The recent advent of general-purpose graphics-processing units (GPGPUs) as inexpensive arithmetic-processing units brings a relevant amount of computing power to modern desktop PCs. This thus providing an interesting pathway to the acceleration of several numerical electromagnetic methods. In this paper, we explain how to exploit GPGPU features by examining how the computational time of the Finite-Difference Time-Domain Method can be reduced. The attainable efficiency is demonstrated by providing numerical results achieved on a two-dimensional study of a human-antenna interaction problem.
Introduction to GPU computing and CUDA programming: A case study on FDTD
DE DONNO, DANILO;ESPOSITO, Alessandra;TARRICONE, Luciano;CATARINUCCI, Luca
2010-01-01
Abstract
The recent advent of general-purpose graphics-processing units (GPGPUs) as inexpensive arithmetic-processing units brings a relevant amount of computing power to modern desktop PCs. This thus providing an interesting pathway to the acceleration of several numerical electromagnetic methods. In this paper, we explain how to exploit GPGPU features by examining how the computational time of the Finite-Difference Time-Domain Method can be reduced. The attainable efficiency is demonstrated by providing numerical results achieved on a two-dimensional study of a human-antenna interaction problem.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
