Program modelling via inter-reference gaps and applications

Author

Phalke, Vidyadhar ; Gopinath, B.

Author_Institution

Dept. of Comput. Sci., Rutgers Univ., NJ, USA

fYear

1995

fDate

18-20 Jan 1995

Firstpage

212

Lastpage

216

Abstract

Locality of reference in program behavior has been studied and modelled extensively because of its application to CPU, cache and virtual memory design, code optimization, multiprogramming etc. In this paper we propose a scheme based on Markov chains for modelling the time interval between successive references to the same address in a program execution. Using this technique and trace driven simulations, it is shown that memory references are predictable and repetitive. This is used to improve miss ratios of memory replacement algorithms. Using trace driven simulations over a wide range of traces we get improvements up to 35% over the least recently used (LRU) replacement algorithm

Keywords

Markov processes; cache storage; paged storage; program diagnostics; software performance evaluation; storage management; CPU design; Markov chains; cache design; code optimization; inter-reference gaps; memory references; memory replacement algorithms; multiprogramming; program execution; program modelling; reference locality; time interval; trace driven simulations; virtual memory design; Application software; Central Processing Unit; Clocks; Computational modeling; Computer science; Computer simulation; Design optimization; Legged locomotion; Predictive models; Prefetching;

fLanguage

English

Publisher

ieee

Conference_Titel

Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, 1995. MASCOTS '95., Proceedings of the Third International Workshop on

Conference_Location

Durham, NC

Print_ISBN

0-8186-6902-0

Type

conf

DOI

10.1109/MASCOT.1995.378685

Filename

378685