Abstract:

Design automation of analog circuits has long been sought. However, achieving robust and efficient analog design automation continues to be a significant challenge. This paper proposes a learning framework, ROSE-Opt, to achieve robust and efficient analog circuit parameter optimization. ROSE-Opt has two important features. First, it incorporates key domain knowledge of analog circuit design, such as circuit topology, couplings between circuit specifications, and variations of process, voltage, and temperature, into the learning loop. This strategy facilitates the training of an artificial agent capable of achieving design goals by identifying device parameters that are optimal and robust. Second, it exploits a two-level optimization method, that is, integrating Bayesian optimization (BO) with reinforcement learning (RL) to improve training efficiency. In particular, BO is used for coarse search by quickly finding an initial starting point for optimization. This sets a solid foundation to efficiently train the RL agent with fewer samples. Experimental evaluations on circuit benchmarks show a promising sampling efficiency and an extraordinary figure of merit in terms of design efficiency and design success rate of our framework, as compared to prior methods. Furthermore, this work thoroughly studies the performance of different RL optimization algorithms, such as Deep Deterministic Policy Gradients (DDPG) with an off- policy learning mechanism and Proximal Policy Optimization (PPO) with an on-policy learning mechanism. This investigation provides users with guidance on choosing the appropriate RL algorithms to optimize the parameters of analog circuit devices. Finally, ROSE-Opt has also been studied to demonstrate promise in parasitic-aware device optimization for analog circuits. In summary, our work reports a knowledge-infused RL design automation framework for reliable and efficient optimization of analog circuits’ device parameters. The codes of our method are open-sourced at https://github.com/xz-group/RoSE.