EFFICIENCY OF MATRIX ELEMENTS COMPUTATIONS ON PARALLEL SYSTEMS*
Trochała Mieczysław, Komasa Jacek
Quantum Chemistry Group, Faculty of Chemistry, Adam Mickiewicz University,
Grunwaldzka 6, 60-780 Poznań, Poland
Received:
Rec. 29 January 2004
DOI: 10.12921/cmst.2003.09.01.137-145
OAI: oai:lib.psnc.pl:546
Abstract:
Experience with adapting sequential programs to a parallel environment is shared with
the reader. Our programs are used in quantum-chemical calculations but certain parts of them are of general application and our results can be adapted to other types of problems. Several PC nodes are connected through a fast network and consolidated to a cluster. Our applications make use of the Message Passing Interface environment. Encouraging results concerning speedup and efficiency have been obtained. Experiments leading to a superlinear speedup using the hyperthreading technology are also reported.
References:
[1] I. Mayer, Simple Theorems, Proofs, and Derivations in Quantum Chemistry, Kluwer Academic 2003.
[2] W. Cencek, The Role of Efficient Programming in Theoretical Chemistry and Physics Problems, in: Computational Methods in Science and Technology, (edited by J. Rychlewski, J. Węglarz, K. W. Wojciechowski) Scientific Publishers OWN, Poznań, Vol. 1, 1996, p. 7-18.
[3] J. Komasa, J. Rychlewski, Parallel Computing 26, 999 (2000).
[4] W. Cencek, J. Komasa, and J. Rychlewski, High-performance Computing in Molecular Sciences in: Handbook on Parallel and Distributed Processing, eds. J. Błażewicz, K. Ecker, B. Plateau, D. Trystram, Springer 2000, p. 505.
[5] http://www.mcs.anl.gov/.
[6] http://www-unix.mcs.anl.gov/mpi/mpich/.
[7] http://www-unix.mcs.anl.gov/mpi/.
[8] P. S. Pacheco, W. C. Ming, MPI Users’ Guide in Fortran,
http: //www.phyast.pitt.edu/beowulf/Tutorial.html.
[9] W. Cencek, High-performance Computing on Heterogeneous Systems, in: Computational Methods in Science and Technology (edited by J. Rychlewski, J. Węglarz, K. W. Wojciechowski)
Scientific Publishers OWN, Poznań, Vol. 5, 1999, p. 7-19.
[10] http://developer.intel.com/technology/hyperthread/.
Experience with adapting sequential programs to a parallel environment is shared with
the reader. Our programs are used in quantum-chemical calculations but certain parts of them are of general application and our results can be adapted to other types of problems. Several PC nodes are connected through a fast network and consolidated to a cluster. Our applications make use of the Message Passing Interface environment. Encouraging results concerning speedup and efficiency have been obtained. Experiments leading to a superlinear speedup using the hyperthreading technology are also reported.
[1] I. Mayer, Simple Theorems, Proofs, and Derivations in Quantum Chemistry, Kluwer Academic 2003.
[2] W. Cencek, The Role of Efficient Programming in Theoretical Chemistry and Physics Problems, in: Computational Methods in Science and Technology, (edited by J. Rychlewski, J. Węglarz, K. W. Wojciechowski) Scientific Publishers OWN, Poznań, Vol. 1, 1996, p. 7-18.
[3] J. Komasa, J. Rychlewski, Parallel Computing 26, 999 (2000).
[4] W. Cencek, J. Komasa, and J. Rychlewski, High-performance Computing in Molecular Sciences in: Handbook on Parallel and Distributed Processing, eds. J. Błażewicz, K. Ecker, B. Plateau, D. Trystram, Springer 2000, p. 505.
[5] http://www.mcs.anl.gov/.
[6] http://www-unix.mcs.anl.gov/mpi/mpich/.
[7] http://www-unix.mcs.anl.gov/mpi/.
[8] P. S. Pacheco, W. C. Ming, MPI Users’ Guide in Fortran,
http: //www.phyast.pitt.edu/beowulf/Tutorial.html.
[9] W. Cencek, High-performance Computing on Heterogeneous Systems, in: Computational Methods in Science and Technology (edited by J. Rychlewski, J. Węglarz, K. W. Wojciechowski)
Scientific Publishers OWN, Poznań, Vol. 5, 1999, p. 7-19.
[10] http://developer.intel.com/technology/hyperthread/.
