Отправить статью по E-mail Parallel Versions of Implicit LU-SGS Method
- Авторы: Chikitkin A.1, Petrov M.1, Titarev V.1,2, Utyuzhnikov S.1,3
-
Учреждения:
- Moscow Institute of Physics and Technology (State University)
- Federal Research Center “Computer Science and Control”
- University of Manchester
- Выпуск: Том 39, № 4 (2018)
- Страницы: 503-512
- Раздел: Article
- URL: https://journals.rcsi.science/1995-0802/article/view/201992
- DOI: https://doi.org/10.1134/S1995080218040054
- ID: 201992
Цитировать
Открытый доступ
Доступ предоставлен
Только для подписчиков
Аннотация
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.
Об авторах
A. Chikitkin
Moscow Institute of Physics and Technology (State University)
Автор, ответственный за переписку.
Email: chikitkin.av@mipt.ru
Россия, Dolgoprudny, Moscow oblast, 141700
M. Petrov
Moscow Institute of Physics and Technology (State University)
Email: chikitkin.av@mipt.ru
Россия, 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
Россия, Dolgoprudny, Moscow oblast, 141700; Moscow, 119333
S. Utyuzhnikov
Moscow Institute of Physics and Technology (State University); University of Manchester
Email: chikitkin.av@mipt.ru
Россия, Dolgoprudny, Moscow oblast, 141700; Manchester, M13 9PL
