Process-in-Memory Using a Magnetic-Tunnel-Junction Synapse and a Neuron Based on a Carbon Nanotube Field-Effect Transistor

被引：30
作者：
Amirany, Abdolah [1 ]
Moaiyeri, Mohammad Hossein [1 ]
Jafari, Kian [1 ]
机构：
[1] Shahid Beheshti Univ, Dept Elect Engn, Tehran 1983963113, Iran
来源：
IEEE MAGNETICS LETTERS | 2019年 / 10卷
关键词：
Spin electronics; magnetic tunnel junction; carbon nanotube field-effect transistor; neural network; associative memory; process-in-memory; VIRTUAL-SOURCE MODEL; PERFORMANCE; FETS;
D O I：
10.1109/LMAG.2019.2958813
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：
Bio-inspired computing attempts to emulate the computations performed by biological neural networks, like those in the human brain, to benefit from efficiencies in flexibility, parallel processing, and, most importantly, learning. We simulate a fully nonvolatile spin-based synapse utilizing a magnetic tunnel junction (MTJ) and a neuron based on a carbon nanotube field-effect transistor (CNTFET). The modeled synapse benefits from the features of MTJs like nonvolatility, high endurance, and reconfigurability. The features of CNTFETs are utilized to streamline the design. The functionality and characteristics of the synapse in the inevitable presence of process variations are validated using Monte Carlo simulations. An associative memory, designed and simulated using the spin-based synapse, performs very similar to its ideal software-based counterpart, with about 8% difference in successful recall rate.
引用
收藏
页数：5
相关论文
共 27 条
[1]   Low Energy Barrier Nanomagnet Design for Binary Stochastic Neurons: Design Challenges for Real Nanomagnets With Fabrication Defects [J].
Abeed, Md. Ahsanul ;
Bandyopadhyay, Supriyo .
IEEE MAGNETICS LETTERS, 2019, 10
[2]   Nonvolatile, Spin-Based, and Low-Power Inexact Full Adder Circuits for Computing-in-Memory Image Processing [J].
Amirany, Abdolah ;
Rajaei, Ramin .
SPIN, 2019, 9 (03)
[3]   Nonvolatile Spin-Based Radiation Hardened Retention Latch and Flip-Flop [J].
Amirany, Abdolah ;
Marvi, Fahimeh ;
Jafari, Kian ;
Rajaei, Ramin .
IEEE TRANSACTIONS ON NANOTECHNOLOGY, 2019, 18 :1089-1096
[4]   Spin-Based Fully Nonvolatile Full-Adder Circuit for Computing in Memory [J].
Amirany, Abdolah ;
Rajaei, Ramin .
SPIN, 2019, 9 (01)
[5]   Fully Nonvolatile and Low Power Full Adder Based on Spin Transfer Torque Magnetic Tunnel Junction With Spin-Hall Effect Assistance [J].
Amirany, Abdolah ;
Rajaei, Ramin .
IEEE TRANSACTIONS ON MAGNETICS, 2018, 54 (12)
[6]   Nonsilicon, Non von Neumann Computing-Part I [J].
Basu, Sankar ;
Bryant, Randal E. ;
De Micheli, Giovanni ;
Theis, Thomas ;
Whitman, Lloyd .
PROCEEDINGS OF THE IEEE, 2019, 107 (01) :11-18
[7]   The emergence of spin electronics in data storage [J].
Chappert, Claude ;
Fert, Albert ;
Van Dau, Frederic Nguyen .
NATURE MATERIALS, 2007, 6 (11) :813-823
[8]  
Chow C., 2004, Methods and Models in Neurophysics: Lecture Notes of the Les Houches Summer School 2003
[9]  
Gurney K., 2018, An Introduction to Neural Networks, DOI [10.1201/9781315273570, DOI 10.1201/9781315273570]
[10]   Low-Barrier Magnet Design for Efficient Hardware Binary Stochastic Neurons [J].
Hassan, Orchi ;
Faria, Rafatul ;
Camsari, Kerem Yunus ;
Sun, Jonathan Z. ;
Datta, Supriyo .
IEEE MAGNETICS LETTERS, 2019, 10
123