전자공학회논문지 (Journal of the Institute of Electronics and Information Engineers)

  • 제52권3호
  • /
  • Pages.116-126
  • /
  • 2015
  • /
  • 2287-5026(pISSN)
  • /
  • 2288-159X(eISSN)
대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지
DOI QR코드

DOI QR Code

분산 이기종 컴퓨팅 시스템에서 임계노드를 고려한 태스크 스케줄링 알고리즘

A Novel Task Scheduling Algorithm Based on Critical Nodes for Distributed Heterogeneous Computing System

  • Kim, Hojoong (Department of Electronic Engineering, Inha University) ;
  • Song, Inseong (Department of Electronic Engineering, Inha University) ;
  • Jeong, Yong Su (Department of Electronic Engineering, Inha University) ;
  • Choi, SangBang (Department of Electronic Engineering, Inha University)
  • 투고 : 2014.12.15
  • 심사 : 2015.03.04
  • 발행 : 2015.03.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

분산 이기종 시스템에서 병렬 응용프로그램의 성능은 태스크를 스케줄링하는 방법에 따라 크게 영향을 받는다. 따라서 병렬 응용프로그램의 성능에 영향을 미치는 요소들을 태스크 스케줄링에 반영함으로써 주어진 환경 내에서 최적의 결과를 도출할 수 있도록 해야 한다. 일반적으로 병렬 응용프로그램의 전체 처리시간에 영향을 미치는 결정적 요소는 입력 그래프의 임계경로이다. 본 논문에서는 임계 경로 상의 임계노드를 고려한 태스크 스케줄링 알고리즘인 CLTS를 제안한다. CLTS는 우선순위 결정 단계에서 계층화를 통해 노드의 병렬처리 효율을 향상시키고 임계노드 처리에 의한 지연시간을 단축시킬 수 있도록 우선순위를 결정한다. 또 프로세서 할당 단계에서는 조건적으로 복제 기반 정책, 혹은 삽입 기반 정책을 사용하여 노드를 프로세서에 할당함으로써 전체 처리시간을 단축시킨다. 제안한 CLTS의 성능 평가를 위해 기존의 리스트 스케줄링 알고리즘인 HCFPD, DCPD와 함께 성능을 비교 평가하였다. 시뮬레이션을 통해 CLTS는 평균 SLR을 기준으로 HCPFD 대비 7.29%, DCPD 대비 8.93% 향상되었고, Speedup을 기준으로 HCPFD 대비 9.21%, DCPD 대비 7.66% 향상된 성능을 보임을 확인하였다.

In a distributed heterogeneous computing system, the performance of a parallel application greatly depends on its task scheduling algorithm. Therefore, in order to improve the performance, it is essential to consider some factors that can have effect on the performance of the parallel application in a given environment. One of the most important factors that affects the total execution time is a critical path. In this paper, we propose the CLTS algorithm for a task scheduling. The CLTS sets the priorities of all nodes to improve overall performance by applying leveling method to improve parallelism of task execution and by reducing the delay caused by waiting for execution of critical nodes in priority phase. After that, it conditionally uses insertion based policy or duplication based policy in processor allocation phase to reduce total schedule time. To evaluate the performance of the CLTS, we compared the CLTS with the DCPD and the HCPFD in our simulation. The results of the simulations show that the CLTS is better than the HCPFD by 7.29% and the DCPD by 8.93%. with respect to the average SLR, and also better than the HCPFD by 9.21% and the DCPD by 7.66% with respect to the average speedup.

키워드

참고문헌

  1. M. Maheswaran, T. D. Braun, and H. J. Siegel, "Heterogeneous distributed computing," Encyclopedia of Electrical and Electronics Engineering, Wiley, New York, Dec. 1999.
  2. H. Togcuglous, 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, pp. 260-274, Mar. 2002. https://doi.org/10.1109/71.993206
  3. T. Hagras and J. Janecek, "A high performance, low complexity algorithm for compile-time task scheduling in heterogeneous systems," Journal of Parallel Computing, vol. 31, no. 7, pp. 653-670, Jul. 2005. https://doi.org/10.1016/j.parco.2005.04.002
  4. C. Liu and C. Li, "Dynamic Critical Path Duplication Task Scheduling Algorithm for Distributed Heterogeneous Computing Systems," Proceedings of the 12th International Conference on Parallel and Distributed Systems (ICPADS'06), pp. 28-38, Minnesota, USA, Jul. 2005.
  5. E. Ilavarasan, P. Thambidurai, and R. Mahilmannan, "Performance Effective Task Scheduling Algorithm for heterogeneous Computing System," IEEE Proceedings of the 4th International Symposium on Parallel and Distributed Computing (ISPDC'05), pp. 28-38, Jul. 2005.
  6. W. Yoon, J. Yoon, J. Yoon, and S. Choi, "A Novel High Performance List Scheduling Algorithm for Distributed Heterogeneous Computing Systems Computing Systems," Journal of the Institute of Electronics and Information Engineers, vol. 47, no. 1, pp. 135-145, Jan. 2010.
  7. M. Kafil and I. Ahmed, "Optimal task assignment in heteroheneous distributed computing systems," IEEE Concurrency, vol. 6, no. 3, pp. 42-51, Jul. 1998. https://doi.org/10.1109/4434.708255
  8. A. Ranaweera and D. P. Agrawal, "A task duplication based scheduling for heterogeneous system," Proc. IPDPS, pp. 445-450, May. 2000.
  9. C. Boeres, J. V. Filho, and V. 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), pp. 214-221, Oct. 2004.