Parallel Computing in Memory Paradigm based on Reconfigurable Spin-Orbit Torque

Zhongkui Zhang; Chao Wang; Zhaohao Wang

doi:10.1145/3565478.3572531

Parallel Computing in Memory Paradigm based on Reconfigurable Spin-Orbit Torque

Zhongkui Zhang
, Chao Wang
, Zhaohao Wang

School of Integrated Circuit Science and Engineering

Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We proposed a parallel computing in memory paradigm based on reconfigurable spin-orbit torque switching. The proposed paradigm can efficiently perform XNOR operation without complicated steps or modifications to array structure. Compared to traditional design, 50% writing energy and 2× sensing margin can be achieved.

Original language	English
Title of host publication	Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450399388
DOIs	https://doi.org/10.1145/3565478.3572531
State	Published - 7 Dec 2022
Event	17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022 - Virtual, Online, United States Duration: 7 Dec 2022 → 9 Dec 2022

Publication series

Name	Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022

Conference

Conference	17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022
Country/Territory	United States
City	Virtual, Online
Period	7/12/22 → 9/12/22

Keywords

BNN
NAND-SPIN
XNOR
reconfigurable SOT

Access to Document

10.1145/3565478.3572531

Cite this

Zhang, Z., Wang, C., & Wang, Z. (2022). Parallel Computing in Memory Paradigm based on Reconfigurable Spin-Orbit Torque. In Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022 Article 4 (Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022). Association for Computing Machinery, Inc. https://doi.org/10.1145/3565478.3572531

@inproceedings{d64e3dff79be4cb7942f03a4d8609c3f,

title = "Parallel Computing in Memory Paradigm based on Reconfigurable Spin-Orbit Torque",

abstract = "We proposed a parallel computing in memory paradigm based on reconfigurable spin-orbit torque switching. The proposed paradigm can efficiently perform XNOR operation without complicated steps or modifications to array structure. Compared to traditional design, 50\% writing energy and 2× sensing margin can be achieved.",

keywords = "BNN, NAND-SPIN, XNOR, reconfigurable SOT",

author = "Zhongkui Zhang and Chao Wang and Zhaohao Wang",

note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022 ; Conference date: 07-12-2022 Through 09-12-2022",

year = "2022",

month = dec,

day = "7",

doi = "10.1145/3565478.3572531",

language = "英语",

series = "Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022",

publisher = "Association for Computing Machinery, Inc",

booktitle = "Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022",

}

Zhang, Z, Wang, C & Wang, Z 2022, Parallel Computing in Memory Paradigm based on Reconfigurable Spin-Orbit Torque. in Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022., 4, Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022, Association for Computing Machinery, Inc, 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022, Virtual, Online, United States, 7/12/22. https://doi.org/10.1145/3565478.3572531

Parallel Computing in Memory Paradigm based on Reconfigurable Spin-Orbit Torque. / Zhang, Zhongkui; Wang, Chao; Wang, Zhaohao.
Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022. Association for Computing Machinery, Inc, 2022. 4 (Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Parallel Computing in Memory Paradigm based on Reconfigurable Spin-Orbit Torque

AU - Zhang, Zhongkui

AU - Wang, Chao

AU - Wang, Zhaohao

PY - 2022/12/7

Y1 - 2022/12/7

N2 - We proposed a parallel computing in memory paradigm based on reconfigurable spin-orbit torque switching. The proposed paradigm can efficiently perform XNOR operation without complicated steps or modifications to array structure. Compared to traditional design, 50% writing energy and 2× sensing margin can be achieved.

AB - We proposed a parallel computing in memory paradigm based on reconfigurable spin-orbit torque switching. The proposed paradigm can efficiently perform XNOR operation without complicated steps or modifications to array structure. Compared to traditional design, 50% writing energy and 2× sensing margin can be achieved.

KW - BNN

KW - NAND-SPIN

KW - XNOR

KW - reconfigurable SOT

UR - https://www.scopus.com/pages/publications/85162856828

U2 - 10.1145/3565478.3572531

DO - 10.1145/3565478.3572531

M3 - 会议稿件

AN - SCOPUS:85162856828

T3 - Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022

BT - Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022

PB - Association for Computing Machinery, Inc

T2 - 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022

Y2 - 7 December 2022 through 9 December 2022

ER -

Zhang Z, Wang C, Wang Z. Parallel Computing in Memory Paradigm based on Reconfigurable Spin-Orbit Torque. In Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022. Association for Computing Machinery, Inc. 2022. 4. (Proceedings of the 17th ACM International Symposium on Nanoscale Architectures, NANOARCH 2022). doi: 10.1145/3565478.3572531

Parallel Computing in Memory Paradigm based on Reconfigurable Spin-Orbit Torque

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this