Scalable Analysis Techniques for Microprocessor Performance Counter Metrics

Contemporary microprocessors provide a rich set of integrated performance counters that allow application developers and system architects alike the opportunity to gather important information about workload behaviors. Current techniques for analyzing data produced from these counters use raw counts, ratios, and visualization techniques help users make decisions about their application performance. While these techniques are appropriate for analyzing data from one process, they do not scale easily to new levels demanded by contemporary computing systems. Very simply, this paper addresses these concerns by evaluating several multivariate statistical techniques on these datasets. We find that several techniques, such as statistical clustering, can automatically extract important features from the data. These derived results can, in turn, be fed directly back to an application developer, or used as input to a more comprehensive performance analysis environment, such as a visualization or an expert system.

[1]  B. C. Curtis,et al.  Very High Resolution Simulation of Compressible Turbulence on the IBM-SP System , 1999, ACM/IEEE SC 1999 Conference (SC'99).

[2]  Jack J. Dongarra,et al.  A Scalable Cross-Platform Infrastructure for Application Performance Tuning Using Hardware Counters , 2000, ACM/IEEE SC 2000 Conference (SC'00).

[3]  Jack J. Dongarra,et al.  End-user Tools for Application Performance Analysis Using Hardware Counters , 2001, ISCA PDCS.

[4]  Ian Foster,et al.  The Grid 2 - Blueprint for a New Computing Infrastructure, Second Edition , 1998, The Grid 2, 2nd Edition.

[5]  Ali S. Hadi,et al.  Finding Groups in Data: An Introduction to Chster Analysis , 1991 .

[6]  Philip C. Roth,et al.  Real-Time Statistical Clustering for Event Trace Reduction , 1997, Int. J. High Perform. Comput. Appl..

[7]  Barton P. Miller,et al.  The Paradyn Parallel Performance Measurement Tool , 1995, Computer.

[8]  Michael Voss,et al.  An Integrated Performance Visualizer for MPI/OpenMP Programs , 2001, WOMPAT.

[9]  J. Vetter,et al.  Managing Performance Analysis with Dynamic Statistical Projection Pursuit , 2000, ACM/IEEE SC 1999 Conference (SC'99).

[10]  Ami Marowka,et al.  The GRID: Blueprint for a New Computing Infrastructure , 2000, Parallel Distributed Comput. Pract..

[11]  Jeffrey S. Vetter,et al.  A Dynamic Tracing Mechanism for Performance Analysis of OpenMP Applications , 2001, WOMPAT.

[12]  Jeffrey S. Vetter.  Performance analysis of distributed applications using automatic classification of communication inefficiencies , 2000, ICS '00.

[13]  Fabrizio Petrini,et al.  A general predictive performance model for wavefront algorithms on clusters of SMPs , 2000, Proceedings 2000 International Conference on Parallel Processing.

[14]  Jeffrey S. Vetter,et al.  An Empirical Performance Evaluation of Scalable Scientific Applications , 2002, ACM/IEEE SC 2002 Conference (SC'02).

[15]  S. Turner,et al.  Performance Analysis Using the MIPS R10000 Performance Counters , 1996, Proceedings of the 1996 ACM/IEEE Conference on Supercomputing.

[16]  Lance M. Berc,et al.  Continuous profiling: where have all the cycles gone? , 1997, ACM Trans. Comput. Syst..

[17]  Jeffrey S. Vetter,et al.  Communication characteristics of large-scale scientific applications for contemporary cluster architectures , 2002, Proceedings 16th International Parallel and Distributed Processing Symposium.

[18]  Jeffrey Dean,et al.  ProfileMe: hardware support for instruction-level profiling on out-of-order processors , 1997, Proceedings of 30th Annual International Symposium on Microarchitecture.

[19]  Pradip Bose,et al.  Performance Analysis and Its Impact on Design , 1998, Computer.

[20]  John M. May,et al.  MPX: Software for multiplexing hardware performance counters in multithreaded programs , 2001, Proceedings 15th International Parallel and Distributed Processing Symposium. IPDPS 2001.