DocumentCode
2818692
Title
Definition of control variables for automatic performance modeling
Author
Mierendorff, Hermann ; Schwamborn, Helmut
Author_Institution
German Nat. Res. Center for Inf. Technol., St. Augustin, Germany
fYear
1997
fDate
19-21 Mar 1997
Firstpage
42
Lastpage
49
Abstract
Automatic model generation is studied as part of a hybrid modeling strategy using simulation for performance analysis. Two major steps have to be carried out in this context. The program which is being investigated has to be translated into a model. During the translation, runtime has to be estimated for numerous computational blocks of statements which are replaced by simple delays. For performance estimation, the model has finally to be analyzed by an evaluation tool. Model evaluation as well as runtime estimation of computational blocks requires values of some variables, the control variables. We discuss the problem of automatic definition of control variables in general and consider some important cases. For the implementation of a model generating tool, we concentrate on parallel Fortran programs using message passing primitives for process communication
Keywords
digital simulation; message passing; software performance evaluation; automatic performance modeling; control variable definition; message passing primitives; model generation; parallel Fortran programs; parallel program; performance analysis; performance estimation; Analytical models; Automatic control; Communication system control; Computational modeling; Delay estimation; Hybrid power systems; Message passing; Performance analysis; Runtime; State estimation;
fLanguage
English
Publisher
ieee
Conference_Titel
Advances in Parallel and Distributed Computing, 1997. Proceedings
Conference_Location
Shanghai
Print_ISBN
0-8186-7876-3
Type
conf
DOI
10.1109/APDC.1997.574012
Filename
574012
Link To Document