Stochastic inner product core for digital FIR filters

The computational operations of stochastic computing (SC) are governed by probability rules which is different from conventional arithmetic computations. Applications of SC to digital signal and image processing problems have been recently reported in the literature. To improve the computational per...

Full description

Saved in:
Bibliographic Details
Main Authors: Hijazin, Ismat, Wong, Ming Ming, Wong, Dennis, Zhang, Cishen
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2018
Subjects:
Online Access:https://hdl.handle.net/10356/89118
http://hdl.handle.net/10220/46080
http://www.wseas.org/multimedia/journals/control/2017/a505903-079.html
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-89118
record_format dspace
spelling sg-ntu-dr.10356-891182019-12-06T17:18:15Z Stochastic inner product core for digital FIR filters Hijazin, Ismat Wong, Ming Ming Wong, Dennis Zhang, Cishen School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering Inner Product Stochastic Computing The computational operations of stochastic computing (SC) are governed by probability rules which is different from conventional arithmetic computations. Applications of SC to digital signal and image processing problems have been recently reported in the literature. To improve the computational performance of SC based finite impulse response (FIR) digital filters, a new stochastic inner product (multiply and accumulate) core with an improved scaling scheme is presented for improving the accuracy and fault tolerance performance of the filters. Taking into account the symmetric property of the coefficients of linear phase FIR filters, the proposed inner product core is designed using tree structured multiplexers which is capable of reducing the critical path and fault propagation in the stochastic circuitry. The designed inner product core can lead to construction of SC based light weight and multiplierless FIR digital filters. As a result, an SC based FIR digital FIR filter is implemented on Altera Cyclone V FPGA which operates on stochastic sequences of 256-bits length (8-bits precision level). Experimental results show that the developed filter has lower hardware cost, better accuracy and higher fault tolerance level compared with other stochastic implementations. Published version 2018-09-24T09:13:08Z 2019-12-06T17:18:15Z 2018-09-24T09:13:08Z 2019-12-06T17:18:15Z 2017 Journal Article Wong, M. M., Wong, D., Zhang, C., & Hijazin, I. (2017). Stochastic inner product core for digital FIR filters. WSEAS Transactions on Systems and Control, 12, 246-252. 1991-8763 https://hdl.handle.net/10356/89118 http://hdl.handle.net/10220/46080 http://www.wseas.org/multimedia/journals/control/2017/a505903-079.html en WSEAS Transactions on Systems and Control © 2017 The Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution License 4.0 7 p. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
Inner Product
Stochastic Computing
spellingShingle DRNTU::Engineering::Computer science and engineering
Inner Product
Stochastic Computing
Hijazin, Ismat
Wong, Ming Ming
Wong, Dennis
Zhang, Cishen
Stochastic inner product core for digital FIR filters
description The computational operations of stochastic computing (SC) are governed by probability rules which is different from conventional arithmetic computations. Applications of SC to digital signal and image processing problems have been recently reported in the literature. To improve the computational performance of SC based finite impulse response (FIR) digital filters, a new stochastic inner product (multiply and accumulate) core with an improved scaling scheme is presented for improving the accuracy and fault tolerance performance of the filters. Taking into account the symmetric property of the coefficients of linear phase FIR filters, the proposed inner product core is designed using tree structured multiplexers which is capable of reducing the critical path and fault propagation in the stochastic circuitry. The designed inner product core can lead to construction of SC based light weight and multiplierless FIR digital filters. As a result, an SC based FIR digital FIR filter is implemented on Altera Cyclone V FPGA which operates on stochastic sequences of 256-bits length (8-bits precision level). Experimental results show that the developed filter has lower hardware cost, better accuracy and higher fault tolerance level compared with other stochastic implementations.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Hijazin, Ismat
Wong, Ming Ming
Wong, Dennis
Zhang, Cishen
format Article
author Hijazin, Ismat
Wong, Ming Ming
Wong, Dennis
Zhang, Cishen
author_sort Hijazin, Ismat
title Stochastic inner product core for digital FIR filters
title_short Stochastic inner product core for digital FIR filters
title_full Stochastic inner product core for digital FIR filters
title_fullStr Stochastic inner product core for digital FIR filters
title_full_unstemmed Stochastic inner product core for digital FIR filters
title_sort stochastic inner product core for digital fir filters
publishDate 2018
url https://hdl.handle.net/10356/89118
http://hdl.handle.net/10220/46080
http://www.wseas.org/multimedia/journals/control/2017/a505903-079.html
_version_ 1681039178447454208