PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning

2021 58TH ACM/IEEE DESIGN AUTOMATION CONFERENCE (DAC)(2021)

引用 25|浏览115
暂无评分
摘要
In this work, we present a reinforcement learning (RL) based approach to designing parallel prefix circuits such as adders or priority encoders that are fundamental to high-performance digital design. Unlike prior methods, our approach designs solutions tabula rasa purely through learning with synthesis in the loop. We design a grid-based state-action representation and an RL environment for constructing legal prefix circuits. Deep Convolutional RL agents trained on this environment produce prefix adder circuits that Pareto-dominate existing baselines with up to 16.0% and 30.2% lower area for the same delay in the 32b and 64b settings respectively. We observe that agents trained with open-source synthesis tools and cell library can design adder circuits that achieve lower area and delay than commercial tool adders in an industrial cell library.
更多
查看译文
关键词
machine learning, reinforcement learning, datapath optimization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络