Monolithic-3D integration augmented design techniques for computing in SRAMs

Srivatsa Srinivasa, Wei Hao Chen, Yung Ning Tu, Meng Fan Chang, John Morgan Sampson, Vijaykrishnan Narayanan

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

Abstract

In-memory computing has emerged as a promising solution to address the logic-memory performance gap. We propose design techniques using monolithic-3D integration to achieve reliable multirow activation which in turn help in computation as part of data readout. Our design is 1.8x faster than the existing techniques for Boolean computations. We quantitatively show no impact to cell stability when multiple rows are activated and thereby requiring no extra hardware for maintaining the cell stability during computations. In-memory digital to analog conversion technique is proposed using a 3D-CAM primitive. The design utilizes relatively low strength layer-2 transistors effectively and provides 7x power savings when compared with a specialized converter in-memory. Lastly, we present a linear classifier system by making use the above-mentioned techniques which is 47x faster while computing vector matrix multiplication using a dedicated hardware engine.

Original languageEnglish (US)
Title of host publication2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728103976
DOIs
StatePublished - Jan 1 2019
Event2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Sapporo, Japan
Duration: May 26 2019May 29 2019

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2019-May
ISSN (Print)0271-4310

Conference

Conference2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019
CountryJapan
CitySapporo
Period5/26/195/29/19

Fingerprint

Static random access storage
Data storage equipment
Hardware
Computer aided manufacturing
Digital to analog conversion
Transistors
Classifiers
Chemical activation
Engines

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Srinivasa, S., Chen, W. H., Tu, Y. N., Chang, M. F., Sampson, J. M., & Narayanan, V. (2019). Monolithic-3D integration augmented design techniques for computing in SRAMs. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings [8702536] (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.2019.8702536
Srinivasa, Srivatsa ; Chen, Wei Hao ; Tu, Yung Ning ; Chang, Meng Fan ; Sampson, John Morgan ; Narayanan, Vijaykrishnan. / Monolithic-3D integration augmented design techniques for computing in SRAMs. 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - IEEE International Symposium on Circuits and Systems).
@inproceedings{3de9c2d49bbb420c810864532340ea1b,
title = "Monolithic-3D integration augmented design techniques for computing in SRAMs",
abstract = "In-memory computing has emerged as a promising solution to address the logic-memory performance gap. We propose design techniques using monolithic-3D integration to achieve reliable multirow activation which in turn help in computation as part of data readout. Our design is 1.8x faster than the existing techniques for Boolean computations. We quantitatively show no impact to cell stability when multiple rows are activated and thereby requiring no extra hardware for maintaining the cell stability during computations. In-memory digital to analog conversion technique is proposed using a 3D-CAM primitive. The design utilizes relatively low strength layer-2 transistors effectively and provides 7x power savings when compared with a specialized converter in-memory. Lastly, we present a linear classifier system by making use the above-mentioned techniques which is 47x faster while computing vector matrix multiplication using a dedicated hardware engine.",
author = "Srivatsa Srinivasa and Chen, {Wei Hao} and Tu, {Yung Ning} and Chang, {Meng Fan} and Sampson, {John Morgan} and Vijaykrishnan Narayanan",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ISCAS.2019.8702536",
language = "English (US)",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings",
address = "United States",

}

Srinivasa, S, Chen, WH, Tu, YN, Chang, MF, Sampson, JM & Narayanan, V 2019, Monolithic-3D integration augmented design techniques for computing in SRAMs. in 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings., 8702536, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019, Sapporo, Japan, 5/26/19. https://doi.org/10.1109/ISCAS.2019.8702536

Monolithic-3D integration augmented design techniques for computing in SRAMs. / Srinivasa, Srivatsa; Chen, Wei Hao; Tu, Yung Ning; Chang, Meng Fan; Sampson, John Morgan; Narayanan, Vijaykrishnan.

2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8702536 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May).

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

TY - GEN

T1 - Monolithic-3D integration augmented design techniques for computing in SRAMs

AU - Srinivasa, Srivatsa

AU - Chen, Wei Hao

AU - Tu, Yung Ning

AU - Chang, Meng Fan

AU - Sampson, John Morgan

AU - Narayanan, Vijaykrishnan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In-memory computing has emerged as a promising solution to address the logic-memory performance gap. We propose design techniques using monolithic-3D integration to achieve reliable multirow activation which in turn help in computation as part of data readout. Our design is 1.8x faster than the existing techniques for Boolean computations. We quantitatively show no impact to cell stability when multiple rows are activated and thereby requiring no extra hardware for maintaining the cell stability during computations. In-memory digital to analog conversion technique is proposed using a 3D-CAM primitive. The design utilizes relatively low strength layer-2 transistors effectively and provides 7x power savings when compared with a specialized converter in-memory. Lastly, we present a linear classifier system by making use the above-mentioned techniques which is 47x faster while computing vector matrix multiplication using a dedicated hardware engine.

AB - In-memory computing has emerged as a promising solution to address the logic-memory performance gap. We propose design techniques using monolithic-3D integration to achieve reliable multirow activation which in turn help in computation as part of data readout. Our design is 1.8x faster than the existing techniques for Boolean computations. We quantitatively show no impact to cell stability when multiple rows are activated and thereby requiring no extra hardware for maintaining the cell stability during computations. In-memory digital to analog conversion technique is proposed using a 3D-CAM primitive. The design utilizes relatively low strength layer-2 transistors effectively and provides 7x power savings when compared with a specialized converter in-memory. Lastly, we present a linear classifier system by making use the above-mentioned techniques which is 47x faster while computing vector matrix multiplication using a dedicated hardware engine.

UR - http://www.scopus.com/inward/record.url?scp=85066797617&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066797617&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2019.8702536

DO - 10.1109/ISCAS.2019.8702536

M3 - Conference contribution

AN - SCOPUS:85066797617

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Srinivasa S, Chen WH, Tu YN, Chang MF, Sampson JM, Narayanan V. Monolithic-3D integration augmented design techniques for computing in SRAMs. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8702536. (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.2019.8702536