Networked Power-Gated MRAMs for Memory-Based Computing

Emerging nonvolatile memory technologies open new perspectives for original computing architectures. In this paper, we propose a new type of flexible and energy-efficient architecture that relies on power-gated distributed magnetoresistive random access memory (MRAM). The proposed architecture uses...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on very large scale integration (VLSI) systems Ročník 26; číslo 12; s. 2696 - 2708
Hlavní autoři: Diguet, Jean-Philippe, Onizawa, Naoya, Rizk, Mostafa, Sepulveda, Johanna, Baghdadi, Amer, Hanyu, Takahiro
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.12.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:1063-8210, 1557-9999
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Emerging nonvolatile memory technologies open new perspectives for original computing architectures. In this paper, we propose a new type of flexible and energy-efficient architecture that relies on power-gated distributed magnetoresistive random access memory (MRAM). The proposed architecture uses a network-on-chip (NoC) to interconnect MRAM-based clusters, processing elements, and managers. The NoC distributes application-specific commands to MRAM devices by means of packets. Configurable network interfaces allow to transform MRAM devices into smart units able to respond to incoming commands. In this context, three types of MRAM designs are proposed with different power-gating policies and granularities. A relevant database search engine case study is considered to illustrate the benefits of this proposed architecture. It is implemented with a sparse-neural-network approach and simulated in SystemC with different scenarios including hundreds of database queries. Hardware designs and accurate power estimations have been conducted. The obtained results demonstrate important power reduction with database hit rates of about 94%. Targeting 65-nm technology, energy savings reach 87% when compared with an static random access memory-based implementation. Moreover, a new asymmetric read/write MRAM type provides from 39% to 50% energy reduction with respect to the other fixed-granularity models. This results in a low-power, highly scalable, and configurable implementation of memory-based computing.
AbstractList Emerging non-volatile memory technologies open new perspectives for original computing architectures. In this paper, we propose a new type of flexible and energy-efficient ar- chitecture that relies on power-gated distributed Magnetoresistive Random-Access Memory (MRAM). The proposed architecture uses a Network-on-Chip (NoC) to interconnect MRAM-based clusters, processing elements, and managers. The NoC distributes application-specific commands to MRAM devices by means of packets. Configurable Network Interfaces (NI) allow to transform MRAM devices into smart units able to respond to incoming commands. In this context, three types of MRAM designs are proposed with different power-gating policies and granularities. A relevant database search engine case study is considered to illus- trate the benefits of this proposed architecture. It is implemented with a Sparse-Neural-Network (SNN) approach and simulated in SystemC with different scenarios including hundreds of database queries. Hardware designs and accurate power estimations have been conducted. The obtained results demonstrate important power reduction with database hit rates of about 94%. Targeting 65nm technology, energy savings reach 87% when compared with an SRAM-based implementation. Moreover, a new asymmetric read/write MRAM type provides from 39% to 50% energy reduction with respect to the other fixed-granularity models. This results in a low-power, highly scalable and configurable implementation of memory-based computing.
Emerging nonvolatile memory technologies open new perspectives for original computing architectures. In this paper, we propose a new type of flexible and energy-efficient architecture that relies on power-gated distributed magnetoresistive random access memory (MRAM). The proposed architecture uses a network-on-chip (NoC) to interconnect MRAM-based clusters, processing elements, and managers. The NoC distributes application-specific commands to MRAM devices by means of packets. Configurable network interfaces allow to transform MRAM devices into smart units able to respond to incoming commands. In this context, three types of MRAM designs are proposed with different power-gating policies and granularities. A relevant database search engine case study is considered to illustrate the benefits of this proposed architecture. It is implemented with a sparse-neural-network approach and simulated in SystemC with different scenarios including hundreds of database queries. Hardware designs and accurate power estimations have been conducted. The obtained results demonstrate important power reduction with database hit rates of about 94%. Targeting 65-nm technology, energy savings reach 87% when compared with an static random access memory-based implementation. Moreover, a new asymmetric read/write MRAM type provides from 39% to 50% energy reduction with respect to the other fixed-granularity models. This results in a low-power, highly scalable, and configurable implementation of memory-based computing.
