IEEE Journal of the Electron Devices Society (Jan 2018)
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
Affiliations
- Y. Ohsawa
- ORCiD
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- H. Yoda
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- N. Shimomura
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- S. Shirotori
- ORCiD
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- S. Fujita
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- K. Koi
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- A. Buyandalai
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- S. Oikawa
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- M. Shimizu
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- Y. Kato
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- T. Inokuchi
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- H. Sugiyama
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- M. Ishikawa
- ORCiD
- Department of Systems Innovation, Graduate School of Engineering Science, Osaka University, Toyonaka, Japan
- K. Ikegami
- ORCiD
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- S. Takaya
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- A. Kurobe
- ORCiD
- Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan
- DOI
- https://doi.org/10.1109/JEDS.2018.2880752
- Journal volume & issue
-
Vol. 6
pp. 1233 – 1238
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 $37~\mu \text{A}$ for about 350 $K_{B}T$ 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
- Magnetic memory
- nonvolatile memory
- magnetic tunneling
- magnetic devices
- learning (artificial intelligence)
- Nanopatterning
