arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.00406eess.SPcs.LG
收藏

GCN-RL Circuit Designer:使用图神经网络和强化学习进行可迁移的晶体管尺寸设计

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

Massachusetts Institute of Technology(麻省理工学院);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Hanrui Wang, Kuan Wang, Jiacheng Yang, Linxiao Shen, Nan Sun, Hae-Seung Lee, Song Han

AI总结:

本文提出 GCN-RL Circuit Designer,结合 GCN 与强化学习实现跨工艺节点和拓扑的晶体管尺寸设计知识迁移,在四类电路上优于传统优化、随机搜索和专家设计。

摘要:

由于巨大的设计空间、复杂的性能权衡以及快速的技术迭代,自动晶体管尺寸设计是电路设计中的一个具有挑战性的问题。尽管已有大量针对单一电路的晶体管尺寸设计工作,但关于将知识从一个电路迁移到另一个电路以减少重新设计开销的研究仍然有限。本文提出 GCN-RL Circuit Designer,利用强化学习(RL)在不同工艺节点和拓扑之间迁移知识。此外,受电路即图这一简单事实启发,我们使用图卷积神经网络(GCN)学习电路拓扑表示。GCN-RL 智能体提取拓扑图的特征,其中顶点为晶体管、边为导线。与传统黑盒优化方法(贝叶斯优化、进化算法)、随机搜索和人类专家设计相比,我们基于学习的优化在四种不同电路上持续取得最高的品质因数(FoM)。在五个工艺节点和两种电路拓扑之间进行的迁移学习实验表明,带迁移学习的 RL 能够比无知识迁移的方法取得高得多的 FoM。我们的可迁移优化方法使晶体管尺寸设计和设计移植更加有效且高效。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