Author Baghdadi, Amer
Sepulveda, Johanna
Diguet, Jean-Philippe
Rizk, Mostafa
Hanyu, Takahiro
Onizawa, Naoya
Author_xml – sequence: 1
  givenname: Jean-Philippe
  orcidid: 0000-0003-0728-6040
  surname: Diguet
  fullname: Diguet, Jean-Philippe
  email: jean-philippe.diguet@univ-ubs.fr
  organization: CNRS, Lab-STICC, Lorient, France
– sequence: 2
  givenname: Naoya
  orcidid: 0000-0002-4855-7081
  surname: Onizawa
  fullname: Onizawa, Naoya
  organization: Tohoku University, Sendai, Japan
– sequence: 3
  givenname: Mostafa
  surname: Rizk
  fullname: Rizk, Mostafa
  organization: Lab-STICC, STICC, France
– sequence: 4
  givenname: Johanna
  surname: Sepulveda
  fullname: Sepulveda, Johanna
  organization: Technical University of Munich, Munich, Germany
– sequence: 5
  givenname: Amer
  surname: Baghdadi
  fullname: Baghdadi, Amer
  organization: Lab-STICC, Lorient, France
– sequence: 6
  givenname: Takahiro
  orcidid: 0000-0002-4397-8290
  surname: Hanyu
  fullname: Hanyu, Takahiro
  organization: Tohoku University, Sendai, Japan
BackLink https://imt-atlantique.hal.science/hal-01869484$$DView record in HAL
BookMark eNp9kMFOAjEQhhujiYC-gF5IPHlYbLvdMj0iUSBZ1Ch6bbq7XV2ELbZFwtvbFfTgwV5mMvm_ZuZro8Pa1BqhM4J7hGBxNXtJnyY9ign0KCScJXCAWiRJ-pEI7zD0mMcRUIKPUdu5OcaEMYFbiN9pvzH2XRfdB7PRNhopH_rp42DquqWx3aleGruNrpUL46FZrta-ql9P0FGpFk6f7msHPd_ezIbjKL0fTYaDNMpZLHxEiC5wmSWZyATNWB6LQgGUMQcOhaYY5yUuQBBaYtVPoJ8lGnQ4KCc8Lwqi4w663P37phZyZaulsltpVCXHg1Q2s3AxFwzYJwnZi112Zc3HWjsv52Zt67CepIQBhUZMSMEulVvjnNWlzCuvfGVqb1W1kATLxqj8Niobo3JvNKD0D_qz0b_Q-Q6qtNa_ADAKPInjL1rXgd8
CODEN IEVSE9
CitedBy_id crossref_primary_10_1109_TCSI_2020_3030104
crossref_primary_10_1109_TPDS_2022_3177957
Cites_doi 10.1038/nmat2804
10.1109/MWSCAS.2012.6292202
10.1109/ISCAS.2012.6271663
10.1109/JSSC.2013.2253412
10.1126/science.1254642
10.1109/TNANO.2010.2041556
10.1109/JSSC.2010.2040120
10.1109/JSSC.2012.2224256
10.1109/JETCAS.2014.2361061
10.1143/APEX.1.091301
10.1109/LMAG.2017.2693961
10.1109/TNANO.2015.2447531
10.1145/2206781.2206851
10.1145/2897937.2898051
10.1109/NEWCAS.2017.8010167
10.1109/TNN.2011.2146789
10.1109/JPROC.2016.2574939
10.1109/CODES-ISSS.2013.6659006
10.1109/TC.2011.66
10.1109/ISVLSI.2017.116
10.1109/30.234644
10.1145/2897937.2905012
10.1063/1.4892924
10.1109/ISSCC.2015.7062962
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
– notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
1XC
VOOES
DOI 10.1109/TVLSI.2018.2856458
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
Hyper Article en Ligne (HAL)
Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle CrossRef
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList

Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1557-9999
EndPage 2708
ExternalDocumentID oai:HAL:hal-01869484v1
10_1109_TVLSI_2018_2856458
8428653
Genre orig-research
GrantInformation_xml – fundername: MFC Project of Future and Rupture IMT Program, France
– fundername: Conseil Régional de Bretagne
  funderid: 10.13039/501100004584
– fundername: Japan Society for the Promotion of Science
  grantid: JP16H06300
  funderid: 10.13039/501100001691
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFS
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
HZ~
H~9
ICLAB
IEDLZ
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
TN5
VH1
AAYXX
CITATION
7SP
8FD
L7M
1XC
VOOES
ID FETCH-LOGICAL-c439t-11ed0fb5b9b92b4c39da88f36868de200cf0d8912f0a7587b5e8e110c16cdd1e3
