Thermal-aware Task Allocation Research Articles

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.

A Fast High-Level Event-Driven Thermal Estimator for Dynamic Thermal Aware Scheduling

Thermal aware scheduling (TAS) is an important system level optimization for many-core systems. A fast event driven thermal estimation method, which includes both the dynamic and leakage power models, for monitoring temperature and guiding dynamic TAS (DTAS) is proposed in this paper. The fast event driven thermal estimation is based upon a thermal map, with occasional thermal sensor-based calibration, which is updated only when a high level event occurs. To minimize the overhead, while maintaining the estimation accuracy, prebuilt look-up-tables and predefined leakage calibration parameters are used to speed up the thermal solution. Experimental results show our method is accurate, producing thermal estimations of similar quality to an existing open-source thermal simulator, while having a considerably reduced computational complexity. Based on this predictive approach, we take full advantage of a projected future thermal map to develop several heuristic policies for DTAS. We show that our proposed predictive policies are significantly better, in terms of minimizing average/peak temperature, reducing the dynamic thermal management overhead and improving other real-time features, than existing DTAS schedulers, making them highly suitable for heuristically guiding thermal aware task allocation and scheduling.