Hardware/Software Partitioning in Embedded System Based on Novel United Evolutionary Algorithm Scheme

Hardware/software partitioning is a key problem in hardware/software co-design and global optimums detection of the objective function is of vital importance in hardware/software partitioning. Though stochastic optimization strategies simulating evolution process are proved to be valuable tools, the balance between exploitation and exploration of which is difficult to be maintained. In this paper, the model of the embedded system was constructed by directed acyclic graph to obtain the objective function. Then some established techniques to improve the performance of evolutionary computation are discussed, such as uniform design,deflection and stretching the objective function, and space contraction. A novel scheme of evolutionary algorithms is proposed to solve the optimization problems through adding evolution operations to the searching space contracted regularly with these techniques. A typical evolutionary algorithm differential evolution is chosen to exhibit the performance of new scheme. The improved algorithm can avoid local optimal solution efficiently and be conveniently implemented in the field of hardware/software partitioning.