Computing Publications

Publications Home » GPA - A tool for fluid scalabilit...

GPA - A tool for fluid scalability analysis of massively parallel systems

Anton Stefanek, Richard Hayden, Jeremy T. Bradley

Conference or Workshop Paper
QEST'11, 8th International Conference on Quantitative Evaluation of Systems
October, 2011
pp.147–148
IEEE
DOI 10.1109/QEST.2011.26
Abstract

Recent ordinary differential equation (ODE) based techniques allow efficient analysis of Markovian population models with extremely large state spaces. In most cases of realistic scale, they provide the only alternative to stochastic simulation. Moreover, numerical solution of the ODEs is cheaper computationally than simulation by orders of magnitude. We present the Grouped PEPA Analyser (GPA) tool with new functionality to exploit computationally inexpensive fluid analysis techniques to allow the exploration of large numbers of system configurations in models with large state spaces.

GPA provides an efficient implementation of the fluid analysis techniques for models described in a stochastic process algebra. It implements recently developed extensions allowing specifications of complex reward measures using combinations of state based, rate accumulated and impulse rewards. Combined with the ability to efficiently capture various passage time metrics, GPA can be used to solve optimisation problems with a reward objective function under different service level agreement type constraints.

Keywords
Fluid and ODE analysis
Performance Modelling and Analysis
Process Algebra
Process Calculi
AESOP
Notes

This paper describes an open-source tool, the Grouped PEPA Analyser, for the rapid performance analysis of massively parallel systems.

The project can be found on: http://code.google.com/p/gpanalyser/

with more information and older versions at: http://www.doc.ic.ac.uk/~as1005/gpa/

PDF of full publication (281 kilobytes)
(need help viewing PDF files?)
PDF of presentation slides (680 kilobytes)
BibTEX file for the publication
N.B.
Conditions for downloading publications from this site.
 

pubs.doc.ic.ac.uk: built & maintained by Ashok Argent-Katwala.