DeeperThings: Fully Distributed CNN Inference on Resource-Constrained Edge Devices

Performing inference of Convolutional Neural Networks (CNNs) on Internet of Things (IoT) edge devices ensures both privacy of input data and possible run time reductions when compared to a cloud solution. As most edge devices are memory- and compute-constrained, they cannot store and execute complex...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of parallel programming Jg. 49; H. 4; S. 600 - 624
Hauptverfasser: Stahl, Rafael, Hoffman, Alexander, Mueller-Gritschneder, Daniel, Gerstlauer, Andreas, Schlichtmann, Ulf
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.08.2021
Springer Nature B.V
Schlagworte:
ISSN:0885-7458, 1573-7640
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Performing inference of Convolutional Neural Networks (CNNs) on Internet of Things (IoT) edge devices ensures both privacy of input data and possible run time reductions when compared to a cloud solution. As most edge devices are memory- and compute-constrained, they cannot store and execute complex CNNs. Partitioning and distributing layer information across multiple edge devices to reduce the amount of computation and data on each device presents a solution to this problem. In this article, we propose DeeperThings, an approach that supports a full distribution of CNN inference tasks by partitioning fully-connected as well as both feature- and weight-intensive convolutional layers. Additionally, we jointly optimize memory, computation and communication demands. This is achieved using techniques to combine both feature and weight partitioning with a communication-aware layer fusion method, enabling holistic optimization across layers. For a given number of edge devices, the schemes are applied jointly using Integer Linear Programming (ILP) formulations to minimize data exchanged between devices, to optimize run times and to find the entire model’s minimal memory footprint. Experimental results from a real-world hardware setup running four different CNN models confirm that the scheme is able to evenly balance the memory footprint between devices. For six devices on 100 Mbit/s connections the integration of layer fusion additionally leads to a reduction of communication demands by up to 28.8%. This results in run time speed-up of the inference task by up to 1.52x compared to layer partitioning without fusing.
AbstractList Performing inference of Convolutional Neural Networks (CNNs) on Internet of Things (IoT) edge devices ensures both privacy of input data and possible run time reductions when compared to a cloud solution. As most edge devices are memory- and compute-constrained, they cannot store and execute complex CNNs. Partitioning and distributing layer information across multiple edge devices to reduce the amount of computation and data on each device presents a solution to this problem. In this article, we propose DeeperThings, an approach that supports a full distribution of CNN inference tasks by partitioning fully-connected as well as both feature- and weight-intensive convolutional layers. Additionally, we jointly optimize memory, computation and communication demands. This is achieved using techniques to combine both feature and weight partitioning with a communication-aware layer fusion method, enabling holistic optimization across layers. For a given number of edge devices, the schemes are applied jointly using Integer Linear Programming (ILP) formulations to minimize data exchanged between devices, to optimize run times and to find the entire model’s minimal memory footprint. Experimental results from a real-world hardware setup running four different CNN models confirm that the scheme is able to evenly balance the memory footprint between devices. For six devices on 100 Mbit/s connections the integration of layer fusion additionally leads to a reduction of communication demands by up to 28.8%. This results in run time speed-up of the inference task by up to 1.52x compared to layer partitioning without fusing.
