A decentralized and fault tolerant convergence detection algorithm for asynchronous iterative algorithms

This article presents an algorithm that performs a decentralized detection of the global convergence of parallel asynchronous iterative applications. This algorithm is fault tolerant. It runs a decentralized saving procedure which enables this algorithm, after a node’s crash, to replace the dead nod...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Journal of supercomputing Jg. 53; H. 2; S. 269 - 292
Hauptverfasser: Charr, Jean-Claude, Couturier, Raphaël, Laiymani, David
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Boston Springer US 01.08.2010
Springer
Springer Verlag
Schlagworte:
Algorithms
Applied sciences
Architecture
Compilers
Computer Science
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Computer systems performance. Reliability
Convergence
Cryptography and Security
Decentralized
Distributed, Parallel, and Cluster Computing
Exact sciences and technology
Fault tolerance
Fault tolerant
Interpreters
Iterative methods
Modeling and Simulation
Processor Architectures
Programming Languages
Robustness
Software
Fault tolerance
Decentralized global convergence detection mechanism
Peer-to-Peer environment
Distributed clusters
Supercomputer
Parallel algorithm
Peer to peer
Iterative method
Distributed system
Modeling
Parallelism
Robustness
Fault tolerant system
Defect detection
Asynchronous transmission
ISSN:0920-8542, 1573-0484
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This article presents an algorithm that performs a decentralized detection of the global convergence of parallel asynchronous iterative applications. This algorithm is fault tolerant. It runs a decentralized saving procedure which enables this algorithm, after a node’s crash, to replace the dead node by a new one which will continue the computing task from the last check point. Combined with the advantages of the asynchronous iteration model, this method allows us to compute very large scale problems using highly volatile parallel architectures like Peer-to-Peer and distributed clusters architectures. We also present the implementation of this algorithm in the JaceP2P platform which is dedicated to designing and executing parallel asynchronous iterative applications in volatile environments. Numerous experiments show the robustness and the efficiency of our algorithm.
Bibliographie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-009-0293-6