Stochastic Computing Based on Volatile GeSe Ovonic Threshold Switching Selectors

被引：5

作者：

Chai, Zheng ^{[1
]}

Freitas, Pedro ^{[1
]}

Zhang, Wei Dong ^{[1
]}

Hatem, Firas ^{[1
]}

Degraeve, Robin ^{[2
]}

Clima, Sergiu ^{[2
]}

Zhang, Jian Fu ^{[1
]}

Marsland, John ^{[1
]}

Fantini, Andrea ^{[2
]}

Garbin, Daniele ^{[2
]}

Goux, Ludovic ^{[2
]}

Kar, Gouri Sankar ^{[2
]}

机构：

[1] Liverpool John Moores Univ, Dept Elect & Elect Engn, Liverpool L3 3AF, Merseyside, England

[2] IMEC, B-3001 Leuven, Belgium

来源：

IEEE ELECTRON DEVICE LETTERS | 2020年 / 41卷 / 10期

基金：

英国工程与自然科学研究理事会;

关键词：

Switches; Streaming media; Stochastic processes; Probabilistic logic; Image edge detection; Weibull distribution; Delays; Selector; GeSe; stochastic computing; memristor; bit stream; random number; OPERATION; NOISE;

D O I：

10.1109/LED.2020.3017095

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Stochastic computing (SC) is a special type of digital compute strategy where values are represented by the probability of 1 and 0 in stochastic bit streams, which leads to superior hardware simplicity and error-tolerance. In this letter, we propose and demonstrate SC with GeSe-based Ovonic Threshold Switching (OTS) selector devices by exploiting their probabilistic switching behavior. The stochastic bit streams generated by OTS are demonstrated with good computation accuracy in both multiplication operation and image processing circuit. Moreover, the bit distribution has been statistically studied and linked to the collective defect de/localization behavior in the chalcogenide material. Weibull distribution of the delay time supports the origin of such probabilistic switching, facilitates further optimization of the operation condition, and lays the foundation for device modelling and circuit design. Considering its other advantages such as simple structure, fast speed, and volatile nature, OTS is a promising material for implementing SC in a wide range of novel applications, such as image processors, neural networks, control systems and reliability analysis.

引用

页码：1496 / 1499

页数：4

共 29 条

[1]

[Anonymous], 2015, THESIS

[2] VLSI Implementation of Deep Neural Network Using Integral Stochastic Computing [J].

Ardakani, Arash ;

Leduc-Primeau, Francois ;

Onizawa, Naoya ;

Hanyu, Takahiro ;

Gross, Warren J. .

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2017, 25 (10) :2688-2699

[3]

Avasarala NS, 2018, 2018 IEEE SYMPOSIUM ON VLSI TECHNOLOGY, P209, DOI 10.1109/VLSIT.2018.8510680

[4]

Chai Z, 2019, S VLSI TECH, pT238, DOI 10.23919/VLSIT.2019.8776566

[5] GeSe-Based Ovonic Threshold Switching Volatile True Random Number Generator [J].

Chai, Zheng ;

Shao, Wei ;

Zhang, Weidong ;

Brown, James ;

Degraeve, Robin ;

Salim, Flora D. ;

Clima, Sergiu ;

Hatem, Firas ;

Zhang, Jian Fu ;

Freitas, Pedro ;

Marsland, John ;

Fantini, Andrea ;

Garbin, Daniele ;

Goux, Ludovic ;

Kar, Gouri Sankar .

IEEE ELECTRON DEVICE LETTERS, 2020, 41 (02) :228-231

[6] Dependence of Switching Probability on Operation Conditions in GexSe1-x Ovonic Threshold Switching Selectors [J].

Chai, Zheng ;

Zhang, Weidong ;

Degraeve, Robin ;

Clima, Sergiu ;

Hatem, Firas ;

Zhang, Jian Fu ;

Freitas, Pedro ;

Marsland, John ;

Fantini, Andrea ;

Garbin, Daniele ;

Goux, Ludovic ;

Kar, Gouri Sankar .

IEEE ELECTRON DEVICE LETTERS, 2019, 40 (08) :1269-1272

[7] Invited Paper: Thin-Film Ovonic Threshold Switch: Its Operation and Application in Modern Integrated Circuits [J].

Czubatyj, Wally ;

Hudgens, Stephen J. .

ELECTRONIC MATERIALS LETTERS, 2012, 8 (02) :157-167

[8]

Gaba S, 2014, IEEE INT SYMP CIRC S, P2592, DOI 10.1109/ISCAS.2014.6865703

[9]

Gaines B. R, 1969, Advances in Information Systems Science, P37

[10]

Garbin D., 2019, IEDM, P35, DOI [10.1109/IEDM19573.2019.8993547, DOI 10.1109/IEDM19573.2019.8993547]

← 1 2 3 →