Author Schlichtmann, Ulf
Hoffman, Alexander
Mueller-Gritschneder, Daniel
Stahl, Rafael
Gerstlauer, Andreas
Author_xml – sequence: 1
  givenname: Rafael
  orcidid: 0000-0002-6824-7638
  surname: Stahl
  fullname: Stahl, Rafael
  email: r.stahl@tum.de
  organization: Technical University of Munich
– sequence: 2
  givenname: Alexander
  surname: Hoffman
  fullname: Hoffman, Alexander
  organization: Technical University of Munich
– sequence: 3
  givenname: Daniel
  surname: Mueller-Gritschneder
  fullname: Mueller-Gritschneder, Daniel
  organization: Technical University of Munich
– sequence: 4
  givenname: Andreas
  surname: Gerstlauer
  fullname: Gerstlauer, Andreas
  organization: University of Texas at Austin
– sequence: 5
  givenname: Ulf
  surname: Schlichtmann
  fullname: Schlichtmann, Ulf
  organization: Technical University of Munich
BookMark eNp9kEtLw0AUhQepYFv9A64CrkfnlWTiTtJWC6VCqeshjzt1SpzUmUTov3dqBMFFV5cL57vn3DNBI9taQOiWkntKSPrgKUmTBBNGcVgpw_wCjWmccpwmgozQmEgZ41TE8gpNvN8TQrJUyjHazAAO4Lbvxu78Y7Tom-YYzYzvnCn7DuooX6-jpdXgwFYQtTbagG97VwHOWxtkhbFBNa93EM3gy1Tgr9GlLhoPN79zit4W823-glevz8v8aYUrnvAOC1kKRrkomSCkJjQrkgxYKanQOi54kmU100kISqGElNWaUC0SnWWy5KXWBZ-iu-HuwbWfPfhO7UMwGywVi0V4O5bBaIrYoKpc670DrQ7OfBTuqChRp-7U0J0K3amf7hQPkPwHVaYrOtPa08PNeZQPqA8-dgfuL9UZ6huSDoRY
CitedBy_id crossref_primary_10_1016_j_vlsi_2024_102299
crossref_primary_10_1155_2021_9361348
crossref_primary_10_1007_s11265_023_01898_0
crossref_primary_10_1109_COMST_2023_3319952
crossref_primary_10_1007_s41870_024_01767_4
crossref_primary_10_1016_j_future_2024_07_037
crossref_primary_10_1007_s10462_022_10141_4
crossref_primary_10_1109_JIOT_2023_3237572
crossref_primary_10_1109_TCE_2024_3481156
crossref_primary_10_1109_ACCESS_2021_3131396
crossref_primary_10_1109_ACCESS_2023_3234245
crossref_primary_10_1109_COMST_2024_3393230
crossref_primary_10_1007_s00034_024_02920_x
crossref_primary_10_1007_s10586_025_05386_x
crossref_primary_10_1007_s41870_024_01728_x
crossref_primary_10_1007_s43926_025_00165_x
crossref_primary_10_1109_TCAD_2024_3438995
crossref_primary_10_1002_ett_4648
crossref_primary_10_3390_en15218241
crossref_primary_10_32604_cmes_2023_023684
crossref_primary_10_1016_j_procir_2023_06_193
crossref_primary_10_3390_s25154595
crossref_primary_10_1109_TMC_2024_3438155
Cites_doi 10.1109/TCAD.2018.2858384
10.1109/ICDCS.2017.226
10.5281/zenodo.3700700
10.1109/CVPR.2015.7298594
10.1109/ASPDAC.2015.7058993
10.1007/s11554-019-00938-y
10.1016/j.neunet.2019.04.021
10.1145/3093337.3037698
10.1109/CVPR.2015.7298965
10.3390/info10060191
10.1109/MICRO.2016.7783725
10.1109/CVPR.2017.690
10.23919/DATE.2017.7927211
10.1109/JIOT.2018.2886757
10.1109/GCWkshps45667.2019.9024610
10.1007/978-3-030-27562-4_6
10.1145/3065386
10.1145/2935643.2935650
10.3390/fi11100209
10.1109/JIOT.2019.2913162
10.1145/2994551.2994564
10.1109/CVPR.2016.435
ContentType Journal Article
Copyright The Author(s) 2021
The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: The Author(s) 2021
– notice: The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID C6C
AAYXX
CITATION
3V.
7SC
7WY
7WZ
7XB
87Z
8AL
8FD
8FE
8FG
8FK
8FL
8G5
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BEZIV
BGLVJ
CCPQU
DWQXO
FRNLG
F~G
GNUQQ
GUQSH
HCIFZ
JQ2
K60
K6~
K7-
L.-
L7M
L~C
L~D
M0C
M0N
M2O
MBDVC
P5Z
P62
PHGZM
PHGZT
PKEHL
PQBIZ
PQBZA
PQEST
PQGLB
PQQKQ
PQUKI
Q9U
DOI 10.1007/s10766-021-00712-3
DatabaseName Springer Nature OA Free Journals
CrossRef
ProQuest Central (Corporate)
Computer and Information Systems Abstracts
ABI/INFORM Collection
ABI/INFORM Global (PDF only)
ProQuest Central (purchase pre-March 2016)
ABI/INFORM Collection
Computing Database (Alumni Edition)
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni) (purchase pre-March 2016)
