Další formáty:
BibTeX
LaTeX
RIS
@article{950226,
author = {Karas, Pavel and Svoboda, David},
article_location = {NEW YORK (USA)},
article_number = {120},
doi = {http://dx.doi.org/10.1186/1687-6180-2011-120},
keywords = {convolution; decomposition; fft; gpu; dif; 3D},
language = {eng},
issn = {1687-6172},
journal = {EURASIP Journal on Advances in Signal Processing},
title = {Convolution of Large 3D Images on GPU and its Decomposition},
url = {http://asp.eurasipjournals.com/content/2011/1/120},
volume = {2011},
year = {2011}
}
TY - JOUR
ID - 950226
AU - Karas, Pavel - Svoboda, David
PY - 2011
TI - Convolution of Large 3D Images on GPU and its Decomposition
JF - EURASIP Journal on Advances in Signal Processing
VL - 2011
IS - 120
SP - 1-12
EP - 1-12
PB - HINDAWI PUBLISHING CORPORATION
SN - 16876172
KW - convolution
KW - decomposition
KW - fft
KW - gpu
KW - dif
KW - 3D
UR - http://asp.eurasipjournals.com/content/2011/1/120
L2 - http://asp.eurasipjournals.com/content/2011/1/120
N2 - In this paper we propose a method for computing convolution of large 3D images. The convolution is performed in a frequency domain using a convolution theorem. The algorithm is accelerated on a graphic card by means of the CUDA parallel computing model. Convolution is decomposed in a frequency domain using the DIF (decimation in frequency) algorithm. We pay attention to keeping our approach efficient in terms of both time and memory consumption and also in terms of memory transfers between CPU and GPU which have a significant influence on overall computational time. We also study the implementation on multiple GPUs and compare the results between the multi-GPU and multi-CPU implementations.
ER -
KARAS, Pavel a David SVOBODA. Convolution of Large 3D Images on GPU and its Decomposition. \textit{EURASIP Journal on Advances in Signal Processing}. NEW YORK (USA): HINDAWI PUBLISHING CORPORATION, 2011, roč.~2011, č.~120, s.~1-12. ISSN~1687-6172. Dostupné z: https://dx.doi.org/10.1186/1687-6180-2011-120.
|
