Ultra-High-Efficiency Writing in Voltage-Control Spintronics Memory (VoCSM): The Most Promising Embedded Memory for Deep Learning

Ultra-High-Efficiency Writing in Voltage-Control Spintronics Memory (VoCSM): The Most Promising Embedded Memory for Deep Learning

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 <inline-formula> <tex-math notation="LaTeX">$37~\mu \tex...

Full description

Bibliographic Details
Main Authors: 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
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Journal of the Electron Devices Society
Subjects:
Magnetic memory
nonvolatile memory
magnetic tunneling
magnetic devices
learning (artificial intelligence)
Nanopatterning
Online Access:https://ieeexplore.ieee.org/document/8531691/
id doaj-03a3df8d0777445cbb1c3a66abffb36d
record_format Article
spelling doaj-03a3df8d0777445cbb1c3a66abffb36d2021-04-05T16:57:03ZengIEEEIEEE Journal of the Electron Devices Society2168-67342018-01-0161233123810.1109/JEDS.2018.28807528531691Ultra-High-Efficiency Writing in Voltage-Control Spintronics Memory (VoCSM): The Most Promising Embedded Memory for Deep LearningY. Ohsawa0https://orcid.org/0000-0003-1316-4517H. Yoda1N. Shimomura2S. Shirotori3https://orcid.org/0000-0002-5985-1489S. Fujita4K. Koi5A. Buyandalai6S. Oikawa7M. Shimizu8Y. Kato9T. Inokuchi10H. Sugiyama11M. Ishikawa12https://orcid.org/0000-0001-5403-1767K. Ikegami13https://orcid.org/0000-0002-6234-4568S. Takaya14A. Kurobe15https://orcid.org/0000-0002-7480-6993Corporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanDepartment of Systems Innovation, Graduate School of Engineering Science, Osaka University, Toyonaka, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanCorporate Research and Development Center, Toshiba Corporation, Kawasaki, JapanOur 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 <inline-formula> <tex-math notation="LaTeX">$37~\mu \text{A}$ </tex-math></inline-formula> for about 350 <inline-formula> <tex-math notation="LaTeX">$K_{B}T$ </tex-math></inline-formula> switching energy. This indicates VoCSM&#x2019;s writing efficiency is so high that VoCSM would be applicable for deep learning memories requiring ultra-low power consumption.https://ieeexplore.ieee.org/document/8531691/Magnetic memorynonvolatile memorymagnetic tunnelingmagnetic deviceslearning (artificial intelligence)Nanopatterning
collection DOAJ
language English
format Article
sources DOAJ
author 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
spellingShingle 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
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
Magnetic memory
nonvolatile memory
magnetic tunneling
magnetic devices
learning (artificial intelligence)
Nanopatterning
author_facet 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
author_sort Y. Ohsawa
title Ultra-High-Efficiency Writing in Voltage-Control Spintronics Memory (VoCSM): The Most Promising Embedded Memory for Deep Learning
title_short Ultra-High-Efficiency Writing in Voltage-Control Spintronics Memory (VoCSM): The Most Promising Embedded Memory for Deep Learning
title_full Ultra-High-Efficiency Writing in Voltage-Control Spintronics Memory (VoCSM): The Most Promising Embedded Memory for Deep Learning
title_fullStr Ultra-High-Efficiency Writing in Voltage-Control Spintronics Memory (VoCSM): The Most Promising Embedded Memory for Deep Learning
title_full_unstemmed Ultra-High-Efficiency Writing in Voltage-Control Spintronics Memory (VoCSM): The Most Promising Embedded Memory for Deep Learning
title_sort ultra-high-efficiency writing in voltage-control spintronics memory (vocsm): the most promising embedded memory for deep learning
publisher IEEE
series IEEE Journal of the Electron Devices Society
issn 2168-6734
publishDate 2018-01-01
description 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 <inline-formula> <tex-math notation="LaTeX">$37~\mu \text{A}$ </tex-math></inline-formula> for about 350 <inline-formula> <tex-math notation="LaTeX">$K_{B}T$ </tex-math></inline-formula> switching energy. This indicates VoCSM&#x2019;s writing efficiency is so high that VoCSM would be applicable for deep learning memories requiring ultra-low power consumption.
topic Magnetic memory
nonvolatile memory
magnetic tunneling
magnetic devices
learning (artificial intelligence)
Nanopatterning
url https://ieeexplore.ieee.org/document/8531691/
work_keys_str_mv AT yohsawa ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT hyoda ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT nshimomura ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT sshirotori ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT sfujita ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT kkoi ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT abuyandalai ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT soikawa ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT mshimizu ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT ykato ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT tinokuchi ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT hsugiyama ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT mishikawa ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT kikegami ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT stakaya ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
AT akurobe ultrahighefficiencywritinginvoltagecontrolspintronicsmemoryvocsmthemostpromisingembeddedmemoryfordeeplearning
_version_ 1721540552256651264

Similar Items