Luminary Cloud Accelerates Engineering Simulations with NVIDIA GPUs

Engineering simulation is a critical tool used across a wide range of industries to accelerate product development, enhance safety, and optimize design. However, these simulations typically require significant high-performance computing (HPC) resources and can be time-consuming. Luminary Cloud, a member of the NVIDIA Inception program, seeks to solve these challenges by leveraging the cloud and NVIDIA GPU technology to accelerate these processes.

Challenges in Computational Fluid Dynamics

Computational fluid dynamics (CFD) plays a vital role in engineering and scientific advancements. However, several challenges hinder its widespread adoption. Recent research highlights these issues, including long simulation processing times, the need for improved simulation robustness and accuracy, inefficient model preparation, and high costs.

• Simulation processing time: Many CFD projects take weeks or even months to complete.
• Simulation robustness: The automatic meshing functionality and price/performance ratio need to be improved.
• Model preparation: Setting up a CFD simulation can be time-consuming, sometimes taking months.
• expense: High licensing costs are a major barrier, and budget constraints are a major challenge for many businesses.

Accelerated simulation using NVIDIA GPUs

NVIDIA GPUs have revolutionized fields ranging from quantum computing to climate science. A.IIt delivers processing speeds up to 1,000x faster than CPU-only processing. In CFD, acceleration can be more than 30x faster than traditional CPU-based computing. These advances have dramatically reduced the time required for complex simulations.

High-Performance Computing in the Cloud

Access to HPC resources is a common challenge in CFD. The cloud offers a solution by providing scalable and efficient HPC resources that can be accessed on demand. This approach increases cost efficiency, reduces time to market, and allows companies to leverage the latest hardware, such as NVIDIA GPUs, without having to have on-premise infrastructure.

Luminary Cloud’s Innovative Solutions

Luminary Cloud provides multiphysics solutions supporting CFD for fluid flow physics and conjugate heat transfer (CHT) for thermal management. The platform leverages cloud-based SaaS and multi-node NVIDIA GPU-accelerated computing to deliver near-real-time engineering experiences. Lumi AI, an AI-based engineering design pilot, automates mesh generation and further improves efficiency by tuning the computational mesh for higher accuracy.

In the demonstration, Luminary Cloud ran 20 parallel simulations, each with 40 million control volumes, completing in under two minutes using a modest number of GPUs. Another simulation, containing the entire aircraft geometry using 150 million control volumes, completed in about seven minutes using 40 NVIDIA A100 GPUs—a task that would have taken hours using traditional methods.

Case Study: Joby Aviation

Joby Aviation has benefited significantly from Luminary Cloud’s platform and NVIDIA GPUs. The platform has enabled Joby to rapidly iterate on designs, reducing the time required for essential redesigns and accelerating the regulatory approval process. These efficiencies are critical in the competitive market for electric air taxis.

“You can take an entire aircraft configuration and run it in minutes. You can have a level of confidence that you never had before: ‘Yes, this might work, this might not work,’” explains Gregor Mikić, Joby’s chief aerodynamicist.

Benefits of Cloud-Based CAE

Luminary Cloud’s solutions provide a new, real-time engineering experience, facilitating highly interactive simulations that accelerate the engineering process. The platform supports a variety of modeling approaches, allowing users to choose the level of accuracy that is right for their project. The user-friendly interface ensures a seamless experience, increasing productivity and enabling exploration of new areas in computational engineering.

For more information about Luminary Cloud, visit the NVIDIA Technology Blog.

Image source: Shutterstock