Knowledge support and automation for performance analysis with PerfExplorer 2.0

摘要: The integration of scalable performance analysis in parallel development tools is difficult. potential size data sets and the need to compare results from multiple experiments presents a challenge manage process information. Simply characterize applications running on potentially hundreds thousands processor cores requires new techniques. Furthermore, many exploratory processes are repeatable could be automated, but now implemented as manual procedures. In this paper, we will discuss current version PerfExplorer, framework which provides dimension reduction, clustering correlation individual trails large dimensions, can perform relative between application executions. PerfExplorer captured form Python scripts, automating what would otherwise time-consuming tasks. We give examples large-scale results, future framework, including encoding processing expert rules, increasing use metadata.