BiMDiM: Area efficient Bi-directional MRAM Digital in-Memory Computing

Dongsu Kim; Yunho Jang; Taehwan Kim; Jongsun Park

doi:10.1109/AICAS54282.2022.9869915

BiMDiM: Area efficient Bi-directional MRAM Digital in-Memory Computing

Dongsu Kim, Yunho Jang, Taehwan Kim, Jongsun Park

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

4 Citations (Scopus)

Abstract

Spin transfer torque MRAM (STT-MRAM) based digital in-memory computing (IMC) has been recently proposed for energy efficient processing of convolutional neural network (CNN). The conventional MRAM based IMC architecture suffers from excessive storage area since a large number of intermediate sum and carry bits should be stored for the following successive additions during multiply-accumulate (MAC) operations. In this paper, we propose an area efficient bi-directional MRAM digital IMC (BiMDiM) scheme, where the size of memory cells storing the intermediate sums and carries can be efficiently reduced by repetitively using the same memory cells during MAC operations. In addition, to reduce the number of inefficient half-additions, which can process only two inputs with almost same hardware cost, the addition re-scheduling is also presented to further improve the energy and latency of BiMDiM. The proposed BiMDiM architecture has been simulated using 28nm CMOS process. When compared to the baseline architecture, the proposed BiMDiM improves area efficiency up to 53%.

Original language	English
Title of host publication	Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	74-77
Number of pages	4
ISBN (Electronic)	9781665409964
DOIs	https://doi.org/10.1109/AICAS54282.2022.9869915
Publication status	Published - 2022
Event	4th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022 - Incheon, Korea, Republic of Duration: 2022 Jun 13 → 2022 Jun 15

Publication series

Name	Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022

Conference

Conference	4th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022
Country/Territory	Korea, Republic of
City	Incheon
Period	22/6/13 → 22/6/15

Bibliographical note

Funding Information:
This work was supported in part by National R&D Program through the National Research Foundation of Korea funded by Ministry of Science and ICT (NRF-2020M3F3A2A01082591), and in part by the National Research Foundation of Korea grant funded by the Korea government (NRF-2020R1A2C3014820). The EDA tool was supported by the IC Design Education Center(IDEC), Korea.

Publisher Copyright:
© 2022 IEEE.

Keywords

Convolutional neural network (CNN)
digital in memory computing (digital IMC)
Memory area
Spin Transfer Torque magnetic random access memory (STT-MRAM)

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Computer Vision and Pattern Recognition
Hardware and Architecture
Human-Computer Interaction
Electrical and Electronic Engineering

Access to Document

10.1109/AICAS54282.2022.9869915

Cite this

Kim, D., Jang, Y., Kim, T., & Park, J. (2022). BiMDiM: Area efficient Bi-directional MRAM Digital in-Memory Computing. In Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022 (pp. 74-77). (Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AICAS54282.2022.9869915

BiMDiM: Area efficient Bi-directional MRAM Digital in-Memory Computing. / Kim, Dongsu; Jang, Yunho; Kim, Taehwan et al.
Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 74-77 (Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022).

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

Kim, D, Jang, Y, Kim, T & Park, J 2022, BiMDiM: Area efficient Bi-directional MRAM Digital in-Memory Computing. in Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022. Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022, Institute of Electrical and Electronics Engineers Inc., pp. 74-77, 4th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022, Incheon, Korea, Republic of, 22/6/13. https://doi.org/10.1109/AICAS54282.2022.9869915

Kim D, Jang Y, Kim T, Park J. BiMDiM: Area efficient Bi-directional MRAM Digital in-Memory Computing. In Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 74-77. (Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022). doi: 10.1109/AICAS54282.2022.9869915

Kim, Dongsu ; Jang, Yunho ; Kim, Taehwan et al. / BiMDiM : Area efficient Bi-directional MRAM Digital in-Memory Computing. Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 74-77 (Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022).

