A General Design for a Scalable MPI-GPU Multi-Resolution 2D Numerical Solver

This article presents a multi-GPU implementation of a Finite-Volume solver on a multi-resolution grid. The implementation completely offloads the computation to the GPUs and communications between different GPUs are implemented by means of the Message Passing Interface (MPI) API. Different domain de...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on parallel and distributed systems 2020-05, Vol.31 (5), p.1036-1047
Hauptverfasser:	Turchetto, Massimiliano, Palu, Alessandro Dal, Vacondio, Renato
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms AMR Computation Computational modeling CUDA Domain decomposition methods dynamic load balancing Dynamic loads Graphics processing units Hilbert curve Hilbert space hilbert space filling curves Load management Load modeling Mathematical model Message passing MPI multi-GPU multi-resolution grid Numerical models Partial differential equations shallow water equations (SWE) Solvers Synchronism Two dimensional displays
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!