangalore)
Rising 2023 | Women in Tech Conference
16-17th Mar, 2023

Conference, in-person (Bangalore)
Data Engineering Summit (DES) 2023
27-28th Apr, 2023

Conference, in-person (Bangalore)
MachineCon 2023
23rd Jun, 2023

Conference, in-person (Bangalore)
Cypher 2023
20-22nd Sep, 2023

3 Ways to Join our Community

Whatsapp group

Discover special offers, top stories, upcoming events, and more.

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Subscribe to our newsletter

Get the latest updates from AIM