ABI/INFORM Collection (Alumni Edition)
ProQuest Research Library
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
ProQuest Central
Business Premium Collection
Technology collection
ProQuest One
ProQuest Central
Business Premium Collection (Alumni)
ABI/INFORM Global (Corporate)
ProQuest Central Student
Research Library Prep
SciTech Premium Collection
ProQuest Computer Science Collection
ProQuest Business Collection (Alumni Edition)
ProQuest Business Collection
Computer Science Database
ABI/INFORM Professional Advanced
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
ABI/INFORM Global
Computing Database
Research Library
Research Library (Corporate)
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic (New)
ProQuest One Academic Middle East (New)
ProQuest One Business (UW System Shared)
ProQuest One Business (Alumni)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central Basic
DatabaseTitle CrossRef
ABI/INFORM Global (Corporate)
ProQuest Business Collection (Alumni Edition)
ProQuest One Business
Research Library Prep
Computer Science Database
ProQuest Central Student
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
Research Library (Alumni Edition)
ABI/INFORM Complete
ProQuest Central
ABI/INFORM Professional Advanced
ProQuest One Applied & Life Sciences
ProQuest Central Korea
ProQuest Research Library
ProQuest Central (New)
Advanced Technologies Database with Aerospace
ABI/INFORM Complete (Alumni Edition)
Advanced Technologies & Aerospace Collection
Business Premium Collection
ABI/INFORM Global
ProQuest Computing
ABI/INFORM Global (Alumni Edition)
ProQuest Central Basic
ProQuest Computing (Alumni Edition)
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Business Collection
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
ProQuest One Business (Alumni)
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
Business Premium Collection (Alumni)
DatabaseTitleList CrossRef

ABI/INFORM Global (Corporate)
Database_xml – sequence: 1
  dbid: BENPR
  name: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1573-7640
EndPage 624
ExternalDocumentID 10_1007_s10766_021_00712_3
GrantInformation_xml – fundername: Technische Universität München (1025)
– fundername: National Science Foundation
  grantid: CNS-1421642
  funderid: http://dx.doi.org/10.13039/100000001
– fundername: Bundesministerium für Bildung und Forschung
  grantid: 01IS17028F
  funderid: http://dx.doi.org/10.13039/501100002347
GroupedDBID -4Z
-59
-5G
-BR
-EM
-Y2
-~C
-~X
.4S
.86
.DC
.VR
06D
0R~
0VY
199
1N0
2.D
203
28-
29J
2J2
2JN
2JY
2KG
2LR
2P1
2VQ
2~H
30V
3V.
4.4
406
408
409
40D
40E
5GY
5QI
5VS
67Z
6NX
78A
7WY
8FE
8FG
8FL
8G5
8TC
8UJ
95-
95.
95~
96X
AAAVM
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AAOBN
AARHV
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYJJ
AAYQN
AAYTO
AAYZH
ABAKF
ABBBX
ABBXA
ABDBF
ABDPE
ABDZT
ABECU
ABFSI
ABFTD
ABFTV
ABHLI
ABHQN
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABQBU
ABQSL
ABSXP
ABTAH
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABUWG
ABWNU
ABXPI
ACAOD
ACBXY
ACDTI
ACGFO
ACGFS
ACHSB
ACHXU
ACIHN
ACKNC
ACMDZ
ACMLO
ACNCT
ACOKC
ACOMO
ACPIV
ACREN
ACUHS
ACZOJ
ADHIR
ADINQ
ADKNI
ADKPE
ADMLS
ADRFC
ADTPH
ADURQ
ADYFF
ADYOE
ADZKW
AEAQA
AEBTG
AEFIE
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AEMSY
AENEX
AEOHA
AEPYU
AESKC
AETLH
AEVLU
AEXYK
AFBBN
AFEXP
AFGCZ
AFKRA
AFLOW
AFQWF
AFWTZ
AFYQB
AFZKB
AGAYW
AGDGC
AGGDS
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHSBF
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJBLW
AJRNO
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMTXH
AMXSW
AMYLF
AOCGG
ARAPS
ARCSS
ARMRJ
AXYYD
AYJHY
AZFZN
AZQEC
B-.
