Learning to Design Circuits
Hanrui Wang∗ EECS Massachusetts Institute of Technology Cambridge, MA 02139、Jiacheng Yang EECS Massachusetts Institute of Technology Cambridge, MA 02139、Hae-Seung Lee EECS Massachusetts Institute of Technology Cambridge, MA 02139、Song Han EECS Massachusetts Institute of Technology Cambridge, MA 02139 Equal Contribution.
Abstract
Analog IC design relies on human experts to search for parameters that satisfy circuit specifications with their experience and intuitions, which is highly labor intensive, time consuming and suboptimal. Machine learning is a promising tool to automate this process. However, supervised learning is difficult for this task due to the low availability of training data: 1) Circuit simulation is slow, thus generating large-scale dataset is time-consuming; 2) Most circuit designs are propitiatory IPs within individual IC companies, making it expensive to collect large-scale datasets. We propose Learning to Design Circuits (L2DC) to leverage reinforcement learning that learns to efficiently generate new circuits data and to optimize circuits. We fix the schematic, and optimize the parameters of the transistors automatically by training an RL agent with no prior knowledge about optimizing circuits. After iteratively getting observations, generating a new set of transistor parameters, getting a reward, and adjusting the model, L2DC is able to optimize circuits. We evaluate L2DC on two transimpedance amplifiers. Trained for a day, our RL agent can achieve comparable or better performance tha
中文速览
模拟集成电路设计长期依赖工程师凭经验手动调整晶体管参数，耗时费力且难以保证最优解，而有监督机器学习又因电路仿真慢、电路设计多为商业机密导致大规模训练数据极难获取。为此，研究者提出了L2DC（Learning to Design Circuits），用深度强化学习（reinforcement learning）框架让智能体在固定电路拓扑的前提下，通过与仿真器反复交互自主探索并优化晶体管的宽长比等参数，无需任何人工先验规则。在斯坦福EE214课程的三级和两级跨阻放大器上测试，L2DC训练约一天即可达到与人类专家相当甚至更优的设计指标，且相比网格搜索辅助的人工设计高出约250倍的采样效率，在相同运行时间下也优于贝叶斯优化。这项工作表明强化学习能有效替代人工经验完成模拟电路参数优化，为自动化芯片设计提供了一条无需大规模标注数据的可行路径。
原文 arXiv:1812.02734;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1812.02734v5