|
Numerical methods and programming, 2011, Volume 12, Issue 1, Pages 176–182
(Mi vmp183)
|
|
|
|
Вычислительные методы и приложения
On the peculiarities of solving large systems of linear algebraic
equations on high performance computing systems of different architecture
B. I. Krasnopolsky Institute of Mechanics, M. V. Lomonosov Moscow State University
Abstract:
The results of testing a set of the Krylov subspace iterative methods
(CGS, BiCGStab) with algebraic multigrid preconditioner for solving large
sparse systems of linear algebraic equations are discussed. The scalability
characteristics for the MPI and hybrid versions of the code on three
HPC-systems are given. The peculiarities of using these methods on computer
systems of different processor architecture (Intel Harpertown, Intel Nehalem,
and AMD Magny-Cours) are analyzed.
Keywords:
iterative methods; systems of linear algebraic equations; scalability.
Citation:
B. I. Krasnopolsky, “On the peculiarities of solving large systems of linear algebraic
equations on high performance computing systems of different architecture”, Num. Meth. Prog., 12:1 (2011), 176–182
Linking options:
https://www.mathnet.ru/eng/vmp183 https://www.mathnet.ru/eng/vmp/v12/i1/p176
|
Statistics & downloads: |
Abstract page: | 132 | Full-text PDF : | 72 | References: | 1 |
|