Eyeing Nvidia’s Omniverse for Fusion Reactor Design

By Oliver Peckham

March 25, 2022

With climate change accelerating and fossil fuel supplies proving increasingly contentious, ensuring a secure supply of clean energy is top-of-mind for many researchers, companies and governments. Fusion energy — which is zero-carbon and low-radioactivity — has long been the Holy Grail in this quest, but has (thus far) not been successfully scaled for production, suffering from high energy input needs and general instability of the delicate fusion reaction.

Now, as Nvidia ramps up its Omniverse tool for digital twins — physically and photographically realistic simulated duplicates of real-world objects and environments — at least one research team has been wondering: could Omniverse be used to assist in fusion reactor design?

This was the subject of a session at Nvidia’s GTC22 presented by Lee Margetts, a professor at the University of Manchester and chair of digital engineering for nuclear fusion for the UK Atomic Energy Authority (UKAEA).

“The basic idea is that we have to heat up hydrogen to very high temperatures, and then a fusion reaction occurs,” Margetts explained. “The outputs of that are helium — which is waste — and energy and neutrons. So this heats up water, which turns the water into steam and drives a steam turbine in exactly the same way as a gas- or coal-fired power station.”

The problem, of course: fusion currently requires much more energy input than it produces energy output. But research teams have made substantial headway on fusion energy recently, from a UK-based team that just last month doubled the world record for energy extracted from a fusion reaction to the much larger fusion reactor, ITER, that is under construction in France.

Margetts said that while there are many projects in the works to support ITER, “the most relevant program to this presentation is STEP,” which stands for the Spherical Tokamak for Energy Production program. “This is an initiative that aims to deliver a prototype fusion energy plant sometime before 2040. … In order to deliver that program, [we need] a revolution in the way that we carry out engineering.”

This, he said, is where Omniverse could help.

The role of digital twins in fusion reactor design

“The challenges of developing a reactor are immense,” Margetts said. “There are many different components, and we have to take into account lots of different areas of physics and engineering. And each of these, if we make a design change in one system, this has a knock-on effect on other systems. Now, this may sound like science fiction, but it would be really great if the design team could work together in a real-time simulation environment considering the design of the whole machine rather than individual subcomponents.”

“This may be realized by disruptive technologies like the Nvidia Omniverse, in concert with exascale computing and artificial intelligence,” he continued. “The latter could help us build … surrogate models of different components and subassemblies so that we could simulate the whole machine.”

Margetts compared the fusion reactor design process to film production and video game design.

“There are a number of common business drivers that each of these industries share,” he said. “The need for increased realism; the desire to support a large team of people working on the same project; and the pressure to deliver a product in a short period of time. And this brings us to the Omniverse, because what the marketing says is that the Omniverse offers improved realism; it has support for managing teams and assets; and through a codesign of rendering tools … there is an opportunity for real-time collaboration.”

But, of course, using Omniverse for fusion reactor design meant conducting a lot of testing — and, Margetts said, “in order to evaluate this from the point of view of engineering, we needed some funding to have a look.” So the team applied for and received funding from the UKAEA’s Fusion Industry Challenges program: £117,000 (~$154,000) for a six-month project to evaluate Omniverse for digital engineering of fusion reactors.

Evaluating Omniverse for fusion reactor design

The goal, Margetts explained, was to evaluate Omniverse in terms of four key questions: was it easy to add extensions for scientific software? Could the team create a digital copy of an existing plant? Were there benefits for robotic maintenance? Could they extract key information from images of plasma? Each of these played on different elements of Omniverse, from the integration of open source tools to GPU-driven tools aimed at photorealism.

GEANT4 in action. Image courtesy of the researchers.

First, they integrated GEANT4, a software package for simulating the path of particles through solid matter that fusion researchers use to simulate the path of neutrons through a fusion reactor. “What we managed to do in a very lightweight way in a very short project is to extend the Omniverse to use this simulation framework with very little coding,” Margetts said.

Vis-a-vis collaboration, he continued, the status quo was lots of engineers using lots of different software packages and collaborating offline. “It becomes very difficult to have a good picture of the status of the design of the whole reactor,” he said.

By way of contrast, another researcher on the project, Muhammad Omer, showed a demo of the interactive process as simulated through Omniverse. “We can see three different engineers working on three different components of a reactor in three different packages from three different locations,” Omer said, explaining that Omniverse helped them to achieve photorealism using Nvidia’s RTX capabilities and that they could easily compare different design options for a component within Omniverse.

Multiple engineers using different tools collaborating on fusion reactor design via Omniverse. Image courtesy of the researchers.

Then: robotics. “Within the reactor, it’s not a very nice place for human beings, and so robotic arms are used to perform maintenance,” Margetts said. “The long-going research activity is to have a look at ways of automating or ways of enabling the robot to make its own decisions. One way is to look at digital twins.” He showed a juxtaposition of a real assembly with real robots and a digital mock-up of the same scene. “For a start, the Omniverse offers a lot of different capabilities for robotics simulation and handling, and this is all already integrated and available,” he said, explaining that if Lidar, cameras and other sensor capabilities were implemented in both the real-life robots and the Omniverse robots, the benefits could be immense.

Focusing on the cameras, Margetts said that cameras within the fusion reactor could be used to offer researchers a live feed of the plasma, but that it was often confined to a single feed. “The question is, could we use that single feed to gain information about what’s going on in the plasma as a whole?”

“Scientists at the UK Atomic Energy Authority in collaboration with Imperial College London have been developing algorithms to create synthetic visualizations of plasma so that they could train neural networks to make decisions as to how to control the device or the fusion reaction,” he continued. And Omniverse, he said, could help by simulating “very accurately what a camera in the real device might be seeing,” helping to train those neural networks.

First impressions and what’s next

Overall, Margetts and his colleagues were impressed by Omniverse’s promise for fusion reactor design. “We’ve completed our phase one evaluation of the Omniverse and we’re very happy and very delighted about what we’ve seen. We believe it’s got great potential as a platform for digital engineering. What we’re hoping is that the UK Atomic Energy Authority will select our project for the next phase and invite us to submit a proposal.”

For that second phase, the researchers hope to build a prototype design platform and create digital twins of the CHIMERA facility at the Culham Centre for Fusion Energy and a robotic arm, among other goals.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire