In modern HPC systems, performance measurements are often disturbed by noise.Because repeating measurements to increase confidence in their results is costly, alternative noise-resilient techniques are desirable. Therefore, we implement a logical clock, which does not rely on real-time measurements, in Score-P. We explore several methods to model computational work with the clock increment, counting OpenMP loop iterations, LLVM basic blocks/statements, or hardware counters.We demonstrate the strengths and weaknesses of using logical time stamps in a trace analysis workflow with Score-P and Scalasca, by evaluating the performance problems we can find in three MPI+OpenMP mini-apps.By design, logical measurements reliably show algorithmic issues, such as load imbalance, but cannot capture external aspects of program execution, for example memory contention.In summary, logical-time based measurements are a specialized but valuable addition to the performance analyst's toolbox.

This repository contains computational artifacts for the paper "Are Noise-resilient Logical Timers useful for Performance Analysis?" to be submitted to ProTools@SC24. See also the SC24 reproducibility initiative. Contains Source code of Score-P , including implementation of the logical clock algorithm from the paper Software to post-process the Cube files generated by measurements Benchmarks Source code Configuration skripts Measurement results, including output logs, Cube files Post-processing skripts and results