Using Differential Execution Analysis to Identify Thread Interference

Understanding the performance of a multi-threaded application is difficult. The threads interfere when they access the same shared resource, which slows down their execution. Unfortunately, current profiling tools report the hardware components or the synchronization primitives that saturate, but th...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on parallel and distributed systems Vol. 30; no. 12; pp. 2866 - 2878
Main Authors: Bouksiaa, Mohamed Said Mosli, Trahay, Francois, Lescouet, Alexis, Voron, Gauthier, Dulong, Remi, Guermouche, Amina, Brunet, Elisabeth, Thomas, Gael
Format: Journal Article
Language:English
Published: New York IEEE 01.12.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Subjects:
ISSN:1045-9219, 1558-2183
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Understanding the performance of a multi-threaded application is difficult. The threads interfere when they access the same shared resource, which slows down their execution. Unfortunately, current profiling tools report the hardware components or the synchronization primitives that saturate, but they cannot tell if the saturation is the cause of a performance bottleneck. In this paper, we propose a holistic metric able to pinpoint the blocks of code that suffer interference the most, regardless of the interference cause. Our metric uses performance variation as a universal indicator of interference problems. With an evaluation of 27 applications we show that our metric can identify interference problems caused by six different kinds of interference in nine applications. We are able to easily remove seven of the bottlenecks, which leads to a performance improvement of up to nine times.
AbstractList Understanding the performance of a multi-threaded application is difficult. The threads interfere when they access the same shared resource, which slows down their execution. Unfortunately, current profiling tools report the hardware components or the synchronization primitives that saturate, but they cannot tell if the saturation is the cause of a performance bottleneck. In this paper, we propose a holistic metric able to pinpoint the blocks of code that suffer interference the most, regardless of the interference cause. Our metric uses performance variation as a universal indicator of interference problems. With an evaluation of 27 applications we show that our metric can identify interference problems caused by 6 different kinds of interference in 9 applications. We are able to easily remove 7 of the bottlenecks, which leads to a performance improvement of up to 9 times
Understanding the performance of a multi-threaded application is difficult. The threads interfere when they access the same shared resource, which slows down their execution. Unfortunately, current profiling tools report the hardware components or the synchronization primitives that saturate, but they cannot tell if the saturation is the cause of a performance bottleneck. In this paper, we propose a holistic metric able to pinpoint the blocks of code that suffer interference the most, regardless of the interference cause. Our metric uses performance variation as a universal indicator of interference problems. With an evaluation of 27 applications we show that our metric can identify interference problems caused by six different kinds of interference in nine applications. We are able to easily remove seven of the bottlenecks, which leads to a performance improvement of up to nine times.
Author Bouksiaa, Mohamed Said Mosli
Lescouet, Alexis
Guermouche, Amina
Trahay, Francois
Brunet, Elisabeth
Voron, Gauthier
Dulong, Remi
