@inproceedings{eda85ca2d50f46768836a91a969a92c3,
title = "Novel views of performance data to analyze large-scale adaptive applications",
abstract = "Performance analysis of parallel scientific codes is becoming increasingly difficult due to the rapidly growing complexity of applications and architectures. Existing tools fall short in providing intuitive views that facilitate the process of performance debugging and tuning. In this paper, we extend recent ideas of projecting and visualizing performance data for faster, more intuitive analysis of applications. We collect detailed per-level and per-phase measurements for a dynamically load-balanced, structured AMR library and project per-core data collected in the hardware domain on to the application's communication topology. We show how our projections and visualizations lead to a rapid diagnosis of and mitigation strategy for a previously elusive scaling bottleneck in the library that is hard to detect using conventional tools. Our new insights have resulted in a 22% performance improvement for a 65,536-core run of the AMR library on an IBM Blue Gene/P system.",
author = "Abhinav Bhatele and Todd Gamblin and Isaacs, {Katherine E.} and Gunney, {Brian T.N.} and Martin Schulz and Bremer, {Peer Timo} and Bernd Hamann",
year = "2012",
doi = "10.1109/SC.2012.80",
language = "English",
isbn = "9781467308069",
series = "International Conference for High Performance Computing, Networking, Storage and Analysis, SC",
booktitle = "2012 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2012",
note = "2012 24th International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2012 ; Conference date: 10-11-2012 Through 16-11-2012",
}