Parallelism of Evolutionary Design of Image Filters for Evolvable Hardware Using GPU

被引：0

作者：

Wu, Chih-Hung ^{[1
]}

Chiang, Chin-Yuan ^{[1
]}

Chen, Yi-Han ^{[1
]}

机构：

[1] Natl Univ Kaohsiung, Dept Elect Engn, Kaohsiung 811, Taiwan

来源：

2013 14TH ACIS INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, ARTIFICIAL INTELLIGENCE, NETWORKING AND PARALLEL/DISTRIBUTED COMPUTING (SNPD 2013) | 2013年

关键词：

Parallelism; GPU; evolutionary design; evolvable hardware; Cartesian genetic programming; image filter; GRAPHICS;

D O I：

10.1109/SNPD.2013.79

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Evolvable Hardware (EHW) is a combination of evolutionary algorithm and reconfigurable hardware devices. Due to its flexible and adaptive ability, EHW-based solutions receive a lot of attention in industrial applications. One of the obstacles to realize an EHW-based method is its very long training time. This study deals with the parallelism of EHW-based design of image filters using graphic processing units (GPUs). The design process is analyzed and decomposed into some smaller processes that can run in parallel. Pixel-based data for training and verifying EHW solutions are partitioned according to the architecture of GPU. Several strategies for deploying parallel processes are developed and implemented. With the proposed method, significant improvements on the efficiency of training EHW models are gained. Using a GPU with 240 cores, a speedup of 64 times is obtained. This paper evaluates and compares the performance of the proposed method with other ones.

引用

页码：592 / 597

页数：6

共 50 条

[31] An Improved Genetic Algorithm Based On Stages Hybridization For Evolvable Hardware Design [J].

Wu, Huicong ;

Wang, Jinze .

PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND MANAGEMENT INNOVATION, 2015, 28 :773-778

[32] Evolvable hardware design based on a novel simulated annealing in an embedded system [J].

He, Guoliang ;

Xiong, Naixue ;

Yang, Laurence T. ;

Kim, Tai-hoon ;

Hsu, Ching Hsien ;

Li, Yuanxiang ;

Hu, Ting .

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2012, 24 (04) :354-370

[33] Functional level implementation of evolvable hardware using genetic algorithms [J].

Karunya, B. ;

Uma, R. .

PROCEEDINGS OF THE INTERNATIONAL CONFERENCE MIXED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2006, :671-+

[34] Applied cloning techniques for a genetic algorithm used in evolvable hardware design [J].

Trinh, VC ;

Holifield, GA ;

Wu, AS .

7TH WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL V, PROCEEDINGS: COMPUTER SCIENCE AND ENGINEERING: I, 2003, :263-268

[35] Evolvable Hardware Using Cluster Growth Along With Evolution Strategy [J].

Srivastava, Atul Kumar ;

Sharma, Ekta .

SOUVENIR OF THE 2014 IEEE INTERNATIONAL ADVANCE COMPUTING CONFERENCE (IACC), 2014, :802-806

[36] A Tutorial on the Implementations of Linear Image Filters in CPU and GPU [J].

Pardo, Alvaro .

COMPUTER SCIENCE (CACIC 2017), 2018, 790 :111-121

[37] A fast evolutionary algorithm for image compression in hardware [J].

Salami, M ;

Hendtlass, T .

DEVELOPMENTS IN APPLIED ARTIFICAIL INTELLIGENCE, PROCEEDINGS, 2002, 2358 :241-252

[38] A new evolvable hardware approach to digital circuits using cultural algorithms [J].

Pan, Zhongliang ;

Chen, Ling ;

Zhang, Guangzhao .

DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS, 2007, 14 :781-785

[39] Adaptive blind equalization using bottleneck networks implemented by evolvable hardware [J].

Murakawa, M ;

Hiraoka, K ;

Higuchi, T ;

Furuya, T ;

Yoshizawa, S .

ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, :89-92

[40] Noise removal of the X-ray medical image using fast spatial filters and GPU [J].

Cadena, Luis ;

Zotin, Alexander ;

Cadena, Franklin ;

Espinosa, Nikolai .

APPLICATIONS OF DIGITAL IMAGE PROCESSING XLI, 2018, 10752

← 1 2 3 4 5 →