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

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

Adjacency-Based Mapping of Mesh Processes for Switch-Based Cluster Systems of Irregular Topology

비규칙 토폴로지 스위치 기반 클러스터 시스템을 위한 메쉬 프로세스의 인접 기반 매핑

  • 모상만 (조선대학교 컴퓨터공학부)
  • Published : 2010.03.25
Download PDF
⟨ Previous Next ⟩

Abstract

Mapping virtual process topology to physical processor topology is one of the most important design issues in parallel programming. However, the mapping problem is complicated due to the topology irregularity and routing complexity. This paper proposes a new process mapping scheme called adjacency-based mapping (AM) for irregular cluster systems assuming that the two-dimensional mesh process topology is specified as an interprocess communication pattern. The cluster systems have been studied and developed for many years since they provide high interconnection flexibility, scalability, and expandability which are not attainable in traditional regular networks. The proposed AM tries to map neighboring processes in virtual process topology to adjacent processors in physical processor topology. Simulation study shows that the proposed AM results in better mapping quality and shorter interprocess latency compared to the conventional approaches.

가상의 프로세스 토폴로지를 물리적인 프로세서 토폴로지로 매핑하는 문제는 병렬 프로그래밍에서 가장 중요한 이슈 중의 하나이다. 그러나 이 매핑은 토폴로지 비규칙성 및 라우팅 복잡성으로 인해 어려운 문제로 여겨지고 있다. 본 논문에서는 프로세스간 통신 패턴으로 2차원 메쉬 프로세스 토폴로지를 가정하여, 비규칙 클러스터 시스템을 위한 새로운 프로세스 매핑 기법인 인접 기반 매핑(AM)을 제안한다. 클러스터 시스템은 전통적인 규칙성 네트워크에서는 달성하기 어려운 상호연결 유연성과 시스템 확장성을 제공하기 때문에 여러 해 동안 활발히 연구 개발되어 오고 있다. 제안한 AM은 가상 프로세스 토폴로지에서 이웃하는 프로세스를 물리적인 프로세서 토폴로지의 인접한 프로세서에게 매핑시킨다. 시뮬레이션 결과에 따르면, 제안한 AM은 기존 방법에 비하여 매핑 품질이 우수하고 프로세스간 지연시간이 감소하는 결과를 나타낸다.

