CIM100x: Computation in-Memory Architecture Based on Resistive Devices

Said Hamdioui; Mottaqiallah Taouil; Hoang Anh Du Nguyen; Adib Haron; Lei Xie; Koen Bertels

CIM100x: Computation in-Memory Architecture Based on Resistive Devices

Said Hamdioui, Mottaqiallah Taouil, Hoang Anh Du Nguyen, Adib Haron, Lei Xie, Koen Bertels

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Abstract

In this paper, we briefly discuss a new proposed architecture, Computation-In-Memory (CIM) architecture, that targets specifically data-intensive applications. The architecture consists of the interwoven placement of computing and storage units, which are physically tightly integrated together inside a non-volatile memristor crossbar. The architecture has the potential of improving the energy-delay product, computing efficiency and performance per area by at least two orders of magnitude with respect to conventional CMOS architectures.

Original language	English
Title of host publication	Proceedings of CNNA 2016
Subtitle of host publication	15th International Workshop on Cellular Nanoscale and their Applications
Place of Publication	Berlin
Publisher	VDE
Pages	95-96
Number of pages	2
ISBN (Electronic)	978-3-8007-4252-3
Publication status	Published - 2016
Event	15th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2016) - Dresden, Germany Duration: 23 Aug 2016 → 25 Aug 2016

Conference

Conference	15th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2016)
Abbreviated title	CNNA 2016
Country/Territory	Germany
City	Dresden
Period	23/08/16 → 25/08/16

Access to Document

http://ieeexplore.ieee.org/document/7827975/

Cite this

@inproceedings{631f617ca9764535b2c56eb97852276c,

title = "CIM100x: Computation in-Memory Architecture Based on Resistive Devices",

abstract = "In this paper, we briefly discuss a new proposed architecture, Computation-In-Memory (CIM) architecture, that targets specifically data-intensive applications. The architecture consists of the interwoven placement of computing and storage units, which are physically tightly integrated together inside a non-volatile memristor crossbar. The architecture has the potential of improving the energy-delay product, computing efficiency and performance per area by at least two orders of magnitude with respect to conventional CMOS architectures.",

author = "Said Hamdioui and Mottaqiallah Taouil and {Du Nguyen}, {Hoang Anh} and Adib Haron and Lei Xie and Koen Bertels",

year = "2016",

language = "English",

pages = "95--96",

booktitle = "Proceedings of CNNA 2016",

publisher = "VDE",

note = "15th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2016), CNNA 2016 ; Conference date: 23-08-2016 Through 25-08-2016",

}

Hamdioui, S , Taouil, M, Du Nguyen, HA, Haron, A, Xie, L & Bertels, K 2016, CIM100x: Computation in-Memory Architecture Based on Resistive Devices. in Proceedings of CNNA 2016: 15th International Workshop on Cellular Nanoscale and their Applications. VDE, Berlin, pp. 95-96, 15th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2016), Dresden, Germany, 23/08/16. <http://ieeexplore.ieee.org/document/7827975/>

CIM100x: Computation in-Memory Architecture Based on Resistive Devices. / Hamdioui, Said ; Taouil, Mottaqiallah; Du Nguyen, Hoang Anh et al.
Proceedings of CNNA 2016: 15th International Workshop on Cellular Nanoscale and their Applications. Berlin: VDE, 2016. p. 95-96.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - CIM100x

T2 - 15th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2016)

AU - Hamdioui, Said

AU - Taouil, Mottaqiallah

AU - Du Nguyen, Hoang Anh

AU - Haron, Adib

AU - Xie, Lei

AU - Bertels, Koen

PY - 2016

Y1 - 2016

N2 - In this paper, we briefly discuss a new proposed architecture, Computation-In-Memory (CIM) architecture, that targets specifically data-intensive applications. The architecture consists of the interwoven placement of computing and storage units, which are physically tightly integrated together inside a non-volatile memristor crossbar. The architecture has the potential of improving the energy-delay product, computing efficiency and performance per area by at least two orders of magnitude with respect to conventional CMOS architectures.

AB - In this paper, we briefly discuss a new proposed architecture, Computation-In-Memory (CIM) architecture, that targets specifically data-intensive applications. The architecture consists of the interwoven placement of computing and storage units, which are physically tightly integrated together inside a non-volatile memristor crossbar. The architecture has the potential of improving the energy-delay product, computing efficiency and performance per area by at least two orders of magnitude with respect to conventional CMOS architectures.

UR - http://resolver.tudelft.nl/uuid:631f617c-a976-4535-b2c5-6eb97852276c

M3 - Conference contribution

SP - 95

EP - 96

BT - Proceedings of CNNA 2016

PB - VDE

CY - Berlin

Y2 - 23 August 2016 through 25 August 2016

ER -

CIM100x: Computation in-Memory Architecture Based on Resistive Devices

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this