GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning
By Hanrui Wang, Kuan Wang, Jiacheng Yang, Linxiao Shen, Nan Sun, Hae-Seung Lee, Song Han. Design Automation Conference, 2020
351 citations recorded by the source corpus.
Automatic transistor sizing is a challenging problem in circuit design due to the large design space, complex performance tradeoffs, and fast technology advancements. Although there have 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.
Subfields: Electrical and Electronic Engineering
View Paper: https://www.semanticscholar.org/paper/780270a7940c96b0c907103ff8e77dfe082f564f
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Electrical and Electronic Engineering
Citations in the corpus
- Machine Learning for Electronic Design Automation: A Survey (2021, background): “DRL is a class of algorithms that incorporated deep learning into the reinforcement learning paradigm, where an agent learns a strategy from the rewards acquired with previous actions to determine the next action.”
- HAT: Hardware-Aware Transformers for Efficient Natural Language Processing (2020, methodology): “Some also involved hardware constraints into optimizations such as MNasNet (Tan et al., 2019), ProxylessNAS (Cai et al., 2019b), FBNet (Wu et al., 2019a) and APQ (Wang et al., 2020b).”
- SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning (2020, background): “Sentence similarity regression result: 3.8 (range [1,5], the higher, the more similar) and automation [25]–[27].”