Energy and thermal aware mapping for mesh-based NoC architectures using multi-objective ant colony algorithm

Where IP cores to be mapped must be carefully solved for any given application in order to optimize different performance metrics in Network-on-Chip (NoC) design flow. The optimization of different performance metrics simultaneously may cause a negative effect on each other because of the strong correlation between these performance metrics. In this paper, we propose a multi-objective ant colony algorithm (MOACA) that maps IP cores onto mesh-based NoC architectures. This algorithm is an efficient way to find the pareto-optimal front which optimizes energy consumption and hotspot temperature of NoC. The algorithm has been implemented and evaluated for synthetic generated benchmarks. Experimental results confirm the efficiency, accuracy and scalability of the algorithm.