Towards In-Memory Computing: Arithmetic Operations on Real Memristors

Thore Kolms; Christine Lang; Andreas Waldner; Philipp Grothe; Jan Haase

doi:10.1109/IECON43393.2020.9254441

Towards In-Memory Computing: Arithmetic Operations on Real Memristors

Thore Kolms, Christine Lang, Andreas Waldner, Philipp Grothe, Jan Haase

Institut für Technische Informatik

Abstract

In-memory-computing is an emerging approach that aims to shift computational load away from CPUs. It does so by taking over simple calculations that can be performed in memory. Apart from improving performance for these operations, this also results in a lower energy consumption, effectively rendering this technique very suitable for embedded systems.Due to being variable as well as non-volatile resistors, memristors are capable of storing analog values. This renders them particularly useful for in-memory computing.This paper presents a prototypical implementation of analog calculations (addition, subtraction and multiplication), including a way of representing the value zero. The prototype shown is based on an ESP32 microcontroller and typical calculations currently take around 1μs.

Originalsprache	Englisch
Titel	IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society
Seitenumfang	6
Herausgeber (Verlag)	IEEE
Erscheinungsdatum	18.10.2020
Seiten	2296-2301
Aufsatznummer	9254441
ISBN (Print)	978-1-7281-5415-2, 978-1-7281-5413-8
ISBN (elektronisch)	978-1-7281-5414-5
DOIs	https://doi.org/10.1109/IECON43393.2020.9254441
Publikationsstatus	Veröffentlicht - 18.10.2020
Veranstaltung	46th Annual Conference of the IEEE Industrial Electronics Society - Virtual, Singapore, Singapur Dauer: 19.10.2020 → 21.10.2020 Konferenznummer: 165032

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

Dokumente

10.1109/IECON43393.2020.9254441

Weitere Links

www.scopus.com

Zitieren

Kolms, T., Lang, C., Waldner, A., Grothe, P., & Haase, J. (2020). Towards In-Memory Computing: Arithmetic Operations on Real Memristors. in IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society (S. 2296-2301). Artikel 9254441 (IECON Proceedings (Industrial Electronics Conference); Band 2020-October). IEEE. https://doi.org/10.1109/IECON43393.2020.9254441

@inproceedings{c3aa445815ea40fb965f4f8cbc29cb56,

title = "Towards In-Memory Computing: Arithmetic Operations on Real Memristors",

abstract = "In-memory-computing is an emerging approach that aims to shift computational load away from CPUs. It does so by taking over simple calculations that can be performed in memory. Apart from improving performance for these operations, this also results in a lower energy consumption, effectively rendering this technique very suitable for embedded systems.Due to being variable as well as non-volatile resistors, memristors are capable of storing analog values. This renders them particularly useful for in-memory computing.This paper presents a prototypical implementation of analog calculations (addition, subtraction and multiplication), including a way of representing the value zero. The prototype shown is based on an ESP32 microcontroller and typical calculations currently take around 1μs.",

author = "Thore Kolms and Christine Lang and Andreas Waldner and Philipp Grothe and Jan Haase",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 46th Annual Conference of the IEEE Industrial Electronics Society , IECON 2020 ; Conference date: 19-10-2020 Through 21-10-2020",

year = "2020",

month = oct,

day = "18",

doi = "10.1109/IECON43393.2020.9254441",

language = "English",

isbn = "978-1-7281-5415-2",

series = "IECON Proceedings (Industrial Electronics Conference)",

publisher = "IEEE",

pages = "2296--2301",

booktitle = "IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society",

}

Kolms, T, Lang, C, Waldner, A, Grothe, P & Haase, J 2020, Towards In-Memory Computing: Arithmetic Operations on Real Memristors. in IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society., 9254441, IECON Proceedings (Industrial Electronics Conference), Bd. 2020-October, IEEE, S. 2296-2301, 46th Annual Conference of the IEEE Industrial Electronics Society , Singapore, Singapur, 19.10.20. https://doi.org/10.1109/IECON43393.2020.9254441

Towards In-Memory Computing: Arithmetic Operations on Real Memristors. / Kolms, Thore; Lang, Christine; Waldner, Andreas et al.
IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society. IEEE, 2020. S. 2296-2301 9254441 (IECON Proceedings (Industrial Electronics Conference); Band 2020-October).

Publikation: Kapitel in Büchern/Berichten/Konferenzbänden › Konferenzbeitrag › Begutachtung

TY - GEN

T1 - Towards In-Memory Computing: Arithmetic Operations on Real Memristors

AU - Kolms, Thore

AU - Lang, Christine

AU - Waldner, Andreas

AU - Grothe, Philipp

AU - Haase, Jan

N1 - Conference code: 165032

PY - 2020/10/18

Y1 - 2020/10/18

N2 - In-memory-computing is an emerging approach that aims to shift computational load away from CPUs. It does so by taking over simple calculations that can be performed in memory. Apart from improving performance for these operations, this also results in a lower energy consumption, effectively rendering this technique very suitable for embedded systems.Due to being variable as well as non-volatile resistors, memristors are capable of storing analog values. This renders them particularly useful for in-memory computing.This paper presents a prototypical implementation of analog calculations (addition, subtraction and multiplication), including a way of representing the value zero. The prototype shown is based on an ESP32 microcontroller and typical calculations currently take around 1μs.

AB - In-memory-computing is an emerging approach that aims to shift computational load away from CPUs. It does so by taking over simple calculations that can be performed in memory. Apart from improving performance for these operations, this also results in a lower energy consumption, effectively rendering this technique very suitable for embedded systems.Due to being variable as well as non-volatile resistors, memristors are capable of storing analog values. This renders them particularly useful for in-memory computing.This paper presents a prototypical implementation of analog calculations (addition, subtraction and multiplication), including a way of representing the value zero. The prototype shown is based on an ESP32 microcontroller and typical calculations currently take around 1μs.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85097801300&origin=inward&txGid=7d14bf1690c16d3b02ed1bb2048333cb

U2 - 10.1109/IECON43393.2020.9254441

DO - 10.1109/IECON43393.2020.9254441

M3 - Conference contribution

SN - 978-1-7281-5415-2

SN - 978-1-7281-5413-8

T3 - IECON Proceedings (Industrial Electronics Conference)

SP - 2296

EP - 2301

BT - IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society

PB - IEEE

T2 - 46th Annual Conference of the IEEE Industrial Electronics Society

Y2 - 19 October 2020 through 21 October 2020

ER -

Towards In-Memory Computing: Arithmetic Operations on Real Memristors

Abstract

UN SDGs

Dokumente

Weitere Links

Fingerprint

Zitieren