Multi-GPU Implementation of the Numerical Algorithm Enhancing Discrete Element Modeling Performance

Multi-GPU Implementation of the Numerical Algorithm Enhancing Discrete Element Modeling Performance Full article

Conference

Computational Science and Its Applications
30 Jun - 3 Jul 2025 , Istanbul

Source

Computational Science and Its Applications (ICCSA 2025 Workshops) : Proceedings
Compilation, Springer Cham. Switzerland.2026. 462 c. ISBN 978-3-031-97596-7.

Journal

Lecture Notes in Computer Science
ISSN: 0302-9743 , E-ISSN: 1611-3349

Output data

Year: 2025, Volume: 15888, Pages: 317-329 Pages count : 13 DOI: 10.1007/978-3-031-97596-7_21

Funding (1)

Russian Science Foundation

19-77-20004-П

This paper presents an algorithm to combine GPU computations for the two-dimensional discrete element method (DEM) with MPI data transfers between computer cluster nodes in distributed-memory systems for one-dimensional domain decomposition. The proposed algorithm redistributes particles between processes, deleting them or adding to the list of particles inside a current subdomain, respectively, in parallel with main GPU calculations to decrease the time loss of calling transferring functions. Strong and weak scaling tests were conducted for the implemented algorithm to show its effectiveness in adding more computational resources to the fixed-size problem and increasing the problem size according to the allocated resources.

Chepelenkova V.D. , Prokhorov D.I. , Lisitsa V.V.
Multi-GPU Implementation of the Numerical Algorithm Enhancing Discrete Element Modeling Performance
In compilation Computational Science and Its Applications (ICCSA 2025 Workshops) : Proceedings. – Springer Cham., 2025. – Т.Part III. – C.317-329. – ISBN 978-3-031-97596-7. DOI: 10.1007/978-3-031-97596-7_21 Scopus OpenAlex

Published print:	May 28, 2025
Published online:	May 28, 2025

Scopus:	2-s2.0-105010814017
OpenAlex:	W4412059140

Пока нет цитирований