I³MS - Mueller Seminar
Prof. Dr. Frank Müller - Elastic and Scalable Communication Tracing, Benchmark Generation and Simulation
Computer Science, North Carolina State University
Characterizing the communication behavior of large-scale applications is a difficult and costly task due to code/system complexity and their long execution times. An alternative to running actual codes is to gather their communication traces and then replay them, which facilitates application tuning and future procurements. While past approaches lacked lossless scalable trace collection, we contribute an approach that provides orders of magnitude smaller communication traces regardless of the number of nodes while preserving structural information. We introduce intra- and inter-node compression techniques of MPI events via elastic representations, devise an efficient clustering approach to represent groups of nodes, and automatically generate communication benchmarks from applications. These benchmarks are show to significantly speed up event-based simulations of HPC network interconnects while preserving the temporal behavior of original applications, thereby paving the path to extreme-scale simulation.