Analog CMOS-based resistive processing unit for deep neural network training

Seyoung Kim, Tayfun Gokmen, Hyung Min Lee, Wilfried E. Haensch

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Recently we have shown that an architecture based on resistive processing unit (RPU) devices has potential to achieve significant acceleration in deep neural network (DNN) training compared to today's software-based DNN implementations running on CPU/GPU. However, currently available device candidates based on non-volatile memory technologies do not satisfy all the requirements to realize the RPU concept. Here, we propose an analog CMOS-based RPU design (CMOS RPU) which can store and process data locally and can be operated in a massively parallel manner. We analyze various properties of the CMOS RPU to evaluate the functionality and feasibility for acceleration of DNN training.

Original languageEnglish
Title of host publication2017 IEEE 60th International Midwest Symposium on Circuits and Systems, MWSCAS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages422-425
Number of pages4
ISBN (Electronic)9781509063895
DOIs
Publication statusPublished - 2017 Sep 27
Event60th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2017 - Boston, United States
Duration: 2017 Aug 62017 Aug 9

Publication series

NameMidwest Symposium on Circuits and Systems
Volume2017-August
ISSN (Print)1548-3746

Conference

Conference60th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2017
CountryUnited States
CityBoston
Period17/8/617/8/9

Fingerprint

Processing
Program processors
Data storage equipment
Deep neural networks
Graphics processing unit

Keywords

  • Deep neural network
  • Machine learning accelerator
  • Resistive memory
  • Resistive processing unit
  • RPU

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Cite this

Kim, S., Gokmen, T., Lee, H. M., & Haensch, W. E. (2017). Analog CMOS-based resistive processing unit for deep neural network training. In 2017 IEEE 60th International Midwest Symposium on Circuits and Systems, MWSCAS 2017 (pp. 422-425). [8052950] (Midwest Symposium on Circuits and Systems; Vol. 2017-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MWSCAS.2017.8052950

Analog CMOS-based resistive processing unit for deep neural network training. / Kim, Seyoung; Gokmen, Tayfun; Lee, Hyung Min; Haensch, Wilfried E.

2017 IEEE 60th International Midwest Symposium on Circuits and Systems, MWSCAS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 422-425 8052950 (Midwest Symposium on Circuits and Systems; Vol. 2017-August).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, S, Gokmen, T, Lee, HM & Haensch, WE 2017, Analog CMOS-based resistive processing unit for deep neural network training. in 2017 IEEE 60th International Midwest Symposium on Circuits and Systems, MWSCAS 2017., 8052950, Midwest Symposium on Circuits and Systems, vol. 2017-August, Institute of Electrical and Electronics Engineers Inc., pp. 422-425, 60th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2017, Boston, United States, 17/8/6. https://doi.org/10.1109/MWSCAS.2017.8052950
Kim S, Gokmen T, Lee HM, Haensch WE. Analog CMOS-based resistive processing unit for deep neural network training. In 2017 IEEE 60th International Midwest Symposium on Circuits and Systems, MWSCAS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 422-425. 8052950. (Midwest Symposium on Circuits and Systems). https://doi.org/10.1109/MWSCAS.2017.8052950
Kim, Seyoung ; Gokmen, Tayfun ; Lee, Hyung Min ; Haensch, Wilfried E. / Analog CMOS-based resistive processing unit for deep neural network training. 2017 IEEE 60th International Midwest Symposium on Circuits and Systems, MWSCAS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 422-425 (Midwest Symposium on Circuits and Systems).
@inproceedings{22b260cb201540179ae08aa5ba49d571,
title = "Analog CMOS-based resistive processing unit for deep neural network training",
abstract = "Recently we have shown that an architecture based on resistive processing unit (RPU) devices has potential to achieve significant acceleration in deep neural network (DNN) training compared to today's software-based DNN implementations running on CPU/GPU. However, currently available device candidates based on non-volatile memory technologies do not satisfy all the requirements to realize the RPU concept. Here, we propose an analog CMOS-based RPU design (CMOS RPU) which can store and process data locally and can be operated in a massively parallel manner. We analyze various properties of the CMOS RPU to evaluate the functionality and feasibility for acceleration of DNN training.",
keywords = "Deep neural network, Machine learning accelerator, Resistive memory, Resistive processing unit, RPU",
author = "Seyoung Kim and Tayfun Gokmen and Lee, {Hyung Min} and Haensch, {Wilfried E.}",
year = "2017",
month = "9",
day = "27",
doi = "10.1109/MWSCAS.2017.8052950",
language = "English",
series = "Midwest Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "422--425",
booktitle = "2017 IEEE 60th International Midwest Symposium on Circuits and Systems, MWSCAS 2017",

}

TY - GEN

T1 - Analog CMOS-based resistive processing unit for deep neural network training

AU - Kim, Seyoung

AU - Gokmen, Tayfun

AU - Lee, Hyung Min

AU - Haensch, Wilfried E.

PY - 2017/9/27

Y1 - 2017/9/27

N2 - Recently we have shown that an architecture based on resistive processing unit (RPU) devices has potential to achieve significant acceleration in deep neural network (DNN) training compared to today's software-based DNN implementations running on CPU/GPU. However, currently available device candidates based on non-volatile memory technologies do not satisfy all the requirements to realize the RPU concept. Here, we propose an analog CMOS-based RPU design (CMOS RPU) which can store and process data locally and can be operated in a massively parallel manner. We analyze various properties of the CMOS RPU to evaluate the functionality and feasibility for acceleration of DNN training.

AB - Recently we have shown that an architecture based on resistive processing unit (RPU) devices has potential to achieve significant acceleration in deep neural network (DNN) training compared to today's software-based DNN implementations running on CPU/GPU. However, currently available device candidates based on non-volatile memory technologies do not satisfy all the requirements to realize the RPU concept. Here, we propose an analog CMOS-based RPU design (CMOS RPU) which can store and process data locally and can be operated in a massively parallel manner. We analyze various properties of the CMOS RPU to evaluate the functionality and feasibility for acceleration of DNN training.

KW - Deep neural network

KW - Machine learning accelerator

KW - Resistive memory

KW - Resistive processing unit

KW - RPU

UR - http://www.scopus.com/inward/record.url?scp=85034014587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034014587&partnerID=8YFLogxK

U2 - 10.1109/MWSCAS.2017.8052950

DO - 10.1109/MWSCAS.2017.8052950

M3 - Conference contribution

AN - SCOPUS:85034014587

T3 - Midwest Symposium on Circuits and Systems

SP - 422

EP - 425

BT - 2017 IEEE 60th International Midwest Symposium on Circuits and Systems, MWSCAS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -