An improved firework algorithm for hardware/software partitioning

Abstract

Hardware/software partitioning is a crucial step in the co-design of embedded system. It can not only shorten the R&D cycle, but also improve the performance of the product. In the co-design of embedded system, the hardware/software partitioning algorithm plays the most important role and many heuristic algorithms have been applied to solve this problem. In this paper, we introduce a novel swarm intelligence optimization algorithm called firework algorithm (FWA) and apply it to hardware/software partitioning. In order to improve the optimization accuracy and decrease the time consumed, operators in the conventional FWA are analyzed and their disadvantages are revealed. Then these operators are modified and an improved version of the conventional FWA called improved firework algorithm (IFWA) is proposed. To avoid overwhelming effects, the IFWA provides an innovative calculation of explosion amplitude and spark’s number by setting up dynamic boundaries. Besides, according to grouping and elite strategy, a new selection strategy is put forward to accelerate the convergence speed of the algorithm. Experiments on 8 instances of hardware/software partitioning are conducted in order to illustrate the performance of the proposed algorithm. Experimental results show that the IFWA outperforms significantly the FWA and several other heuristic algorithms in terms of optimization accuracy, time consumed, and convergence speed.