Comparison of Time and Energy Oriented Scheduling for Task-Based Programs
The purpose of task scheduling is to find a beneficial assignment of tasks to execution units of a parallel system, where the specific goal is captured in a special optimization function, and tasks are usually described by corresponding properties, such as the execution time. However, today not only the parallel execution time is to be minimized, but also other metrics, such as the energy consumption. In this article, we investigate several scheduling algorithms with different frequency scaling policies. Our specific goal is to consider application specific scheduling with respect to time and energy. For this purpose, we use real measured data for the tasks leading to diverse effects concerning time, energy and power consumption. As application tasks we use the SPEC benchmarks.
KeywordsScheduling Task-based programs Energy efficiency Energy-oriented objective function SPEC benchmarks
This work was performed within the Federal Cluster of Excellence EXC 1075 “MERGE Technologies for Multifunctional Lightweight Structures” supported by the German Research Foundation (DFG). This work is also supported by the German Ministry of Science and Education (BMBF), project number 01IH16012A/B.
- 1.Aupy, G., Benoit, A., Renaud-Goud, P., Robert, Y.: Energy-aware algorithms for task graph scheduling, replica placement and checkpoint strategies. In: Khan, S.U., Zomaya, A.Y. (eds.) Handbook on Data Centers, pp. 37–80. Springer, New York (2015). https://doi.org/10.1007/978-1-4939-2092-1_2 Google Scholar
- 5.Kühnemann, M., Rauber, T., Rünger, G.: A source code analyzer for performance prediction. In: Proceedings of 18th IPDPS, Workshop on Massively Parallel Processing (CDROM). IEEE (2004). https://doi.org/10.1109/IPDPS.2004.1303333
- 7.Leung, J., Kelly, L., Anderson, J.: Handbook of Scheduling: Algorithms, Models, and Performance Analysis. CRC Press Inc., Boca Raton (2004)Google Scholar
- 15.Treibig, J., Hager, G., Wellein, G.: LIKWID: a lightweight performance-oriented tool suite for x86 multicore environments. In: Proceedings of 39th International Conference on Parallel Processing Workshops, ICPP 2010, pp. 207–216. IEEE Computer Society (2010)Google Scholar