Skip to main content
SpringerLink
Log in
Book cover

Encyclopedia of Parallel Computing pp 1191–1199Cite as

MPI-IO

  • Reference work entry

  • 316 Accesses

Synonyms

MPI-2 I/O

Definition

MPI-IO is a portable interface defined by the Message Passing Interface (MPI) Forum in order to perform parallel I/O operations within distributed memory programs, leveraging MPI key concepts such as communicators, datatypes, and collective operations. It was first introduced as the I/O chapter of the second specification of the Message Passing Interface, referred to as MPI-2.

Discussion

Introduction

In June 1994, the MPI Forum released their first draft MPI 1.0, defining point-to-point and collective communication operations between tasks (i.e., virtual processes) within a given context, called a communicator. Point-to-point communication operations could be either blocking or nonblocking. This draft also introduced the concept of a datatype describing a virtual data layout in the memory of the sending or the receiving process(es). In March 1995, a second draft MPI 1.1 was released to correct errors and make clarifications from the first draft.

Until July...

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   1,600.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD   1,799.99
Price excludes VAT (USA)
  • Durable hardcover 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

Learn about institutional subscriptions

Bibliography

  1. Allsopp NK, Hague JF, Prost JP (2001) Experiences in using MPI-IO on top of GPFS for the IFS weather forecast code. In: Proc Euro-Par, Manchester, UK

    Google Scholar 

  2. Corbett P, Feitelson D, Fineberg S, Hsu Y, Nitzberg B, Prost JP, Snir M, Traversat B, Wong P (2001) Overview of the MPI-IO parallel I/O interface. Chapter in: High performance mass storage and parallel I/O: technologies and applications, Jin H, Cortes T, Buyya R (eds). Wiley/IEEE Press, ISBN: 0-471-20809-4

    Google Scholar 

  3. Dickens P, Logan J (2008) Towards a high performance implementation of MPI-IO on the Lustre file system. In: Proc GADA’08: grid computing, high-performance and distributed applications, Monterrey, Mexico

    Google Scholar 

  4. Latham R, Ross R, Thakur R (2004) The impact of file systems on MPI-IO scalability. In: Proc EuroPVM/MPI, 2004, Budapest

    Google Scholar 

  5. Message Passing Interface Forum (1998) MPI-2: a message passing interface standard. HPCA 12(1–2)

    Google Scholar 

  6. Prost JP, Treumann R, Hedges R, Jia B, Koniges A (2001) MPI-IO/GPFS, an optimized implementation on top of GPFS. In: Proc Supercomputing, Denver, CO

    Google Scholar 

  7. Prost JP, Treumann R, Hedges R, Koniges A, White A (2000) Towards a high-performance implementation of MPI-IO on top of GPFS. In: Proc Euro-Par 2000, Munich, Germany, pp 1253–1262

    Google Scholar 

  8. Rabenseifner R, Koniges A, Prost JP, Hedges R (2004) The parallel effective I/O bandwidth benchmark: b_eff_io. Chapter in: parallel I/O for cluster computing, Cérin C, Jin H (eds). Kogan Page Science, London, ISBN 1-903996-50-3, pp 107–132

    Google Scholar 

  9. Thakur R, Gropp W, Lusk E (1996) An abstract-device interface for implementing portable parallel-I/O interfaces. In: Proc 6th Symposium on the frontiers of massively parallel computation Annapolis, MD, pp 180–187

    Chapter  Google Scholar 

  10. Thakur R, Gropp W, Lusk E (1999) On implementing MPI-IO portably and with high performance. In: Proc 6th Workshop on Input/Output in parallel and distributed systems, Atlanta, GA, pp 23–32

    Chapter  Google Scholar 

  11. Worringen J, Träff JL, Ritzdorf H (2003) Improving generic non-contiguous file access for MPI-IO. In: Proc 10th European PVM/MPI User’s Group Meeting, Venice, Italy, Lecture Notes in Computer Science, vol 2840, Springer-Verlag, pp 309–318

    Google Scholar 

  12. Yu H, Sahoo RK, Howson C, Almasi G, Castanos JG, Gupta M, Moreira JE, Parker JJ, Engelsiepen TE, Ross R, Thakur R, Latham R, Gropp W (2006) High performance file I/O for the BlueGene/L supercomputer. In: Proc 12th International symposium on high-performance computer architecture (HPCA-12), Austin, TX

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. 3 Place Carnot, 25500, Morteau, France

    Jean-Pierre Prost Dr. (Computer Research Retiree)

Authors
  1. Jean-Pierre Prost Dr.
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. University of Illinois at Urbana-Champaign, Urbana, IL, USA

    David Padua

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer Science+Business Media, LLC

About this entry

Cite this entry

Prost, JP. (2011). MPI-IO. In: Padua, D. (eds) Encyclopedia of Parallel Computing. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-09766-4_297

Download citation

Publish with us

Policies and ethics

Search

Navigation