\"\" \"\" \"\"
Go backward to Traces
Go up to Top
Go forward to Profile and Counts
RISC-Linz logo

Summary of Data Collection

The more detailed, the more intrusive and the more processing effort.
  1. Use profile and count information to obtain parameter values needed to complete performance models.
  2. Measure execution times for a range of processor counts and problem sizes, and compare results with predictions.
  3. If observed and modeled performance differ, use profile and count information to verify basic assumptions of model.
  4. If aspects are still unexplained, use tracing and study performance on a few processors. Increase processor number as understanding improves.

Author: Wolfgang Schreiner
Last modification: November 15, 1996