DocumentCode :
1374593
Title :
Nonnegative Tensor Factorization Accelerated Using GPGPU
Author :
Antikainen, J. ; Havel, J. ; Josth, R. ; Herout, A. ; Zemcik, P. ; Hauta-Kasari, Markku
Author_Institution :
Sch. of Comput., Univ. of Eastern Finland, Joensuu, Finland
Volume :
22
Issue :
7
fYear :
2011
fDate :
7/1/2011 12:00:00 AM
Firstpage :
1135
Lastpage :
1141
Abstract :
This article presents an optimized algorithm for Nonnegative Tensor Factorization (NTF), implemented in the CUDA (Compute Uniform Device Architecture) framework, that runs on contemporary graphics processors and exploits their massive parallelism. The NTF implementation is primarily targeted for analysis of high-dimensional spectral images, including dimensionality reduction, feature extraction, and other tasks related to spectral imaging; however, the algorithm and its implementation are not limited to spectral imaging. The speedups measured on real spectral images are around 60 - 100× compared to a traditional C implementation compiled with an optimizing compiler. Since common problems in the field of spectral imaging may take hours on a state-of-the-art CPU, the speedup achieved using a graphics card is attractive. The implementation is publicly available in the form of a dynamically linked library, including an interface to MATLAB, and thus may be of help to researchers and engineers using NTF on large problems.
Keywords :
computer graphic equipment; coprocessors; image processing; matrix decomposition; parallel architectures; spectral analysis; tensors; CPU; CUDA; GPGPU; NTF implementation; compute uniform device architecture; contemporary graphics processor; graphics card; graphics processing unit; nonnegative tensor factorization; parallelism; spectral analysis; spectral imaging; Graphics; Graphics processing unit; Image color analysis; Imaging; Instruction sets; Tensile stress; GPU.; Nonnegative tensor factorization; spectral analysis;
fLanguage :
English
Journal_Title :
Parallel and Distributed Systems, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9219
Type :
jour
DOI :
10.1109/TPDS.2010.194
Filename :
5629330
Link To Document :
بازگشت