Thomas, Gael
Author_xml – sequence: 1
  givenname: Mohamed Said Mosli
  surname: Bouksiaa
  fullname: Bouksiaa, Mohamed Said Mosli
  email: mohamed.mosli_bouksiaa@telecom-sudparis.eu
  organization: Telecom SudParis, Évry, France
– sequence: 2
  givenname: Francois
  orcidid: 0000-0001-7329-1812
  surname: Trahay
  fullname: Trahay, Francois
  email: francois.trahay@telecom-sudparis.eu
  organization: Telecom SudParis, Évry, France
– sequence: 3
  givenname: Alexis
  surname: Lescouet
  fullname: Lescouet, Alexis
  email: alexis.lescouet@telecom-sudparis.eu
  organization: Telecom SudParis, Évry, France
– sequence: 4
  givenname: Gauthier
  surname: Voron
  fullname: Voron, Gauthier
  email: gauthier.voron@pro.mnesic.fr
  organization: Telecom SudParis, Évry, France
– sequence: 5
  givenname: Remi
  surname: Dulong
  fullname: Dulong, Remi
  email: remi.dulong@telecom-sudparis.eu
  organization: Telecom SudParis, Évry, France
– sequence: 6
  givenname: Amina
  surname: Guermouche
  fullname: Guermouche, Amina
  email: amina.guermouche@telecom-sudparis.eu
  organization: Telecom SudParis, Évry, France
– sequence: 7
  givenname: Elisabeth
  surname: Brunet
  fullname: Brunet, Elisabeth
  email: Elisabeth.Brunet@telecom-sudparis.eu
  organization: Telecom SudParis, Évry, France
– sequence: 8
  givenname: Gael
  surname: Thomas
  fullname: Thomas, Gael
  email: gael.thomas@telecom-sudparis.eu
  organization: Telecom SudParis, Évry, France
BackLink https://hal.science/hal-02179717$$DView record in HAL
BookMark eNp9kLFOwzAQhi1UJErhARBLJCaGFJ_t1PZYtYVWqgQSYbacxKauQlLsFNG3JyGFgYHJp7vvs-7-czSo6sogdAV4DIDlXfo0fx4TDHJMJOFMwAkaQpKImICgg7bGLIklAXmGzkPYYgwswWyIFi_BVa_R3FlrvKkap8to8WnyfePqKppWujwEF6KmjlZFN7aHKN14o4toVTXGf0u5uUCnVpfBXB7fEUrvF-lsGa8fH1az6TrOKcdNnBe2kDzDglsiJmZiGVgsMqCaMpgIY4ikbAKQSSHaRi6opZnWhc0KTlhOR-i2_3ajS7Xz7k37g6q1U8vpWnU9TIBLDvwDWvamZ3e-ft-b0KhtvfftPUERCowKyRhvKd5Tua9D8Maq3DW6u73x2pUKsOriVV28qotXHeNtTfhj_iz0n3PdO84Y88sLngjKCP0CRI2Gnw
CODEN ITDSEO
CitedBy_id crossref_primary_10_1145_3460433
crossref_primary_10_1145_3469379_3469391
Cites_doi 10.1145/3225058.3225094
10.1109/PDP.2015.30
10.1109/IISWC.2012.6402901
10.1145/1952682.1952688
10.1145/2815400.2815409
10.1145/1755913.1755947
10.1145/2845079
10.1109/ISPASS.2012.6189221
10.1109/ISCA.2014.6853224
10.1007/11428848_22
10.1145/2485922.2485966
10.1145/1274971.1274976
10.1145/2660193.2660234
10.1145/1693453.1693489
10.1145/2503210.2503247
10.1145/3064176.3064179
10.1109/ISCA.1995.524546
10.1145/2901318.2901340
10.1109/PACT.2007.4336237
10.1145/2854038.2854039
10.1145/1869459.1869519
10.1145/1791194.1791198
10.1109/ISPASS.2016.7482081
10.1109/CCGrid.2011.83
10.1145/2660193.2660210
10.1145/1454115.1454128
10.1109/IPDPS.2014.28
10.1145/2807591.2807648
10.1145/2503210.2503269
10.1145/2048066.2048070
10.1145/2555243.2555244
10.1145/1772954.1772991
10.1145/2465351.2465366
10.1145/2591062.2591107
10.1109/IPDPS.2003.1213517
10.1145/2451116.2451157
10.1145/2541940.2541968
10.1109/HPCA.2007.346181
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
– notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
1XC
VOOES
DOI 10.1109/TPDS.2019.2927481
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Hyper Article en Ligne (HAL)
Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
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 1558-2183
EndPage 2878
ExternalDocumentID oai:HAL:hal-02179717v1
10_1109_TPDS_2019_2927481
8758342
Genre orig-research
GroupedDBID --Z
-~X
.DC
0R~
29I
4.4
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
HZ~
IEDLZ
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
TN5
TWZ
UHB
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
RIG
1XC
5VS
ABFSI
AETIX
AGSQL
AI.
