Abstract
We consider temperature-aware, energy-efficient scheduling of streaming applications with parallelizable tasks and throughput requirement on multi-/many-core embedded devices with discrete dynamic voltage and frequency scaling (DVFS). Given the few available discrete frequency levels, we provide the task schedule in a conservative and a relaxed form so that using them adaptively decreases power consumption, i.e. lowers chip temperature, without hurting throughput in the long run. We support our proposal by a toolchain to compute the schedules and evaluate the power reduction with synthetic task sets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Moreover, the executions of the mapped tasks must be ordered in time in a kind of “puzzle” such that the total execution time is minimized or below a given threshold.
- 2.
Heterogeneous cores are possible, but we assume identical cores here for simplicity.
- 3.
We do not model the idle power further as it did not play a role in our experiments.
- 4.
Checking against \(M'\) essentially amounts to examining whether the ranking criterion places the task at the top of list for which the makespan increase is smallest when lowering operating frequency by one level. Since \((1-\epsilon ) M > M'\) is possible, the chances for a relaxed schedule differing from the conservative one increase when not solely focusing on \(M'\) for the extended deadline calculation.
- 5.
This can be avoided by treating the tasks in the order of the core group they are mapped to, and apply the above sorting only within each group. As long as only tasks of groups 1 and 2 are modified, one can simply add up the increase in runtimes.
References
Chantem, T., Hu, X., Dick, R.: Temperature-aware scheduling and assignment for hard real-time applications on MPSoCs. IEEE Trans. VLSI Syst. 19(10), 1884–1897 (2011)
Chrobak, M., Dürr, C., Hurand, M., Robert, J.: Algorithms for temperature-aware task scheduling in microprocessor systems. In: 4th International Conference on Algorithmic Aspects in Information and Management (AAIM), pp. 120–130 (2008)
Coskun, A., Simunic Rosing, T., Whisnant, K.: Temperature aware task scheduling in MPSoCs. In: Design, Automation and Test in Europe, pp. 1659–1664 (2007)
Hällis, F., Holmbacka, S., Lafond, S., Lilius, J.: Thermal Influence on the energy efficiency of workload consolidation in many-core architecture. In: 24th Tyrrhenian International Workshop on Digital Communications (2013)
Holmbacka, S., Keller, J.: Workload type-aware scheduling on big.LITTLE platforms. In: 17th International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP), pp. 3–17 (2018)
Jayaseelan, R., Mitra, T.: Temperature aware scheduling for embedded processors. J. Low Power Electron. 5(3), 363–372 (2009)
Jia, G., Yuan, Y., Wan, J., Jiang, C., Li, X., Dai, D.: Temperature-aware scheduling based on dynamic time-slice scaling. In: 14th International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP), pp. 310–322 (2014)
Jin, P., Hao, X., Wang, X., Yue, L.: Energy-efficient task scheduling for CPU-intensive streaming jobs on Hadoop. IEEE Trans. Parallel Distrib. Syst. 30(6), 1298–1311 (2019)
Kahn, G.: The semantics of a simple language for parallel programming. In: IFIP Congress on Information Processing, North-Holland, pp. 471–475 (1974)
Krzywda, J., Ali-Eldin, A., Carlson, T.E., Östberg, P.O., Elmroth, E.: Power-performance tradeoffs in data center servers: DVFS, CPU pinning, horizontal, and vertical scaling. Fut. Gener. Comput. Syst. 81, 114–128 (2018)
Matteis, T.D., Mencagli, G.: Proactive elasticity and energy awareness in data stream processing. J. Syst. Softw. 127, 302–319 (2017)
Melot, N., Kessler, C., Keller, J., Eitschberger, P.: Fast crown scheduling heuristics for energy-efficient mapping and scaling of moldable streaming tasks on manycore systems. ACM Trans. Archit. Code Optim. 11(4), 62:1–62:24 (2015)
Melot, N., Kessler, C., Keller, J., Eitschberger, P.: Co-optimizing core allocation, mapping and DVFS in streaming programs with moldable tasks for energy efficient execution on manycore architectures. In: 19th International Conference on Application Concurrency to System Design (ACSD), pp. 63–72 (2019)
Mohaqeqi,, M., Kargahi, M., Gharedaghi, F.: Temperature-aware speed scheduling in periodic real-time systems. CSI J. Comput. Sci. Eng. 12(2), 36–46 (2014)
Rajan, D., Yu, P.: Temperature-aware scheduling: when is system-throttling good enough? In: 9th International Conference on Web-Age Information Management, pp. 397–404 (2008)
Stavrinides, G.L., Karatza, H.D.: Energy-aware scheduling of real-time workflow applications in clouds utilizing DVFS and approximate computations. In: 6th International Conference on Future Internet of Things and Cloud, pp. 33–40 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kessler, C., Litzinger, S., Keller, J. (2020). Adaptive Crown Scheduling for Streaming Tasks on Many-Core Systems with Discrete DVFS. In: Schwardmann, U., et al. Euro-Par 2019: Parallel Processing Workshops. Euro-Par 2019. Lecture Notes in Computer Science(), vol 11997. Springer, Cham. https://doi.org/10.1007/978-3-030-48340-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-48340-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-48339-5
Online ISBN: 978-3-030-48340-1
eBook Packages: Computer ScienceComputer Science (R0)