MTJ-Based p-Bit Designs for Enhanced Tunability

Saleh Bunaiyan; Feras Al-Dirini

doi:10.1109/NMDC46933.2022.10052369

MTJ-Based p-Bit Designs for Enhanced Tunability

Saleh Bunaiyan^*
, Feras Al-Dirini

^*Corresponding author for this work

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

1 Scopus citations

Abstract

Probabilistic bits (p-bits) can be viewed as tunable random number generators (RNGs), whose stochasticity coupled with their tunability makes them enablers for an emerging class of applications, including probabilistic computing. Their tunability is the feature that makes them unique to conventional RNGs. This paper studies the tunability range of existing p-bit designs reported in the literature, highlighting that existing designs have a limited input voltage range within which the p-bit's stochastic response can be tuned, on the order of sub 0.5 V. This may greatly limit their scalability in large p-bit networks. Accordingly, this work proposes several variant p-bit designs that enable a wider input voltage tunability range and a more continuous response for p-bits. The designs employ both bipolar and continuous stochastic MTJs, and demonstrate an enhancement in the tunability range beyond 4 V (close to half of the supply voltage range).

Original language	English
Title of host publication	2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	14-16
Number of pages	3
ISBN (Electronic)	9781728174105
DOIs	https://doi.org/10.1109/NMDC46933.2022.10052369
State	Published - 2022
Event	2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022 - Nanjing, China Duration: 18 Nov 2022 → 20 Nov 2022

Publication series

Name	2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022

Conference

Conference	2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022
Country/Territory	China
City	Nanjing
Period	18/11/22 → 20/11/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

MTJ
low barrier magnets (LBM)
p-bit
p-bit network
probabilistic
stochastic
tunability

ASJC Scopus subject areas

Hardware and Architecture
Electrical and Electronic Engineering
Electronic, Optical and Magnetic Materials
Instrumentation

Access to Document

10.1109/NMDC46933.2022.10052369

Cite this

@inproceedings{1b1105c715154363b6ed6516e0b8095c,

title = "MTJ-Based p-Bit Designs for Enhanced Tunability",

abstract = "Probabilistic bits (p-bits) can be viewed as tunable random number generators (RNGs), whose stochasticity coupled with their tunability makes them enablers for an emerging class of applications, including probabilistic computing. Their tunability is the feature that makes them unique to conventional RNGs. This paper studies the tunability range of existing p-bit designs reported in the literature, highlighting that existing designs have a limited input voltage range within which the p-bit's stochastic response can be tuned, on the order of sub 0.5 V. This may greatly limit their scalability in large p-bit networks. Accordingly, this work proposes several variant p-bit designs that enable a wider input voltage tunability range and a more continuous response for p-bits. The designs employ both bipolar and continuous stochastic MTJs, and demonstrate an enhancement in the tunability range beyond 4 V (close to half of the supply voltage range).",

keywords = "MTJ, low barrier magnets (LBM), p-bit, p-bit network, probabilistic, stochastic, tunability",

author = "Saleh Bunaiyan and Feras Al-Dirini",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022 ; Conference date: 18-11-2022 Through 20-11-2022",

year = "2022",

doi = "10.1109/NMDC46933.2022.10052369",

language = "English",

series = "2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022",

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

pages = "14--16",

booktitle = "2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022",

address = "United States",

}

Bunaiyan, S & Al-Dirini, F 2022, MTJ-Based p-Bit Designs for Enhanced Tunability. in 2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022. 2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022, Institute of Electrical and Electronics Engineers Inc., pp. 14-16, 2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022, Nanjing, China, 18/11/22. https://doi.org/10.1109/NMDC46933.2022.10052369

MTJ-Based p-Bit Designs for Enhanced Tunability. / Bunaiyan, Saleh; Al-Dirini, Feras.
2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 14-16 (2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022).

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

TY - GEN

T1 - MTJ-Based p-Bit Designs for Enhanced Tunability

AU - Bunaiyan, Saleh

AU - Al-Dirini, Feras

PY - 2022

Y1 - 2022

N2 - Probabilistic bits (p-bits) can be viewed as tunable random number generators (RNGs), whose stochasticity coupled with their tunability makes them enablers for an emerging class of applications, including probabilistic computing. Their tunability is the feature that makes them unique to conventional RNGs. This paper studies the tunability range of existing p-bit designs reported in the literature, highlighting that existing designs have a limited input voltage range within which the p-bit's stochastic response can be tuned, on the order of sub 0.5 V. This may greatly limit their scalability in large p-bit networks. Accordingly, this work proposes several variant p-bit designs that enable a wider input voltage tunability range and a more continuous response for p-bits. The designs employ both bipolar and continuous stochastic MTJs, and demonstrate an enhancement in the tunability range beyond 4 V (close to half of the supply voltage range).

AB - Probabilistic bits (p-bits) can be viewed as tunable random number generators (RNGs), whose stochasticity coupled with their tunability makes them enablers for an emerging class of applications, including probabilistic computing. Their tunability is the feature that makes them unique to conventional RNGs. This paper studies the tunability range of existing p-bit designs reported in the literature, highlighting that existing designs have a limited input voltage range within which the p-bit's stochastic response can be tuned, on the order of sub 0.5 V. This may greatly limit their scalability in large p-bit networks. Accordingly, this work proposes several variant p-bit designs that enable a wider input voltage tunability range and a more continuous response for p-bits. The designs employ both bipolar and continuous stochastic MTJs, and demonstrate an enhancement in the tunability range beyond 4 V (close to half of the supply voltage range).

KW - MTJ

KW - low barrier magnets (LBM)

KW - p-bit

KW - p-bit network

KW - probabilistic

KW - stochastic

KW - tunability

UR - https://www.scopus.com/pages/publications/85150204652

U2 - 10.1109/NMDC46933.2022.10052369

DO - 10.1109/NMDC46933.2022.10052369

M3 - Conference contribution

AN - SCOPUS:85150204652

T3 - 2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022

SP - 14

EP - 16

BT - 2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE Nanotechnology Materials and Devices Conference, NMDC 2022

Y2 - 18 November 2022 through 20 November 2022

ER -

MTJ-Based p-Bit Designs for Enhanced Tunability

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this