Ranking Cost: Building An Efficient and Scalable Circuit Routing Planner with Evolution-Based Optimization

TL;DR

This paper introduces Ranking Cost, a novel circuit routing algorithm that combines search-based and learning-based methods, achieving higher connectivity and scalability in electronic design automation.

Contribution

It proposes a new scalable routing algorithm that integrates A* search with Evolution Strategies, featuring cost maps and a trainable ranking parameter, trained end-to-end without artificial data.

Findings

Outperforms baseline algorithms in connectivity rates

Demonstrates better scalability for large-scale applications

Effective integration of search and learning methods

Abstract

Circuit routing has been a historically challenging problem in designing electronic systems such as very large-scale integration (VLSI) and printed circuit boards (PCBs). The main challenge is that connecting a large number of electronic components under specific design rules involves a very large search space. Early solutions are typically designed with hard-coded heuristics, which suffer from problems of non-optimal solutions and lack of flexibility for new design needs. Although a few learning-based methods have been proposed recently, they are typically cumbersome and hard to extend to large-scale applications. In this work, we propose a new algorithm for circuit routing, named Ranking Cost, which innovatively combines search-based methods (i.e., A* algorithm) and learning-based methods (i.e., Evolution Strategies) to form an efficient and trainable router. In our method, we introduce a new set of variables called cost maps, which can help the A* router to find out proper paths to achieve the global objective. We also train a ranking parameter, which can produce the ranking order and further improve the performance of our method. Our algorithm is trained in an end-to-end manner and does not use any artificial data or human demonstration. In the experiments, we compare with the sequential A* algorithm and a canonical reinforcement learning approach, and results show that our method outperforms these baselines with higher connectivity rates and better scalability.