Browse > Article
http://dx.doi.org/10.3745/KIPSTA.2007.14-A.4.215

Analysis of Performance Requirement for Large-Scale InfiniBand-based DVSM System  

Cho, Myeong-Jin (고려대학교 전자전기공학과)
Kim, Seon-Wook (고려대학교 전기전자전파공학과)
Abstract
For past years, many distributed virtual shared-memory(DVSM) systems have been studied in order to develop a low-cost shared memory system with a fast interconnection network. But the DVSM needs a lot of data and control communication between distributed processing nodes in order to provide memory consistency in software, and this communication overhead significantly dominates the overall performance. In general, the communication overhead also increases as the number of processing nodes increase, so communication overhead is a very important performance factor for developing a large-scale DVSM system. In this paper, we study the performance scalability quantitatively and qualitatively for developing a large-scale DVSM system based on the next generation interconnection network, called the InfiniBand. Based on the study, we analyze a performance requirement of the next-coming interconnection network to be used for developing a performance-scalable DVSM system in the future.
Keywords
Distributed virtual shared memory; InfiniBand; FESI protocol; Performance analysis;
Citations & Related Records
연도 인용수 순위
  • Reference
1 조명진, 김선욱, 'InfiniBand 기반 분산 가상 공유 메모리 시스템에서의프로토콜 과부하 분석,' 한국정보과학회 HPC 연구회 추계학술발표대회, pp19-26, 경희대학교,2006
2 Inho Park, Soon Wook Kim, 'The distributed virtual shared-memory system based on the Infiniband architecture,' Journal of Parallel and Distributed Computing, vol. 65, Issue 10, pp.1271-1280, 2005   DOI   ScienceOn
3 Amdahl, G.M. 'Validity of the single-processor approach to achieving large scale computing capabilities,' In AFIPS Conierence Proceedings, vol. 30, AFIPS Press, Reston, VA., pp.483 - 485, 1967   DOI
4 A. L. Cox C. Amza, S. Dwarkadas, P. Keleher, H.Lu, R. Rajamony, and W. Zwaenepoel, 'TreadMarks : Shared memory computing on networks of workstations,' In IEEE Computer, number 2, pp.18-28, 1996   DOI   ScienceOn
5 V. Aslot, M. Domeika, R. Eigenmann, G. Gaertner, W. B. Jones and B. Parady. 'SPEComp: A New Benchmark Suite for Measuring Parallel Computer Performance.' In Workshop on OpenMP Applications and Tools, pp.1-10, July 2001   DOI   ScienceOn
6 http:;/www.ksc.re.kr/infor/infor_1.htm
7 http/zwww.openmp.org/
8 Leonidas Kontothanassis, Galen Hunt, Robert Stets, Nikolaos Hardavellas, Michal, Cierniak, Srinivasan Parthasarthy, Wagner Meira, Sandhya Dwarkadas, and Michael Scott. 'VM-based shared memory on low-latency, remote-memory access networks,' ISCA-24, pp.157-169, 1997   DOI
9 Rudrajit Samanta, Angelos Bilas, Liviu Iftode, and Jaswinder P. Singh, 'Home-based SVM protocols for SMP clusters: Design, simulations, implementation and performance,' HPCA-4, pp.113-124, January 1998   DOI
10 http;//www.infinibandta.org/
11 Keleher. P., Cox. A.L., Zwaenepoel. W., 'Lazy Release Consistency for Software Distributed Shared Memory,' ISCA, pp.13-21, 1992   DOI
12 http://www.spec.org/omp/
13 Inho Park, Soon Wook Kim, 'Study of OpenMP applications on the InfiniBand-based software distributed shared-memory system,' Parallel Computing, vol. 31, Issues 10-12, pp.1099-1113, October 2005   DOI   ScienceOn
14 T. Birk and L. Liss and A. Schuster, 'Efficient Exploitation of Kernel Access to InfiniBand: a Software DSM Example,' Hot Interconnects, pp.130-135, August 2003
15 http://www.mellanox.com/