Use of AI/ML in Electronic Design Automation and Engineering Simulation

Read full text Summarise with VIRAT
Authors: Prith Banerjee
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This talk will describe how AI/Machine Learning is being applied to the field of Engineering Simulation and Electronic Design Automation. First, we will describe how AI/ML can be used to speed up engineering simulation by developing surrogate models by training neural networks using actual multi-physics simulations over various CAD models, and different boundary conditions. This requires the customers to train the AI models using an AI platform. Second, we will discuss how to develop foundational models for simulation by training AI models over a wide range of CAD models and boundary conditions. This approach does not require the customer to train any AI models, but instead they can use pretrained models on any given CAD geometry. Third, we will discuss how AI/ML models are used to make simulation tools easier to use by automatically setting the parameters of the simulation tools in order to get the best performance and accuracy. Fourth, we will discuss how generative models can be used to explore new designs and optimize product designs. Next, we will explore how AI/ML methods are used in electronic design automation tools such as placement, routing, synthesis and verification using reinforcement learning. These techniques have been used for design space optimization, analog space optimization, verification space optimization, and test space optimization. Finally, we will conclude the talk by showing how Agentic AI techniques can be used in engineering simulation and EDA to automate various tasks and workflows using the concept of ''Agent Engineers''.

Fields of Study & Subjects

VLSI and FPGA Design Techniques Model Reduction and Neural Networks Machine Learning in Materials Science

Publication details

Journal / source
International Symposium on Physical Design
Pages
142–143
Publication date
15 March 2026
Language
EN