Advertisement

Hardware Measurements and Their Application on Performance Evaluation in a Processor-Array

Part of the Computing Supplementum book series (COMPUTING, volume 3)

Abstract

Hardware Measurements and Their Application on Performance Evaluation in a Processor-Array. The applicability of hardware measurements to different performance measures is discussed. As an example it is shown that software events, e.g. the process-flow, can be evaluated by means of pure hardware measurements if a good machine architecture supports the system’s organization by appropriate hardware.

Keywords

Main Memory Total Processing Time Process Number Performance Component Information Path 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Zusammenfassung

Hardware-Messungen zur Leistungsbewertung in.einem Prozessorfeld. Die Eignung von Hardware- Messungen zur Leistungsbewertung bei verschiedenen Leistungsmaßen wird diskutiert. An einem Beispiel wird gezeigt, daß Software-Ereignisse, hier die Abfolge von Prozessen, mittels reiner Hardware- Messungen bewertet werden können, wenn die Maschinenarchitektur die Systemorganisation durch geeignete Hardware unterstützt.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    AEG-Telefunken: Prozeßrechner AEG 80–40, 80–60. Befehlshandbuch, Konstanz, Pub. Nr. ESV. 16.26/0977 (1977).Google Scholar
  2. [2]
    Agrawala, A. K., Mohr, J. M., Bryant, R. M.: An approach to the workload characterization problem. Computer 9, 18–32 (1976).MATHCrossRefGoogle Scholar
  3. [3]
    Anderson, D. W., et al.: General purpose hardware monitor. IBM Techn. Disclosure Bull. 10, 1184–1186 (1968).Google Scholar
  4. [4]
    Apple, C. T.: The program monitor -A device for program Performance measurement. ACM 20th Nat. Conference 1965, pp. 66–75.Google Scholar
  5. [5]
    Aschenbrenner, R. A., et al.: The neurotron monitor system. AFIPS 39, 31–37 (1971).Google Scholar
  6. [6]
    Bode, A., Händler, W.: Classification d’architectures paralleles: Introduction de la notion ECS et application au projet EGPA. R.A.I.R.O. Informatique/Computer Science 12, 317–331 (1978).Google Scholar
  7. [7]
    Denning, P. J.: Why our approach to Performance evaluation is SDRAWKCAB. ACM Performance Evaluation Review 2, 13–16 (1973)CrossRefGoogle Scholar
  8. [8]
    Estrin, G., et al.: SNUPER-computer, a Computer in instrumentation automation. Proc. AFIPS 30, 645–656 (1967).Google Scholar
  9. [9]
    Estrin, G., Müntz, R. R., Uzgalis, R. C.: Modeling, measurement and Computer power. Proc. AFIPS 40, 725–738 (1972).Google Scholar
  10. [10]
    Ferrari, D.: Workload characterization and selection in Computer Performance measurement. Comp. 5, 18–24 (1972).Google Scholar
  11. [11]
    Ferrari, D.: An approach to the design of a learning memory manager. SIGMETRICS/CMG VIII Conf. on Computer Performance, Washington D.C., 1977.Google Scholar
  12. [12]
    Ferrari, D.: Computer systems Performance evaluation. Englewood Cliffs, N.J.: Prentice-Hall 1978.Google Scholar
  13. [13]
    Füller, S. H., Ousterhout, J. K., Raskin, L., Rubinfeld, P. I., Sindhu, P. J., Swan, R. J.: Multi- microprocessors: An overview and working example. Proc. IEEE 66, 216–228 (1978).CrossRefGoogle Scholar
  14. [14]
    Gay, F. A., Ketelsen, M. L.: Performance evaluation for graceful degrading systems. Proc. 9th Int. Symp. on Fault-Tolerant Computing, Madison, 1979, pp. 51–58.Google Scholar
  15. [15]
    Gibson, J. C: The Gibson mix. IBM Techn. Rep. 00.2043 (1970).Google Scholar
  16. [16]
    Händler, W., Klar, R.: Fitting processors to the needs of a general purpose array (EGPA). Proc. of Micro-8, Chicago, 1975, pp. 87–97.Google Scholar
  17. [17]
    Händler, W., Hofmann, F., Schneider, H. J.: A general purpose array with a broad spectrum of applications. Ist Workshop on Computer Architecture, Erlangen, May 1975 (Informatik- Fachberichte, Vol. 4), pp. 311–334. Berlin-Heidelberg-New York: Springer 1976.Google Scholar
  18. [18]
    Hellerman, L.: A measure of computational work. IEEE Trans. Comp. C-21, 439–446 (1972).MathSciNetCrossRefGoogle Scholar
  19. [19]
    Hercksen, U., Klar, R., Stelzner, J.: Instrumentierung eines Prozessor-Feldes. 9. Jahrestagung der Gl, Bonn (Informatik-Fachberichte, Vol. 19), pp. 467–478. Berlin-Heidelberg-New York: Springer 1979.Google Scholar
