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

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

An Efficient Submesh Allocation Scheme for Mesh-Connected Multicomputer Systems

메쉬 구조 다중컴퓨터 시스템을 위한 효율적인 서브메쉬 할당방법

  • 이원주 (두원공과대학 인터넷프로그래밍과) ;
  • 전창호 (한양대학교 전자컴퓨터공학과)
  • Published : 2003.11.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a new submesh allocation scheme which improves the performance of multicomputer systems. The key idea of this allocation scheme is to reduce waiting time of task by minimizing the submesh search time and the submesh a]location delay caused by external fragmentation. This scheme reduces the submesh search time by classifying independent free submeshes according to their types (square, horizontal rectangle, vertical rectangle) and searching a best-fit submesh from the classified free submesh list. If a submesh allocation delay occurs due to external fragmentation, the proposed scheme relocates tasks, executing In allocated submeshes, to another free submeshes and compacts processor fragmentation. This results in reducing the submesh allocation delay. Through simulation, we show that it is more effective to reduce the submesh allocation delay due to external fragmentation than reducing the submesh search time with respect to the waiting time of task. We also show that the proposed strategy improves the performance compared to previous strategies.

본 논문에서는 메쉬 구조 다중컴퓨터 시스템의 성능을 향상시킬 수 있는 새로운 서브메쉬 할당방법을 제안한다. 이 할당방법의 특징은 가용 서브메쉬의 탐색시간과 외적단편화로 인한 서브메쉬의 할당지연을 최소화함으로써 태스크의 대기시간을 줄이는 것이다. 이 할당방법은 가용 서브메쉬를 유형(정방형, 가로 직사각형, 세로 직사각형)에 따라 분류하고, 태스크와 동일한 유형별 가용 서브메쉬 리스트에서 최적의 서브메쉬를 찾아 할당함으로써 서브메 쉬 탐색시간을 줄인다. 또한 외적단편화로 인해 서브메쉬의 할당지연이 발생하면할당 서브메쉬에서 수행중인 태스크를 다른 가용 서브메쉬에 재배치하고, 프로세서 단편을 통합하여 할당함으로써 서브메쉬의 할당지연을 최소화한다. 시뮬레이션을 통하여 서브메쉬 탐색시간을 줄이는 방법보다 외적단편화로 인한 서브메쉬의 할당지연을 줄이는 방법이 태스크의 대기시간을 단축하는데 더 효과적임을 보인다. 그리고 제안한 할당방법이 시스템의 성능 향상 면에서 기존의 할당방법들보다 우수함을 보인다.

Keywords

References

  1. Intel Corp., A Touchstone DELTA System Descripttion, 1991
  2. Intel Corp., Paragon XP/S Product Overview, 1991
  3. R. Alverson et al., 'The Tera Computer System,' Proc. 1990 Int'l Conf. Supercomputing, pp. 1-6, Nov. 1990 https://doi.org/10.1145/77726.255132
  4. K. Hwang, Advanced computer Architecture, McGraw-Hill, 1996
  5. K. Li and K.H. Cheng, 'A Two-Dimensional Buddy System for Dynamic Resource Allocation in a Partitionable Mesh Connected system,' IEEE Journal of Parallel and Distributed Computing, vol. 12, pp. 79-83, May 1991 https://doi.org/10.1016/0743-7315(91)90032-5
  6. P.J. Chuang and N.F. Tzeng, 'An Efficient Submesh Allocation Strategy for Mesh Computer Systems,' Proc. Int'l Conf. Distributed Computing Systems, pp. 256-263, Aug. 1991 https://doi.org/10.1109/ICDCS.1991.148674
  7. J. Ding and L.N. Bhuyan, 'An Adaptive Submesh Allocation Strategy for Two-Dimensional Mesh Connected Systems,' Proc. Int'l Conf. Parallel Preocessing, pp. II-193-200, Aug. 1993 https://doi.org/10.1109/ICPP.1993.39
  8. Y. Zhu, 'Efficient Processor Allocation Strategies for Mesh Connected Parallel Computers,' IEEE Journal of Parallel and Distributed Computing, vol. 16, pp. 328-337, Dec. 1992 https://doi.org/10.1016/0743-7315(92)90016-G
  9. D.D. Sharma and D.K. Pradhan, 'A Fast and Efficient Strategy for Submesh Allocation in Mesh-Connected Parallel Computers,' IEEE Symp. Parallel and Distributed Processing, pp. 682-689, Dec. 1993 https://doi.org/10.1109/SPDP.1993.395466
  10. S. Bhattacharya and W.T. Tsai, 'Lookahead Processor Allocation in Mesh-Connected Massively Parallel Multicomputer,' Proc. Int'l Parallel Processing Symp., pp. 868-875, Apr. 1994 https://doi.org/10.1109/IPPS.1994.288204
  11. T. Liu, W.K. Huang, F. Lombardi, and L.N. Bhuyan, 'A Submesh Allocation Scheme for Mesh-Connected Multiprocessor Systems,' Proc. Int'l Conf. Parallel Processing, pp. II-159-II-163, Aug. 1995
  12. S.M. Yoo and H.Y. Youn, B. Shirazi, 'An Efficient Task Allocation Scheme for 2D Mesh Architecture,' IEEE Trans. on Parallel and Distributed Systems, vol. 8, no. 9, pp. 934-942, Sep. 1997 https://doi.org/10.1109/71.615439
  13. G.M. Kim and H.S. Yoon, 'On Submesh Allocation for Mesh Multicomputers: A Best-Fit Allocation and a Virtual Submesh Allocation for Faulty Meshes,' IEEE Trans. on Parallel and Distributed Systems, vol. 9, no. 2, pp. 175-185, Feb. 1998 https://doi.org/10.1109/71.663881
  14. C.H. Chung and J.Y. Juang, 'A Partial compaction scheme for processor allocation in hypercube multicomputers,' Proc. Int'l Conf. Parallel Processing, pp. I-211-I-217, Aug. 1990
  15. N.F. Tzeng, H.L. Chen, 'Fast Compaction in Hypercubes,' IEEE Trans. on Parallel and Distributed Systems, vol. 9, no. 1, pp. 50-56, Jan. 1998 https://doi.org/10.1109/71.655243
  16. S.M. Yoo and H. Choo, H.Y. Youn, C. Yu, Y. Lee, 'On Task Relocation in Two-Dimensional Meshes,' IEEE Journal of Parallel and Distributed Computing, vol. 60, no 5, pp. 616-638, May 2000 https://doi.org/10.1006/jpdc.1999.1604
  17. S.M. Ross, Introduction to Probability Models, sixth edition, Academic Press, 1985
  18. P. Krueger, T.H. Lai, and V.A. Radiya, 'Processor Allocation vs. Job Scheduling on Hypercube Computers,' Proc. 11th Int'l Conf. Distributed Computing Systems, pp. 394-401, Aug. 1991 https://doi.org/10.1109/ICDCS.1991.148700