Automatic detection of parallel applications computation phases
Document typeConference report
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Rights accessRestricted access - publisher's policy
Analyzing parallel programs has become increasingly difficult due to the immense amount of information collected on large systems. The use of clustering techniques has been proposed to analyze applications. However, while the objective of previous works is focused on identifying groups of processes with similar characteristics, we target a much finer granularity in the application behavior. In this paper, we present a tool that automatically characterizes the different computation regions between communication primitives in message-passing applications. This study shows how some of the clustering algorithms which may be applicable at a coarse grain are no longer adequate at this level. Density-based clustering algorithms applied to the performance counters offered by modern processors are more appropriate in this context. This tool automatically generates accurate displays of the structure of the application as well as detailed reports on a broad range of metrics for each individual region detected.
CitationGonzález, J.; Gimenez, J.; Labarta, J. Automatic detection of parallel applications computation phases. A: IEEE International Parallel and Distributed Processing Symposium. "IPDPS 2009 Rome: proceedings of the 23rd IEEE International Symposium on Parallel and Distributed Processing". Roma: Institute of Electrical and Electronics Engineers (IEEE), 2014, p. 1-11.
|Automatic detec ... ons computation phases.pdf||Automatic detection of parallel applications computation phases||427.5Kb||Restricted access|