Implementation of the FDTD algorithm on GPU using a pyramid method
| Autor: | S. A. Malysheva, D. L. Golovashkin |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Computer science
Computation 0211 other engineering and technologies Graphics processing unit Finite-difference time-domain method Context (language use) 02 engineering and technology Parallel computing Atomic and Molecular Physics and Optics Computer Science Applications Computational science CUDA symbols.namesake 020303 mechanical engineering & transports 0203 mechanical engineering Maxwell's equations 021105 building & construction symbols Pyramid (image processing) Electrical and Electronic Engineering ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | Computer Optics. 40:179-187 |
| ISSN: | 2412-6179 0134-2452 |
| DOI: | 10.18287/2412-6179-2016-40-2-179-187 |
| Popis: | In this paper we develop a pyramid method in the context of solving time-dependent Maxwell's equations based on the finite difference time domain (FDTD) approach, which is implemented on a graphics processing unit (GPU). Application of this method allows the impact of the GPU's limited memory capacity on the computation time to be reduced, which is significant for the FDTD method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|