AIBXA
ALLEH
E.L
H~9
ICLAB
IFJZH
RNI
RZB
VH1
VOOES
ID FETCH-LOGICAL-c370t-cdfd97b087f286e6f41f08b13a34168ee2934611b988416c83f3baadfbd724c3
IEDL.DBID RIE
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000498569400018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1045-9219
IngestDate Sat Oct 25 10:05:36 EDT 2025
Mon Jun 30 04:14:54 EDT 2025
Tue Nov 18 22:43:54 EST 2025
Sat Nov 29 06:06:47 EST 2025
Wed Aug 27 02:47:29 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 12
Keywords Multithreading
Performance analysis
Bottleneck detection
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c370t-cdfd97b087f286e6f41f08b13a34168ee2934611b988416c83f3baadfbd724c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-7329-1812
0000-0003-3653-3784
0000-0002-9444-1071
0009-0008-2481-7257
OpenAccessLink https://hal.science/hal-02179717
PQID 2314389447
PQPubID 85437
PageCount 13
ParticipantIDs hal_primary_oai_HAL_hal_02179717v1
proquest_journals_2314389447
crossref_citationtrail_10_1109_TPDS_2019_2927481
crossref_primary_10_1109_TPDS_2019_2927481
ieee_primary_8758342
PublicationCentury 2000
PublicationDate 2019-12-01
PublicationDateYYYYMMDD 2019-12-01
PublicationDate_xml – month: 12
  year: 2019
  text: 2019-12-01
  day: 01
PublicationDecade 2010
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on parallel and distributed systems
PublicationTitleAbbrev TPDS
PublicationYear 2019
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
– name: Institute of Electrical and Electronics Engineers
References ref13
ref56
ref12
ref15
ref14
ref53
ref52
ref55
ref11
ref54
ref10
zhuang (ref38) 0
frumkin (ref36) 2004
ref17
ref16
ref18
(ref3) 0
lozi (ref26) 2012
ref51
ref50
(ref41) 0
eranian (ref4) 2006
ref48
ref47
ref42
aulagnon (ref24) 2012
ref44
ref43
xu (ref46) 2010
lachaize (ref5) 2012
ref49
ref8
ref9
scott (ref27) 1993
joukov (ref21) 2006
zhao (ref19) 2016
ref40
ref34
ref31
ref30
ref33
ref32
ref2
lozi (ref29) 2016; 33
(ref1) 0
fitzpatrick (ref37) 2004; 2004
jaleel (ref6) 2008
ghemawat (ref39) 2011
ref23
ref25
ref20
bailey (ref35) 2011
ref22
chung (ref45) 2008
ref28
günther (ref7) 2009
References_xml – start-page: 65
  year: 2012
  ident: ref26
  article-title: Remote core locking: migrating critical-section execution to improve the performance of multithreaded applications
  publication-title: Proc USENIX Annu Tech Conf
– ident: ref54
  doi: 10.1145/3225058.3225094
– start-page: 1
  year: 2008
  ident: ref45
  article-title: A framework for automated performance bottleneck detection
  publication-title: Proc Int Parallel Distrib Process Symp
– ident: ref25
  doi: 10.1109/PDP.2015.30
– ident: ref31
  doi: 10.1109/IISWC.2012.6402901
– ident: ref8
  doi: 10.1145/1952682.1952688
– year: 1993
  ident: ref27
  article-title: False sharing and its effect on shared memory performance
  publication-title: Proc USENIX Symp Experiences Distrib Multiprocessor Syst
– ident: ref40
  doi: 10.1145/2815400.2815409
– year: 0
  ident: ref41
  article-title: Facebook rocksdb
– ident: ref52
  doi: 10.1145/1755913.1755947
– start-page: 5
  year: 2012
  ident: ref5
  article-title: MemProf: A memory profiler for NUMA multicore systems
  publication-title: Proc USENIX Annu Tech Conf
– volume: 33
  start-page: 13:1
  year: 2016
  ident: ref29
  article-title: Fast and portable locking for multicore architectures
  publication-title: ACM Trans Comput Syst
  doi: 10.1145/2845079
– ident: ref56
  doi: 10.1109/ISPASS.2012.6189221
– start-page: 603
  year: 2016
  ident: ref19
