This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Performance Measurement Intrusion and Perturbation Analysis
July 1992 (vol. 3 no. 4)
pp. 433-450
The authors study the instrumentation perturbations of software event tracing on the Alliant FX/80 vector multiprocessor in sequential, vector, concurrent, and vector-concurrent modes. Based on experimental data, they derive a perturbation model that can approximate true performance from instrumented execution. They analyze the effects of instrumentation coverage, (i.e., the ratio of instrumented to executed statements), source level instrumentation, and hardware interactions. The results show that perturbations in execution times for complete trace instrumentations can exceed three orders of magnitude. With appropriate models of performance perturbation, these perturbations in execution time can be reduced to less than 20% while retaining the additional information from detailed traces. In general, it is concluded that it is possible to characterize perturbations through simple models. This permits more detailed, accurate instrumentation than traditionally believed possible.

[1] W. Abu-Sufah and A. Malony, "Vector processing on the Alliant FX/8 multiprocessor," inProc. 1986 Int. Conf. Parallel Processing, Aug. 1986, pp. 559-566.
[2] R. Arlauskas, "iPSC/2 System: A Second Generation Hypercube,"Proc. Third Conf. Hypercube Concurrent Computers and Applications, 1988, pp. 33-36.
[3] S. Chen, "Large-scale and high-speed multiprocessor system for scientific applications: Cray X-MP-2 series," inProc. NATO Workshop High Speed Computat.J. Kowalik, Ed., Springer-Verlag, 1984, pp. 59-67.
[4] D. Ferrari, "Considerations on the insularity of performance evaluation,"IEEE Trans. Software Eng., vol. SE-12, no. 6, June 1986.
[5] K. Gallivan, D. Gannon, W. Jalby, A. Malony, and H. Wijshoff, "Behavioral characterization of multiprocessor memory systems: A case study," inProc. 1989 ACM SIGMETRICS Conf. Measurement Modeling Comput. Syst., Berkeley, CA, May 1989, pp. 79-88.
[6] D. Gannon, W. Jalby, and K. Gallivan, "Strategies for cache and local memory management by global program transformation," inProc. 1st Inc. Conf. Supercomputing, Athens, Greece, June 1987.
[7] H. Gantt, "Organizing for work,"Indust. Management 58, pp. 89-93, Aug. 1919.
[8] A. Malony, "Performance observability," Ph.D. dissertation, Dep. Comput. Sci., Univ. of Illinois at Urbana-Champaign, Sept. 1990.
[9] A. Malony, "Event based performance perturbation: A case study," inProc. Third ACM SIGPLAN Symp. Principles Practice Parallel Programming, Apr. 1991.
[10] A. Malony, J. Larson, and D. Reed, "Tracing Application Program Execution on the Cray X-MP and Cray 2,"Proc. 1990 Supercomputing Conf., CS Press, Los Alamitos, Calif., 1990, pp. 60-73.
[11] A. Malony and D. Reed, "Models for performance perturbation analysis," inProc. Workshop Parallel Distributed Debugging, ACM Sigplan/Sigops and Office of Naval Research, May 1991.
[12] F. McMahon, "The Livermore Fortran kernels: A computer test of the numerical performance range," Tech. Rep. UCRL-53745, Lawrence Livermore National Laboratory, Dec. 1986.
[13] R. Perron and C. Mundie, "The architecture of the Alliant FX/8 computer," inProc. Spring COMPCON '86, Mar. 1986, pp. 390-393.
[14] A. Smith, "Cache Memories,"Computing Surveys, Vol. 14, No. 3, Sept. 1982, pp. 473- 530.
[15] T. Cheung and J. E. Smith, "A simulation study of the CRAY X-MP memory system,"IEEE Trans. Computers, vol. C-35, pp. 613-622, July 1986.
[16] M. J. Wolfe, "Optimizing supercompilers for supercomputers," Ph.D. thesis, Ctr. Supercomput. Res. and Development, Univ. Illinois, Urbana-Champaign, 1980.
[17] C.Q. Yang and B.P. Miller, "Critical Path Analysis for the Execution of Parallel and Distributed Programs,"Proc. 8th Int'l Conf. Distributed Computing Systems, IEEE Computer Society Press, Los Alamitos, Calif., 1988, pp. 366-375.

Index Terms:
Index Termsperformance measurement; perturbation analysis; instrumentation perturbations; softwareevent tracing; Alliant FX/80 vector multiprocessor; true performance; instrumentedexecution; instrumentation coverage; source level instrumentation; hardwareinteractions; parallel programming; performance evaluation; perturbation theory
Citation:
A.D. Malony, D.A. Reed, H.A.G. Wijshoff, "Performance Measurement Intrusion and Perturbation Analysis," IEEE Transactions on Parallel and Distributed Systems, vol. 3, no. 4, pp. 433-450, July 1992, doi:10.1109/71.149962
Usage of this product signifies your acceptance of the Terms of Use.