Spintronic In-Memory Pattern Matching

Zamshed I. Chowdhury; S. Karen Khatamifard; Zhengyang Zhao; Masoud Zabihi; Salonik Resch; Meisam Razaviyayn; Jian Ping Wang; Sachin Sapatnekar; Ulya R. Karpuzcu

doi:10.1109/JXCDC.2019.2951157

Spintronic In-Memory Pattern Matching

Zamshed I. Chowdhury, S. Karen Khatamifard, Zhengyang Zhao, Masoud Zabihi, Salonik Resch, Meisam Razaviyayn, Jian Ping Wang, Sachin Sapatnekar, Ulya R. Karpuzcu

Research output: Contribution to journal › Article › peer-review

11 Scopus citations

Abstract

Traditional Von Neumann computing is falling apart in the era of exploding data volumes as the overhead of data transfer becomes forbidding. Instead, it is more energy-efficient to fuse compute capability with memory where the data reside. This is particularly critical to pattern matching, a key computational step in large-scale data analytics, which involves repetitive search over very large databases residing in memory. Emerging spintronic technologies show remarkable versatility for the tight integration of logic and memory. In this article, we introduce SpinPM, a novel high-density, reconfigurable spintronic in-memory pattern matching spin-orbit torque (SOT)-specifically spin Hall effect (SHE)-substrate, and demonstrate the performance benefit SpinPM can achieve over conventional and near-memory processing systems.

Original language	English (US)
Article number	8890687
Pages (from-to)	206-214
Number of pages	9
Journal	IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
Volume	5
Issue number	2
DOIs	https://doi.org/10.1109/JXCDC.2019.2951157
State	Published - Dec 2019

Bibliographical note

Funding Information:
1Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455 USA 2Department of Industrial & Systems Engineering, University of Southern California, Los Angeles, CA 90089 USA CORRESPONDING AUTHOR: Z. I. CHOWDHURY ([email protected]) This work was supported in part by NSF under Grant SPX-1725420. This article has supplementary downloadable material available at http://ieeexplore.ieee.org, provided by the authors.

Publisher Copyright:
© 2014 IEEE.

Keywords

Computational random access memory
pattern matching
processing in memory
spin Hall effect (SHE) magnetic tunnel junction (MTJ)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Publisher link

10.1109/JXCDC.2019.2951157

Find It

Find It at U of M Libraries

Cite this

@article{ca83b81b560c4eba83b638df8918021b,

title = "Spintronic In-Memory Pattern Matching",

abstract = "Traditional Von Neumann computing is falling apart in the era of exploding data volumes as the overhead of data transfer becomes forbidding. Instead, it is more energy-efficient to fuse compute capability with memory where the data reside. This is particularly critical to pattern matching, a key computational step in large-scale data analytics, which involves repetitive search over very large databases residing in memory. Emerging spintronic technologies show remarkable versatility for the tight integration of logic and memory. In this article, we introduce SpinPM, a novel high-density, reconfigurable spintronic in-memory pattern matching spin-orbit torque (SOT)-specifically spin Hall effect (SHE)-substrate, and demonstrate the performance benefit SpinPM can achieve over conventional and near-memory processing systems.",

keywords = "Computational random access memory, pattern matching, processing in memory, spin Hall effect (SHE) magnetic tunnel junction (MTJ)",

author = "Chowdhury, {Zamshed I.} and {Karen Khatamifard}, S. and Zhengyang Zhao and Masoud Zabihi and Salonik Resch and Meisam Razaviyayn and Wang, {Jian Ping} and Sachin Sapatnekar and Karpuzcu, {Ulya R.}",

note = "Funding Information: 1Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455 USA 2Department of Industrial & Systems Engineering, University of Southern California, Los Angeles, CA 90089 USA CORRESPONDING AUTHOR: Z. I. CHOWDHURY ([email protected]) This work was supported in part by NSF under Grant SPX-1725420. This article has supplementary downloadable material available at http://ieeexplore.ieee.org, provided by the authors. Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2019",

month = dec,

doi = "10.1109/JXCDC.2019.2951157",

language = "English (US)",

volume = "5",

pages = "206--214",

journal = "IEEE Journal on Exploratory Solid-State Computational Devices and Circuits",

issn = "2329-9231",

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

number = "2",

}

TY - JOUR

T1 - Spintronic In-Memory Pattern Matching

AU - Chowdhury, Zamshed I.

AU - Karen Khatamifard, S.

AU - Zhao, Zhengyang

AU - Zabihi, Masoud

AU - Resch, Salonik

AU - Razaviyayn, Meisam

AU - Wang, Jian Ping

AU - Sapatnekar, Sachin

AU - Karpuzcu, Ulya R.

N1 - Funding Information: 1Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455 USA 2Department of Industrial & Systems Engineering, University of Southern California, Los Angeles, CA 90089 USA CORRESPONDING AUTHOR: Z. I. CHOWDHURY ([email protected]) This work was supported in part by NSF under Grant SPX-1725420. This article has supplementary downloadable material available at http://ieeexplore.ieee.org, provided by the authors. Publisher Copyright: © 2014 IEEE.

PY - 2019/12

Y1 - 2019/12

N2 - Traditional Von Neumann computing is falling apart in the era of exploding data volumes as the overhead of data transfer becomes forbidding. Instead, it is more energy-efficient to fuse compute capability with memory where the data reside. This is particularly critical to pattern matching, a key computational step in large-scale data analytics, which involves repetitive search over very large databases residing in memory. Emerging spintronic technologies show remarkable versatility for the tight integration of logic and memory. In this article, we introduce SpinPM, a novel high-density, reconfigurable spintronic in-memory pattern matching spin-orbit torque (SOT)-specifically spin Hall effect (SHE)-substrate, and demonstrate the performance benefit SpinPM can achieve over conventional and near-memory processing systems.

AB - Traditional Von Neumann computing is falling apart in the era of exploding data volumes as the overhead of data transfer becomes forbidding. Instead, it is more energy-efficient to fuse compute capability with memory where the data reside. This is particularly critical to pattern matching, a key computational step in large-scale data analytics, which involves repetitive search over very large databases residing in memory. Emerging spintronic technologies show remarkable versatility for the tight integration of logic and memory. In this article, we introduce SpinPM, a novel high-density, reconfigurable spintronic in-memory pattern matching spin-orbit torque (SOT)-specifically spin Hall effect (SHE)-substrate, and demonstrate the performance benefit SpinPM can achieve over conventional and near-memory processing systems.

KW - Computational random access memory

KW - pattern matching

KW - processing in memory

KW - spin Hall effect (SHE) magnetic tunnel junction (MTJ)

UR - http://www.scopus.com/inward/record.url?scp=85075537819&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075537819&partnerID=8YFLogxK

U2 - 10.1109/JXCDC.2019.2951157

DO - 10.1109/JXCDC.2019.2951157

M3 - Article

AN - SCOPUS:85075537819

SN - 2329-9231

VL - 5

SP - 206

EP - 214

JO - IEEE Journal on Exploratory Solid-State Computational Devices and Circuits

JF - IEEE Journal on Exploratory Solid-State Computational Devices and Circuits

IS - 2

M1 - 8890687

ER -

Spintronic In-Memory Pattern Matching

Abstract

Bibliographical note

Keywords

UN SDGs

Publisher link

Find It

Other files and links

Fingerprint

Cite this