Optimizing the computation of a parallel 3D finite difference algorithm for graphics processing units
| Autor: | D. P. Kikola, Marcin Słodkowski, J. Sikorski, Sebastian Cygert, Joanna Porter-Sobieraj |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Computer Networks and Communications
Computer science Computation Locality Graphics processing unit Finite difference Parallel computing Stencil Computer Science Applications Theoretical Computer Science Computational science CUDA Computational Theory and Mathematics Shared memory CUDA Pinned memory Graphics Software |
| Zdroj: | Concurrency and Computation: Practice and Experience. 27:1591-1602 |
| ISSN: | 1532-0626 |
| DOI: | 10.1002/cpe.3351 |
| Popis: | This paper explores the possibilities of using a graphics processing unit for complex 3D finite difference computation via MUSTA-FORCE and WENO algorithms. We propose a novel algorithm based on the new properties of CUDA surface memory optimized for 2D spatial locality and compare it with 3D stencil computations carried out via shared memory, which is currently considered to be the best approach. A case study was performed for the extensive generation of a time series of 3D grids of arbitrary size used in the computation of collisions between heavy nuclei in terms of relativistic hydrodynamics. It proved that implementation based on surface memory is as much as 23% faster than an equivalent implementation using shared memory. Copyright © 2014 John Wiley & Sons, Ltd. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text