Machine Learning to Accelerate Electronic Design

Overview

The Golden Age of machine learning is upon EDA. Over the last few years, we have seen companies grow their ML teams and strategies, and ML research projects are emerging in all areas of EDA. However, we have not yet seen much of this investment convert into real production flows and work. This is because it is hard to turn research prototypes into production-ready ML tools that function correctly in the real world. This talk reviews a set of second-order challenges that make it difficult to bring ML solutions to production, and discusses approaches for solving them. The Solido machine-learning based variation-aware design and characterization products, acquired by Mentor in 2017, will be the focus of the talk.

What You Will Learn

• Introduction to machine learning
• Impact of ML on semiconductor
• Impact of ML on electronic design automation
• Limitation of traditional ML approaches for electronic design
• Approaches to apply ML for electronic design
• Benefits achieved in applying ML to variation-aware design and characterization

Who Should Attend

• Semiconductor management
• Analog/mixed-signal design engineer
• Digital IC design and implementation engineer
• Timing signoff engineer
• Standard cell and I/O design engineer
• Memory IP design engineer
• Library characterization engineer
• Digital engineering manager
• SoC chip architect

Products Covered

• Solido Design Automation
• Solido Characterization Suite
• Solido Variation Designer