Theoretica chimica acta

, Volume 84, Issue 4–5, pp 363–375 | Cite as

Moving beyond message passing. Experiments with a distributed-data model

  • Robert J. Harrison
Article
Received:
Accepted:

Summary

A message-passing model provides a natural and efficient parallel implementation for many applications in chemical physics on MIMD machines. However, although the distinction between local and non-local memory is at the very heart of writing efficient parallel programs, message passing leaves all responsibility for data management to the applications. This has significant, detrimental implications for both ease of programming and efficient use of shared and distributed resources. Examined here is a simple model which increments message passing with Linda-like tools for the manipulation of distributed-data structures. This is applied to common algorithms in chemical physics.

Key words

Distributed-data model Message passing 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    iPSC/2 Users Guide (1988) Intel CorporationGoogle Scholar
  2. 2.
    Express is a product of ParaSoft, Mission Viejo, CAGoogle Scholar
  3. 3.
    Harrison RJ (1991) Int J Quant Chem in pressGoogle Scholar
  4. 4.
    p4 are a set of portable message passing routines being distributed by Ewing Lusk of the Math and Comp Sci division at Argonne. They are the current version of the tools described in Ref. [5]Google Scholar
  5. 5.
    Boyle J, Butler R, Disz T, Glickfeld B, Lusk E, Overbeek R, Patterson J, Stevens R (1987) Portable programs for parallel processors, Holt, Rinehart, Winston, NYGoogle Scholar
  6. 6.
    Geist GA, Heath MT, Peyton BW, Worley PH (1990) Oak Ridge Natl Laboratory Tech Report TM-11616:1Google Scholar
  7. 7.
    Beguelin A, Dongarra J, Geist A, Manchek R, Sunderam V (1991) Oak Ridge Natl Laboratory Tech Report TM-11826:1Google Scholar
  8. 8.
    May D (1983) ACM SIGPLAN Notices 18:69Google Scholar
  9. 9.
    Bowler KC, Kenway RD, Pawley GS, Roweth D (1984) Occam 2 Programming Language, Prentice-Hall, Englewood Cliffs, NJGoogle Scholar
  10. 10.
    The IBM LCAP project provides a counter example with use of loop and process level parallel extensions to FORTRAN on their mixed shared and local memory architecture. See Refs. [11, 12] and references thereinGoogle Scholar
  11. 11.
    Watts JE, Dupuis M, Villar HO (August 29, 1986) IBM Tech Rep KGN-78:1Google Scholar
  12. 12.
    Dupuis M, Watts JD (1987) Theor Chim Acta 71:91Google Scholar
  13. 13.
    Harrison RJ, Kendall RA (1991) Theor Chim Acta 79:337Google Scholar
  14. 14.
    Almasi GS, Gottlieb A (1989) Highly parallel computing, Benjamin/Cummings, Redwood City, CAGoogle Scholar
  15. 15.
    Andrews GR (1991) Concurrent Programming: principles and practice, Benjamin/Cummings, Redwood City, CAGoogle Scholar
  16. 16.
    Carriero N, Gelernter D (1989) Communications of the ACM 32:444Google Scholar
  17. 17.
    Foster I, Taylor S (1990) Strand, new concepts in parallel programming. Prentice-Hall, NJGoogle Scholar
  18. 18.
    Chandy KM, Misra J (1988) Parallel program design, A foundation. Addison-Wesley, Reading, MAGoogle Scholar
  19. 19.
    Carriero N, Gelernter D (1990) How to write parallel programs. A first course. MIT Press, Cambridge, MAGoogle Scholar
  20. 20.
    C-Linda is distributed commercially by Scientific Computing Associates, New Haven, ConnecticutGoogle Scholar
  21. 21.
    Chandy KM, Taylor S, Kesselman C, Foster I (February 1990) Caltech Comp. Sci. Tech. Report CS-TR-90-03:1Google Scholar
  22. 22.
    Foster I, Taylor S (January 1990) Argonne National Laboratory Report ANL/MCS-TM-137:1Google Scholar
  23. 23.
    Several tools (e.g. VAST, MIMDIZER, FORGE) are developed and distributed by Pacific Sierra, Palcerville, CA. See the article by J. Levesque in these proceedings.Google Scholar
  24. 24.
    Kuck DJ, Davidson ES, Lawrie DH, Sameh AH (1987) in: Dongarra J (ed) Experimental parallel computing architectures. Elsevier, North-Holland, Amsterdam, p 1Google Scholar
  25. 25.
    Guzzi M, Padua D, Hoeflinger J, Lawrie D (1990) J Supercomputing 3:37Google Scholar
  26. 26.
    Cooper KD, Kennedy K, Torczon L (1986) ACM SICPLAN Notices 21:58Google Scholar
  27. 27.
    Wilson G (ed) (1991) Linda-like systems and their implementation. Edinburgh Parallel Computing Centre Techn Rep 91-13Google Scholar
  28. 28.
    Bain WL (1989) ACM SIGPLAN Notices 24:95Google Scholar
  29. 29.
    Callsen CJ, Cheng I, Hagen PL, p 39 in [27].Google Scholar
  30. 30.
    Schoinas G, pp. 105 in [27]Google Scholar
  31. 31.
    Ben-Ari M (1982) Principles of concurrent programming, Prentice-Hall, Englewood Cliffs, NJGoogle Scholar
  32. 32.
    Anderson RJ, Synder L (1991) Proc IEEE 79:480Google Scholar

Copyright information

© Springer-Verlag 1993

Authors and Affiliations

  • Robert J. Harrison
    • 1
  1. 1.Theoretical Chemistry Group, Chemistry DivisionArgonne National LaboratoryArgonneUSA

Personalised recommendations