Skip to main content

A Comparative Study of the ECMWF Weather Model on Several Multiprocessor Architectures

  • Conference paper
Multiprocessing in Meteorological Models

Abstract

The European Centre for Medium-Range Weather Forecasts (ECMWF) first begun using multiprocessors in the early 1980s for the production of their weather service products. In the past few years, with the increasing number of and variety of multiprocessor systems on the market, it has become necessary to broaden the evaluation of multiprocessing. Toward this end, ECMWF has developed a suite of four benchmarks for the evaluation of multiprocessing. It should be noted that this benchmark suite is strictly for the evaluation of multiprocessing and is not in itself a complete benchmark suite. Every effort was made to allow for the study of multiprocessing and not raw performance. As a result, this study focuses on the efficiency of the multiprocessing systems available. Of the machines available on the market, only four were chosen for detailed study, partially because of their performance characteristics and partially because of the availability of hardware. The study will focus on the Cray X/MP 4-processor system, the ETA 10 (only simulations were performed), the IBM 3090/400 with vector facility, and the Floating Point Systems T series. The four benchmarks developed at ECMWF are MANDEL, MATRIX, SPEC and MODEL. Each of these is described below in terms of their structure and what aspect of multiprocessing they address.

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 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
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.

Similar content being viewed by others

References

  1. Steppeler, J., Galerkin and Finite Element Methods in Numerical Weather Prediction series: Bonner Meteorologische Abhandlungen ( Dummler, Bonn WG ) 1987.

    Google Scholar 

  2. Snelling, D. F., “Tools for Accessing Multiprocessing,” This publication.

    Google Scholar 

  3. Cray Research Inc., Fortran Reference Manual SR-0009, (Cray Research Inc.; Mendota Heights, Minnesota ), 1986.

    Google Scholar 

  4. Cray Research Inc., Programming Library Reference Manual SR-0113, (Cray Research Inc.; Mendota Heights, Minnesota ), 1986.

    Google Scholar 

  5. Dent D. W. and J. K. Gibson, A Memory Manager for Single and Multitasking Applications European Centre for Medium-Range Weather Forecasts, Technical Memorandum No. 104.

    Google Scholar 

  6. Dent, D., “The ECMWF Model Past Present and Future,” This publication.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1988 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Hoffmann, GR., Snelling, D.F. (1988). A Comparative Study of the ECMWF Weather Model on Several Multiprocessor Architectures. In: Hoffmann, GR., Snelling, D.F. (eds) Multiprocessing in Meteorological Models. Topics in Atmospheric and Oceanic Sciences. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-83248-2_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-83248-2_28

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-83250-5

  • Online ISBN: 978-3-642-83248-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics