Monolithic 3D+-IC based massively parallel compute-in-memory macro for accelerating database and machine learning primitives

Akshay Krishna Ramanathan; Srivatsa Srinivasa Rangachar; Je Min Hung; Chun Ying Lee; Cheng Xin Xue; Sheng Po Huang; Fu Kuo Hsueh; Chang Hong Shen; Jia Min Shieh; Wen Kuan Yeh; Mon Shu Ho; Hariram Thirucherai Govindarajan; Jack Sampson; Meng Fan Chang; Vijaykrishnan Narayanan

doi:10.1109/IEDM13553.2020.9372111

Monolithic 3D+-IC based massively parallel compute-in-memory macro for accelerating database and machine learning primitives

Akshay Krishna Ramanathan, Srivatsa Srinivasa Rangachar, Je Min Hung, Chun Ying Lee, Cheng Xin Xue, Sheng Po Huang, Fu Kuo Hsueh, Chang Hong Shen, Jia Min Shieh, Wen Kuan Yeh, Mon Shu Ho, Hariram Thirucherai Govindarajan, Jack Sampson, Meng Fan Chang, Vijaykrishnan Narayanan

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

6 Scopus citations

Abstract

This paper demonstrates the first Monolithic 3D+-IC based Compute-in-Memory (CiM) Macro performing massively parallel beyond-Boolean operations targeting database and machine learning (ML) applications. The proposed CiM technique supports data filtering, sorting, and sparse matrix-matrix multiplication (SpGEMM) operations. Our system exhibits up to 272x speedup and 151x energy savings compared to the ASIC baseline.

Original language	English (US)
Title of host publication	2020 IEEE International Electron Devices Meeting, IEDM 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	28.5.1-28.5.4
ISBN (Electronic)	9781728188881
DOIs	https://doi.org/10.1109/IEDM13553.2020.9372111
State	Published - Dec 12 2020
Event	66th Annual IEEE International Electron Devices Meeting, IEDM 2020 - Virtual, San Francisco, United States Duration: Dec 12 2020 → Dec 18 2020

Publication series

Name	Technical Digest - International Electron Devices Meeting, IEDM
Volume	2020-December
ISSN (Print)	0163-1918

Conference

Conference	66th Annual IEEE International Electron Devices Meeting, IEDM 2020
Country/Territory	United States
City	Virtual, San Francisco
Period	12/12/20 → 12/18/20

All Science Journal Classification (ASJC) codes

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Electrical and Electronic Engineering
Materials Chemistry

Access to Document

10.1109/IEDM13553.2020.9372111

Cite this

Ramanathan, A. K., Rangachar, S. S., Hung, J. M., Lee, C. Y., Xue, C. X., Huang, S. P., Hsueh, F. K., Shen, C. H., Shieh, J. M., Yeh, W. K., Ho, M. S., Govindarajan, H. T., Sampson, J., Chang, M. F., & Narayanan, V. (2020). Monolithic 3D+-IC based massively parallel compute-in-memory macro for accelerating database and machine learning primitives. In 2020 IEEE International Electron Devices Meeting, IEDM 2020 (pp. 28.5.1-28.5.4). Article 9372111 (Technical Digest - International Electron Devices Meeting, IEDM; Vol. 2020-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IEDM13553.2020.9372111

Ramanathan, Akshay Krishna ; Rangachar, Srivatsa Srinivasa ; Hung, Je Min et al. / Monolithic 3D+-IC based massively parallel compute-in-memory macro for accelerating database and machine learning primitives. 2020 IEEE International Electron Devices Meeting, IEDM 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 28.5.1-28.5.4 (Technical Digest - International Electron Devices Meeting, IEDM).

@inproceedings{db5ec4a6132748af802769c57248203d,

title = "Monolithic 3D+-IC based massively parallel compute-in-memory macro for accelerating database and machine learning primitives",

abstract = "This paper demonstrates the first Monolithic 3D+-IC based Compute-in-Memory (CiM) Macro performing massively parallel beyond-Boolean operations targeting database and machine learning (ML) applications. The proposed CiM technique supports data filtering, sorting, and sparse matrix-matrix multiplication (SpGEMM) operations. Our system exhibits up to 272x speedup and 151x energy savings compared to the ASIC baseline.",

author = "Ramanathan, {Akshay Krishna} and Rangachar, {Srivatsa Srinivasa} and Hung, {Je Min} and Lee, {Chun Ying} and Xue, {Cheng Xin} and Huang, {Sheng Po} and Hsueh, {Fu Kuo} and Shen, {Chang Hong} and Shieh, {Jia Min} and Yeh, {Wen Kuan} and Ho, {Mon Shu} and Govindarajan, {Hariram Thirucherai} and Jack Sampson and Chang, {Meng Fan} and Vijaykrishnan Narayanan",

