Performance Evaluation Tools for Message-Passing Parallel Programs
DOI:
https://doi.org/10.7494/csci.1999.1.1.3576Abstract
This article presents issues related to the analysis of the quality of parallel programs based on the paradigm of sending messages (including PVM [1], MPI [2]) and the construction of tools enabling this analysis. Information about existing tools is dispersed and usually unilaterally presented by the authors, hence the purpose of this article was to collect this information in one place and to carry out a systematic assessment of tools: their advantages and limitations. This should help you choose the right tool. The summary, based on the comparative analysis presented in the paper, proposes further actions aimed at improving the functionality of the toolsDownloads
References
PVM: Parallel Virtual Machinę. A Users’ Guide and Tutorialfor networked Parallel Computing. Cambridge, Massachusetts, MIT Press 1994
Dongarra J., Hempel R., Hey A.J.G., Walker D.W.: A proposal for a user-level, message passing interface in a distributed memory environment. Report ORNL/TM-
, 1993
Jain R.: The art ofComputersystemsperformance analysis. John Wiley & Sons 1991
Malony A.D.: Performance Observability. PhD Thesis, University of Illinois Urbana- Champain, 1990
Hollingsworth J.K., Lumpp J.E., Miller B.P.: Techniąuesfor performance measure- ment o f parallel programs. Parallel Computers: Theory and Practice (IEEE Press),
,225-240
Arrouye Y.: Environments de visualization pour l ’evaluation des performances des systemes paralleles: etude, conception et realisation. These de PhD, Institut National Polytechniąue de Grenoble, november 1995
Heath M.T., Finger J.E.: ParaGraph: A Toolfor Yizualizing Performance ofParallel Programs. Oak Ridge National Laboratory, 1994;
http://www.netlib.org/paragraph/
Geist G.A., Heath M.T., Peyton B.W., Worley P.H.: A User’s Guide to PICL: a portable instrumented Communications library. Technical Report No. ORNL/TM-
, Oak Ridge, Tennessee, Oak Ridge National Laboratory, January 1992
Lusk E.: Upshot, Technical Report CIS-TR-92-21, Argonne National Laboratory, ANL 97403, October 1992, http://www-c.mcs.anl.gov/home/lusk/upshot/index.html;
http://www.mcs.anl.gov/mpi/mpich/
Yan J.C.: Performance tuning with AIMS - an automated instrumentation and monitoring system fo r multicomputers, [w:] Proceedings o f the 27th Hawaii International Conference on System Sciences, Hawaii, 1994; http://science.nas.nasa.gov/Software/Archives/
Sarukkai S.R., Malony A.D.: Perturbation analysis ofhigh level instrumentationfor SPMDprograms, [w:] ACM SIGPLAN San Diego, CA, July 1993, Notices 44-53
Calzarossa M., Massari L., Merlo J., Tessera D.: Parallel Performance Evaluation: The Medea Tool, [w:] Liddell, H., Colbrook, A., Hertzberger, B., Sloot, P., (eds.), Proc. Int. Conf. High,, Performance Computing and Networking, Brussels, Belgium, April 1996, Springer-Verlag Lecture Notes in Computer Science 1067, 1996, 522-529; e-mail: medea@,gilda.unipv.it
Pozetti E., Serazzi G., Vetland V.: ParMon - A tool for monitoring parallel
programs, Technical Report CNR Progetto Finalizzato Sistemi Informatici e Calcolo Parallelo, R3/148, Romę, 1994.
Zima H.P., Chapman B.: Compiling for Distributed-Memory Systems, [w:l Proc. of the IEEE, 81(2), 1993,264-287,
Butler R., Lusk E.: Monitors, Messages, and Clusters: The p4 Parallel Programming System, [w:] Parallel Computing, 20, 1994, 547-564
VAMPIR/VAMPIRtrace - Performance Analysis o f MPI Programs; http://www.pallas.de/pages/vampir.htm
Kohl J.A., Geist G.A.: The PVM 3.4 Tracing facility and XPVM 1.1. [w:] Proceedings of the 29th Hawaii International Conference on System Sciences, Hawaii, 1996;
http://www.netlib.org/utk/icl/xpvm/xpvm.html
Lange F., Kroeger R., Gergeleit M.: JEWEL: Design and Implementation of a Distributed Measurement System, [w:] IEEE Transactions on Parallel and Distributed Systems, 3(6), November 1992, 657-671; http://wsv.gmd.de/aiw/AP.htm#1992 (Arbeitspapiere Nr 710)
