LAUSR

Hardware/software partitioning plays an important role in the co-design system of software and hardware. It can improve the performance of the embedded system to a great degree. Multi-objective hardware/software partitioning aims to optimize the system performance from multi-aspects simultaneously. In recent years, more and more heuristic algorithms are utilized to solve multi-objective problems. In this paper, we apply a firework algorithm (FWA) to solve the problem of multi-objective hardware/software partitioning. The sorting method for multi-objective solutions is described in detail. The calculation of explosion amplitude is modified according to the number of iterations. Due to binary coding, the method of generating new solutions is updated. Finally, a multi-objective FWA (MOFWA) for multi-objective hardware/software partitioning is proposed. To validate the performance of the MOFWA, experiments on six instances are conducted. The proposed MOFWA is compared with three famous multi-objective optimization algorithms, the nondominated sorting genetic algorithm II, the strength Pareto evolutionary algorithm 2, and the Pareto envelope-based selection algorithm in terms of S-metric. The experimental results show that the MOFWA significantly outperforms the three other algorithms.