Fast Digital Circuit Synthesis Framework Based on Deep Reinforcement Learning Using Scoreboard
Open Access
- 28 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 57798-57808
Abstract
In a field of circuit design that uses deep learning such as layout optimization, parameter optimization, and circuit synthesis automation, the proposed framework, fast-GateRL, addresses the digital circuit synthesis automation based on deep reinforcement learning at a CMOS transistor level. The fast-GateRL considers the threshold voltage and avoids shoot-through current paths, whereas the previous GateRL deals with transistors as ideal switches. It also achieves high-speed circuit extraction by mask generation of the prohibited and meaningless connections, intermediate rewards based on a scoreboard, and initial state selection with the trimmed circuit connections. The new connection is generated by the deep neural network to support a deep Q-network. The fast-GateRL is evaluated on 16 two-input digital logic circuits that are verified by SPICE simulation. In addition, the ablation test confirms that scoreboard and initial state selection help the proposed framework reduce the search time for final logic circuits substantially.Keywords
Funding Information
- Samsung Display Co., Ltd.
This publication has 21 references indexed in Scilit:
- Deep Reinforcement Learning for Analog Circuit Sizing with an Electrical Design Space and Sparse Rewards2022
- A survey on machine learning-based routing for VLSI physical designIntegration, 2022
- ECNet is an evolutionary context-integrated deep learning framework for protein engineeringNature Communications, 2021
- Review: Machine learning techniques in analog/RF integrated circuit design, synthesis, layout, and testIntegration, 2021
- Application of deep learning algorithms in geotechnical engineering: a short critical reviewArtificial Intelligence Review, 2021
- A survey on deep learning in medicine: Why, how and when?Information Fusion, 2021
- Semi-Supervised Artificial Neural Networks towards Analog IC Placement Recommender2020
- Exploring a Machine Learning Approach to Performance Driven Analog IC Placement2020
- LSOracle: a Logic Synthesis Framework Driven by Artificial Intelligence: Invited Paper2019
- Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures EngineeringIntegrating Materials and Manufacturing Innovation, 2018