A clustering algorithm for circuit partitioning

This paper describes a fast greedy clustering algorithm for circuit partitioning. The algorithm is used to generate a good initial partitioning, then a module interchange approach is used to improve the initial partitioning. The proposed algorithm is tested against three well known algorithms namely, simulated annealing, Tabu search approach, and module interchange algorithm alone using some benchmark netlist partitioning problems (between 300 to 3000 nets and modules each). Test results show that the proposed algorithm yields results comparable to that of the other approaches with a faster execution time.