  article-title: Non-intrusive performance profiling for entire software stacks based on the flow reconstruction principle
  publication-title: Proc Operating Syst Des Implementation
– ident: ref47
  doi: 10.1109/ISCA.2014.6853224
– volume: 2004
  year: 2004
  ident: ref37
  article-title: Distributed caching with memcached
  publication-title: Linux J
– year: 0
  ident: ref38
  article-title: memaslap: Load testing and benchmarking a server
– year: 0
  ident: ref1
  article-title: Intel® vtune™ amplifier 2017
– ident: ref49
  doi: 10.1007/11428848_22
– ident: ref55
  doi: 10.1145/2485922.2485966
– ident: ref22
  doi: 10.1145/1274971.1274976
– ident: ref18
  doi: 10.1145/2660193.2660234
– start-page: 1254
  year: 2011
  ident: ref35
  article-title: Nas parallel benchmarks
  publication-title: Encyclopedia of Parallel Computing
– ident: ref12
  doi: 10.1145/1693453.1693489
– ident: ref16
  doi: 10.1145/2503210.2503247
– ident: ref20
  doi: 10.1145/3064176.3064179
– ident: ref33
  doi: 10.1109/ISCA.1995.524546
– year: 2004
  ident: ref36
  article-title: Benchmarking memory performance with the data cube operator
– start-page: 28
  year: 2008
  ident: ref6
  article-title: CMP$im: A pin-based on-the-fly multi-core cache simulator
  publication-title: Proc 4th Ann Workshop Modeling Benchmarking and Simulation
– ident: ref43
  doi: 10.1145/2901318.2901340
– ident: ref9
  doi: 10.1109/PACT.2007.4336237
– ident: ref11
  doi: 10.1145/2854038.2854039
– ident: ref15
  doi: 10.1145/1869459.1869519
– start-page: 26
  year: 2009
  ident: ref7
  article-title: Assessing cache false sharing effects by dynamic binary instrumentation
  publication-title: Proc Workshop Binary Instrum Appl
  doi: 10.1145/1791194.1791198
– ident: ref30
  doi: 10.1109/ISPASS.2016.7482081
– ident: ref23
  doi: 10.1109/CCGrid.2011.83
– ident: ref14
  doi: 10.1145/2660193.2660210
– ident: ref34
  doi: 10.1145/1454115.1454128
– ident: ref17
  doi: 10.1109/IPDPS.2014.28
– start-page: 269
  year: 2006
  ident: ref4
  article-title: Perfmon2: A flexible performance monitoring interface for linux
  publication-title: Proceedings of Ottawa Linux Symposium 2006
– year: 2011
  ident: ref39
  article-title: LevelDB
– ident: ref51
  doi: 10.1145/2807591.2807648
– ident: ref48
  doi: 10.1145/2503210.2503269
– ident: ref28
  doi: 10.1145/2048066.2048070
– ident: ref10
  doi: 10.1145/2555243.2555244
– year: 0
  ident: ref3
  article-title: Oprofile. a system profiler for linux
– ident: ref44
  doi: 10.1145/1772954.1772991
– start-page: 395
  year: 2012
  ident: ref24
  article-title: Runtime function instrumentation with EZTrace
  publication-title: Proc Workshop Productiv Perform
– ident: ref50
  doi: 10.1145/2465351.2465366
– start-page: 76
  year: 2010
  ident: ref46
  article-title: Cache contention and application performance prediction for multi-core systems
  publication-title: Proc Int Symp Perform Anal Syst Softw
– ident: ref42
  doi: 10.1145/2591062.2591107
– ident: ref2
  doi: 10.1109/IPDPS.2003.1213517
– ident: ref53
  doi: 10.1145/2451116.2451157
– start-page: 89
  year: 2006
  ident: ref21
  article-title: Operating system profiling via latency analysis
  publication-title: Proc Operating Syst Des Implementation
– ident: ref13
  doi: 10.1145/2541940.2541968
– ident: ref32
  doi: 10.1109/HPCA.2007.346181
SSID ssj0014504
Score 2.311439
Snippet Understanding the performance of a multi-threaded application is difficult. The threads interfere when they access the same shared resource, which slows down...
