Preference-driven hierarchical hardware/software partitioning

In this paper, we present a hierarchical evolutionary ap-proach to hardware/software partitioning for real-time em-bedded systems. In contrast to most of previous approaches, we apply a hierarchical structure and dynamically deter-mine the granularity of tasks and hardware modules to adaptively optimize the solution while keeping the search space as small as possible. Two new search operators are described, which exploit the proposed hierarchical struc-ture. Efficient ranking is another problem addressed in this paper. Imprecisely Specified Multiple Attribute Utility The-ory has the advantage of constraining the solution space based on the designer’s preference, but suffers from high computation overhead. We propose a new technique to re-duce the overhead. Experiment results show that our algo-rithm is both effective and efficient. 1