Image Based Virtual Dimension Compute Unified Device Architecture of Parallel Processing Technology

ABSTRACT

There are a number of virtual dimension typical targets in hyperspectral image. Determining the virtual dimension is the first step in many applications of hyperspectral image. In view of the virtual dimension calculation method of having high time complexity problem, according to the calculation of highly parallel features, in this paper graphics processing unit (GPU) using the Compute Unified Device Architecture (CUDA) and its extended linear algebraic toolbox of CULA and Thrust are studied, to realize virtual dimension calculation. The parallel realization of the algorithm in each step was further optimized to obtain greater acceleration performance. Through the function of CUDA on GPU parallel computing and CPU non parallel calculation, and experimental verification of the virtual dimension, it was fund that the CUDA parallel computing can significantly speed up the implementation of the algorithm.

Keywords:

Compute unified device architecture, graphics processing unit, harsanyifarrand-chang, virtual dimension, hyperspectral images.