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000451999000014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1063-8210
IngestDate Tue Oct 14 21:02:08 EDT 2025
Sun Nov 09 06:07:43 EST 2025
Sat Nov 29 03:36:14 EST 2025
Tue Nov 18 21:09:55 EST 2025
Wed Aug 27 02:51:23 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 12
Keywords Sparse-neural networks
NOC
Index Terms-MRAM
MRAM
Database
Sparse- neural networks
Power-gating
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c439t-11ed0fb5b9b92b4c39da88f36868de200cf0d8912f0a7587b5e8e110c16cdd1e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-4397-8290
0000-0002-4855-7081
0000-0003-0728-6040
0000-0002-6181-6500
OpenAccessLink https://imt-atlantique.hal.science/hal-01869484
PQID 2148288564
PQPubID 85424
PageCount 13
ParticipantIDs crossref_citationtrail_10_1109_TVLSI_2018_2856458
hal_primary_oai_HAL_hal_01869484v1
crossref_primary_10_1109_TVLSI_2018_2856458
proquest_journals_2148288564
ieee_primary_8428653
PublicationCentury 2000
PublicationDate 2018-12-01
PublicationDateYYYYMMDD 2018-12-01
PublicationDate_xml – month: 12
  year: 2018
  text: 2018-12-01
  day: 01
PublicationDecade 2010
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on very large scale integration (VLSI) systems
PublicationTitleAbbrev TVLSI
PublicationYear 2018
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref15
ref14
gaillardon (ref6) 2016
ref11
ref2
ref1
ref17
ref16
ref19
ref18
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref8
ref7
(ref27) 2017
ref9
ref4
ref3
ref5
rahimi (ref10) 2014
References_xml – ident: ref19
  doi: 10.1038/nmat2804
– ident: ref13
  doi: 10.1109/MWSCAS.2012.6292202
– ident: ref26
  doi: 10.1109/ISCAS.2012.6271663
– ident: ref21
  doi: 10.1109/JSSC.2013.2253412
– ident: ref14
  doi: 10.1126/science.1254642
– ident: ref8
  doi: 10.1109/TNANO.2010.2041556
– ident: ref20
  doi: 10.1109/JSSC.2010.2040120
– ident: ref24
  doi: 10.1109/JSSC.2012.2224256
– ident: ref16
  doi: 10.1109/JETCAS.2014.2361061
– ident: ref3
  doi: 10.1143/APEX.1.091301
– ident: ref25
  doi: 10.1109/LMAG.2017.2693961
– start-page: 427
  year: 2016
  ident: ref6
  article-title: The programmable logic-in-memory (PLiM) computer
  publication-title: Proc DATE
– ident: ref15
  doi: 10.1109/TNANO.2015.2447531
– ident: ref9
  doi: 10.1145/2206781.2206851
– year: 2017
  ident: ref27
  publication-title: ML Repository
– ident: ref11
  doi: 10.1145/2897937.2898051
– ident: ref2
  doi: 10.1109/NEWCAS.2017.8010167
– ident: ref1
  doi: 10.1109/TNN.2011.2146789
– ident: ref4
  doi: 10.1109/JPROC.2016.2574939
– ident: ref17
  doi: 10.1109/CODES-ISSS.2013.6659006
– ident: ref18
  doi: 10.1109/TC.2011.66
– ident: ref5
  doi: 10.1109/ISVLSI.2017.116
– start-page: 1
  year: 2014
  ident: ref10
  article-title: Energy-efficient GPGPU architectures via collaborative compilation and memristive memory-based computing
  publication-title: Proc DAC
– ident: ref7
  doi: 10.1109/30.234644
– ident: ref12
  doi: 10.1145/2897937.2905012
– ident: ref23
  doi: 10.1063/1.4892924
– ident: ref22
  doi: 10.1109/ISSCC.2015.7062962
SSID ssj0014490
Score 2.2590926
Snippet Emerging nonvolatile memory technologies open new perspectives for original computing architectures. In this paper, we propose a new type of flexible and...
Emerging non-volatile memory technologies open new perspectives for original computing architectures. In this paper, we propose a new type of flexible and...
