Result: Parallel short range molecular dynamics simulations on computer clusters: Performance evaluation and modeling

Title:
Parallel short range molecular dynamics simulations on computer clusters: Performance evaluation and modeling
Authors:
KARAKASIDIS, T. E, CHOLEVAS, N. S, LIAKOPOULOS, A. B
Source:
International conference of computational methods in sciences and engineering 2003 (ICCMSE 2003)Mathematical and computer modelling. 42(7-8):783-798
Publisher Information:
Oxford: Elsevier Science, 2005.
Publication Year:
2005
Physical Description:
print, 22 ref
Original Material:
INIST-CNRS
Subject Terms:
Computer science, Informatique, Mathematics, Mathématiques, Sciences exactes et technologie, Exact sciences and technology, Sciences et techniques communes, Sciences and techniques of general use, Mathematiques, Mathematics, Analyse numérique. Calcul scientifique, Numerical analysis. Scientific computation, Méthodes de calcul scientifique (y compris calcul symbolique, calcul algébrique), Methods of scientific computing (including symbolic computation, algebraic computation), Physique, Physics, Physique atomique et moleculaire, Atomic and molecular physics, Processus de collision et interactions atomiques et moléculaires, Atomic and molecular collision processes and interactions, Transfert d'énergie intramoléculaire; dynamique intramoléculaire; dynamique des molécules de van der waals, Intramolecular energy transfer; intramolecular dynamics; dynamics of van der waals molecules, Domaines classiques de la physique (y compris les applications), Fundamental areas of phenomenology (including applications), Mécanique des fluides, Fluid dynamics, Méthodes de calcul en mécanique des fluides, Computational methods in fluid dynamics, Sciences appliquees, Applied sciences, Informatique; automatique theorique; systemes, Computer science; control theory; systems, Informatique théorique, Theoretical computing, Algorithmique. Calculabilité. Arithmétique ordinateur, Algorithmics. Computability. Computer arithmetics, Analyse assistée, Computer aided analysis, Análisis asistido, Calcul automatique, Computing, Cálculo automático, Calcul parallèle, Parallel computation, Cálculo paralelo, Calcul réparti, Distributed computing, Cálculo repartido, Calcul scientifique, Scientific computation, Computación científica, Dynamique moléculaire, Molecular dynamics, Dinámica molecular, Evaluation performance, Performance evaluation, Evaluación prestación, Liquide, Liquid, Líquido, Mathématiques appliquées, Applied mathematics, Matemáticas aplicadas, Modèle Lennard Jones, Lennard Jones model, Modelo Lennard Jones, Modèle mathématique, Mathematical model, Modelo matemático, Performance système, System performance, Eficacia sistema, Simulation ordinateur, Computer simulation, Simulación computadora, Temps exécution, Execution time, Tiempo ejecución, Clustering, Décomposition atome, Atom decomposition, MPI, Atom Decomposition, Cluster computing, Lennard-Jones liquid, Parallel simulations
Document Type:
Conference Conference Paper
File Description:
text
Language:
English
Author Affiliations:
Hydromechanics Laboratory, School of Engineering, University of Thessaly, Pedion Areos, 38334 Volos, Greece
Department of Mechanical and Industrial Engineering, School of Engineering, University of Thessaly, Pedion Areos, 38334 Volos, Greece
ISSN:
0895-7177
Access URL:
http://pascal-francis.inist.fr/vibad/index.php?action=search&terms=17286651
Rights:
Copyright 2006 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Atomic and molecular physics

Computer science; theoretical automation; systems

Mathematics

Physics: fluid mechanics
Accession Number:
edscal.17286651
Database:
PASCAL Archive

Further Information

This paper describes the performance of a portable molecular dynamics code running on an eight-node PC cluster. The molecular dynamics code is based on the atom decomposition method for distributing the computation load among the processors and the MPI protocol for managing communications among processors. We discuss the Changes made to the serial code with an effort to maintain its readability. We examined the program performance for system sizes of order 102 to 104 atoms and number of processors varying from 1 to 8, by measuring the total execution time and the corresponding speedup, as well as the communication time for data exchange and the time for the calculation of interatomic forces. Using simple communication and computation load considerations, we propose models in order to explain the observed behaviour and predict the optimal usage of the cluster. It turns out that using few parameters that can be easily measured one can predict quite accurately the optimal usage of small clusters running short range molecular dynamics programs.