Skip to main content
SpringerLink
Log in
Book cover

International Conference on High-Performance Computing and Networking

HPCN-Europe 1999: High-Performance Computing and Networking pp 784–793Cite as

MaDCoWS: A scalable distributed shared memory environment for massively parallel multiprocessors

  • Track C3: Computational Science
  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1593))

Abstract

In this paper we present MaDCoWS, a software implementation of a Distributed Shared Memory (DSM) runtime system, specifically designed for massively parallel 2-D grid multiprocessors. The system takes advantage of the network topology in order to minimise the paths of the message sequences realising the shared operations. As a result its performance is increased and the system becomes scalable even to very large processor numbers. We present the basic ideas for 2-D optimisations, the implementation structure and results from synthetic and application benchmarks executed on a 1024 processor Parsytec GCel.

This work was partly supported by the Greek General Secretariat of Research and Technology under the YPER-94 program.

This is a preview of subscription content, log in via an institution.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Parsytec Computer GmbH, ‘PARIX 1.2: User Manual', 1993.

    Google Scholar 

  2. Cordsen, J. et al., W. ‘On the Coexistence of Shared-Memory and Message Passing in the Programming of Parallel Applications'. In Proc. of the HPCNE'97, pp. 718–727, Apr 1997.

    Google Scholar 

  3. Freeh, V. W. and Andrews, G. R. ‘Dynamically Controlling False Sharing in Distributed Shared Memory'. In Proc. of the Fifth IEEE Int'l Symp. on High Performance Distributed Computing (HPDC-5), pages 403–411, August 1996.

    Google Scholar 

  4. Lamport, L. ‘How to Make a Multiprocessor Computer That Correctly Executes Multiprocess programs'. IEEE Transactions on Computers, C-28(9):690–691, Sept. 1979.

    Google Scholar 

  5. Gharachorloo, K., Gupta, A., and Hennessy, J. L. Revision to ‘Memory Consistency and Event Ordering in Scalable Shared-Memory Multiprocessors'. Technical Report CSL-TR-93-568, Computer Systems Laboratory, Stanford University, April 1993.

    Google Scholar 

  6. Dimitrelos, D and Halatsis, C. ‘Improving the Performance of Distributed Shared Memory Environments on Grid Multiprocessors', Submitted to EUROPAR'99.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Athens High Performance Computing Laboratory and Department of Informatics, University of Athens, Athens, Greece

    Dimitris Dimitrelos & Constantine Halatsis

Authors
  1. Dimitris Dimitrelos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Constantine Halatsis
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Peter Sloot Marian Bubak Alfons Hoekstra Bob Hertzberger

Rights and permissions

Reprints and permissions

Copyright information

© 1999 Springer-Verlag

About this paper

Cite this paper

Dimitrelos, D., Halatsis, C. (1999). MaDCoWS: A scalable distributed shared memory environment for massively parallel multiprocessors. In: Sloot, P., Bubak, M., Hoekstra, A., Hertzberger, B. (eds) High-Performance Computing and Networking. HPCN-Europe 1999. Lecture Notes in Computer Science, vol 1593. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0100639

Download citation

  • DOI: https://doi.org/10.1007/BFb0100639

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-65821-4

  • Online ISBN: 978-3-540-48933-7

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation