SGA - a self-adaptable granularity approach for hardware/software co-design

In hardware/software co-design for SOC, the granularity selected during hardware/software partitioning has great impact on the quality of the final implementation. Different approaches determining the partitioning granularity have been developed in recent years. However, previous all approaches have fixed clustering metrics and granularity evaluation function in design process. In this paper, a self-adaptable flexible granularity approach for software/hardware co-design is presented.