Skip to main content

Evaluation of 18-stage pipeline hardware sorter

  • Parallel Hashing And Sorting
  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 368))

Abstract

Since the sorting is one of the most fundamental and frequently used operation in the current computer system, we have so far developed a high speed hardware sorter.

In this paper, we present the results of the performance evaluation of the 18-stage pipeline hardware sorter. One of the key features of our sorter is its employment of novel "string length tuning" algorithm, by which any length of records can be sorted very efficiently. The sorter can sort 256K records at one time. The sorting speed is 4 Mbytes/sec. Its memory capacity is 8 Mbytes. This practical scale sorting machine is connected to the system bus of a host computer through the bus adapter. Incorporating the sorter as a device in the operating system, we have evaluated its performance. The sorter showed much higher performance than the software sort utility on the host machine.

We are now making a sorting element board into a VLSI sort chip. The future plan is also briefly presented.

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

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Kung,H.T.:The Structure of Parallel Algorithms, Advances in Computer 19,Academic Press,1980.

    Google Scholar 

  2. Yasuura,H.:The Parallel Enumeration Sorting Scheme for VLSI, IEEE, Trans. Comput. Vol.C-31, No.12, 1983.

    Google Scholar 

  3. Tanaka,Y. et.al.:Pipeline Searching and Sorting Modules as Components of a Data Flow Database Computer, IFIP 80,1980

    Google Scholar 

  4. Todd,S.:Algorithm and Hardware for Merge Sort Using Multiple Processors, IBM J.R&D, 22,5,1978.

    Google Scholar 

  5. Zeidler, H:Data handling and dedicated hardware for the sort problem, Database Machines, Springer Verlag, 1983(Proc. of IWDM-83).

    Google Scholar 

  6. Kitsuregawa,M. et.al:Architecture and Performance of Relational Algebra Machine GRACE, Int.Conf.on Parallel Processing 84,1984

    Google Scholar 

  7. Kakuta,T. et.al:The design and implementation of Relational Database Machine Delta, Database Machines Fourth International Workshop, Springer Verlag, 1985.

    Google Scholar 

  8. Torii,S. et.al.:A Relational Database System Architecture Based on Vector Processing Method, Proc. of 3rd Int. Conf. on Data Engineering, 1987.

    Google Scholar 

  9. Kitsuregawa,M.et.al:Organization of Pipeline Merge Sorter, Trans, IECE Japan, J66-D, 1983. Its English translation is available in scripta electronica japonica III, vol.14, 1983.

    Google Scholar 

  10. Kitsuregawa,M. et.al:Memory Management Algorithms in Pipeline Merge Sorter, Database Machines Fourth International Workshop, Springer Verlag, 1985.

    Google Scholar 

  11. Kitsuregawa,M. et.al: Design and implementation of high speed pipeline merge sorter with run length tuning mechanism, Proc. of 5th Int. Workshop on Database Machines, 1987(Database Machines and Knowledge Base Machines, Kluwer Academic Publishers, Kitsuregawa Ed. 1988).

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Haran Boral Pascal Faudemay

Rights and permissions

Reprints and permissions

Copyright information

© 1989 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kitsuregawa, M., Yang, W., Fushimi, S. (1989). Evaluation of 18-stage pipeline hardware sorter. In: Boral, H., Faudemay, P. (eds) Database Machines. IWDM 1989. Lecture Notes in Computer Science, vol 368. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-51324-8_33

Download citation

  • DOI: https://doi.org/10.1007/3-540-51324-8_33

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-51324-7

  • Online ISBN: 978-3-540-46197-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics