A dynamic, decentralised search algorithm for efficient data retrieval in a distributed tuple space

Authors:
Alistair Atkinson
Affiliations:
Eastern Institute of Technology, New Zealand
Venue:
AusPDC '10 Proceedings of the Eighth Australasian Symposium on Parallel and Distributed Computing - Volume 107
Year:
2010

Citing 14
Cited 0

Generative communication in Linda

ACM Transactions on Programming Languages and Systems (TOPLAS)
Reevaluating Amdahl's law

Communications of the ACM
Introduction to algorithms

Introduction to algorithms
How to write parallel programs: a first course

How to write parallel programs: a first course
Coordination with scopes

SAC '00 Proceedings of the 2000 ACM symposium on Applied computing - Volume 1
Algorithm 64: Quicksort

Communications of the ACM
WCL: A co-ordination language for geographically distributed agents

World Wide Web
Scientific Computation with JavaSpaces

HPCN Europe 2001 Proceedings of the 9th International Conference on High-Performance Computing and Networking
An Efficient Distributed Tuple Space Implementation for Networks of Workstations

Euro-Par '96 Proceedings of the Second International Euro-Par Conference on Parallel Processing - Volume I
A new approach to scalable Linda-systems based on swarms

Proceedings of the 2003 ACM symposium on Applied computing
On the implementation of SwarmLinda

ACM-SE 42 Proceedings of the 42nd annual Southeast regional conference
Linda implementations in Java for concurrent systems: Research Articles

Concurrency and Computation: Practice & Experience
Validity of the single processor approach to achieving large scale computing capabilities

AFIPS '67 (Spring) Proceedings of the April 18-20, 1967, spring joint computer conference
Tupleware: A Distributed Tuple Space for Cluster Computing

PDCAT '08 Proceedings of the 2008 Ninth International Conference on Parallel and Distributed Computing, Applications and Technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an algorithm which may be used to efficiently search for and retrieve tuples in a distributed tuple space. The algorithm, a core part of the Tupleware system, is based on the success or failure of previous tuple requests to remote nodes in the system, and this data is used determine the relative probability of particular remote nodes being able to fulfil subsequent future requests. The logic of this algorithm is distributed and decentralised: each node dynamically calculates its relationship with other nodes at runtime. The behaviour of the algorithm using two applications is analysed, and shows significant improvement in terms of efficiency and performance compared to comparable tuple space implementations.