The documents distributed by this server have been provided by the
contributing authors as a means to ensure timely dissemination of
scholarly and technical work on a noncommercial basis. Copyright and all
rights therein are maintained by the authors or by other copyright
holders, notwithstanding that they have offered their works here
electronically. It is understood that all persons copying this
information will adhere to the terms and constraints invoked by each
author's copyright. These works may not be reposted without the explicit
permission of the copyright holder.
Publications of SPCL
A. Calotoiu, M. Geisenhofer, F. Kummer, M. Ritter, J. Weber, T. Hoefler, M. Oberlack, F. Wolf:
Empirical Modeling of Spatially Diverging Performance
(In 2020 IEEE/ACM International Workshop on HPC User Support Tools (HUST) and Workshop on Programming and Performance Visualization, ISBN: , Nov. 2020)
Abstract
A common simplification made when modeling the
performance of a parallel program is the assumption that the
performance behavior of all processes or threads is largely
uniform. Empirical performance-modeling tools such as Extra-P
exploit this common pattern to make their modeling process more
noise resilient, mitigating the effect of outliers by summarizing
performance measurements of individual functions across all
processes. While the underlying assumption does not equally
hold for all applications, knowing the qualitative differences in
how the performance of individual processes changes as execution parameters are varied can reveal important performance
bottlenecks such as malicious patterns of load imbalance. A
challenge for empirical modeling tools, however, arises from
the fact that the behavioral class of a process may depend on
the process configuration, letting process ranks migrate between
classes as the number of processes grows. In this paper, we
introduce a novel approach to the problem of modeling of
spatially diverging performance based on a certain type of process
clustering. We apply our technique to identify a previously
unknown performance bottleneck in the BoSSS fluid-dynamics
code. Removing it made the code regions in question running up
to 20 times and the application as a whole run up to 4.5 times
faster
Documents
download article:
Recorded talk (best effort)
BibTeX
@inproceedings{, author={Alexandru Calotoiu and Markus Geisenhofer and Florian Kummer and Marcus Ritter and Jens Weber and Torsten Hoefler and Martin Oberlack and Felix Wolf}, title={{Empirical Modeling of Spatially Diverging Performance}}, year={2020}, month={11}, booktitle={2020 IEEE/ACM International Workshop on HPC User Support Tools (HUST) and Workshop on Programming and Performance Visualization}, isbn={}, }
