Emerging ML-AI Techniques for Analog and RF EDA

TL;DR

This survey reviews how machine learning techniques are increasingly integrated into analog and RF electronic design automation, addressing design complexity, automation, and efficiency challenges.

Contribution

It provides a comprehensive overview of state-of-the-art ML methods applied to analog and RF EDA, highlighting emerging trends and challenges.

Findings

ML enhances automation and design quality in analog/RF circuits.

ML techniques reduce design time and improve meeting specifications.

Emerging trends include robustness to variations and interconnect parasitics.

Abstract

This survey explores the integration of machine learning (ML) into EDA workflows for analog and RF circuits, addressing challenges unique to analog design, which include complex constraints, nonlinear design spaces, and high computational costs. State-of-the-art learning and optimization techniques are reviewed for circuit tasks such as constraint formulation, topology generation, device modeling, sizing, placement, and routing. The survey highlights the capability of ML to enhance automation, improve design quality, and reduce time-to-market while meeting the target specifications of an analog or RF circuit. Emerging trends and cross-cutting challenges, including robustness to variations and considerations of interconnect parasitics, are also discussed.