DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks

TL;DR

DNN-Opt introduces a reinforcement learning inspired deep neural network framework that significantly improves the efficiency and effectiveness of analog circuit sizing, including large industrial circuits, by reducing the required samples and enhancing performance.

Contribution

It presents a novel two-stage deep learning optimization framework leveraging RL algorithms, extending to large industrial circuits with device identification, and demonstrating superior sample efficiency and performance.

Findings

Achieves 5-30x sample efficiency over existing methods.

Successfully applied to large industrial circuits.

First DNN-based circuit sizing on industrial-scale circuits.

Abstract

Analog circuit sizing takes a significant amount of manual effort in a typical design cycle. With rapidly developing technology and tight schedules, bringing automated solutions for sizing has attracted great attention. This paper presents DNN-Opt, a Reinforcement Learning (RL) inspired Deep Neural Network (DNN) based black-box optimization framework for analog circuit sizing. The key contributions of this paper are a novel sample-efficient two-stage deep learning optimization framework leveraging RL actor-critic algorithms, and a recipe to extend it on large industrial circuits using critical device identification. Our method shows 5--30x sample efficiency compared to other black-box optimization methods both on small building blocks and on large industrial circuits with better performance metrics. To the best of our knowledge, this is the first application of DNN-based circuit sizing on industrial scale circuits.