ISSN 2542–0380
Труды Института механики им. Р.Р. Мавлютова
Электронный научный журнал | Electronic Scientific Journal
Proceedings of the Mavlyutov Institute of Mechanics


© Институт механики
им. Р.Р. Мавлютова
УФИЦ РАН

Яндекс.Метрика web site traffic statistics

Mikhaylenko C.I. The high-performance technique for solving an explicit finite-difference problems on the MPI technology Proceedings of the Mavlyutov Institute of Mechanics. 2016. 11(2). 247–253.
2016. Vol. 11. Issue 2, Pp. 247–253
URL: http://proc.uimech.org/uim2016.2.036
DOI: 10.21662/uim2016.2.036
The high-performance technique for solving an explicit finite-difference problems on the MPI technology
Mikhaylenko C.I.
Mavlyutov Institute of Mechanics, Ufa

Abstract

The technique for high-performance computing cluster architecture using messaging passing interface (MPI) is presented. The technique is based on the spatial domain decomposition. It is shown that when calculating multistage each spatial subregion separate process can achieve a multiple number of computational processes linear growth performance multiprocessor applications up to the start time / end of the computational process. An assessment of the minimum amount of computational grid points attributable to each computational process, at which the linear increase in performance.

Keywords

parallel technique,
MPI,
domain decomposition method,
numerical simulation,
CFD