Scientific Library of Tomsk State University

   E-catalog        

Normal view MARC view

Parallel implementation of a numerical method for solving transport equations for the mesoscale meteorological model TSUNM3 A. V. Starchenko, E. A. Danilkin, S. A. Prokhanov, D. V. Leshchinskiy

Contributor(s): Starchenko, Alexander V | Danilkin, Evgeniy A | Prokhanov, Sergey A | Leshchinskiy, Dmitriy VMaterial type: ArticleArticleContent type: Текст Media type: электронный Subject(s): мезомасштабные метеорологические модели | TSUNM3, мезомасштабная метеорологическая модель | уравнения переноса | численные методы решенияGenre/Form: статьи в журналах Online resources: Click here to access online In: Journal of Physics: Conference Series Vol. 1715. P. 012073 (1-9)Abstract: A parallel algorithm for numerical solution of a generalized unsteady 3-dimensional advection-diffusion equation for a mesoscale meteorological model TSUNM3 is considered. Efficiency of parallel implementation of the solver with Message Passing Interface (MPI), Open Multi-Processing (OpenMP), Open Accelerators (OpenACC), and NVidia Compute Unified Device Architecture (CUDA) technologies was compared. The efficiency of the MPIparallelized code of TSUNM3 model with a two-dimensional domain decomposition strategy applied is not less than 75% on 256–512 processes on Cyberia supercomputer of Tomsk State University.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

Библиогр.: 18 назв.

A parallel algorithm for numerical solution of a generalized unsteady 3-dimensional advection-diffusion equation for a mesoscale meteorological model TSUNM3 is considered. Efficiency of parallel implementation of the solver with Message Passing Interface (MPI), Open Multi-Processing (OpenMP), Open Accelerators (OpenACC), and NVidia Compute Unified Device Architecture (CUDA) technologies was compared. The efficiency of the MPIparallelized code of TSUNM3 model with a two-dimensional domain decomposition strategy applied is not less than 75% on 256–512 processes on Cyberia supercomputer of Tomsk State University.

There are no comments on this title.

to post a comment.
Share