Image Based Virtual Dimension Compute Unified Device Architecture of Parallel Processing Technology
نویسندگان
چکیده
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.
منابع مشابه
Recognition of convolutional neural network based on CUDA Technology
For the problem whether Graphic Processing Unit(GPU),the stream processor with high performance of floating— point computing is applicable to neural networks, this paper proposes the parallel recognition algorithm of Convolutional Neural Networks(CNNs).It adopts Compute Unified Device Architecture(CUDA)technology, definite the parallel data structures, and describes the mapping mechanism for co...
متن کاملFuzzy Logic-Based Image Processing Using Graphics Processor Units
This paper introduces a parallelization of fuzzy logicbased image processing using Graphics Processor Units (GPUs). Using an NVIDIA 8800 Ultra, a 126 time speed improvement can be made to fuzzy edge extraction making its processing real-time. The GPU can process approximately 42 frames per second at 640x480 image resolution, thus 307,200 inference processes per frame. With a computational speed...
متن کاملParallelization of the Local Threshold and Boolean Function Based Edge Detection Algorithm Using CUDA
In this paper we present a parallelized algorithm for edge detection for gray scale images. The chosen method is the local threshold and boolean function based edge detection. This method differs from common edge detectors in the use of bit map patterns instead of analyzing gradient changes in the image for edge recognition. The parallelization is implemented on the GPU, exploiting its multithr...
متن کاملEfficient parallelization of the genetic algorithm solution of traveling salesman problem on multi-core and many-core systems
Efficient parallelization of genetic algorithms (GAs) on state-of-the-art multi-threading or many-threading platforms is a challenge due to the difficulty of schedulation of hardware resources regarding the concurrency of threads. In this paper, for resolving the problem, a novel method is proposed, which parallelizes the GA by designing three concurrent kernels, each of which running some depe...
متن کاملMulti-GPU Accelerated Parallel Algorithm of Wallis Transformation for Image Enhancement
With the development of satellite remote sensing technology, satellite remote sensing data obtained by the amount will increase rapidly. Consequently, the process of Wallis transformation is faced with such challenges as large data size, high intensity, high computational complexity and large computational quantity, and so on. A fast algorithm and efficient implementation of Wallis filtering ba...
متن کامل