Thermal-aware task allocation and scheduling for periodic real-time applications in mesh-based heterogeneous NoCs

With continuous technology scaling, the power density and hence the temperature of Network-on-Chip (NoC) may increase rapidly. This in-turn degrades the performance of the chip and increases the chances of creating thermal hot-spots. Task allocation and scheduling (TAS) in NoC-based Multiprocessor Systems-on-Chip have significant effects on the energy consumption of the chip and the finish time of the application. Temperature profile of a chip depends on the power consumptions of the tiles and their relative positions. In this paper, we have proposed a simulated annealing based thermal-aware Task Allocation and Scheduling (TAS) method which jointly optimizes the task to core allocation and task-scheduling problem for the periodic real-time applications. It is a platform-based TAS procedure and is applicable for the Networks-on-Chip (NoCs) containing both the homogeneous and heterogeneous cores. Along with temperature minimization, our proposed method has also been applied with the objective of minimizing the finish time of the application. The trade-off between the application finish time and the peak temperature of the chip has also been analyzed in this work. An integer linear programming formulation for the TAS problem, mentioned in a recent literature, has been adopted to evaluate the accuracy of the solutions provided by our proposed method. We have also compared our method with a thermal-aware TAS technique proposed in a recent literature and found \(12.74\%\) and \(35.06\%\) improvements in the finish time of the application and the peak temperature of the chip respectively for a fully heterogeneous NoC-platform.