Sampling based random number generator for stochastic computing

M. Burak Karadeniz; Mustafa Altun

doi:10.1109/ICECS.2017.8292041

Sampling based random number generator for stochastic computing

M. Burak Karadeniz^*, Mustafa Altun

^*Corresponding author for this work

Department of Electronics and Communication Engineering

Istanbul Technical University

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

3 Citations (Scopus)

Abstract

Linear feedback shift register (LFSR) has been widely used to generate stochastic bit streams. Although using LFSR's offers feasibility because of their compatibility with CMOS technology, lack of randomness and related area consumption which is linearly proportional to the number of bits in a stream satisfying a certain probability value, can easily go beyond practical limits. Until now, no distinguished and practical way has been found to compete with LFSR to generate stochastic bit streams. True random number generators (TRNG) are widely used to compensate the poor randomness of LFSR but their complex design which is increased by the sake of acquiring random source, and their uncontrollability to generate random bit stream with desired probability, which is necessary for stochastic applications, make them out of action. Here we propose a novel programmable sampling based stochastic number generator (SBRNG) using CMOS technology. We achieve 100x higher speed, and 640x effective length of stochastic bit streams compared to LFSR based generators. We also claim that the circuit area complexity in terms of the number of effective bits is much better for SBRNG compared to LFSR based generators.

Original language	English
Title of host publication	ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	227-230
Number of pages	4
ISBN (Electronic)	9781538619117
DOIs	https://doi.org/10.1109/ICECS.2017.8292041
Publication status	Published - 2 Jul 2017
Event	24th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2017 - Batumi, Georgia Duration: 5 Dec 2017 → 8 Dec 2017

Publication series

Name	ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems
Volume	2018-January

Conference

Conference	24th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2017
Country/Territory	Georgia
City	Batumi
Period	5/12/17 → 8/12/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Funding

Acknowledgment: This work is supported by the TUBITAK 1001 project # 116E250.

Funders	Funder number
TUBITAK 1001	116E250

Keywords

analog to digital converter (.ADC)
CMOS
LFSR
quantization
stochastic number generator
TRNG

Access to Document

10.1109/ICECS.2017.8292041

Cite this

Karadeniz, M. B., & Altun, M. (2017). Sampling based random number generator for stochastic computing. In ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems (pp. 227-230). (ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICECS.2017.8292041

@inproceedings{ad39ece095e84d51b6e9a50f06b11f75,

title = "Sampling based random number generator for stochastic computing",

abstract = "Linear feedback shift register (LFSR) has been widely used to generate stochastic bit streams. Although using LFSR's offers feasibility because of their compatibility with CMOS technology, lack of randomness and related area consumption which is linearly proportional to the number of bits in a stream satisfying a certain probability value, can easily go beyond practical limits. Until now, no distinguished and practical way has been found to compete with LFSR to generate stochastic bit streams. True random number generators (TRNG) are widely used to compensate the poor randomness of LFSR but their complex design which is increased by the sake of acquiring random source, and their uncontrollability to generate random bit stream with desired probability, which is necessary for stochastic applications, make them out of action. Here we propose a novel programmable sampling based stochastic number generator (SBRNG) using CMOS technology. We achieve 100x higher speed, and 640x effective length of stochastic bit streams compared to LFSR based generators. We also claim that the circuit area complexity in terms of the number of effective bits is much better for SBRNG compared to LFSR based generators.",

keywords = "analog to digital converter (.ADC), CMOS, LFSR, quantization, stochastic number generator, TRNG",

author = "Karadeniz, {M. Burak} and Mustafa Altun",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 24th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2017 ; Conference date: 05-12-2017 Through 08-12-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/ICECS.2017.8292041",

language = "English",

series = "ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "227--230",

booktitle = "ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems",

address = "United States",

}

Karadeniz, MB & Altun, M 2017, Sampling based random number generator for stochastic computing. in ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems. ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 227-230, 24th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2017, Batumi, Georgia, 5/12/17. https://doi.org/10.1109/ICECS.2017.8292041

Sampling based random number generator for stochastic computing. / Karadeniz, M. Burak; Altun, Mustafa.
ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems. Institute of Electrical and Electronics Engineers Inc., 2017. p. 227-230 (ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems; Vol. 2018-January).

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

TY - GEN

T1 - Sampling based random number generator for stochastic computing

AU - Karadeniz, M. Burak

AU - Altun, Mustafa

PY - 2017/7/2

Y1 - 2017/7/2

N2 - Linear feedback shift register (LFSR) has been widely used to generate stochastic bit streams. Although using LFSR's offers feasibility because of their compatibility with CMOS technology, lack of randomness and related area consumption which is linearly proportional to the number of bits in a stream satisfying a certain probability value, can easily go beyond practical limits. Until now, no distinguished and practical way has been found to compete with LFSR to generate stochastic bit streams. True random number generators (TRNG) are widely used to compensate the poor randomness of LFSR but their complex design which is increased by the sake of acquiring random source, and their uncontrollability to generate random bit stream with desired probability, which is necessary for stochastic applications, make them out of action. Here we propose a novel programmable sampling based stochastic number generator (SBRNG) using CMOS technology. We achieve 100x higher speed, and 640x effective length of stochastic bit streams compared to LFSR based generators. We also claim that the circuit area complexity in terms of the number of effective bits is much better for SBRNG compared to LFSR based generators.

AB - Linear feedback shift register (LFSR) has been widely used to generate stochastic bit streams. Although using LFSR's offers feasibility because of their compatibility with CMOS technology, lack of randomness and related area consumption which is linearly proportional to the number of bits in a stream satisfying a certain probability value, can easily go beyond practical limits. Until now, no distinguished and practical way has been found to compete with LFSR to generate stochastic bit streams. True random number generators (TRNG) are widely used to compensate the poor randomness of LFSR but their complex design which is increased by the sake of acquiring random source, and their uncontrollability to generate random bit stream with desired probability, which is necessary for stochastic applications, make them out of action. Here we propose a novel programmable sampling based stochastic number generator (SBRNG) using CMOS technology. We achieve 100x higher speed, and 640x effective length of stochastic bit streams compared to LFSR based generators. We also claim that the circuit area complexity in terms of the number of effective bits is much better for SBRNG compared to LFSR based generators.

KW - analog to digital converter (.ADC)

KW - CMOS

KW - LFSR

KW - quantization

KW - stochastic number generator

KW - TRNG

UR - http://www.scopus.com/inward/record.url?scp=85047244924&partnerID=8YFLogxK

U2 - 10.1109/ICECS.2017.8292041

DO - 10.1109/ICECS.2017.8292041

M3 - Conference contribution

AN - SCOPUS:85047244924

T3 - ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems

SP - 227

EP - 230

BT - ICECS 2017 - 24th IEEE International Conference on Electronics, Circuits and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 24th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2017

Y2 - 5 December 2017 through 8 December 2017

ER -

Sampling based random number generator for stochastic computing

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this