Profiling of OpenMP Tasks with Score-P

With the task construct, the OpenMP 3.0 specification introduces an additional level of parallelism that challenges established schemes of performance profiling. First, a thread may execute a sequence of interleaved task fragments the profiling system must properly distinguish to enable correct performance analyses. Furthermore, the additional parallelization dimension requires new visualization methods for presenting analysis results. Finally, as a new programming paradigm, tasking implicitly introduces paradigm-specific performance issues and creates a need for corresponding optimization strategies. This paper presents solutions to overcome the challenges of profiling applications based on OpenMP tasks. Second, the paper describes metrics that may help uncover performance problems related to tasking. We present an implementation of our solution within the Score-P performance measurement system, which we evaluate using the Barcelona OpenMP Task Suite.