Ultra-high-efficiency writing in voltage-control spintronics memory (VoCSM): The most promising embedded memory for deep learning

Y. Ohsawa; H. Yoda; N. Shimomura; S. Shirotori; S. Fujita; K. Koi; A. Buyandalai; S. Oikawa; M. Shimizu; Y. Kato; T. Inokuchi; H. Sugiyama; M. Ishikawa; K. Ikegami; S. Takaya; A. Kurobe

doi:10.1109/JEDS.2018.2880752

Ultra-high-efficiency writing in voltage-control spintronics memory (VoCSM): The most promising embedded memory for deep learning

Y. Ohsawa, H. Yoda, N. Shimomura, S. Shirotori, S. Fujita, K. Koi, A. Buyandalai, S. Oikawa, M. Shimizu, Y. Kato, T. Inokuchi, H. Sugiyama, M. Ishikawa, K. Ikegami, S. Takaya, A. Kurobe

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

Our new proposal of voltage-control spintronics memory (VoCSM) in which spin-orbit torque in conjunction with the voltage-control-magnetic-anisotropy effect works as the writing principle showed small switching current of 37 μA for about 350 K_BT switching energy. This indicates VoCSM's writing efficiency is so high that VoCSM would be applicable for deep learning memories requiring ultra-low power consumption.

Original language	English
Article number	8531691
Pages (from-to)	1238-1243
Number of pages	6
Journal	IEEE Journal of the Electron Devices Society
Volume	6
DOIs	https://doi.org/10.1109/JEDS.2018.2880752
Publication status	Published - 2018
Externally published	Yes

Keywords

learning (artificial intelligence)
magnetic devices
Magnetic memory
magnetic tunneling
Nanopatterning
nonvolatile memory

Access to Document

10.1109/JEDS.2018.2880752

Cite this

Ohsawa, Y., Yoda, H., Shimomura, N., Shirotori, S., Fujita, S., Koi, K., Buyandalai, A., Oikawa, S., Shimizu, M., Kato, Y., Inokuchi, T., Sugiyama, H., Ishikawa, M., Ikegami, K., Takaya, S., & Kurobe, A. (2018). Ultra-high-efficiency writing in voltage-control spintronics memory (VoCSM): The most promising embedded memory for deep learning. IEEE Journal of the Electron Devices Society, 6, 1238-1243. Article 8531691. https://doi.org/10.1109/JEDS.2018.2880752

@article{b7c848a8efc246efbe0cb745a57fc382,

title = "Ultra-high-efficiency writing in voltage-control spintronics memory (VoCSM): The most promising embedded memory for deep learning",

abstract = "Our new proposal of voltage-control spintronics memory (VoCSM) in which spin-orbit torque in conjunction with the voltage-control-magnetic-anisotropy effect works as the writing principle showed small switching current of 37 μA for about 350 KBT switching energy. This indicates VoCSM's writing efficiency is so high that VoCSM would be applicable for deep learning memories requiring ultra-low power consumption.",

keywords = "learning (artificial intelligence), magnetic devices, Magnetic memory, magnetic tunneling, Nanopatterning, nonvolatile memory",

author = "Y. Ohsawa and H. Yoda and N. Shimomura and S. Shirotori and S. Fujita and K. Koi and A. Buyandalai and S. Oikawa and M. Shimizu and Y. Kato and T. Inokuchi and H. Sugiyama and M. Ishikawa and K. Ikegami and S. Takaya and A. Kurobe",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.",

year = "2018",

doi = "10.1109/JEDS.2018.2880752",

language = "English",

volume = "6",

pages = "1238--1243",

journal = "IEEE Journal of the Electron Devices Society",

issn = "2168-6734",

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

}

Ohsawa, Y, Yoda, H, Shimomura, N, Shirotori, S, Fujita, S, Koi, K, Buyandalai, A, Oikawa, S, Shimizu, M, Kato, Y, Inokuchi, T, Sugiyama, H, Ishikawa, M, Ikegami, K, Takaya, S & Kurobe, A 2018, 'Ultra-high-efficiency writing in voltage-control spintronics memory (VoCSM): The most promising embedded memory for deep learning', IEEE Journal of the Electron Devices Society, vol. 6, 8531691, pp. 1238-1243. https://doi.org/10.1109/JEDS.2018.2880752

TY - JOUR

T1 - Ultra-high-efficiency writing in voltage-control spintronics memory (VoCSM)

T2 - The most promising embedded memory for deep learning

AU - Ohsawa, Y.

AU - Yoda, H.

AU - Shimomura, N.

AU - Shirotori, S.

AU - Fujita, S.

AU - Koi, K.

AU - Buyandalai, A.

AU - Oikawa, S.

AU - Shimizu, M.

AU - Kato, Y.

AU - Inokuchi, T.

AU - Sugiyama, H.

AU - Ishikawa, M.

AU - Ikegami, K.

AU - Takaya, S.

AU - Kurobe, A.

PY - 2018

Y1 - 2018

N2 - Our new proposal of voltage-control spintronics memory (VoCSM) in which spin-orbit torque in conjunction with the voltage-control-magnetic-anisotropy effect works as the writing principle showed small switching current of 37 μA for about 350 KBT switching energy. This indicates VoCSM's writing efficiency is so high that VoCSM would be applicable for deep learning memories requiring ultra-low power consumption.

AB - Our new proposal of voltage-control spintronics memory (VoCSM) in which spin-orbit torque in conjunction with the voltage-control-magnetic-anisotropy effect works as the writing principle showed small switching current of 37 μA for about 350 KBT switching energy. This indicates VoCSM's writing efficiency is so high that VoCSM would be applicable for deep learning memories requiring ultra-low power consumption.

KW - learning (artificial intelligence)

KW - magnetic devices

KW - Magnetic memory

KW - magnetic tunneling

KW - Nanopatterning

KW - nonvolatile memory

UR - http://www.scopus.com/inward/record.url?scp=85056321826&partnerID=8YFLogxK

U2 - 10.1109/JEDS.2018.2880752

DO - 10.1109/JEDS.2018.2880752

M3 - Article

AN - SCOPUS:85056321826

SN - 2168-6734

VL - 6

SP - 1238

EP - 1243

JO - IEEE Journal of the Electron Devices Society

JF - IEEE Journal of the Electron Devices Society

M1 - 8531691

ER -

Ultra-high-efficiency writing in voltage-control spintronics memory (VoCSM): The most promising embedded memory for deep learning

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this