SourceID hal
proquest
crossref
ieee
SourceType Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2696
SubjectTerms Bandwidth
Computation
Computer architecture
Computer Arithmetic
Computer memory
Computer Science
Computer simulation
Distributed memory
Distributed, Parallel, and Cluster Computing
Electric power distribution
Electronics
Embedded Systems
Energy management
Engineering Sciences
Information Theory
magnetoresistive random access memory (MRAM)
Magnetoresistivity
Micro and nanotechnologies
Microelectronics
Microprocessors
network-on-chip (NoC)
Networking and Internet Architecture
Neural networks
Nonvolatile memory
power gating (PG)
Power management
Random access memory
Reduction
Search engines
Signal and Image Processing
sparse neural networks (SNNs)
Static random access memory
System on chip
Title Networked Power-Gated MRAMs for Memory-Based Computing
URI https://ieeexplore.ieee.org/document/8428653
https://www.proquest.com/docview/2148288564
https://imt-atlantique.hal.science/hal-01869484
Volume 26
WOSCitedRecordID wos000451999000014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1557-9999
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014490
  issn: 1063-8210
  databaseCode: RIE
  dateStart: 19930101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5c8aAH3-L6oog3jSbbNJ0cV1EUdhfxhbfSJikKsoq7Cv57M2m3KIrgpZSSlDCTZGaSme8D2It1onmuHdNWlkyWAllhVekfgekFBXcBZ7aXDgZ4f68vp-CgqYVxzoXkM3dIr-Eu3z6bNzoqO0JJdZRxC1ppmla1Ws2NgZS6Qh5QMUMfx0wKZLg-urnrXV9QFhcedpDQU_CbEWo9UApk4Fb5sSEHK3O28L_xLcJ87U1G3Ur9SzDlhssw9wVjcAXUoEr0dja6JEY0RudlNupfdfujyHusUZ9ybT_YsTdnNqpIHnzHVbg9O705OWc1WQIz3qcYMyGc5WWRFLrQnUKaWNscsYwVKrTOrwVTcotadEqe-xghLRKHzovHCGWsFS5eg-nh89CtQ2S0VFah3wmkkiaxWHgfzZYSc5Nwk2MbxER6mamRxInQ4ikLEQXXWZB4RhLPaom3Yb_p81LhaPzZetcrpWlIENjn3V5G3zhxaEmU76INK6SCplUt_TZsTXSY1etxlHUI7hTp5xu_99qEWRpAlaiyBdPj1ze3DTPmffw4et0JU-0TKhrN7A
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fSxwxEB70Wmj7YFu19NTWpfhmo8luNk4er6Vy4t4hehbfwm6SxUI5i3cn9L83k91bFKXQl2VZJkuY_JiZZOb7APYynWteas-0kzWTtUBWOVWHR2R6QcF9xJktjsZjvLrSZyvwtauF8d7H5DN_QK_xLt_d2AUdlR2ipDrKbBVe5FKmoqnW6u4MpNQN9oDKGIZIZlkiw_Xh5GdxcUJ5XHiQIuGn4CMztHpNSZCRXeXJlhztzPHb_-vhO1hr_clk0EyA97Dip-vw5gHK4AaocZPq7V1yRpxojE7MXDI6H4xmSfBZkxFl2_5l34JBc0lD8xAabsLl8Y_J9yFr6RKYDV7FnAnhHa-rvNKVTitpM-1KxDpTqND5sBpszR1qkda8DFHCUZV79EE9VijrnPDZB-hNb6b-IyRWS-UUhr1AKmlzh1Xw0lwtsbQ5tyX2QSy1Z2yLJU6UFr9NjCm4NlHjhjRuWo33Yb9r86dB0vin9JcwKJ0ggWAPB4Whb5xYtCTKO9GHDRqCTqrVfh92lmNo2hU5MykBniL9fOv5VrvwajgZFaY4GZ9uw2vqTJO2sgO9-e3Cf4KX9m7-a3b7OU67ewy00TM
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Networked+Power-Gated+MRAMs+for+Memory-Based+Computing&rft.jtitle=IEEE+transactions+on+very+large+scale+integration+%28VLSI%29+systems&rft.au=Diguet%2C+Jean-Philippe&rft.au=Onizawa%2C+Naoya&rft.au=Rizk%2C+Mostafa&rft.au=Sepulveda%2C+Johanna&rft.date=2018-12-01&rft.pub=IEEE&rft.issn=1063-8210&rft.volume=26&rft.issue=12&rft.spage=2696&rft.epage=2708&rft_id=info:doi/10.1109%2FTVLSI.2018.2856458&rft.externalDocID=8428653
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-8210&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-8210&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-8210&client=summon