Dependence Cluster Causes

Binkley, Dave

doi:10.4230/DagSemProc.08161.4

Document

Dependence Cluster Causes

Author Dave Binkley

Part of: Volume: Dagstuhl Seminar Proceedings, Volume 8161
Part of: Series: Dagstuhl Seminar Proceedings (DagSemProc)
License: Creative Commons Attribution 4.0 International license
Publication Date: 2008-08-28

PDF

File

PDF

DagSemProc.08161.4.pdf

Filesize: 282 kB
13 pages

Document Identifiers

DOI: 10.4230/DagSemProc.08161.4
URN: urn:nbn:de:0030-drops-15711

Subject Classification

Keywords

Data Dependence
Control Dependence
Slice
Cluster

Metrics

Access Statistics
Total Accesses (updated on a weekly basis)

0

PDF Downloads

0

Metadata Views

Abstract

A dependence cluster is a maximal set of program components that all depend upon one another.  For small programs, programmers as well as static-analysis tools can overcome the negative effects of large dependence clusters.  However, this ability diminished as program size increases.  Thus, the existence of large dependence clusters presents a serious challenge to the scalability of modern software.  Recent ongoing work into the existence and causes of dependence clusters is presented.  A better understanding of clusters and their causes is a precursor to the construction of more informed analysis tools and ideally the eventual breaking or proactive avoidance of large dependence clusters.

Cite As Get BibTex

Dave Binkley. Dependence Cluster Causes. In Scalable Program Analysis. Dagstuhl Seminar Proceedings, Volume 8161, pp. 1-13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008) https://doi.org/10.4230/DagSemProc.08161.4

Author Details

Dave Binkley

Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail