Skip to main content

Abstract

The VIRTUal System (VIRTUS) project is focused on providing advanced features for high performance communication and I/O in cluster environments. In this paper we report our experience in porting MPICH 1.1.x atop the Fast Messages library and how we used the features of FM to provide efficient communication for non-contiguous data structures. The porting concerned two different internal interfaces of MPICH 1.1.x called channel and ADI-2, respectively. The ADI-2 interface offers a rich set of primitives that allow the implementation of communication support to MPI derived data types. We present extensive experimental data gathered on Solaris, Linux and WinNT platforms that show how the ADI-2 interface achieves the same performance levels of FM for contiguous and non-contiguous data. These results confirm the effectiveness of FM’s interface and implementation in delivering the raw hardware performance of the communication subsystem to the applications.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Boden, N.J., Cohen, D., Felderman, R.E., Kalawik, A.E., Seitz, C.L., Seizovic, J.N., Su, W.-K.: Myrinet-a gigabit-per-second local-area network. IEEE Micro 15(1) (February 1995)

    Google Scholar 

  2. O’Carroll, F., Tezuka, H., Hori, A., Ishikawa, Y.: The design and implementation of zero copy MPI using commodity hardware with a high performance network. In: Procs. of International Conference on Supercomputing, Melbourne, Australia, July 13-17, pp. 243–250 (1997)

    Google Scholar 

  3. Chien, A.A., Pakin, S., Lauria, M., Buchanan, M., Hane, K., Giannini, L., Prusakova, J.: High Performance Virtual Machines (HPVM): Clusters with Super- computing APIs and Performance. In: Procs. of 8th SIAM Conference on Parallel Processing for Scientific Computing (PP 1997) (March 1997)

    Google Scholar 

  4. Dubnicki, C., Iftode, L., Felten, E., Li, K.: Software support for virtual memory-mapped communication. In: Procs. of the 1996 International Parallel Processing Symposium (August 1996)

    Google Scholar 

  5. von Eicken, T., Culler, D., Goldstein, S., Schauser, K.: Active Messages: a mechanism for integrated communication and computation. In: Procs. of the International Symposium on Computer Architecture (May 1992)

    Google Scholar 

  6. von Eicken, T., Basu, A., Buch, V., Vogels, W.: U-Net: a user-level network interface for parallel and distributed computing. In: Procs. of the 15th ACM Symposium on Operating System Principles (December 1995)

    Google Scholar 

  7. Franke, H., Wu, C.E., Riviere, M., Prattnaik, P., Snir, M.: MPI Programming Environment for IBM SP1/SP2. In: Procs. of 15th International Conference on Distributed Computing Systems, Vancouver, Canada, May 30-June 2 (1995)

    Google Scholar 

  8. Gropp, W., Lusk, E., Doss, N., Skjellum, A.: A High-Performance Portable Implementation of the MPI Message Passing Interface Standard, Tech. Rep. Preprint MCS-P567-0296, Argonne National Laboratory, available from: ftp://ftp.mcs.anl.gov/pub/mpi/workingnote/mpicharticle.ps

  9. Gropp, W., Lusk, E.: MPICH Working Note: The Secon Generation ADI for the MPICH Implementation of MPI, Tech. Rep., Argonne National Laboratory, available from: ftp://ftp.mcs.anl.gov/pub/mpi/workingnote/nextgen.ps

  10. Gropp, W., Lusk, E.: MPICH Working Note: Creating a new MPICH de- vice using the Channel interface, Technical Report, Argonne National Laboratory, available from: ftp://ftp.mcs.anl.gov/pub/mpi/workingnote/newadi.ps.

  11. Lauria, M., Chien, A.A.: MPI-FM: High performance MPI on workstation clusters. Journal of Parallel and Distributed Computing 40(1), 4–18 (1997)

    Article  Google Scholar 

  12. Lauria, M., Pakin, S., Chien, A.A.: Efficient Layering for High Speed Communication: Fast Messages 2.x. In: Procs. of the 7th High Performance Distributed Computing Conference (HPDC7), Chicago, Illinois, July 28-31 (1998)

    Google Scholar 

  13. Message Passing Interface Forum, Document for standard message-passing interface, Tech. Rep. CS-93-214, Univ. of Tennessee (November 1993)

    Google Scholar 

  14. Tezuka, H., Hori, A., Ishikawa, Y., Sato, M.: PM: An Operating System Coordinated High Performance Communication Library. In: Hertzberger, B., Sloot, P.M.A. (eds.) HPCN-Europe 1997. LNCS, vol. 1225. Springer, Heidelberg (1997)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2000 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Cristaldi, R., Iannello, G. (2000). MPI Derived Data Types Support in VIRTUS. In: Falsafi, B., Lauria, M. (eds) Network-Based Parallel Computing. Communication, Architecture, and Applications. CANPC 2000. Lecture Notes in Computer Science, vol 1797. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10720115_7

Download citation

  • DOI: https://doi.org/10.1007/10720115_7

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-67879-3

  • Online ISBN: 978-3-540-44655-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics