PIRA is a tool to automatically filter and focus Score-P's profiling to relevant program regions. This involves both static, i.e., source-code feature, and dynamic, i.e., runtime information, analysis. It uses the whole-program call-graph representation MetaCG for its analyses and has been used for automatic (a) hot-spot detection and refinement, (b) scalability analysis, (c) kernel identification, and (d) MPI load-imbalance detection.

In this talk, we present an overview of MetaCG and PIRA together with its analyses and a focus on the most recent addition of automatic (MPI) load-imbalance detection. Our experiments on the SPEC CPU 2006 suite show that PIRA automatically constructs overview measurements with runtime overhead < 10%. For the load-imbalance detection, our experiments on MPI-parallel LULESH and the Ice-sheet and Sea-level System Model~(ISSM) show that PIRA keeps the runtime overhead below 15%, while correctly identifying the existing load imbalances.

PIRA and MetaCG are available under BSD 3-clause license at https://github.com/tudasc/pira and https://github.com/tudasc/metacg.