Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

A Novel High Performance List Scheduling Algorithm for Distributed Heterogeneous Computing Systems

분산 이기종 컴퓨팅 시스템을 위한 새로운 고성능 리스트 스케줄링 알고리즘

  • Published : 2010.01.25
Download PDF
⟨ Previous Next ⟩

Abstract

Efficient Directed Acyclic Graph(DAG) scheduling is critical for achieving high performance in Distributed Heterogeneous computing System(DHCS). In this paper, we present a new high-performance scheduling algorithm, called the LCFT(Levelized Critical First Task) algorithm, for DHCS. The LCFT algorithm is a list-based scheduling that uses a new attribute to efficiently select tasks for scheduling in DHCS. The complexity of LCFT is $O(\upsilon+e)(p+log\;\upsilon)$. The performance of the algorithm has been observed by its application to some practical DAGs, and by comparing it with other existing scheduling algorithms such as PETS, HPS, HCPT and GCA in terms of the schedule length and SpeedUp. The comparison studies show that LCFT significantly outperforms PETS, HPS, HCPT and GCA in schedule length, SpeedUp.

분산 이기종 컴퓨팅 시스템(Distributed Heterogeneous Computing System, DHCS)에서 방향성 비순환 그래프(Directed Acyclic Graph, DAG)의 효율적인 스케줄링은 시스템의 높은 성능을 만드는데 매우 중요한 역할을 한다. 본 논문은 DHCS에서 고성능의 새로운 스케줄링 알고리즘인 LCFT(Levelized Critical First Task)을 제안한다. LCFT 알고리즘은 DHCS에서 스케줄링을 위해 효율적인 태스크 선택 방법을 이용하는 리스트 스케줄링 기반의 알고리즘이다. LCFT 알고리즘의 복잡도는 $O(\upsilon+e)(p+log\;\upsilon)$을 갖는다. LCFT의 성능 비교를 위해 다양한 DAG 그래프를 이용하여 기존의 알고리즘인 PETS, HPS, HCPT, GCA와 스케줄링의 길이와 속도를 실험하였으며 실험 결과 LCFT 알고리즘이 다른 알고리즘 보다 성능 향상이 있는 것을 확인할 수 있었다.

Keywords

References

  1. T.Braun, H.J. Siegel, N. Beck, L.L. Boloni, M.Maheswaran, A.I.Reuther, J.P Robertson, M.D. Theys, B.Yao, D.Hengsen, and R.F. Freund, "A Comparison Study of Static Mapping Heuristics for a Classes of Meta-Tasks on Heterogeneous Computing Systems," Proc, Heterogeneous Computing Workshop, pp.15-29, 1999.
  2. Oliver Sinnen, "Task Scheduling For Parallel Systems," Wiley, pp.7-35, 2007.
  3. J. D. Ullman, "NP-Complete Scheduling Problems," J.Computer and Systems Sciences, vol. 10, pp. 384-393, 1975. https://doi.org/10.1016/S0022-0000(75)80008-0
  4. Cristina Boeres, Jos'e Viterbo Filho and Vinod E. F. Rebello, "A cluster-based strategy for scheduling task on heterogeneous processors," Proc. 16th Symp. on Computer Architecture and High Performance Computing (SBAC-PAD), 2004.
  5. S.Darbha, D.P.Agrawal. "Optimal Scheduling Algorithm for Distributed-Memory Machines," IEEE Trans. Parallel and Distributed Systems, 9(1), 97-95, Jan. 1998. https://doi.org/10.1109/71.663861
  6. Lan Zhou, Sun Shixin, "Scheduling algorithm based on critical tasks in heterogeneous environments," Journal of Systems Engineering and Electronics, Vol. 19, No. 2, pp.398-404, 2008. https://doi.org/10.1016/S1004-4132(08)60099-7
  7. Kafil, M. and I. Ahmed, "Optimal task assignment in heterogeneous distributed computing systems," IEEE Concurrency, 6: 42-51, 1998. https://doi.org/10.1109/4434.708255
  8. Ranaweera, A. and D.P. Agrawal, "A task duplication based algorithm for heterogeneous systems," Proc. IPDPS, pp: 445-450, 2000.
  9. T.Hagras, J.Janecek "A High Performance, Low Complexity Algorithm for Compile-Time Task Scheduling in Heterogeneous Systems," Parallel and Computing, 31, 653-670, 2005. https://doi.org/10.1016/j.parco.2005.04.002
  10. T. Hagras and J. Janecek, "A Simple Scheduling Heuristic for Heterogeneous Computing. Environments," IEEE Proceedings of Second International Symposium on Parallel and. Distributed Computing (ISPDC'03), pp. 104– 110, October 2003.
  11. 윤완오, 윤정희, 이창호, 김효기, 최상방, "분산 이기종 컴퓨팅 시스템에서 효율적인 리스트 스케줄링 알고리즘," 전자공학회 논문지, 제46권 CI편, 제3호, 86-95쪽, 2009년 5월.
  12. H. Togcuglou, S, Hariri and M.Y. Wu, "Performance Effective and Low-Complexity Task Scheduling for Heterogeneous Computing," IEEE Trans. On Parallel and Distributed Systems, vol 13, No.3, Feb. 2002.
  13. H. Togcuglou, S, Hariri and M.Y. Wu, "Task Scheduling Algorithms for Heterogeneous Processor," Proceeding of the HCW, pp.3-14, 1999.
  14. Ching-Hsien Hsu, Chih-Wei Hsieh and Chao-Tung Yang, "A Generalized Critical Task Anticipation Technique for DAG Scheduling," ICA3PP, LNCS 4494, pp.493-505, 2007.
  15. Michael A. Iverson, F. Ozgunner and Gregory J. Follen, "Parallelizing Existing Applications in a Distributed Heterogeneous Environment," Proceeding Heterogeneous Computing Workshop, pp.93-100, 1995.
  16. E. Ilavarasan and P. Thambidurai, "Low Complexity Performance Effective Task Scheduling Algorithm for Heterogeneous Computing Environments," Journal of Computer Sciences 3(2), pp. 94-103, 2007. https://doi.org/10.3844/jcssp.2007.94.103
  17. E. Ilavarasan, P. Thambidurai and R. Mahilmannan, "High Performance Task Scheduling Algorithm for Heterogeneous Computing System," LNCS 3718, pp. 193-203, 2005.
  18. Takao Tobita and Hironory kasahara, "A Standard Task Graph Set for Fair Evaluation of Multiprocessor Scheduling Algorithms," Journal of Scheduling, 5, pp. 379-394, 2002. https://doi.org/10.1002/jos.116
  19. http://www.kasahara.elec.waseda.ac.jp.