B0M
BA0
BBWZM
BDATZ
BENPR
BEZIV
BGLVJ
BGNMA
BKOMP
BPHCQ
BSONS
C6C
CAG
CCPQU
COF
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
DU5
DWQXO
E.L
EAD
EAP
EAS
EBLON
EBS
EDO
EIOEI
EJD
EMK
EPL
ESBYG
ESX
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRNLG
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNUQQ
GNWQR
GQ6
GQ7
GQ8
GROUPED_ABI_INFORM_COMPLETE
GROUPED_ABI_INFORM_RESEARCH
GUQSH
GXS
H13
HCIFZ
HF~
HG5
HG6
HMJXF
HQYDN
HRMNR
HVGLF
HZ~
H~9
I-F
I09
IHE
IJ-
IKXTQ
ITM
IWAJR
IXC
IZIGR
IZQ
I~X
I~Z
J-C
J0Z
JBSCW
JCJTX
JZLTJ
K60
K6V
K6~
K7-
KDC
KOV
KOW
LAK
LLZTM
M0C
M0N
M2O
M4Y
MA-
MS~
N2Q
NB0
NDZJH
NPVJJ
NQJWS
NU0
O9-
O93
O9G
O9I
O9J
OAM
OVD
P19
P62
P9O
PF0
PQBIZ
PQBZA
PQQKQ
PROAC
PT4
PT5
Q2X
QOK
QOS
R89
R9I
RHV
RNI
RNS
ROL
RPX
RSV
RZC
RZE
RZK
S16
S1Z
S26
S27
S28
S3B
SAP
SCJ
SCLPG
SCO
SDH
SDM
SHX
SISQX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
T16
TAE
TEORI
TN5
TSG
TSK
TSV
TUC
TUS
U2A
U5U
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
VXZ
W23
W48
WH7
WK8
YLTOR
Z45
Z7R
Z7X
Z81
Z83
Z88
Z8R
Z8W
Z92
ZMTXR
ZY4
~8M
~EX
AAPKM
AAYXX
ABBRH
ABDBE
ABFSG
ABRTQ
ACSTC
ADHKG
AEZWR
AFDZB
AFFHD
AFHIU
AFOHR
AGQPQ
AHPBZ
AHWEU
AIXLP
ATHPR
AYFIA
CITATION
PHGZM
PHGZT
PQGLB
7SC
7XB
8AL
8FD
8FK
JQ2
L.-
L7M
L~C
L~D
MBDVC
PKEHL
PQEST
PQUKI
Q9U
ID FETCH-LOGICAL-c363t-48b42134b2400d019a69e2b814ff5a3699d2f60001ebe72df01f46f998b3bffa3
IEDL.DBID RSV
ISICitedReferencesCount 28
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000637633600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0885-7458
IngestDate Tue Nov 04 23:01:39 EST 2025
Tue Nov 18 21:53:07 EST 2025
Sat Nov 29 01:59:46 EST 2025
Fri Feb 21 02:47:53 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords Deep learning
Distributed computing
IoT
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c363t-48b42134b2400d019a69e2b814ff5a3699d2f60001ebe72df01f46f998b3bffa3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-6824-7638
OpenAccessLink https://link.springer.com/10.1007/s10766-021-00712-3
PQID 2546405836
PQPubID 48389
PageCount 25
ParticipantIDs proquest_journals_2546405836
crossref_primary_10_1007_s10766_021_00712_3
crossref_citationtrail_10_1007_s10766_021_00712_3
springer_journals_10_1007_s10766_021_00712_3
PublicationCentury 2000
PublicationDate 20210800
2021-08-00
20210801
PublicationDateYYYYMMDD 2021-08-01
PublicationDate_xml – month: 8
  year: 2021
  text: 20210800
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle International journal of parallel programming
PublicationTitleAbbrev Int J Parallel Prog
PublicationYear 2021
Publisher Springer US
Springer Nature B.V
Publisher_xml – name: Springer US
– name: Springer Nature B.V
References KangYNeurosurgeon: collaborative intelligence between the cloud and mobile edgeACM SIGARCH Comput. Arch. News201745161562910.1145/3093337.3037698
Martins Campos de OliveiraFBorinEPartitioning convolutional neural networks to maximize the inference rate on constrained iot devicesFuture Internet2019111020910.3390/fi11100209
Motamedi, M., Fong, D., Ghiasi, S.: Fast and energy-efficient CNN inference on IoT devices. arXiv preprint arXiv:161107151 (2016)
Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)
AyindeBOInancTZuradaJMRedundant feature pruning for accelerated inference in deep neural networksNeural Netw.201911814815810.1016/j.neunet.2019.04.021
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)
Alwani, M., Chen, H., Ferdman, M., Milder, P.: Fused-layer CNN accelerators. In: IEEE/ACM International Symposium on Microarchitecture (2016)
Iandola, FN., et al.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5 mb model size. arXiv preprint arXiv:160207360 (2016)
johnjforrest, et al.: coin-or/cbc: Version 2.10.5. (2020) https://doi.org/10.5281/zenodo.3700700
ChenJiRAF: A deep reinforcement learning approach for collaborative mobile edge computing IoT networksIEEE Internet Things J.2019647011702410.1109/JIOT.2019.2913162
Chien, SY., et al.: Distributed computing in IoT: System-on-a-chip for smart cameras as an example. In: Asia and South Pacific Design Automation Conference, IEEE (2015)
ShengJComputation offloading strategy in mobile edge computingInformation201910619110.3390/info10060191