Keywords

References

  1. H. Chen, and P. Wyckoff, "Simulation Studies of Gigabit Ethernet versus Myrinet using Real Application Cores," Proc. of 4th Workshop on Communication, Architecture, and Applications for Network-Based Parallel Computing (CANPC), 2000.
  2. R. Buyya, High Performance Cluster Computing: Architectures and Systems, Prentice-Hall Inc., NJ, 1999.
  3. G. F. Pfister, In Search of Clusters, 2nd Ed., Chapter 5, Prentice-Hall, Inc., NJ, 1998.
  4. P. Czarnul, "Dynamic Process Partitioning and Migration for Irregular Applications," Proc. of Int. Conf .on Parallel Computing in Electrical Engineering, 2002.
  5. J. M. Orduna, F. Silla, and J. Duoto, "On the Development of a Communication-Aware Task Mapping Technique," Journal of Systems Architecture, Vol. 50, No. 4, pp. 207-220, Mar. 2004. https://doi.org/10.1016/j.sysarc.2003.09.002
  6. D. Avresky and N. Natchev, "Dynamic Reconfiguration in Computer Clusters with Irregular Topologies in the Presence of Multiple Node and Link Failures," IEEE Trans. on Computers, Vol. 54, No. 5, pp. 603-615, May 2005. https://doi.org/10.1109/TC.2005.76
  7. M. D. Schroeder, et.al., "Autonet: a High-speed, Self-configuring Local Area Network Using Point-to-point Links," SRC Research Report, No.59, Digital Equipment Corporation, April 1990.
  8. A. M. Mainwaring, B. N. Chun, S. Schleimer, and D. S. Wilkerson, "System Area Network Mapping," Proc. of Annual Symp. on Parallel Algorithms and Architectures, 1997.
  9. W. Qiao and L. M. Ni, "Adaptive Routing in Irregular Networks Using Cut-Through Switches," Proc. of Int. Conf. on Parallel Processing, 1996.
  10. F. Silla and J. Duato, "On the Use of Virtual Channels in Networks of Workstations with Irregular Topology," Proc. of Workshop on Parallel Computer Routing and Communication, Also in Lecture Notes in Computer Science, Vol. 1417, pp. 202-216, 1997.
  11. F. Silla, J. Duato, A. Sivasubramaniam and C. R. Das, "Virtual Channel Multiplexing in Networks of Workstations with Irregular Topology," Proc. of Int. Conf. on High Performance Computing, pp. 147-154, Dec. 1998.
  12. C. Glass and L. Ni, "The Turn Model for Adaptive Routing," Journal of the ACM, Vol. 41 No. 4, Sep. 1994.
  13. Message Passing Interface Forum, MPI: A Message-Passing Interface Standard, Version 2.1, June 23, 2008.
  14. S. Moh, C. Yu, H. Y. Youn, B. Lee, and D. Han, "Mapping Strategies for Switch-Based Cluster Systems of Irregular Topology," Proc. of 8th Int. Conf .on Parallel and Distributed Systems, pp. 733-740, Jun. 2001.
  15. O. KrAamer and H. MAuhlenbein, "Mapping Strategies in Message-Based Multiprocessor Systems," Parallel Computing, Vol. 9, pp. 213-225, 1989. https://doi.org/10.1016/0167-8191(89)90129-4
  16. T. Hatazaki, "Rank Reordering Strategies for MPI Topology Creation Functions," Lecture Notes in Computer Science, Vol. 1497, pp. 188-195, 1998.
  17. N. Boden, et.al., "Myrinet: A Gigabit-per-Second Local Area Network," IEEE Micro, Vol. 15 No. 1, pp. 29-36, Feb. 1995. https://doi.org/10.1109/40.342015
  18. R. Kesavan, K. Bondalapati, and D. K. Panda, "Multicast on Irregular Switch-Based Networks with Wormhole Routing," Proc. of Int. Symp. on High Performance Computer Architecture, 1997.
  19. R. Kesavan and D. K. Panda, "Multicasting on Switch-Based Irregular Networks using Multi-drop Path-Based Multidestination Worms," Proc. of Workshop on Parallel Computer Routing and Communication, Also in Lecture Notes in Computer Science, Vol. 1417, pp. 217-230, 1997.
  20. R. Sivaram, D. K. Panda, and C. B. Stunkel, "Multicasting in Irregular Networks with Cut-Through Switches Using Tree-Based Multidestination Worms," Proc. of Workshop on Parallel Computer Routing and Communication, Also in Lecture Notes in Computer Science, Vol. 1417, pp. 39-52, 1997.
  21. C. B. Stunkel, R. Sivaram, and D. K. Panda, "Implementing Multidestination Worms in Switch-Based Parallel Systems: Architectural Alternatives and their Impact," Proc. of Int. Symp. on Computer Architecture, 1997.
  22. R. Calkin, R. Hempel, H.-C. Hoppe, and P. Wypior, "Portable programming with the PARMACS message-passing library," Parallel Computing, Vol. 20, pp. 614-632, 1994.
  23. R. M. Butler and E. L. Lusk, "Monitors, Messages, and Clusters: the p4 Parallel Programming System," Parallel Computing, 1994.
  24. M. J. Berger and S. H. Bokhari, "A Partitioning Strategy for Nonuniform Problems on Multiprocessors," IEEE Trans. on Computers, Vol. C-36, No. 5, pp. 570-580, May 1987. https://doi.org/10.1109/TC.1987.1676942
  25. S. H. Bokhari, "On the Mapping Problem," IEEE Trans. on Computers, Vol. C-30, No. 3, pp. 207-214, March 1981. https://doi.org/10.1109/TC.1981.1675756
  26. S. Moh, "Adjacency-Based Mesh Process Mapping for Irregular Cluster Systems," Proc. of 11th IEEE Int. Conf. on High Performance Computing and Communications, pp. 500-505, Seoul, Korea, June 2009.