GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning

Abstract

Automatic transistor sizing is a challenging problem in circuit design due to the large design space, complex performance trade-offs, and fast technological advancements. Although there has been plenty of work on transistor sizing targeting on one circuit, limited research has been done on transferring the knowledge from one circuit to another to reduce the re-design overhead. In this paper, we present GCN-RL Circuit Designer, leveraging reinforcement learning (RL) to transfer the knowledge between different technology nodes and topologies. Moreover, inspired by the simple fact that circuit is a graph, we learn on the circuit topology representation with graph convolutional neural networks (GCN). The GCN-RL agent extracts features of the topology graph whose vertices are transistors, edges are wires. Our learning-based optimization consistently achieves the highest Figures of Merit (FoM) on four different circuits compared with conventional black-box optimization methods (Bayesian Optimization, Evolutionary Algorithms), random search, and human expert designs. Experiments on transfer learning between five technology nodes and two circuit topologies demonstrate that RL with transfer learning can achieve much higher FoMs than methods without knowledge transfer. Our transferable optimization method makes transistor sizing and design porting more effective and efficient.

Accepted to the 57th Design Automation Conference (DAC 2020); 6 pages, 8 figures

References in corpus (3)

• Semi-Supervised Classification with Graph Convolutional Networks
• Practical Bayesian Optimization of Machine Learning Algorithms
• SpArch: Efficient Architecture for Sparse Matrix Multiplication

Cited by in corpus (14)

• SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
• HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
• A Survey of Machine Learning for Computer Architecture and Systems
• Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
• ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Models
• Trust-Region Method with Deep Reinforcement Learning in Analog Design Space Exploration
• Comprehensive Mapping of Continuous/Switching Circuits in CCM and DCM to Machine Learning Domain using Homogeneous Graph Neural Networks
• Machine Learning for Electronic Design Automation: A Survey
• AnaFlow: Agentic LLM-based Workflow for Reasoning-Driven Explainable and Sample-Efficient Analog Circuit Sizing
• BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matrices
• SF-SGL: Solver-Free Spectral Graph Learning from Linear Measurements
• Program-to-Circuit: Exploiting GNNs for Program Representation and Circuit Translation
• Analog Circuit Design with Dyna-Style Reinforcement Learning
• DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks