Geodesic
Combined MPI+threads parallel implementation of the block method
Numerical methods and programming, Tome 11 (2010) no. 1, pp. 127-136

Voir la notice de l'article provenant de la source Math-Net.Ru

Combined MPI+threads parallel algorithms are developed to approximate the solutions of the nonstationary heat conductivity equation with phase transition by the analytical block method. The block method is based on the approximation of the solution to a boundary value problem by the special functions that are the fundamental solutions of the Helmholtz equation. As a result, there appear block systems of linear algebraic equations with block sparse structures and dense submatrices. Intensive computations with dense submatrices are parallelized on the basis of threads with the use of shared memory. Relatively independent computations with block sparse structures are parallelized on distributed memory with the aid of MPI. Such a combined approach to the organization of parallel computing allows one to efficiently use the heterogeneous memory structure in the modern cluster systems.
Keywords: analytical methods; approximation; parallel computing; iterative methods; distributed and shared memory. 
@article{VMP_2010_11_1_a14,
     author = {D. B. Volkov-Bogorodskii and G. B. Sushko and S. A. Kharchenko},
     title = {Combined {MPI+threads} parallel implementation of the block method},
     journal = {Numerical methods and programming},
     pages = {127--136},
     publisher = {mathdoc},
     volume = {11},
     number = {1},
     year = {2010},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VMP_2010_11_1_a14/}
}
TY  - JOUR
AU  - D. B. Volkov-Bogorodskii
AU  - G. B. Sushko
AU  - S. A. Kharchenko
TI  - Combined MPI+threads parallel implementation of the block method
JO  - Numerical methods and programming
PY  - 2010
SP  - 127
EP  - 136
VL  - 11
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/VMP_2010_11_1_a14/
LA  - ru
ID  - VMP_2010_11_1_a14
ER  - 
%0 Journal Article
%A D. B. Volkov-Bogorodskii
%A G. B. Sushko
%A S. A. Kharchenko
%T Combined MPI+threads parallel implementation of the block method
%J Numerical methods and programming
%D 2010
%P 127-136
%V 11
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/VMP_2010_11_1_a14/
%G ru
%F VMP_2010_11_1_a14
D. B. Volkov-Bogorodskii; G. B. Sushko; S. A. Kharchenko. Combined MPI+threads parallel implementation of the block method. Numerical methods and programming, Tome 11 (2010) no. 1, pp. 127-136. http://geodesic.mathdoc.fr/item/VMP_2010_11_1_a14/