Cost model for distributed shared memory using competitive update

Jai Hoon Kim, Nitin H. Vaidya

Research output: Contribution to conferencePaper

Abstract

This paper presents a new `cost' analysis model for distributed shared memory (DSM) using competitive update protocol. The cost metric of interest here is the overhead of message passing necessary to implement DSM. This approach is based on segment model proposed previously. Input parameter for the cost analysis model proposed here is the probability density function of the number of remote updates in a segment. This distribution can quite accurately characterize many applications. The proposed model is validated by comparing analytical results obtained using the model to experimental results. The competitive update protocol for shared memory is defined using a parameter called `update limit' (or threshold). Using the proposed model, we compute the optimal update limit for competitive update protocol.

Original languageEnglish (US)
Pages112-117
Number of pages6
StatePublished - Dec 1 1997
EventProceedings of the 1997 4th International Conference on High Performance Computing, HiPC - Bangalore, India
Duration: Dec 18 1997Dec 21 1997

Other

OtherProceedings of the 1997 4th International Conference on High Performance Computing, HiPC
CityBangalore, India
Period12/18/9712/21/97

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Cost model for distributed shared memory using competitive update'. Together they form a unique fingerprint.

  • Cite this

    Kim, J. H., & Vaidya, N. H. (1997). Cost model for distributed shared memory using competitive update. 112-117. Paper presented at Proceedings of the 1997 4th International Conference on High Performance Computing, HiPC, Bangalore, India, .