Alert button
Picture for Nan Sun

Nan Sun

Alert button

RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL

Jul 13, 2022
Wei Shi, Hanrui Wang, Jiaqi Gu, Mingjie Liu, David Pan, Song Han, Nan Sun

Figure 1 for RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL
Figure 2 for RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL
Figure 3 for RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL
Figure 4 for RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL

Analog/mixed-signal circuit design is one of the most complex and time-consuming stages in the whole chip design process. Due to various process, voltage, and temperature (PVT) variations from chip manufacturing, analog circuits inevitably suffer from performance degradation. Although there has been plenty of work on automating analog circuit design under the typical condition, limited research has been done on exploring robust designs under real and unpredictable silicon variations. Automatic analog design against variations requires prohibitive computation and time costs. To address the challenge, we present RobustAnalog, a robust circuit design framework that involves the variation information in the optimization process. Specifically, circuit optimizations under different variations are considered as a set of tasks. Similarities among tasks are leveraged and competitions are alleviated to realize a sample-efficient multi-task training. Moreover, RobustAnalog prunes the task space according to the current performance in each iteration, leading to a further simulation cost reduction. In this way, RobustAnalog can rapidly produce a set of circuit parameters that satisfies diverse constraints (e.g. gain, bandwidth, noise...) across variations. We compare RobustAnalog with Bayesian optimization, Evolutionary algorithm, and Deep Deterministic Policy Gradient (DDPG) and demonstrate that RobustAnalog can significantly reduce required optimization time by 14-30 times. Therefore, our study provides a feasible method to handle various real silicon conditions.

Viaarxiv icon

DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks

Oct 01, 2021
Ahmet F. Budak, Prateek Bhansali, Bo Liu, Nan Sun, David Z. Pan, Chandramouli V. Kashyap

Figure 1 for DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks
Figure 2 for DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks
Figure 3 for DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks
Figure 4 for DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks

Analog circuit sizing takes a significant amount of manual effort in a typical design cycle. With rapidly developing technology and tight schedules, bringing automated solutions for sizing has attracted great attention. This paper presents DNN-Opt, a Reinforcement Learning (RL) inspired Deep Neural Network (DNN) based black-box optimization framework for analog circuit sizing. The key contributions of this paper are a novel sample-efficient two-stage deep learning optimization framework leveraging RL actor-critic algorithms, and a recipe to extend it on large industrial circuits using critical device identification. Our method shows 5--30x sample efficiency compared to other black-box optimization methods both on small building blocks and on large industrial circuits with better performance metrics. To the best of our knowledge, this is the first application of DNN-based circuit sizing on industrial scale circuits.

* Accepted to 58th Design Automation Conference (DAC 2021), 6 pages, 5 figures 
Viaarxiv icon

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

Apr 30, 2020
Hanrui Wang, Kuan Wang, Jiacheng Yang, Linxiao Shen, Nan Sun, Hae-Seung Lee, Song Han

Figure 1 for GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning
Figure 2 for GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning
Figure 3 for GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning
Figure 4 for GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning

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 
Viaarxiv icon