An Efficient Hierarchical Fuzzy Approach for System Level System-on-a-Chip Design

One of the most important bottleneck in the overall design flow of a complex embedded system is due to the simulation. Simulation occurs at every phase of the design flow. In this paper we focus on system level design proposing a novel approach to speed up the evaluation of a system configuration. The approach, which uses a fuzzy system as approximator for the different components of the system, is used to accelerate the design space exploration of a VLIW based parameterized SoC platform for the optimization of both performance and power dissipation. The experiments carried out on a multimedia benchmark suite, demonstrate the scalability and the accuracy of the proposed approach