DocumentCode :
855236
Title :
Hardware acceleration for similarity computations of feature vectors
Author :
Perera, Darshika G. ; Li, Kin Fun
Author_Institution :
Darshika G. Perera & Kin Fun Li are with the Dept. of Electr. & Comput. Eng., Victoria Univ., Victoria, BC
Volume :
33
Issue :
1
fYear :
2008
Firstpage :
21
Lastpage :
30
Abstract :
In Web mining applications, an enormous amount of data needs to be processed quickly and efficiently. Thus, hardware support is crucial to enhance the performance of these operations. In this work, chip-level hardware support for similarity measure calculation is introduced and then extended to similarity matrix computation. Both software and hardware versions of various similarity computations are implemented with a hierarchical platform-based design approach to facilitate component reuse at different levels of abstraction. Software modules are executed on a reconfigurable soft processor core on the same field-programmable gate array (FPGA) as the hardware implementations for the purpose of performance comparison. Preliminary results using parallel hardware are also presented. In addition, performance gain from hardware as opposed to a general-purpose processor is examined. Experimental results show that the performance of similarity computation for a set of feature vectors could be significantly enhanced by using on-chip hardware.
Keywords :
Internet; data mining; field programmable gate arrays; microprocessor chips; Web mining; chip-level hardware support; feature vectors; field-programmable gate array; hardware acceleration; hardware support; hierarchical platform-based design approach; on-chip hardware; reconfigurable soft processor core; similarity computations; software modules; Acceleration; Data mining; Field programmable gate arrays; Hardware; Information retrieval; Performance gain; Semiconductor device measurement; Software performance; Web mining; Web search; Web mining; feature vectors; hardware acceleration; performance evaluation; similarity matrix; similarity measures;
fLanguage :
English
Journal_Title :
Electrical and Computer Engineering, Canadian Journal of
Publisher :
ieee
ISSN :
0840-8688
Type :
jour
DOI :
10.1109/CJECE.2008.4621791
Filename :
4621791
Link To Document :
بازگشت