Lavin, A., Gray, S.: Fast algorithms for convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)
Mao, J., et al.: MoDnn: Local distributed mobile computing system for deep neural network. In: Design, Automation & Test in Europe, IEEE (2017)
Arredondo-Velázquez, M., et al.: A streaming architecture for convolutional neural networks based on layer operations chaining. J. Real Time Image Process. (2020)
Redmon, J.: Darknet: open source neural networks in c. (2013–2016). http://pjreddie.com/darknet
Teerapittayanon, S., McDanel, B., Kung, HT.: Distributed deep neural networks over the cloud, the edge and end devices. In: IEEE International Conference on Distributed Computing Systems (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)
ZhaoZBarijoughKMGerstlauerADeepThings: Distributed adaptive deep learning inference on resource-constrained IoT edge clustersIEEE Trans. Comput. Aided Design Integr. Circuits Syst.2018372348235910.1109/TCAD.2018.2858384
KhelifiHNeurosurgeon: ccollaborative intelligence between the cloud and mobile edgeIEEE Commun. Lett.2018231615629
Perron, L., Furnon, V.: Or-tools. (2019). https://developers.google.com/optimization
Bhattacharya, S., Lane, ND.: Sparsification and separation of deep learning layers for constrained resource inference on wearables. In: ACM Conference on Embedded Network Sensor Systems (2016)
Huynh, LN., Balan, RK., Lee, Y.: Deepsense: A gpu-based deep convolutional neural network framework on commodity mobile devices. In: Workshop on Wearable Systems and Applications, ACM (2016)
SahniYCaoJYangLData-aware task allocation for achieving low latency in collaborative edge computingIEEE Internet Things J.2018623512352410.1109/JIOT.2018.2886757
Bisschop, J.: AIMMS optimization modeling. Lulu. com (2006)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556 (2014)
KrizhevskyASutskeverIHintonGEImagenet classification with deep convolutional neural networksCommun. ACM20176061097110510.1145/3065386
Stahl, R., et al.: Fully distributed deep learning inference on resource-constrained edge devices. In: International Conference on Embedded Computer Systems, Springer (2019)
Tu, Y., Lin, Y.: Deep neural network compression technique towards efficient digital signal modulation recognition in edge device. IEEE Access (2019)
712_CR19
712_CR7
712_CR8
712_CR17
712_CR9
712_CR15
712_CR16
712_CR14
712_CR10
Z Zhao (712_CR29) 2018; 37
Y Kang (712_CR11) 2017; 45
Y Sahni (712_CR22) 2018; 6
H Khelifi (712_CR12) 2018; 23
712_CR28
712_CR26
BO Ayinde (712_CR3) 2019; 118
712_CR27
712_CR24
712_CR25
A Krizhevsky (712_CR13) 2017; 60
712_CR20
712_CR21
J Chen (712_CR6) 2019; 6
F Martins Campos de Oliveira (712_CR18) 2019; 11
712_CR1
712_CR2
J Sheng (712_CR23) 2019; 10
712_CR4
712_CR5
References_xml – reference: Huynh, LN., Balan, RK., Lee, Y.: Deepsense: A gpu-based deep convolutional neural network framework on commodity mobile devices. In: Workshop on Wearable Systems and Applications, ACM (2016)
– reference: Chien, SY., et al.: Distributed computing in IoT: System-on-a-chip for smart cameras as an example. In: Asia and South Pacific Design Automation Conference, IEEE (2015)
– reference: Tu, Y., Lin, Y.: Deep neural network compression technique towards efficient digital signal modulation recognition in edge device. IEEE Access (2019)
– reference: Mao, J., et al.: MoDnn: Local distributed mobile computing system for deep neural network. In: Design, Automation & Test in Europe, IEEE (2017)
– reference: Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556 (2014)
– reference: SahniYCaoJYangLData-aware task allocation for achieving low latency in collaborative edge computingIEEE Internet Things J.2018623512352410.1109/JIOT.2018.2886757
– reference: ChenJiRAF: A deep reinforcement learning approach for collaborative mobile edge computing IoT networksIEEE Internet Things J.2019647011702410.1109/JIOT.2019.2913162
– reference: Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)
– reference: Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)
– reference: Alwani, M., Chen, H., Ferdman, M., Milder, P.: Fused-layer CNN accelerators. In: IEEE/ACM International Symposium on Microarchitecture (2016)
