Performance analysis of distributed applications using automatic classification of communication inefficiencies
Abstract
The method and system described herein presents a technique for performance analysis that helps users understand the communication behavior of their message passing applications. The method and system described herein may automatically classifies individual communication operations and reveal the cause of communication inefficiencies in the application. This classification allows the developer to quickly focus on the culprits of truly inefficient behavior, rather than manually foraging through massive amounts of performance data. Specifically, the method and system described herein trace the message operations of Message Passing Interface (MPI) applications and then classify each individual communication event using a supervised learning technique: decision tree classification. The decision tree may be trained using microbenchmarks that demonstrate both efficient and inefficient communication. Since the method and system described herein adapt to the target system's configuration through these microbenchmarks, they simultaneously automate the performance analysis process and improve classification accuracy. The method and system described herein may improve the accuracy of performance analysis and dramatically reduce the amount of data that users must encounter.
- Inventors:
- Issue Date:
- Research Org.:
- The Regents of the Univ. of California, Oakland, CA (United States); Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1175231
- Patent Number(s):
- 6850920
- Application Number:
- 09/922,355
- Assignee:
- The Regents of the University of California (Oakland, CA)
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06F - ELECTRIC DIGITAL DATA PROCESSING
- DOE Contract Number:
- W-7405-ENG-48
- Resource Type:
- Patent
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING
Citation Formats
Vetter, Jeffrey S. Performance analysis of distributed applications using automatic classification of communication inefficiencies. United States: N. p., 2005.
Web.
Vetter, Jeffrey S. Performance analysis of distributed applications using automatic classification of communication inefficiencies. United States.
Vetter, Jeffrey S. Tue .
"Performance analysis of distributed applications using automatic classification of communication inefficiencies". United States. https://www.osti.gov/servlets/purl/1175231.
@article{osti_1175231,
title = {Performance analysis of distributed applications using automatic classification of communication inefficiencies},
author = {Vetter, Jeffrey S.},
abstractNote = {The method and system described herein presents a technique for performance analysis that helps users understand the communication behavior of their message passing applications. The method and system described herein may automatically classifies individual communication operations and reveal the cause of communication inefficiencies in the application. This classification allows the developer to quickly focus on the culprits of truly inefficient behavior, rather than manually foraging through massive amounts of performance data. Specifically, the method and system described herein trace the message operations of Message Passing Interface (MPI) applications and then classify each individual communication event using a supervised learning technique: decision tree classification. The decision tree may be trained using microbenchmarks that demonstrate both efficient and inefficient communication. Since the method and system described herein adapt to the target system's configuration through these microbenchmarks, they simultaneously automate the performance analysis process and improve classification accuracy. The method and system described herein may improve the accuracy of performance analysis and dramatically reduce the amount of data that users must encounter.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2005},
month = {2}
}
Works referenced in this record:
Timestamp consistency and trace-driven analysis for distributed parallel systems
conference, April 1995
- Wu, C. E.; Liu, Yew-Huey; Hsu, Yarsun
- Proceedings of 9th International Parallel Processing Symposium
Trace-based analysis and tuning for distributed parallel applications
conference, January 1994
- Wu, C. E.; Liu, Y. -H.; Benveniste, C.
- Proceedings of 1994 International Conference on Parallel and Distributed Systems
A survey of decision tree classifier methodology
journal, January 1991
- Safavian, S. R.; Landgrebe, D.
- IEEE Transactions on Systems, Man, and Cybernetics, Vol. 21, Issue 3