DocumentCode :
260238
Title :
Divide and conquer skeleton on GPU
Author :
Baghayeri, Fahimeh ; Deldari, Hossein ; Bahrepour, Davoud
Author_Institution :
Dept. of Comput. Eng., Islamic Azad Univ., Mashhad, Iran
fYear :
2014
fDate :
26-27 Nov. 2014
Firstpage :
1
Lastpage :
6
Abstract :
Parallelism is a suitable approach for speeding up the massive computations of applications, but parallel programming is difficult yet. Algorithmic skeleton is a parallel programming model that provides a high level of abstraction for programmers. This approach uses the pre-defined components to facilitate easier parallel programming. Divide and conquer (DC) is an appropriate parallel pattern for implementation as a skeleton. The solution of the original problem is obtained by dividing it into smaller sub-problems and solving them in parallel. Today, graphics processor unit (GPU) is an attractive computational processor for doing tasks in parallel, because it has a large number of process units. In this paper, divide and conquer skeleton on GPU has been proposed and named OC_GFV.DC_GPU is a divide and conquer skeleton that is implemented on GPU that using a consistent programming interface in C++ for easier parallel programming. Performance of this skeleton has been evaluated by mergesort and sobeledge detection. The results show that obtained speedup at this skeleton is more than 2 on GPU.
Keywords :
C++ language; divide and conquer methods; edge detection; graphics processing units; parallel programming; C++; DC_GPU; computational processor; consistent programming interface; divide and conquer skeleton; graphics processor unit; mergesort; parallel pattern; parallel programming model; sobeledge skeleton; Computational modeling; Graphics processing units; Libraries; Parallel processing; Parallel programming; Skeleton; Algorithmic Skeleton; Divide and Conquer Skeleton; Graphics Processor Unit(GPU); Mergesort; Programming Interface in C++; Sobel Edge Detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Technology, Communication and Knowledge (ICTCK), 2014 International Congress on
Conference_Location :
Mashhad
Type :
conf
DOI :
10.1109/ICTCK.2014.7033531
Filename :
7033531
Link To Document :
بازگشت