  20. [20]
    Hercksen, U., Hessenauer, H., Klar, R., Stelzner, J.: An integrated hardware-monitor for evaluation of process parameters in the processor array EGPA. Internal Report, University Erlangen, 1979.Google Scholar
  21. [21]
    Huang, J. C: Program instrumentation and testing. Computer 11, 25–32 (1978).CrossRefGoogle Scholar
  22. [22]
    Hughes, J.: Performance evaluation techniques and system reliability-A practical approach. ACM/NBS Performance Evaluation Workshop, San Diego, 1973.Google Scholar
  23. [23]
    Hughes, J., Cronshaw, D.: On using a hardware monitor as an intelligent peripheral. ACM Performance Evaluation Review 2, 3–19 (1973).CrossRefGoogle Scholar
  24. [24]
    IBM anonym: Throughput evaluations for IBM 7090/7094 data processing systems. Internal Report, 1963.Google Scholar
  25. [25]
    Iyer, R. K.: On the employment of variance for reliability modelling of fault tolerant systems. Proc. 9th Int. Symp. on Fault-Tolerant Computing, Madison, 1979, pp. 63–66.Google Scholar
  26. [26]
    Klar, R., Spies, P. P.: Adaptive Betriebsprogramme und ihre Unterstützung durch einen Zählmonitor. In: Betriebsprogrammierung. Vorträge des Kolloquiums des IMMD, Erlangen 1968 (Händler, W., Spies, O., eds.), pp. 151–174. München-Wien: Oldenbourg 1969.Google Scholar
  27. [27]
    Klar, R.: Messung von Rechneraktivitäten. Arbeitsberichte des IMMD, Erlangen 4, No. 2 (1971).Google Scholar
  28. [28]
    Klar, R., Schreiber, H., Widjaja, H. C.: Messungen mit dem Zählmonitor II. Arbeitsberichte des IMMD, Erlangen 8, No. 9 (1975).Google Scholar
  29. [29]
    Klar, R.: Digitale Rechenautomaten. Berlin-New York: W. de Gruyter 1975.Google Scholar
  30. [30]
    Lucas, H. C.: Performance evaluation and monitoring. Computing Surveys 3, 79–92 (1971).MATHCrossRefGoogle Scholar
  31. [31]
    Marathe, M., Füller, S.: A study of multiprocessor contention for shared data in C.mmp. SIGMETRICS/CMG VHIth Conf. on Computer Performance, Washington D.C., 1977.Google Scholar
  32. [32]
    Mayer, R. E.: A psychology of learning BASIC. Comm. ACM 22, 589–593 (1979).CrossRefGoogle Scholar
  33. [33]
    Meyer, J. F., Furchtgott, D. G., Wu, L. T.: Performability evaluation of the SIFT Computer. Proc. 9th Int. Symp. on Fault-Tolerant Computing, Madison, 1979, pp. 43–50.Google Scholar
  34. [34]
    Morgan, D. E., Banks, W., Colvin, W., Sutton, D.: A Performance measurement system for Computer networks. Information Processing 74, 29–33 (1974).Google Scholar
  35. [35]
    Nonnenmacher, W.: Das Siemens Datenverarbeitungssystem 3003. Siemens Zeitschrift 38, 141–152 (1964).Google Scholar
  36. [36]
    Rudolph, J. A.: A production implementation of an associative array processor STARAN. Proc. AFIPS 41, 229–241 (1972).Google Scholar
  37. [37]
    Schmid, E.: Rechenzeitvergleich bei Digitalrechnern. Computing 5, 163–177 (1970).MATHCrossRefGoogle Scholar
  38. [38]
    Schreiber, H.: Hardware-Messung und Analyse des Ablaufgeschehens in Rechnerkernen. Arbeitsberichte des IMMD, Erlangen 11, No. 7 (1978).Google Scholar
  39. [39]
    Schulman, F. D.: Hardware measurement device for IBM system /360 time-sharing evaluation. Proc. 22nd Nat. Conf. ACM P-67, 103–109 (1967).Google Scholar
  40. [40]
    Stang, H., Southgate, P.: Performance evaluation of third-generation Computing systems. Datamation 1969, 181–189.Google Scholar
  41. [41]
    Svoboda, L.: Online system Performance measurements with Software and hybrid monitors. ACM 4th Symp. on Operating System Principles, Yorktown Heights 1973.Google Scholar
  42. [42]
    Svoboda, L.: Computer Performance measurement and evaluation methods: Analysis and application. New York: Elsevier 1976.Google Scholar
  43. [43]
    [36]Tesdata: Warum Hardware-Messung? Eine Einführung in die Leistungsmessung an EDV- Anlagen mit Hardware-Monitoren. ONLINE, Zeitschrift für Datenverarbeitung, No. 9, 10 (1974).Google Scholar
  44. [44]
    Brooks, R. E.: Studying programmer behavior experimentally: The problems of proper methodology. CACM 23, No. 4, 207–213 (1980).MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag 1981

Authors and Affiliations

  • R. Klar
    • 1
  1. 1.Institut für Mathematische Maschinen und Datenverarbeitung (III)Universität Erlangen-NürnbergErlangenFederal Republic of Germany

Personalised recommendations