System-Level Modeling and Simulation of MPSoC Run-Time Management Using Execution Traces Analysis

Abstract

Dynamic management of modern Multi-Processors System on Chip (MPSoC) become mandatory for optimization purpose. Evaluation of these run-time resource management strategies in MPSoCs is essential early in the design process to guarantee a reduced design cycle. However, most of the existing system-level simulation-based evaluation frameworks consider static application mapping and do not allow runtime management effects to be evaluated. In this paper, we present a modeling and simulation approach that allows integration of run-time management strategies in multicore system simulation. We have integrated the proposed approach in an industrial modeling and simulation framework. A case-study with seven applications (85 running tasks in total) on a heterogeneous multicore platform is considered and different management strategies are evaluated according to latency and power consumption criteria.