Energy efficient in-memory computing platform based on 4-terminal spin hall effect-driven domain wall motion devices

Shaahin Angizi; Zhezhi He; Deliang Fan

doi:10.1145/3060403.3060459

Energy efficient in-memory computing platform based on 4-terminal spin hall effect-driven domain wall motion devices

Shaahin Angizi, Zhezhi He, Deliang Fan

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

12 Scopus citations

Abstract

In this paper, we propose an energy efficient in-memory computing platform based on novel 4-terminal spin Hall effect-driven domain wall motion devices that could be employed as both non-volatile memory cell and in-memory logic unit. The proposed designs lead to unity of memory and logic. The device to architecture level simulation results show that, with 45% area increase, the proposed in-memory computing platform achieves the write energy ∼ 15.6 fJ/bit which is more than one order lower than that of standard 1-transistor 1-magnetic tunnel junction counterpart while keeping the identical 1ns writing speed. In addition, the proposed in-memory logic scheme improves the operating energy by 61.3% as compared with the conventional nonvolatile in-memory logic designs.

Original language	English (US)
Title of host publication	GLSVLSI 2017 - Proceedings of the Great Lakes Symposium on VLSI 2017
Publisher	Association for Computing Machinery
Pages	77-82
Number of pages	6
ISBN (Electronic)	9781450349727
DOIs	https://doi.org/10.1145/3060403.3060459
State	Published - May 10 2017
Externally published	Yes
Event	27th Great Lakes Symposium on VLSI, GLSVLSI 2017 - Banff, Canada Duration: May 10 2017 → May 12 2017

Publication series

Name	Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI
Volume	Part F127756

Other

Other	27th Great Lakes Symposium on VLSI, GLSVLSI 2017
Country/Territory	Canada
City	Banff
Period	5/10/17 → 5/12/17

Keywords

Domain wall motion device
In-memory computing
Spin Hall effect

ASJC Scopus subject areas

General Engineering

Access to Document

10.1145/3060403.3060459

Cite this

Angizi, S., He, Z., & Fan, D. (2017). Energy efficient in-memory computing platform based on 4-terminal spin hall effect-driven domain wall motion devices. In GLSVLSI 2017 - Proceedings of the Great Lakes Symposium on VLSI 2017 (pp. 77-82). (Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI; Vol. Part F127756). Association for Computing Machinery. https://doi.org/10.1145/3060403.3060459

Energy efficient in-memory computing platform based on 4-terminal spin hall effect-driven domain wall motion devices. / Angizi, Shaahin; He, Zhezhi; Fan, Deliang.
GLSVLSI 2017 - Proceedings of the Great Lakes Symposium on VLSI 2017. Association for Computing Machinery, 2017. p. 77-82 (Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI; Vol. Part F127756).

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

Angizi, S, He, Z & Fan, D 2017, Energy efficient in-memory computing platform based on 4-terminal spin hall effect-driven domain wall motion devices. in GLSVLSI 2017 - Proceedings of the Great Lakes Symposium on VLSI 2017. Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI, vol. Part F127756, Association for Computing Machinery, pp. 77-82, 27th Great Lakes Symposium on VLSI, GLSVLSI 2017, Banff, Canada, 5/10/17. https://doi.org/10.1145/3060403.3060459

@inproceedings{8d32f992751940b1846483602a44e21f,

title = "Energy efficient in-memory computing platform based on 4-terminal spin hall effect-driven domain wall motion devices",

abstract = "In this paper, we propose an energy efficient in-memory computing platform based on novel 4-terminal spin Hall effect-driven domain wall motion devices that could be employed as both non-volatile memory cell and in-memory logic unit. The proposed designs lead to unity of memory and logic. The device to architecture level simulation results show that, with 45% area increase, the proposed in-memory computing platform achieves the write energy ∼ 15.6 fJ/bit which is more than one order lower than that of standard 1-transistor 1-magnetic tunnel junction counterpart while keeping the identical 1ns writing speed. In addition, the proposed in-memory logic scheme improves the operating energy by 61.3% as compared with the conventional nonvolatile in-memory logic designs.",

keywords = "Domain wall motion device, In-memory computing, Spin Hall effect",

author = "Shaahin Angizi and Zhezhi He and Deliang Fan",

note = "Publisher Copyright: {\textcopyright} 2017 ACM.; 27th Great Lakes Symposium on VLSI, GLSVLSI 2017 ; Conference date: 10-05-2017 Through 12-05-2017",

year = "2017",

month = may,

day = "10",

doi = "10.1145/3060403.3060459",

language = "English (US)",

series = "Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI",

publisher = "Association for Computing Machinery",

pages = "77--82",

booktitle = "GLSVLSI 2017 - Proceedings of the Great Lakes Symposium on VLSI 2017",

}

TY - GEN

T1 - Energy efficient in-memory computing platform based on 4-terminal spin hall effect-driven domain wall motion devices

AU - Angizi, Shaahin

AU - He, Zhezhi

AU - Fan, Deliang

PY - 2017/5/10

Y1 - 2017/5/10

N2 - In this paper, we propose an energy efficient in-memory computing platform based on novel 4-terminal spin Hall effect-driven domain wall motion devices that could be employed as both non-volatile memory cell and in-memory logic unit. The proposed designs lead to unity of memory and logic. The device to architecture level simulation results show that, with 45% area increase, the proposed in-memory computing platform achieves the write energy ∼ 15.6 fJ/bit which is more than one order lower than that of standard 1-transistor 1-magnetic tunnel junction counterpart while keeping the identical 1ns writing speed. In addition, the proposed in-memory logic scheme improves the operating energy by 61.3% as compared with the conventional nonvolatile in-memory logic designs.

AB - In this paper, we propose an energy efficient in-memory computing platform based on novel 4-terminal spin Hall effect-driven domain wall motion devices that could be employed as both non-volatile memory cell and in-memory logic unit. The proposed designs lead to unity of memory and logic. The device to architecture level simulation results show that, with 45% area increase, the proposed in-memory computing platform achieves the write energy ∼ 15.6 fJ/bit which is more than one order lower than that of standard 1-transistor 1-magnetic tunnel junction counterpart while keeping the identical 1ns writing speed. In addition, the proposed in-memory logic scheme improves the operating energy by 61.3% as compared with the conventional nonvolatile in-memory logic designs.

KW - Domain wall motion device

KW - In-memory computing

KW - Spin Hall effect

UR - http://www.scopus.com/inward/record.url?scp=85021227901&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021227901&partnerID=8YFLogxK

U2 - 10.1145/3060403.3060459

DO - 10.1145/3060403.3060459

M3 - Conference contribution

AN - SCOPUS:85021227901

T3 - Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI

SP - 77

EP - 82

BT - GLSVLSI 2017 - Proceedings of the Great Lakes Symposium on VLSI 2017

PB - Association for Computing Machinery

T2 - 27th Great Lakes Symposium on VLSI, GLSVLSI 2017

Y2 - 10 May 2017 through 12 May 2017

ER -

Energy efficient in-memory computing platform based on 4-terminal spin hall effect-driven domain wall motion devices

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this