– reference: Bisschop, J.: AIMMS optimization modeling. Lulu. com (2006)
– reference: Lavin, A., Gray, S.: Fast algorithms for convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)
– reference: Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2015)
– reference: ShengJComputation offloading strategy in mobile edge computingInformation201910619110.3390/info10060191
– reference: AyindeBOInancTZuradaJMRedundant feature pruning for accelerated inference in deep neural networksNeural Netw.201911814815810.1016/j.neunet.2019.04.021
– reference: Stahl, R., et al.: Fully distributed deep learning inference on resource-constrained edge devices. In: International Conference on Embedded Computer Systems, Springer (2019)
– reference: johnjforrest, et al.: coin-or/cbc: Version 2.10.5. (2020) https://doi.org/10.5281/zenodo.3700700
– reference: Perron, L., Furnon, V.: Or-tools. (2019). https://developers.google.com/optimization/
– reference: Redmon, J.: Darknet: open source neural networks in c. (2013–2016). http://pjreddie.com/darknet/
– reference: Iandola, FN., et al.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5 mb model size. arXiv preprint arXiv:160207360 (2016)
– reference: KangYNeurosurgeon: collaborative intelligence between the cloud and mobile edgeACM SIGARCH Comput. Arch. News201745161562910.1145/3093337.3037698
– reference: Martins Campos de OliveiraFBorinEPartitioning convolutional neural networks to maximize the inference rate on constrained iot devicesFuture Internet2019111020910.3390/fi11100209
– reference: ZhaoZBarijoughKMGerstlauerADeepThings: Distributed adaptive deep learning inference on resource-constrained IoT edge clustersIEEE Trans. Comput. Aided Design Integr. Circuits Syst.2018372348235910.1109/TCAD.2018.2858384
– reference: Arredondo-Velázquez, M., et al.: A streaming architecture for convolutional neural networks based on layer operations chaining. J. Real Time Image Process. (2020)
– reference: Bhattacharya, S., Lane, ND.: Sparsification and separation of deep learning layers for constrained resource inference on wearables. In: ACM Conference on Embedded Network Sensor Systems (2016)
– reference: KhelifiHNeurosurgeon: ccollaborative intelligence between the cloud and mobile edgeIEEE Commun. Lett.2018231615629
– reference: Motamedi, M., Fong, D., Ghiasi, S.: Fast and energy-efficient CNN inference on IoT devices. arXiv preprint arXiv:161107151 (2016)
– reference: KrizhevskyASutskeverIHintonGEImagenet classification with deep convolutional neural networksCommun. ACM20176061097110510.1145/3065386
– reference: Teerapittayanon, S., McDanel, B., Kung, HT.: Distributed deep neural networks over the cloud, the edge and end devices. In: IEEE International Conference on Distributed Computing Systems (2017)
– volume: 37
  start-page: 2348
  year: 2018
  ident: 712_CR29
  publication-title: IEEE Trans. Comput. Aided Design Integr. Circuits Syst.
  doi: 10.1109/TCAD.2018.2858384
– ident: 712_CR24
– ident: 712_CR27
  doi: 10.1109/ICDCS.2017.226
– ident: 712_CR10
  doi: 10.5281/zenodo.3700700
– volume: 23
  start-page: 615
  issue: 1
  year: 2018
  ident: 712_CR12
  publication-title: IEEE Commun. Lett.
– ident: 712_CR26
  doi: 10.1109/CVPR.2015.7298594
– ident: 712_CR7
  doi: 10.1109/ASPDAC.2015.7058993
– ident: 712_CR20
– ident: 712_CR2
  doi: 10.1007/s11554-019-00938-y
– volume: 118
  start-page: 148
  year: 2019
  ident: 712_CR3
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2019.04.021
– volume: 45
  start-page: 615
  issue: 1
  year: 2017
  ident: 712_CR11
  publication-title: ACM SIGARCH Comput. Arch. News
  doi: 10.1145/3093337.3037698
– ident: 712_CR15
  doi: 10.1109/CVPR.2015.7298965
– volume: 10
  start-page: 191
  issue: 6
  year: 2019
  ident: 712_CR23
  publication-title: Information
  doi: 10.3390/info10060191
– ident: 712_CR19
– ident: 712_CR1
  doi: 10.1109/MICRO.2016.7783725
– ident: 712_CR21
  doi: 10.1109/CVPR.2017.690
– ident: 712_CR9
– ident: 712_CR16
  doi: 10.23919/DATE.2017.7927211
– volume: 6
  start-page: 3512
  issue: 2
  year: 2018
  ident: 712_CR22
  publication-title: IEEE Internet Things J.