SourceID hal
proquest
crossref
ieee
SourceType Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2866
SubjectTerms bottleneck detection
Computer Science
Distributed, Parallel, and Cluster Computing
Energy storage
Generators
Interference
multithreading
Operating Systems
Performance analysis
Power system stability
Real-time systems
Renewable energy sources
Supply and demand
Synchronism
Title Using Differential Execution Analysis to Identify Thread Interference
URI https://ieeexplore.ieee.org/document/8758342
https://www.proquest.com/docview/2314389447
https://hal.science/hal-02179717
Volume 30
WOSCitedRecordID wos000498569400018&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: 1558-2183
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014504
  issn: 1045-9219
  databaseCode: RIE
  dateStart: 19900101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH848aAHp1NxOiWIJzGubbImOYpueBAR7MFbSfOBgmwyp-h_b5KmRVEEbyW8QOgvLy8v7-MHcOzZolWqLM6MVthZCIUlGREsjOTM0oTb3AayCXZzw-_vxe0SnLa1MMaYkHxmzvxniOXrmXr1T2VDd7fmhLoDt8NYXtdqtREDOgpUgc67GGHh1DBGMNNEDIvbyzufxCXOMuGcMJ5-s0GdB58BGahVfpzHwchMuv9b3gasx8skOq_R34QlM-1BtyFqQFFve7D2pevgFoxDmgC6jNQoTsWf0PjdqLAFUdOlBC1mqK7itR-ocIhLjcLzYSwQ3IZiMi4urnBkU8CKsGSBlbZasCpxEGQ8N7mlqU14lRLpDFnOjXGGn-ZpWgnuQ5GKE0sqKbWtNMuoIjuwPJ1NzS4gSTUxWuhUUU09nlxbaTJn-CUxSUX6kDS_t1Sx07gnvHgqg8eRiNIjUnpEyohIH07aKc91m42_hI8cZq2cb5B9dX5d-jHvYQnnob45oS2PUCsVwenDoIG4jNr6Uro7rieBp5Tt_T5rH1b9Auo0lgEsL-av5gBW1Nvi8WV-GDbiJ0IH2gE
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSyQxEC58ge7B54qz6yOIJ7G1u5PpTo6yjow4DoJ98BbSeaAgM4vODPrvTWUyzYqy4K0JFQj9pVKp1OMDOEK2aJ1pl-TW6MRbCJ0o2qaJsIqXjqXcFS6QTZT9Pr-_F7dzcNLUwlhrQ_KZPcXPEMs3Qz3Gp7Izf7fmlPkDdxGZs2K1VhMzYO1AFuj9i3YivCLGGGaWirPq9uIO07jEaS68G8azD1Zo_gFzIAO5yqcTOZiZy7XvLXAdVuN1kpxP8d-AOTvYhLUZVQOJmrsJP_7pO7gFnZAoQC4iOYpX8ifSebU6bEIy61NCRkMyreN1b6TymCtDwgNiLBH8CdVlp_rTTSKfQqJpmY4SbZwRZZ16EHJe2MKxzKW8zqjypqzg1nrTz4osqwXHYKTm1NFaKeNqU-ZM021YGAwHdgeIYoZaI0ymmWGIKDdO2dybfkVtWtMWpLPfK3XsNY6UF08y-BypkIiIRERkRKQFx82Uv9NGG_8TPvSYNXLYIrt73pM4hj6W8D7qxAttIUKNVASnBbsziGXU1xfpb7lIA89Y-evrWQew3K1uerJ31b_-DSu4mGlSyy4sjJ7Hdg-W9GT0-PK8HzblO8Ys3Uo
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=Using+Differential+Execution+Analysis+to+Identify+Thread+Interference&rft.jtitle=IEEE+transactions+on+parallel+and+distributed+systems&rft.au=Bouksiaa%2C+Mohamed+Said+Mosli&rft.au=Trahay%2C+Francois&rft.au=Lescouet%2C+Alexis&rft.au=Voron%2C+Gauthier&rft.date=2019-12-01&rft.issn=1045-9219&rft.eissn=1558-2183&rft.volume=30&rft.issue=12&rft.spage=2866&rft.epage=2878&rft_id=info:doi/10.1109%2FTPDS.2019.2927481&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TPDS_2019_2927481
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1045-9219&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1045-9219&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1045-9219&client=summon