By Topic

Static Average Case Analysis Fork-Join Framework Programs Based on MOQA Method

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Ang Gao ; Dept. of Comput. Sci., Univ. Coll. Cork, Cork, Ireland ; Rea, K. ; Schellekens, M.

With the advancement of multi-core processors, parallel algorithms especially multithreaded algorithms, are of increasing importance to developers. The requirement for parallel algorithm analysis also increased. In this paper we present a new way to analyze fork-join multithreaded algorithms. Our approach is based on a novel static average case analysis method named MOQA. By extending MOQA theory to a parallel field and using the traceability of the MOQA data structure, we show that multithreaded algorithms which satisfy MOQA theory can be easily analysed. Parallel quick sort is shown as an example for which we derived equations for its work and span, something that cannot be achieved by current tools. Finally we validate our claims by running the parallel program and by comparing the boundary predicted by static analysis with real speedup from the experiment and show that our method is much more accurate than asymptotic analysis.

Published in:

Parallel Computing in Electrical Engineering (PARELEC), 2011 6th International Symposium on

Date of Conference:

3-7 April 2011