  doi: 10.1109/JIOT.2018.2886757
– ident: 712_CR28
  doi: 10.1109/GCWkshps45667.2019.9024610
– ident: 712_CR17
– ident: 712_CR25
  doi: 10.1007/978-3-030-27562-4_6
– volume: 60
  start-page: 1097
  issue: 6
  year: 2017
  ident: 712_CR13
  publication-title: Commun. ACM
  doi: 10.1145/3065386
– ident: 712_CR5
– ident: 712_CR8
  doi: 10.1145/2935643.2935650
– volume: 11
  start-page: 209
  issue: 10
  year: 2019
  ident: 712_CR18
  publication-title: Future Internet
  doi: 10.3390/fi11100209
– volume: 6
  start-page: 7011
  issue: 4
  year: 2019
  ident: 712_CR6
  publication-title: IEEE Internet Things J.
  doi: 10.1109/JIOT.2019.2913162
– ident: 712_CR4
  doi: 10.1145/2994551.2994564
– ident: 712_CR14
  doi: 10.1109/CVPR.2016.435
SSID ssj0009788
Score 2.4517694
Snippet Performing inference of Convolutional Neural Networks (CNNs) on Internet of Things (IoT) edge devices ensures both privacy of input data and possible run time...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 600
SubjectTerms Artificial neural networks
Communication
Computation
Computer Science
Electronic devices
Inference
Integer programming
Internet of Things
Linear programming
Memory devices
Optimization
Partitioning
Processor Architectures
Run time (computers)
Software Engineering/Programming and Operating Systems
Theory of Computation
Weight
SummonAdditionalLinks – databaseName: Computer Science Database
  dbid: K7-
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NSwMxEA1aPXjxW6xWycGbBptsms16EWkVRSkiCt6W7GYigrS1rYL_3kyadVHQi-fNhpA3k0ySmfcIORBgUwOWs5S7gklr2kxLjvkOkIHSuqPKgPRN2u_rx8fsNl64TWJaZbUmhoXaDku8Iz9G3nYfXOhEnY5eGapG4etqlNCYJwtcCI52fp2ymnQ3DbqT3pE6LJUdHYtmYulcqjD91h-m_S4rWPJ9Y6qjzR8PpGHfuVj574hXyXKMOOnZzETWyBwM1slKpeZAo3NvkLsewAjGMyHPE4pn0w_aQ15dlMQCS7v9Pr2q6gPpcECrq3-Gqp9Ba8K3OrdPQHsQFqBN8nBxft-9ZFFxgZWJSqZM6kIixVuBmaXWR39GZSAKzaVzHZOoLLPCKYwLPfapsK7NnVTOH9mKpHDOJFukMRgOYJtQh4Sj3HLv1kaWGox0mQUpTNspMLzdJLya7ryMdOQ40pe8JlJGiHIPUR4gypMmOfz6ZzQj4_izdavCJY-OOclrUJrkqEK2_vx7bzt_97ZLlkQwJkwNbJHGdPwGe2SxfJ8-T8b7wSw_AYET5cI
  priority: 102
  providerName: ProQuest
Title DeeperThings: Fully Distributed CNN Inference on Resource-Constrained Edge Devices
URI https://link.springer.com/article/10.1007/s10766-021-00712-3
https://www.proquest.com/docview/2546405836
Volume 49
WOSCitedRecordID wos000637633600001&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: PRVAVX
  databaseName: Springer Journals - Owned
  customDbUrl:
  eissn: 1573-7640
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0009788
  issn: 0885-7458
  databaseCode: RSV
