Leveraging Caliper and Benchpark to Analyze MPI Communication Patterns: Insights from AMG2023, Kripke, and Laghos

We introduce "communication regions" into the widely used Caliper HPC profiling tool. A communication region is an annotation enabling capture of metrics about the data being communicated (including statistics of these metrics), and metrics about the MPI processes involved in the communications, something not previously possible in Caliper. We explore the utility of communication regions with three representative modeling and simulation applications—AMG2023, Kripke, and Laghos—all part of the comprehensive Benchpark suite that includes Caliper annotations. Enhanced Caliper reveals detailed communication behaviors. Using Caliper and Thicket in tandem, we create new visualizations of MPI communication patterns, including halo exchanges. Our findings reveal communication bottlenecks and detailed behaviors, indicating significant utility of the special-regions addition to Caliper. The comparative scaling behavior of both CPU- and GPU-oriented systems are shown; we are able to look at different regions within a given application, and see how scalability and message-traffic metrics differ.