Skip to main content

Vector Computers in Astronomical Data Analysis

  • Chapter
Data Analysis in Astronomy II

Part of the book series: Ettore Majorana International Science Series ((POLS,volume 21))

Abstract

Three different astronomical observatories have installed vector computers during 1985–86. These machines have been purchased with astronomy money for use principally in astronomy data analysis applications, not principally for theoretical modelling.The three installations are: This paper outlines the performance reasons why such vector machines are being chosen for astronomical data analysis applications—reasons which imply that more such vector machines will be installed in the future. The author makes several predictions for the period mid-1986 through 1988:

  • Several more vendors will enter the vector computer market,

  • Vector floating point workstations will be offered,

  • Existing scalar computers will be given vector extensions, and

  • More astronomical institutes will procure vector machines.

“A scalar computer is one that provides instructions only for manipulating data items comprising single numbers, in contrast to the vector computer that also has instructions for manipulating data items comprising an ordered set of numbers (that is to say a vector).”1

NRAO is operated by Associated Universities, Inc., under contract with the U.S. National Science

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

Bibliography—for Further Reading

  • Reference [l] above is good on comparisons between the architectures of the Cray-1, Cyber 205 and AP-120B, especially on the concept of the vector half-length of a pipeline.

    Google Scholar 

  • Ibbett, R.N. 1982, “The Architecture of High Performance Computers”, Springer-Verlag, New York. Good historical source on hardware developments; good discussion of Cray-1 architecture in section 6.4; especially good discussion of the STAR-100 and Cyber 205 in sections 7.3 and 7. 4.

    Google Scholar 

  • Kuck, D.J., Lawrie, D.H., and Sameh, A.H. (eds.) 1977, “High Speed Computer and Algorithm Organization”, Academic Press, New York. A superb reference source. Contains both facts and food for thought on a variety of issues, machines, applications, etc. See especially pp. 71–84, “An Evaluation of the Cray-1 Computer”, and pp. 287–298, “A Large Mathematical Model Implementation on the STAR-100 Computers”, and don’t overlook pp. 3–12, “It’s Really Not as Much Fun Building a Supercomputer as it is Simply Inventing One”.

    Google Scholar 

  • Kuhn, R.H., and Padua, D.A. (eds.) 1981, “Tutorial on Parallel Processing”, IEEE Computer Society. See especially pp. 464–472, “Sorting on STAR”, by H.S. Stone.

    Google Scholar 

  • Metcalf, M. 1982, “Fortran Optimization”, Academic Press, New York. Mostly concerned with scalar optimization strategies; somewhat weak on details in places. Note Chapter 10 (“Fortran Portability”). See especially the Hitachi Integrated Array Processor discussion in Chapter 11 (“Vector Processors”), and the brief discussion in Chapter 12 (“Future Fortran”) of the array processing language extensions proposed for Fortran “8X” by the ANSI X3J3 committee.

    Google Scholar 

  • Peterson, W.P. 1983, “Vector Fortran for Numerical Problems on CRAY-1”, Comm. of the A.C.M., vol. 26, pp. 1008–1021. Contains an excellent discussion of vectorization strategies appropriate for vector register machines such as Convex and Cray, plus much food for thought about other architectures.

    Google Scholar 

  • Rodrigue, G. (ed.) 1982, “Parallel Computations”, Academic Press, New York. An excellent tutorial source. See especially pp. 129–151, “Swimming Upstream: Calculating Table Lookups and Piecewise Functions” by P.F. Dubois, for a sophisticated discussion of the uses of advanced vector operators.

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1986 Plenus Press, New York

About this chapter

Cite this chapter

Wells, D.C. (1986). Vector Computers in Astronomical Data Analysis. In: Di GesĂą, V., Scarsi, L., Crane, P., Friedman, J.H., Levialdi, S. (eds) Data Analysis in Astronomy II. Ettore Majorana International Science Series, vol 21. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-2249-8_29

Download citation

  • DOI: https://doi.org/10.1007/978-1-4613-2249-8_29

  • Publisher Name: Springer, Boston, MA

  • Print ISBN: 978-1-4612-9317-0

  • Online ISBN: 978-1-4613-2249-8

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics