MAPPING OF QUALITY ADJUSTABLE APPLICATIONS ON NoCBASED RECONFIGURABLE PLATFORMS USING REGION SELECTION STRATEGY AND NSGA2 ALGORITHM

Abstract

Network on Chip (NoC) and FPGA-based reconfigurable Systems on Chip are a new trend to provide high performance, flexibility, reducing cost and time to market for the embedded systems. The problem of mapping quality adjustable applications onto heterogeneous NoC-based reconfigurable platforms at run-time with resource constraints while ensuring the maximum overall quality of service of the applications is a big challenge. In this paper, we use a new approach to solve the problem of mapping quality adjustable applications onto heterogeneous NoC-based dynamically reconfigurable platforms under resource constraints while ensuring the maximum overall quality of service (QoS) of the applications. That is a combine between near convex region selection strategy and the NSGA2 algorithm. Simulation results show that this new approach improves on average up to 36,11% of overall QoS in comparison with some existing solutions.