Event Actions
Abstract
Integrated systems today contain a large number of components, coupled together through complex multiphysics. The design of such systems requires the use of software tools that employ algorithmic techniques to automate the solution of underlying computational problems for analyzing and optimizing circuit performance. Electronic design automation has traditionally used a toolbox that includes numerical analysis, combinatorial optimization, graph methods, and linear/nonlinear optimization, to name a few, but in recent years, machine learning (ML) has opened new doors for enhanced computational efficiency. Where should we stay with traditional methods, and where can ML be a game-changer? This talk provides an overview of our experiences in developing automation solutions for both digital and analog integrated systems, showcasing success stories for both traditional and ML-based solutions, and hazarding educated guesses into the evolution of these approaches in the future.
Biography
Sachin S. Sapatnekar is the Henle Chair in Electrical and Computer Engineering, and a Distinguished McKnight University Professor at the University of Minnesota. His research interests include design automation methods for analog and digital circuits, circuit reliability, algorithms and architectures for machine learning, and emerging computational paradigms. He is a Fellow of the IEEE and the ACM.