Parallel Program Performance Metrics: A Comparison and Validation

There are many metrics designed to assist in the performance debugging of large-scale parallel applications. We describe a new technique, called True Zeroing, that permits direct quantitative comparison of the guidance supplied by these metrics on real applications. We apply this technique to three programs that include both numeric and symbolic applications. We compare three existing metrics: Gprof, Critical Path, and Quartz/NPT, and several new variations. Critical Path provided the best overall guidance, but it was not infallible. We also include a set of recommendations to tool builders based on the experience gained during our case study. 1. Introduction Performance metrics are a tool to help programmers reduce the running time of their applications. Profiling metrics are performance metrics that can be quantified for individual program components (such as procedures). These profiling metrics help direct the programmer to the place in the program that is causing the performance ..