The strong correlation between code signatures and performance

Jeremy Lau, Jack Sampson, Erez Perelman, Greg Hamerly, Brad Caldert

Research output: Chapter in Book/Report/Conference proceedingConference contribution

61 Scopus citations

Abstract

A recent study [1] examined the use of sampled hardware counters to create sampled code signatures. This approach is attractive because sampled code signatures can be quickly gathered for any application. The conclusion of their study was that there exists a fuzzy correlation between sampled code signatures and performance predictability. The paper raises the question of how much information is lost in the sampling process, and our paper focuses on examining this issue. We first focus on showing that there exists a strong correlation between code signatures and performance. We then examine the relationship between sampled and full code signatures, and how these affect performance predictability. Our results confirm that there is a fuzzy correlation found in recent work for the SPEC programs with sampled code signatures, but that a strong correlation exists with full code signatures. In addition, we propose converting the sampled instruction counts, used in the prior work, into sampled code signatures representing loop and procedure execution frequencies. These sampled loop and procedure code signatures allow phase analysis to more accurately and easily find patterns, and they correlate better with performance.

Original languageEnglish (US)
Title of host publicationISPASS 2005 - IEEE International Symposium on Performance Analysis of Systems and Software
Pages236-247
Number of pages12
DOIs
StatePublished - 2005
EventISPASS 2005 - IEEE International Symposium on Performance Analysis of Systems and Software - Austin, TX, United States
Duration: Mar 20 2005Mar 22 2005

Publication series

NameISPASS 2005 - IEEE International Symposium on Performance Analysis of Systems and Software
Volume2005

Other

OtherISPASS 2005 - IEEE International Symposium on Performance Analysis of Systems and Software
CountryUnited States
CityAustin, TX
Period3/20/053/22/05

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint Dive into the research topics of 'The strong correlation between code signatures and performance'. Together they form a unique fingerprint.

Cite this