SLDPSO-TA: Track Assignment Algorithm Based on Social Learning Discrete Particle Swarm Optimization

Abstract

In modern circuit design, the short-circuit problem is one of the key factors affecting routability. With the continuous reduction in feature sizes, the short-circuit problem grows significantly in detailed routing. Track assignment, as a crucial intermediary phase between global routing and detailed routing, plays a vital role in preprocessing the short-circuit problem. However, existing track assignment algorithms face the challenge of easily falling into local optimality. As a typical swarm intelligence technique, particle swarm optimization (PSO) is a powerful tool with excellent optimization ability to solve large-scale problems. To address the above issue, we propose an effective track assignment algorithm based on social learning discrete particle swarm optimization (SLDPSO-TA). First, an effective wire model that considers the local nets is proposed. By considering the pin distribution of local nets, this model extracts and allocates more segments to fully leverage the role of track assignment. Second, an integer encoding strategy is employed to ensure that particles within the encoding space range correspond one-to-one with the assignment scheme, effectively expanding the search space. Third, a social learning mode based on the example pool is introduced to PSO, which is composed of other particles that are superior to the current particle. By learning from various objects in the example pool, the diversity of the population is improved. Fourth, a negotiation-based refining strategy is utilized to further reduce overlap. This strategy intelligently transfers and redistributes wire segments in congested areas to reduce congestion across the entire routing panel. Experimental results on multiple benchmarks demonstrate that the proposed SLDPSO-TA can achieve the best overlap cost optimization among all the existing methods, effectively reducing congestion in critical routing areas.