Computing complex functions using factorization in unipolar stochastic logic

Yin Liu; Keshab K. Parhi

doi:10.1145/2902961.2902999

Computing complex functions using factorization in unipolar stochastic logic

Yin Liu, Keshab K. Parhi

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

This paper addresses computing complex functions using unipolar stochastic logic. Stochastic computing requires simple logic gates and is inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Implementations of complex functions cost extremely low hardware complexity compared to traditional two's complement implementation. In this paper an approach based on polynomial factorization is proposed to compute functions in unipolar stochastic logic. In this approach, functions are expressed using polynomials, which are derived from Taylor expansion or Lagrange interpolation. Polynomials are implemented in stochastic logic by using factorization. Experimental results in terms of accuracy and hardware complexity are presented to compare the proposed designs of complex functions with previous implementations using Bernstein polynomials.

Original language	English (US)
Title of host publication	GLSVLSI 2016 - Proceedings of the 2016 ACM Great Lakes Symposium on VLSI
Publisher	Association for Computing Machinery
Pages	109-112
Number of pages	4
ISBN (Electronic)	9781450342742
DOIs	https://doi.org/10.1145/2902961.2902999
State	Published - May 18 2016
Event	26th ACM Great Lakes Symposium on VLSI, GLSVLSI 2016 - Boston, United States Duration: May 18 2016 → May 20 2016

Publication series

Name	Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI
Volume	18-20-May-2016

Other

Other	26th ACM Great Lakes Symposium on VLSI, GLSVLSI 2016
Country/Territory	United States
City	Boston
Period	5/18/16 → 5/20/16

Keywords

Complex functions
Polynomial factorization
Stochastic division
Stochastic logic
Stochastic subtraction
Unipolar representation

Publisher link

10.1145/2902961.2902999

Find It

Find It at U of M Libraries

Cite this

Computing complex functions using factorization in unipolar stochastic logic. / Liu, Yin; Parhi, Keshab K.
GLSVLSI 2016 - Proceedings of the 2016 ACM Great Lakes Symposium on VLSI. Association for Computing Machinery, 2016. p. 109-112 (Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI; Vol. 18-20-May-2016).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Liu, Y & Parhi, KK 2016, Computing complex functions using factorization in unipolar stochastic logic. in GLSVLSI 2016 - Proceedings of the 2016 ACM Great Lakes Symposium on VLSI. Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI, vol. 18-20-May-2016, Association for Computing Machinery, pp. 109-112, 26th ACM Great Lakes Symposium on VLSI, GLSVLSI 2016, Boston, United States, 5/18/16. https://doi.org/10.1145/2902961.2902999

@inproceedings{d4840aeceb004a8082326c41a51e3490,

title = "Computing complex functions using factorization in unipolar stochastic logic",

abstract = "This paper addresses computing complex functions using unipolar stochastic logic. Stochastic computing requires simple logic gates and is inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Implementations of complex functions cost extremely low hardware complexity compared to traditional two's complement implementation. In this paper an approach based on polynomial factorization is proposed to compute functions in unipolar stochastic logic. In this approach, functions are expressed using polynomials, which are derived from Taylor expansion or Lagrange interpolation. Polynomials are implemented in stochastic logic by using factorization. Experimental results in terms of accuracy and hardware complexity are presented to compare the proposed designs of complex functions with previous implementations using Bernstein polynomials.",

keywords = "Complex functions, Polynomial factorization, Stochastic division, Stochastic logic, Stochastic subtraction, Unipolar representation",

author = "Yin Liu and Parhi, {Keshab K.}",

note = "Publisher Copyright: {\textcopyright} 2016 ACM. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; 26th ACM Great Lakes Symposium on VLSI, GLSVLSI 2016 ; Conference date: 18-05-2016 Through 20-05-2016",

year = "2016",

month = may,

day = "18",

doi = "10.1145/2902961.2902999",

language = "English (US)",

series = "Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI",

publisher = "Association for Computing Machinery",

pages = "109--112",

booktitle = "GLSVLSI 2016 - Proceedings of the 2016 ACM Great Lakes Symposium on VLSI",

}

TY - GEN

T1 - Computing complex functions using factorization in unipolar stochastic logic

AU - Liu, Yin

AU - Parhi, Keshab K.

PY - 2016/5/18

Y1 - 2016/5/18

N2 - This paper addresses computing complex functions using unipolar stochastic logic. Stochastic computing requires simple logic gates and is inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Implementations of complex functions cost extremely low hardware complexity compared to traditional two's complement implementation. In this paper an approach based on polynomial factorization is proposed to compute functions in unipolar stochastic logic. In this approach, functions are expressed using polynomials, which are derived from Taylor expansion or Lagrange interpolation. Polynomials are implemented in stochastic logic by using factorization. Experimental results in terms of accuracy and hardware complexity are presented to compare the proposed designs of complex functions with previous implementations using Bernstein polynomials.

AB - This paper addresses computing complex functions using unipolar stochastic logic. Stochastic computing requires simple logic gates and is inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Implementations of complex functions cost extremely low hardware complexity compared to traditional two's complement implementation. In this paper an approach based on polynomial factorization is proposed to compute functions in unipolar stochastic logic. In this approach, functions are expressed using polynomials, which are derived from Taylor expansion or Lagrange interpolation. Polynomials are implemented in stochastic logic by using factorization. Experimental results in terms of accuracy and hardware complexity are presented to compare the proposed designs of complex functions with previous implementations using Bernstein polynomials.

KW - Complex functions

KW - Polynomial factorization

KW - Stochastic division

KW - Stochastic logic

KW - Stochastic subtraction

KW - Unipolar representation

UR - http://www.scopus.com/inward/record.url?scp=84974723603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84974723603&partnerID=8YFLogxK

U2 - 10.1145/2902961.2902999

DO - 10.1145/2902961.2902999

M3 - Conference contribution

AN - SCOPUS:84974723603

T3 - Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI

SP - 109

EP - 112

BT - GLSVLSI 2016 - Proceedings of the 2016 ACM Great Lakes Symposium on VLSI

PB - Association for Computing Machinery

T2 - 26th ACM Great Lakes Symposium on VLSI, GLSVLSI 2016

Y2 - 18 May 2016 through 20 May 2016

ER -

Computing complex functions using factorization in unipolar stochastic logic

Abstract

Publication series

Other

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this