A Mini Tutorial of Processing in Memory: From Principles, Devices to Prototypes

Biao Pan; Guangyao Wang; He Zhang; Wang Kang; Weisheng Zhao

doi:10.1109/TCSII.2022.3172494

A Mini Tutorial of Processing in Memory: From Principles, Devices to Prototypes

Biao Pan
, Guangyao Wang
, He Zhang
, Wang Kang^*
, Weisheng Zhao

^*此作品的通讯作者

集成电路科学与工程学院

Beihang University

科研成果: 期刊稿件 › 文章 › 同行评审

12 引用（Scopus）

摘要

Data movement overheads caused by the recent explosion in big data applications have made traditional von Neumann architecture fails to tackle big data workloads. Processing in Memory (PIM), where computational tasks are performed within the memory, has drawn increasing attention. To present meaningful insights to readers, we divide current PIM paradigm into charge-based and resistance-based categories according to different memory devices. This mini tutorial aims to provide a concise overview of the implementation of PIM schemes, highlighting important macro prototypes in artificial intelligence applications that have been released in the past five years.

源语言	英语
页（从-至）	3044-3050
页数	7
期刊	IEEE Transactions on Circuits and Systems II: Express Briefs
卷	69
期	7
DOI	https://doi.org/10.1109/TCSII.2022.3172494
出版状态	已出版 - 1 7月 2022

访问文件

10.1109/TCSII.2022.3172494

其它文件与链接

链接到 Scopus 的出版物

引用此

@article{56b3e5cf643540da85fa39ca55dce5fd,

title = "A Mini Tutorial of Processing in Memory: From Principles, Devices to Prototypes",

abstract = "Data movement overheads caused by the recent explosion in big data applications have made traditional von Neumann architecture fails to tackle big data workloads. Processing in Memory (PIM), where computational tasks are performed within the memory, has drawn increasing attention. To present meaningful insights to readers, we divide current PIM paradigm into charge-based and resistance-based categories according to different memory devices. This mini tutorial aims to provide a concise overview of the implementation of PIM schemes, highlighting important macro prototypes in artificial intelligence applications that have been released in the past five years.",

keywords = "DRAM, MRAM, Processing in memory, RRAM, SRAM",

author = "Biao Pan and Guangyao Wang and He Zhang and Wang Kang and Weisheng Zhao",

note = "Publisher Copyright: {\textcopyright} 2004-2012 IEEE.",

year = "2022",

month = jul,

day = "1",

doi = "10.1109/TCSII.2022.3172494",

language = "英语",

volume = "69",

pages = "3044--3050",

journal = "IEEE Transactions on Circuits and Systems II: Express Briefs",

issn = "1549-7747",

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

number = "7",

}

TY - JOUR

T1 - A Mini Tutorial of Processing in Memory

T2 - From Principles, Devices to Prototypes

AU - Pan, Biao

AU - Wang, Guangyao

AU - Zhang, He

AU - Kang, Wang

AU - Zhao, Weisheng

PY - 2022/7/1

Y1 - 2022/7/1

N2 - Data movement overheads caused by the recent explosion in big data applications have made traditional von Neumann architecture fails to tackle big data workloads. Processing in Memory (PIM), where computational tasks are performed within the memory, has drawn increasing attention. To present meaningful insights to readers, we divide current PIM paradigm into charge-based and resistance-based categories according to different memory devices. This mini tutorial aims to provide a concise overview of the implementation of PIM schemes, highlighting important macro prototypes in artificial intelligence applications that have been released in the past five years.

AB - Data movement overheads caused by the recent explosion in big data applications have made traditional von Neumann architecture fails to tackle big data workloads. Processing in Memory (PIM), where computational tasks are performed within the memory, has drawn increasing attention. To present meaningful insights to readers, we divide current PIM paradigm into charge-based and resistance-based categories according to different memory devices. This mini tutorial aims to provide a concise overview of the implementation of PIM schemes, highlighting important macro prototypes in artificial intelligence applications that have been released in the past five years.

KW - DRAM

KW - MRAM

KW - Processing in memory

KW - RRAM

KW - SRAM

UR - https://www.scopus.com/pages/publications/85129375987

U2 - 10.1109/TCSII.2022.3172494

DO - 10.1109/TCSII.2022.3172494

M3 - 文章

AN - SCOPUS:85129375987

SN - 1549-7747

VL - 69

SP - 3044

EP - 3050

JO - IEEE Transactions on Circuits and Systems II: Express Briefs

JF - IEEE Transactions on Circuits and Systems II: Express Briefs

IS - 7

ER -

A Mini Tutorial of Processing in Memory: From Principles, Devices to Prototypes

摘要

访问文件

其它文件与链接

学术指纹

引用此