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3db9MwED9tLQ-8rIwPrayr_MAbWIoTx3Z42_qhTdtCVb4KL5ETnxHS1FZtQeK_x3YTyhCbBC-WojiWdefzneO73w_gRYxGajSMSmZLyo2OqOLM5ztghkKpVFRB01cyz9Vslk3qorB1k-3eXEmGnfq3YjcpfMKsO_46vxjTZB_azt0pb47Ttx92ULsysE0680mp5KmqS2X-PsZtd7SLMf-4Fg3eZtz5v3k-goM6uiSn2-VwCHs4fwydhrmB1Ib8BKZDxCWutqSdr4k_h_4gQ4-h6-mv0JBBnpOLphaQLOak-c1PPcNn4JVwvUbmC5Ihhs3mKbwfj94NzmnNrkCrRCQbylXJPZxb6bNIjYv0tMgwLhXj1qY6EVlmYit8DOj0LGNjI2a5sO54VialtTp5Bq35Yo5HQKwHF2WGORPWvFKouc0M8lhHVqBmURdYI-SiqqHH_Uxvih1oshda4YRWBKEVSRde_vpmuQXeuLd3r9FdURvhuvBQ_y4eVYnowqtGV7vXd4_2_N-6H8PDOKjbpwX2oLVZfcMTeFB933xdr_qwLz9-6kP7bJRPpu7pUlLXXkcD38ZvXDtJP_fDEv4JLWPiMQ
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB2VggQXyqdYKOADnMAidryOg1RVaLdVV10ihIrUW3DiMapU7S67C6h_it-IxxsTgURvPXCOYyXxm_FMPPMewAuJrrDoBC-Eb7hyNuNGCap3wBK1MUPdxpWeFlVlTk_LD1vwM_XCUFll8onRUbt5S__I3xBvewguTK73F185qUbR6WqS0NjA4hgvfoSUbbU3GYf1fSnl4cHJ6Ih3qgK8zXW-5so0imjMGqqedCHCsbpE2RihvB_aXJelk15T7BPer5DOZ8Ir7UNa0uSN9zYP816D60oFc6BSwWzUk_wWUecyGO6QF2pouiadrlWv0FTuG5L3sKtLnv-5EfbR7V8HsnGfO9z5377QHbjdRdTs3cYE7sIWzu7BTlKrYJ3zug8fx4gLXG6ESt8yyr0v2Jh4g0nyCx0bVRWbpP5HNp-xdLTBSdU0ammEUQfuC7IxRgf7AD5dyZs9hO3ZfIaPgHkiVBVOBLdlVWvQKl86VNJmXqMV2QBEWt667ejW6UnP654omiBRB0jUERJ1PoBXv-9ZbMhGLh29m3BQd45nVfcgGMDrhKT-8r9ne3z5bM_h5tHJ-2k9nVTHT-CWjECmMshd2F4vv-FTuNF-X5-tls-iSTD4fNUI-wUqRkHk
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3fi9QwEB7OU8QXz5-4emoe9EnDbdI0TQURud7ickdZROHwpabNRATZXXdX5f41_zoz2cai4L3dg89NQ9J8mcw0M98H8ESiKyw6wQvhW66cHXOjBOU7YInamFx3caVPiro2p6flbAd-ploYSqtMNjEaarfo6B_5AfG2B-fCZPrA92kRs2ryavmVk4IU3bQmOY0tRI7x7EcI39Yvp1VY66dSTo7eHb7hvcIA7zKdbbgyrSJKs5YyKV3wdqwuUbZGKO9zm-mydNJr8oPCXAvp_Fh4pX0IUdqs9d5mod9LcLkIMSYFfrP8w0D4W0TNy7CJc16o3PQFO33ZXqEp9TcE8uGElzz781AcPN2_LmfjmTfZ-5-_1g243nva7PV2a9yEHZzfgr2kYsF6o3Yb3laIS1xtBUxfMIrJz1hFfMIkBYaOHdY1m6a6SLaYs3TlwUntNGpshFZH7hOyCqPhvQPvL2Rmd2F3vpjjPWCeiFaFE8GcWdUZtMqXDpW0Y6_RivEIRFrqputp2GmkX5qBQJrg0QR4NBEeTTaCZ7_fWW5JSM5tvZ8w0fQGad0MgBjB84Sq4fG_e7t_fm-P4WoAVnMyrY8fwDUZMU3Zkfuwu1l9w4dwpfu--bxePYq7g8HHiwbYL8zsSvU
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=DeeperThings%3A+Fully+Distributed+CNN+Inference+on+Resource-Constrained+Edge+Devices&rft.jtitle=International+journal+of+parallel+programming&rft.au=Stahl%2C+Rafael&rft.au=Hoffman%2C+Alexander&rft.au=Mueller-Gritschneder%2C+Daniel&rft.au=Gerstlauer%2C+Andreas&rft.date=2021-08-01&rft.issn=0885-7458&rft.eissn=1573-7640&rft.volume=49&rft.issue=4&rft.spage=600&rft.epage=624&rft_id=info:doi/10.1007%2Fs10766-021-00712-3&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s10766_021_00712_3
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0885-7458&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0885-7458&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0885-7458&client=summon