Email this article Parallel Versions of Implicit LU-SGS Method
- Authors: Chikitkin A.1, Petrov M.1, Titarev V.1,2, Utyuzhnikov S.1,3
-
Affiliations:
- Moscow Institute of Physics and Technology (State University)
- Federal Research Center “Computer Science and Control”
- University of Manchester
- Issue: Vol 39, No 4 (2018)
- Pages: 503-512
- Section: Article
- URL: https://journals.rcsi.science/1995-0802/article/view/201992
- DOI: https://doi.org/10.1134/S1995080218040054
- ID: 201992
Cite item
Open Access
Access granted
Subscription Access
Abstract
Different parallel distributed-memory versions of Lower-Upper Symmetric Gauss–Seidel (LU-SGS) method for solution of discrete equations in finite-volume framework are compared in terms of parallel structure of algorithms. New version based on multilevel recursive decomposition is proposed.
About the authors
A. Chikitkin
Moscow Institute of Physics and Technology (State University)
Author for correspondence.
Email: chikitkin.av@mipt.ru
Russian Federation, Dolgoprudny, Moscow oblast, 141700
M. Petrov
Moscow Institute of Physics and Technology (State University)
Email: chikitkin.av@mipt.ru
Russian Federation, Dolgoprudny, Moscow oblast, 141700
V. Titarev
Moscow Institute of Physics and Technology (State University); Federal Research Center “Computer Science and Control”
Email: chikitkin.av@mipt.ru
Russian Federation, Dolgoprudny, Moscow oblast, 141700; Moscow, 119333
S. Utyuzhnikov
Moscow Institute of Physics and Technology (State University); University of Manchester
Email: chikitkin.av@mipt.ru
Russian Federation, Dolgoprudny, Moscow oblast, 141700; Manchester, M13 9PL
