NVIDIA’s Modulus & Omniverse Drive Physics Models and Simulations

A manufacturing plant in Taiwan’s Silicon Valley is harnessing the power of AI-enabled digital twins to enhance energy efficiency. Wistron, a global designer and manufacturer of computers and electronics systems, has created virtual models that optimize operations and maximize throughput in its physical facilities. One notable use case involves the development of a digital copy of a room where nVidia DGX systems undergo thermal stress tests. By leveraging NVIDIA Modulus, a framework for building AI models that understand the laws of physics, Wistron was able to accurately predict airflow and temperature in the test facilities. The simulation, which would have taken 15 hours using traditional methods on a CPU, was completed in just 3.3 seconds on an NVIDIA GPU running inference with an AI model developed using Modulus. This represents a remarkable 15,000x speedup. The results were then integrated into tools and applications built by Wistron developers using NVIDIA Omniverse, a platform for creating 3D workflows and applications based on OpenUSD.

Wistron’s use of Omniverse-powered software has allowed the company to create immersive simulations that operators can interact with using VR headsets. The AI models developed using Modulus ensure that the airflows in the simulation adhere to the laws of physics. This capability has enabled Wistron to remotely control the test process and the room’s temperature in near real-time, resulting in significant time and energy savings. By combining separate models for predicting air temperature and airflow, Wistron has eliminated the risk of overheating in the test room. Additionally, the company has implemented a recommendation system to identify optimal locations for testing computer baseboards. The digital twin, connected to thousands of networked sensors, has boosted the facility’s overall energy efficiency by up to 10%. This translates to an annual electricity reduction of up to 121,600 kWh and a substantial decrease in carbon emissions by 60,192 kilograms.

Wistron is now expanding its AI model to track over a hundred variables in a space housing 50 computer racks. The team is also simulating all the mechanical details of the servers and testers. The final model will not only optimize test scheduling but also enhance the energy efficiency of the facilities’ air conditioning system. Derek Lai, a Wistron technical supervisor specializing in physics-informed neural networks, emphasized the potential of the tools and applications being developed with Omniverse to improve the layout of DGX factories, thereby enhancing throughput and overall efficiency.

Meanwhile, Siemens Energy is demonstrating the transformative power of digital industrialization using Modulus and Omniverse. The Munich-based company, responsible for generating one-sixth of the world’s electricity, achieved a remarkable 10,000x speedup in simulating a heat-recovery steam generator using a physics-informed AI model. By utilizing a digital twin to detect corrosion at an early stage, these massive systems can reduce downtime by 70%, potentially saving the industry $1.7 billion annually compared to traditional simulations that took weeks. Georg Rollmann, head of advanced analytics and AI at Siemens Energy, highlighted how the reduced computational time enables the development of energy-efficient digital twins, contributing to a sustainable, reliable, and affordable energy ecosystem.

The application of digital twins extends beyond manufacturing to various industries. Automotive companies are utilizing this technology for designing new cars and manufacturing plants. Scientists are leveraging digital twins in fields as diverse as astrophysics, genomics, and weather forecasting. Furthermore, digital twins are even being utilized to create a virtual replica of Earth, aiding in the understanding and mitigation of climate change impacts.

Physics simulations, typically run on supercomputer-class systems, consume an estimated 200 billion CPU core hours and 4 terawatt hours of energy annually. However, physics-informed AI is revolutionizing these complex workflows by accelerating them an average of 200 times faster, resulting in significant time, cost, and energy savings.

To gain further insights into the work of Wistron and industries utilizing generative AI, you can listen to a talk from GTC (GPU Technology Conference) and explore the impact of accelerated computing on sustainability.

Background Information

---

About nVidia: NVIDIA has firmly established itself as a leader in the realm of client computing, continuously pushing the boundaries of innovation in graphics and AI technologies. With a deep commitment to enhancing user experiences, NVIDIA's client computing business focuses on delivering solutions that power everything from gaming and creative workloads to enterprise applications. for its GeForce graphics cards, the company has redefined high-performance gaming, setting industry standards for realistic visuals, fluid frame rates, and immersive experiences. Complementing its gaming expertise, NVIDIA's Quadro and NVIDIA RTX graphics cards cater to professionals in design, content creation, and scientific fields, enabling real-time ray tracing and AI-driven workflows that elevate productivity and creativity to unprecedented heights. By seamlessly integrating graphics, AI, and software, NVIDIA continues to shape the landscape of client computing, fostering innovation and immersive interactions in a rapidly evolving digital world.

  

Technology Explained

---

CPU: The Central Processing Unit (CPU) is the brain of a computer, responsible for executing instructions and performing calculations. It is the most important component of a computer system, as it is responsible for controlling all other components. CPUs are used in a wide range of applications, from desktop computers to mobile devices, gaming consoles, and even supercomputers. CPUs are used to process data, execute instructions, and control the flow of information within a computer system. They are also used to control the input and output of data, as well as to store and retrieve data from memory. CPUs are essential for the functioning of any computer system, and their applications in the computer industry are vast.

---

GPU: GPU stands for Graphics Processing Unit and is a specialized type of processor designed to handle graphics-intensive tasks. It is used in the computer industry to render images, videos, and 3D graphics. GPUs are used in gaming consoles, PCs, and mobile devices to provide a smooth and immersive gaming experience. They are also used in the medical field to create 3D models of organs and tissues, and in the automotive industry to create virtual prototypes of cars. GPUs are also used in the field of artificial intelligence to process large amounts of data and create complex models. GPUs are becoming increasingly important in the computer industry as they are able to process large amounts of data quickly and efficiently.