A tool for performance modeling of parallel programs

  • Authors:

  • J. A. Gonzá/lez;C. Rodrí/guez;G. Rodrí/guez;F. de Sande;M. Printista

  • Affiliations:

  • Dpto. Estadí/stica, I.O. y Computació/n, Universidad de La Laguna, La Laguna, 38271, Spain. Tel.: +34 922 318187/ Fax: +34 922 318170/ E-mail: casiano@ull.es;Dpto. Estadí/stica, I.O. y Computació/n, Universidad de La Laguna, La Laguna, 38271, Spain. Tel.: +34 922 318187/ Fax: +34 922 318170/ E-mail: casiano@ull.es (Corresponding author);Dpto. Estadí/stica, I.O. y Computació/n, Universidad de La Laguna, La Laguna, 38271, Spain. Tel.: +34 922 318187/ Fax: +34 922 318170/ E-mail: casiano@ull.es;Dpto. Estadí/stica, I.O. y Computació/n, Universidad de La Laguna, La Laguna, 38271, Spain. Tel.: +34 922 318187/ Fax: +34 922 318170/ E-mail: casiano@ull.es;Universidad Nacional de San Luis, Ejé/rcito de los Andes 950, San Luis, Argentina. E-mail: mprinti@unsl.edu.ar

  • Venue:
  • Scientific Programming
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Current performance prediction analytical models try to characterize the performance behavior of actual machines through a small set of parameters. In practice, substantial deviations are observed. These differences are due to factors as memory hierarchies or network latency. A natural approach is to associate a different proportionality constant with each basic block, and analogously, to associate different latencies and bandwidths with each "communication block". Unfortunately, to use this approach implies that the evaluation of parameters must be done for each algorithm. This is a heavy task, implying experiment design, timing, statistics, pattern recognition and multi-parameter fitting algorithms. Software support is required. We present a compiler that takes as source a C program annotated with complexity formulas and produces as output an instrumented code. The trace files obtained from the execution of the resulting code are analyzed with an interactive interpreter, giving us, among other information, the values of those parameters.