Abstract
Scheduling algorithm impacts system substantially in terms of throughput and load balance. Traditional methods rely on static criteria, such as earliest finishing time, critical path, and the importance of the nodes, to prioritise workloads towards various hardware settings. In practice, however, a global static scheduling method often works suboptimally given the dependence complexity among tasks and the performance diversity on separate hardware configurations. To cope with such issue, in this paper, we propose an improved heterogeneous dynamic list scheduling algorithm (IHDSA) to balance workload across heterogeneous cores and optimize communication overhead adaptively. The proposed algorithm performs three steps. First, it transforms the DAG task graph into a list and marks job status. Then, it calculates the shortest completion time of three distinctive scheduling schemes and selects the best solution among the three. Finally, it sets up thresholds for computing units and monitors the status to balance the usage of those cores. In our experiment, the IHDSA adaptive scheduling improves the performance significantly over the static counterpart.
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
References
Ashouraie, M., Navimipour, N.J.: Priority-based task scheduling on heterogeneous resources in the expert cloud. Kybernetes 44(10), 1455–1471 (2015)
Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. Concurr. Comput. Pract. Exp. 23(2), 187–198 (2011)
Baskiyar, S., SaiRanga, P.C.: Scheduling directed a-cyclic task graphs on heterogeneous network of workstations to minimize schedule length. In: Proceedings of the 2003 International Conference on Parallel Processing Workshops 2003, pp. 97–103 (2003)
Bittencourt, L.F., Sakellariou, R., Madeira, E.R.M.: Dag scheduling using a lookahead variant of the heterogeneous earliest finish time algorithm. In: 2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing, pp. 27–34 (2010)
Carvalho, E., Calazans, N.L.V., Moraes, F.G.: Dynamic task mapping for MPSoCs. IEEE Des. Test Comput. 27, 26–35 (2010)
Castrillon, J., Tretter, A., Leupers, R., Ascheid, G.: Communication-aware mapping of KPN applications onto heterogeneous MPSoCs. DAC Design Automation Conference 2012, 1262–1267 (2012)
Dathathri, R., et al.: Gluon: a communication-optimizing substrate for distributed heterogeneous graph analytics. In: PLDI, pp. 752–768. ACM (2018)
Gao, K., Suganthan, P., Chua, T., Chong, C., Cai, T., Pan, Q.K.: A two-stage artificial bee colony algorithm scheduling flexible job-shop scheduling problem with new job insertion. Expert Syst. Appl. 42(21), 7653–7663 (2015). https://doi.org/10.1016/j.eswa.2015.06.004
Zhao, H., Sakellariou, R.: Scheduling multiple DAGs onto heterogeneous systems. In: Proceedings 20th IEEE International Parallel Distributed Processing Symposium, p. 14 (2006)
Khokhar, A.A., Prasanna, V.K., Shaaban, M.E., Wang, C.: Heterogeneous computing: challenges and opportunities. IEEE Comput. 26(6), 18–27 (1993)
Middendorf, L., Zebelein, C., Haubelt, C.: Dynamic task mapping onto multi-core architectures through stream rewriting. In: 2013 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS), pp. 196–204 (2013)
Munir, E.U., Mohsin, S., Hussain, A., Nisar, M.W., Ali, S.: SDBATs: a novel algorithm for task scheduling in heterogeneous computing systems. In: 2013 IEEE International Symposium on Parallel Distributed Processing, Workshops and PhD Forum, pp. 43–53 (2013)
Möller, L., Indrusiak, L.S., Ost, L., Moraes, F., Glesner, M.: Comparative analysis of dynamic task mapping heuristics in heterogeneous NoC-based MPSoCs. In: 2012 International Symposium on System on Chip (SoC), pp. 1–4 (2012)
Nasonov, D.A., Visheratin, A.A., Butakov, N., Shindyapina, N., Melnik, M., Boukhanovsky, A.: Hybrid evolutionary workflow scheduling algorithm for dynamic heterogeneous distributed computational environment. J. Appl. Log. 24, 50–61 (2017)
Bajaj, R., Agrawal, D.P.: Improving scheduling of tasks in a heterogeneous environment. IEEE Trans. Parallel Distrib. Syst. 15(2), 107–118 (2004)
Rogers, P.: Heterogeneous system architecture overview. In: Hot Chips Symposium, pp. 1–41. IEEE (2013)
Sakellariou, R., Zhao, H.: A hybrid heuristic for DAG scheduling on heterogeneous systems. In: Proceedings of the 18th International Parallel and Distributed Processing Symposium, 2004, p. 111 (2004)
Saldaña, M., Shannon, L., Chow, P.: The routability of multiprocessor network topologies in FPGAs. In: SLIP, pp. 49–56. ACM (2006)
Samadi, Y., Zbakh, M., Tadonki, C.: E-HEFT: enhancement heterogeneous earliest finish time algorithm for task scheduling based on load balancing in cloud computing. In: HPCS, pp. 601–609. IEEE (2018)
Shekar, V., Izadi, B.: Energy aware scheduling for DAG structured applications on heterogeneous and DVS enabled processors. In: International Conference on Green Computing, pp. 495–502 (2010)
Wen, Y., O’Boyle, M.F.P.: Merge or separate?: multi-job scheduling for OpenCL Kernels on CPU/GPU platforms. In: GPGPU@PPoPP, pp. 22–31. ACM (2017)
Xu, Y., Li, K., Khac, T.T., Qiu, M.: A multiple priority queueing genetic algorithm for task scheduling on heterogeneous computing systems. In: 2012 IEEE 14th International Conference on High Performance Computing and Communication, 2012 IEEE 9th International Conference on Embedded Software and Systems, pp. 639–646 (2012)
Zarkesh-Ha, P., Davis, J.A., Meindl, J.D.: Prediction of net-length distribution for global interconnects in a heterogeneous system-on-a-chip. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 8(6), 649–659 (2000)
Acknowledgement
This work was supported by Science Foundation Ireland grant 13/RC/2094 to Lero - The Irish Software Research Centre.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, W. et al. (2020). An Improved Heterogeneous Dynamic List Schedule Algorithm. In: Qiu, M. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2020. Lecture Notes in Computer Science(), vol 12452. Springer, Cham. https://doi.org/10.1007/978-3-030-60245-1_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-60245-1_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60244-4
Online ISBN: 978-3-030-60245-1
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)