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
收藏
页码：592 / 597
页数：6
相关论文
共 50 条
[21]   Research on the Method of Parity Checker Design Based on Evolvable Hardware [J].
Wang Kuifu ;
Yan Jingfeng .
2010 THE 3RD INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND INDUSTRIAL APPLICATION (PACIIA2010), VOL III, 2010, :57-59
[22]   Research on the Method of Parity Checker Design Based on Evolvable Hardware [J].
Wang, Kuifu ;
Yan, Jingfeng .
APPLIED INFORMATICS AND COMMUNICATION, PT III, 2011, 226 :119-124
[23]   Implementation of an Adaptive Filter using an Evolvable Hardware Strategy [J].
Lovay, M. ;
Peretti, G. ;
Romero, E. .
IEEE LATIN AMERICA TRANSACTIONS, 2015, 13 (04) :927-934
[24]   Self-Reconfigurable Evolvable Hardware System for Adaptive Image Processing [J].
Salvador, Ruben ;
Otero, Andres ;
Mora, Javier ;
de la Torre, Eduardo ;
Riesgo, Teresa ;
Sekanina, Lukas .
IEEE TRANSACTIONS ON COMPUTERS, 2013, 62 (08) :1481-1493
[25]   VISUAL ANALYSIS OF A CARDIOVASCULAR SYSTEM BASED ON ECG AND ABP SIGNALS USING EVOLVABLE HARDWARE DESIGN [J].
Xiong, Fan ;
Shrestha, Prabhu ;
Tanik, Murat ;
Tanik, John ;
Vasana, Susan .
JOURNAL OF INTEGRATED DESIGN & PROCESS SCIENCE, 2011, 15 (04) :49-84
[26]   Fast cone-beam CT image reconstruction using GPU hardware [J].
Yan, Guorui ;
Tian, Jie ;
Zhu, Shouping ;
Dai, Yakang ;
Qin, Chenghu .
JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY, 2008, 16 (04) :225-234
[27]   RETRACTED: Design and implementation of dynamic partial reconfiguration using adaptive evolvable hardware (Retracted Article) [J].
Geetamma, T. ;
Seventline, J. Beatrice .
2015 INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONICS, SIGNALS, COMMUNICATION AND OPTIMIZATION (EESCO), 2015,
[28]   A novel and practicable on-chip adaptive lossless image compression scheme using intrinsic evolvable hardware [J].
He, Jingsong ;
Yao, Xin ;
Chen, Yunbi .
CONNECTION SCIENCE, 2007, 19 (04) :281-295
[29]   Evolutionary Design of Image Filter Using PicoBlaze Embedded Processor [J].
Zhang, Kai-feng ;
Tao, Hua-min ;
Xiao, Shan-zhu .
COMMUNICATIONS AND INFORMATION PROCESSING, PT 2, 2012, 289 :190-197
[30]   Toward an evolvable neuromolecular hardware: a hardware design fbr a multilevel artificial brain with digital circuits [J].
Chen, JC ;
Chen, RD .
NEUROCOMPUTING, 2002, 42 :9-34
12345