@inproceedings{f89de4edcdbb4e579e36a62c891662ff,

title = "BiMDiM: Area efficient Bi-directional MRAM Digital in-Memory Computing",

abstract = "Spin transfer torque MRAM (STT-MRAM) based digital in-memory computing (IMC) has been recently proposed for energy efficient processing of convolutional neural network (CNN). The conventional MRAM based IMC architecture suffers from excessive storage area since a large number of intermediate sum and carry bits should be stored for the following successive additions during multiply-accumulate (MAC) operations. In this paper, we propose an area efficient bi-directional MRAM digital IMC (BiMDiM) scheme, where the size of memory cells storing the intermediate sums and carries can be efficiently reduced by repetitively using the same memory cells during MAC operations. In addition, to reduce the number of inefficient half-additions, which can process only two inputs with almost same hardware cost, the addition re-scheduling is also presented to further improve the energy and latency of BiMDiM. The proposed BiMDiM architecture has been simulated using 28nm CMOS process. When compared to the baseline architecture, the proposed BiMDiM improves area efficiency up to 53%.",

keywords = "Convolutional neural network (CNN), digital in memory computing (digital IMC), Memory area, Spin Transfer Torque magnetic random access memory (STT-MRAM)",

author = "Dongsu Kim and Yunho Jang and Taehwan Kim and Jongsun Park",

note = "Funding Information: This work was supported in part by National R&D Program through the National Research Foundation of Korea funded by Ministry of Science and ICT (NRF-2020M3F3A2A01082591), and in part by the National Research Foundation of Korea grant funded by the Korea government (NRF-2020R1A2C3014820). The EDA tool was supported by the IC Design Education Center(IDEC), Korea. Publisher Copyright: {\textcopyright} 2022 IEEE.; 4th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022 ; Conference date: 13-06-2022 Through 15-06-2022",

year = "2022",

doi = "10.1109/AICAS54282.2022.9869915",

language = "English",

series = "Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "74--77",

booktitle = "Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022",

}

TY - GEN

T1 - BiMDiM

T2 - 4th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022

AU - Kim, Dongsu

AU - Jang, Yunho

AU - Kim, Taehwan

AU - Park, Jongsun

N1 - Funding Information: This work was supported in part by National R&D Program through the National Research Foundation of Korea funded by Ministry of Science and ICT (NRF-2020M3F3A2A01082591), and in part by the National Research Foundation of Korea grant funded by the Korea government (NRF-2020R1A2C3014820). The EDA tool was supported by the IC Design Education Center(IDEC), Korea. Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - Spin transfer torque MRAM (STT-MRAM) based digital in-memory computing (IMC) has been recently proposed for energy efficient processing of convolutional neural network (CNN). The conventional MRAM based IMC architecture suffers from excessive storage area since a large number of intermediate sum and carry bits should be stored for the following successive additions during multiply-accumulate (MAC) operations. In this paper, we propose an area efficient bi-directional MRAM digital IMC (BiMDiM) scheme, where the size of memory cells storing the intermediate sums and carries can be efficiently reduced by repetitively using the same memory cells during MAC operations. In addition, to reduce the number of inefficient half-additions, which can process only two inputs with almost same hardware cost, the addition re-scheduling is also presented to further improve the energy and latency of BiMDiM. The proposed BiMDiM architecture has been simulated using 28nm CMOS process. When compared to the baseline architecture, the proposed BiMDiM improves area efficiency up to 53%.

AB - Spin transfer torque MRAM (STT-MRAM) based digital in-memory computing (IMC) has been recently proposed for energy efficient processing of convolutional neural network (CNN). The conventional MRAM based IMC architecture suffers from excessive storage area since a large number of intermediate sum and carry bits should be stored for the following successive additions during multiply-accumulate (MAC) operations. In this paper, we propose an area efficient bi-directional MRAM digital IMC (BiMDiM) scheme, where the size of memory cells storing the intermediate sums and carries can be efficiently reduced by repetitively using the same memory cells during MAC operations. In addition, to reduce the number of inefficient half-additions, which can process only two inputs with almost same hardware cost, the addition re-scheduling is also presented to further improve the energy and latency of BiMDiM. The proposed BiMDiM architecture has been simulated using 28nm CMOS process. When compared to the baseline architecture, the proposed BiMDiM improves area efficiency up to 53%.

KW - Convolutional neural network (CNN)

KW - digital in memory computing (digital IMC)

KW - Memory area

KW - Spin Transfer Torque magnetic random access memory (STT-MRAM)

UR - http://www.scopus.com/inward/record.url?scp=85139081092&partnerID=8YFLogxK

U2 - 10.1109/AICAS54282.2022.9869915

DO - 10.1109/AICAS54282.2022.9869915

M3 - Conference contribution

AN - SCOPUS:85139081092

T3 - Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022

SP - 74

EP - 77

BT - Proceeding - IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2022

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 13 June 2022 through 15 June 2022

ER -

BiMDiM: Area efficient Bi-directional MRAM Digital in-Memory Computing

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this