Performance tuning with instruction-level cost derived from call-stack sampling

ABSTRACT

Except for program-counter histogramming, most modern profiling tools summarize at the level of entire functions or basic blocks, with or without additional information such as calling context or call graphs. This paper explicates the value of information about the cost of specific instructions, relative to summaries that do not include it. A good source of this information is time-random sampling of the call stack. To get the diagnostic benefit of instruction costs it is not necessary to measure them with high precision or efficiency. In fact, manual sampling suffices quite well, when it can be used. Other benefits of call stack sampling are that it can be used with unmodified software and libraries, and it is easily confined to the time intervals of interest. As with other profiling techniques, it can be employed repeatedly to remove all significant performance problems in single-thread programs.

REFERENCES

• 1: Glenn Ammons , Thomas Ball , James R. Larus, Exploiting hardware performance counters with flow and context sensitive profiling, Proceedings of the ACM SIGPLAN 1997 conference on Programming language design and implementation, p.85-96, June 16-18, 1997, Las Vegas, Nevada, United States
• 2: {Ammons04} Glenn Ammons, Jong-Deok Choi, Manish Gupta, Nikhil Swamy, Finding and Removing Performance Bottlenecks in Large Systems, European conference on object-oriented programming, Oslo, Norway, 2004, http://pages.cs.wisc.edu/~ammons/bottlenecks.pdf
• 3: Michael R. Dunlavey, Building Better Applications: A Theory of Efficient Software Development, John Wiley & Sons, Inc., New York, NY, 1994
• 4: Nathan Froyd , John Mellor-Crummey , Rob Fowler, Low-overhead call path profiling of unmodified, optimized code, Proceedings of the 19th annual international conference on Supercomputing, June 20-22, 2005, Cambridge, Massachusetts [doi>10.1145/1088149.1088161]
• 5: Susan L. Graham , Peter B. Kessler , Marshall K. McKusick, gprof: a call graph execution profiler, ACM SIGPLAN Notices, v.39 n.4, April 2004 [doi>10.1145/989393.989401]
• 6: {SGI} SGI Altix Applications Development and Optimization, http://sc.tamu.edu/help/SGI.Tutorial/sgi-tutorial.pdf
• 7: {Sun} Sun Studio Performance Analyzer. http://developers.sun.com/sunstudio/analyzer_index.html

INDEX TERMS

Primary Classification:
  D. Software
  D.3 PROGRAMMING LANGUAGES
      D.3.4 Processors
          Subjects: Compilers

Additional Classification:
  D. Software
  D.3 PROGRAMMING LANGUAGES
      D.3.2 Language Classifications

          Nouns: Java
      D.3.3 Language Constructs and Features

General Terms:
Algorithms, Design, Experimentation, Measurement, Performance, Theory

Keywords:
bottleneck, call stack sampling, instrumentation, optimization, performance analysis, profiling, software development