note = "Funding Information: ACKNOWLEDGMENT The authors would like to thank the support of TSRI, Taiwan. This work was supported in part by Semiconductor Research Corporation (SRC) Center for Research in Intelligent Storage and Processing in Memory (CRISP). Publisher Copyright: {\textcopyright} 2020 IEEE.; 66th Annual IEEE International Electron Devices Meeting, IEDM 2020 ; Conference date: 12-12-2020 Through 18-12-2020",

year = "2020",

month = dec,

day = "12",

doi = "10.1109/IEDM13553.2020.9372111",

language = "English (US)",

series = "Technical Digest - International Electron Devices Meeting, IEDM",

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

pages = "28.5.1--28.5.4",

booktitle = "2020 IEEE International Electron Devices Meeting, IEDM 2020",

address = "United States",

}

Ramanathan, AK, Rangachar, SS, Hung, JM, Lee, CY, Xue, CX, Huang, SP, Hsueh, FK, Shen, CH, Shieh, JM, Yeh, WK, Ho, MS, Govindarajan, HT, Sampson, J, Chang, MF & Narayanan, V 2020, Monolithic 3D+-IC based massively parallel compute-in-memory macro for accelerating database and machine learning primitives. in 2020 IEEE International Electron Devices Meeting, IEDM 2020., 9372111, Technical Digest - International Electron Devices Meeting, IEDM, vol. 2020-December, Institute of Electrical and Electronics Engineers Inc., pp. 28.5.1-28.5.4, 66th Annual IEEE International Electron Devices Meeting, IEDM 2020, Virtual, San Francisco, United States, 12/12/20. https://doi.org/10.1109/IEDM13553.2020.9372111

Monolithic 3D+-IC based massively parallel compute-in-memory macro for accelerating database and machine learning primitives. / Ramanathan, Akshay Krishna; Rangachar, Srivatsa Srinivasa; Hung, Je Min et al.
2020 IEEE International Electron Devices Meeting, IEDM 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 28.5.1-28.5.4 9372111 (Technical Digest - International Electron Devices Meeting, IEDM; Vol. 2020-December).

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

TY - GEN

T1 - Monolithic 3D+-IC based massively parallel compute-in-memory macro for accelerating database and machine learning primitives

AU - Ramanathan, Akshay Krishna

AU - Rangachar, Srivatsa Srinivasa

AU - Hung, Je Min

AU - Lee, Chun Ying

AU - Xue, Cheng Xin

AU - Huang, Sheng Po

AU - Hsueh, Fu Kuo

AU - Shen, Chang Hong

AU - Shieh, Jia Min

AU - Yeh, Wen Kuan

AU - Ho, Mon Shu

AU - Govindarajan, Hariram Thirucherai

AU - Sampson, Jack

AU - Chang, Meng Fan

AU - Narayanan, Vijaykrishnan

N1 - Funding Information: ACKNOWLEDGMENT The authors would like to thank the support of TSRI, Taiwan. This work was supported in part by Semiconductor Research Corporation (SRC) Center for Research in Intelligent Storage and Processing in Memory (CRISP). Publisher Copyright: © 2020 IEEE.

PY - 2020/12/12

Y1 - 2020/12/12

N2 - This paper demonstrates the first Monolithic 3D+-IC based Compute-in-Memory (CiM) Macro performing massively parallel beyond-Boolean operations targeting database and machine learning (ML) applications. The proposed CiM technique supports data filtering, sorting, and sparse matrix-matrix multiplication (SpGEMM) operations. Our system exhibits up to 272x speedup and 151x energy savings compared to the ASIC baseline.

AB - This paper demonstrates the first Monolithic 3D+-IC based Compute-in-Memory (CiM) Macro performing massively parallel beyond-Boolean operations targeting database and machine learning (ML) applications. The proposed CiM technique supports data filtering, sorting, and sparse matrix-matrix multiplication (SpGEMM) operations. Our system exhibits up to 272x speedup and 151x energy savings compared to the ASIC baseline.

UR - http://www.scopus.com/inward/record.url?scp=85102923853&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85102923853&partnerID=8YFLogxK

U2 - 10.1109/IEDM13553.2020.9372111

DO - 10.1109/IEDM13553.2020.9372111

M3 - Conference contribution

AN - SCOPUS:85102923853

T3 - Technical Digest - International Electron Devices Meeting, IEDM

SP - 28.5.1-28.5.4

BT - 2020 IEEE International Electron Devices Meeting, IEDM 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 66th Annual IEEE International Electron Devices Meeting, IEDM 2020

Y2 - 12 December 2020 through 18 December 2020

ER -

Ramanathan AK, Rangachar SS, Hung JM, Lee CY, Xue CX, Huang SP et al. Monolithic 3D+-IC based massively parallel compute-in-memory macro for accelerating database and machine learning primitives. In 2020 IEEE International Electron Devices Meeting, IEDM 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 28.5.1-28.5.4. 9372111. (Technical Digest - International Electron Devices Meeting, IEDM). doi: 10.1109/IEDM13553.2020.9372111

Monolithic 3D+-IC based massively parallel compute-in-memory macro for accelerating database and machine learning primitives

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this