Performance visualization and analysis of parallel discrete event simulations with projections

In designing software for Parallel Discrete Event Simulation (PDES), detailed performance analysis has proved essential to address the challenges of minimizing overhead, maximizing parallelism and achieving scal-ability. This paper describes Projections[12], a perfor-mance visualization and analysis tool for parallel ap-plications in CHARM++, and its usage in the analysis of PDES applications. We discuss PDES analysis from three points of view: PDES tool design, PDES simu-lation design and PDES model analysis. We describe enhancements to Projections that make PDES-specific performance visualizations possible. We also develop generic analysis capabilities that can be used by other PDES engines. We demonstrate the utility of these fea-tures with POSE[21, 22] applications. 1 1