Pattern Matching of Collective MPI Operations

Programming message passing systems can be tedious and error-prone, especially for the inexperienced user facing the sheer amount of available functionality in todays message passing libraries. Instead of choosing the most optimal communication function, many users tend to apply only a small set of well-known standard operations. This paper describes a pattern matching approach based on execution traces which detects connected groups of point-to-point communication operations that may resemble existing collective operations. After highlighting the detected patterns, users are able to improve their codes by replacing the point-to-point operations with more appropriate and efficient collective alternatives.