How Cloud Computing, Machine Learning and High-Performance Computing (HPC) are Accelerating the Adoption of HRLES and WMLES Methods for Industry

Speaker: Neil Ashton, Amazon Web Services
March 28, 2023

Presentation

Abstract

In this talk we’ll focus on how cloud computing, machine learning and HPC are converging together (from a software and hardware perspective), to significantly accelerate the adoption of HRLES and WMLES CFD methods for industry as well as bring disruptive technologies such as machine learning closer. Using examples from automotive, aerospace and manufacturing we’ll firstly look at recent work in the 3rd automotive CFD prediction workshop (AutoCFD3) and the 4th High-Lift Prediction Workshop (HLPW-4) to demonstrate the trend with high-fidelity approaches for external aerodynamics. Secondly, we’ll focus on the convergence of AI/ML and HPC and how this is influencing the evolution of new hardware i.e., GPUs and also help explain the trend for the acceleration towards GPU-enabled mainstream CFD solvers. We’ll show examples of how the cloud can democratize access to cutting edge hardware and software and finally explore recent work around machine learning approaches and how they are offering a potential new route to innovation in CFD methods.

Biography

Neil Ashton is a Principal Computational Engineering Specialist at Amazon Web Services (AWS), as well as being a fellow of the Institute of Mechanical Engineering (IMechE). He leads the Amazon-wide CFD working group and acts as a CFD subject matter expert across the diverse departments using CFD at Amazon. Prior to joining AWS he obtained a Masters and Ph.D. at the University of Manchester, and previous positions were at the University of Oxford, NASA Ames Research Center, and Lotus Formula 1 Team, as well as consultancy roles for a range of automotive and aerospace companies. His expertise is on applying and developing the next generation of CFD approaches with a particular focus on interplay between high-fidelity turbulence models, machine learning and high-performance computing. He created the Automotive CFD Prediction Workshop (whose 4th edition is happening in September 2024), and has lead the hybrid RANS-LES technical working group for the 5th AIAA High-Lift Prediction CFD Workshop.

Seminar Participation

Attending In Person

For select seminars, you may wish to attend in-person if you are in the vicinity of NASA Ames Research Center. These AMS seminars are held in Building N258 in Room 127, just off the front lobby. Sessions available to attend in-person will be indicated in the announcement information. In-person participants without NASA badges will need a valid visitor badge (US citizenship or permanent residency is required) to enter the facility.

Join Us Online

To attend an AMS seminar, click on the Microsoft Teams link in the seminar description. You can connect through the desktop Teams App if you have it, or you can select "Watch on the Web Instead" to enter the meeting as a guest. Please ensure that you've muted your microphone in Teams before you select "Join Now" to enter the meeting lobby.