Load balancing in homogeneous pipeline based applications

We propose to use knowledge about a parallel application’s structure that was acquired with the use of a skeleton based development strategy to dynamically improve its performance. Parallel/distributed programming provides the possibility of solving highly demanding computational problems. However,...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Parallel computing Ročník 38; číslo 3; s. 125 - 139
Hlavní autoři: Moreno, A., Cesar, E., Guevara, A., Sorribes, J., Margalef, T.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.03.2012
Témata:
ISSN:0167-8191, 1872-7336
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We propose to use knowledge about a parallel application’s structure that was acquired with the use of a skeleton based development strategy to dynamically improve its performance. Parallel/distributed programming provides the possibility of solving highly demanding computational problems. However, this type of application requires support tools in all phases of the development cycle because the implementation is extremely difficult, especially for non-expert programmers. This work shows a new strategy for dynamically improving the performance of pipeline applications. We call this approach Dynamic Pipeline Mapping (DPM), and the key idea is to have free computational resources by gathering the pipeline’s fastest stages and then using these resources to replicate the slowest stages. We present two versions of this strategy, both with complexity O( N log ( N)) on the number of pipe stages, and we compare them to an optimal mapping algorithm and to the Binary Search Closest (BSC) algorithm [1]. Our results show that the DPM leads to significant performance improvements, increasing the application throughput up to 40% on average.
AbstractList We propose to use knowledge about a parallel application’s structure that was acquired with the use of a skeleton based development strategy to dynamically improve its performance. Parallel/distributed programming provides the possibility of solving highly demanding computational problems. However, this type of application requires support tools in all phases of the development cycle because the implementation is extremely difficult, especially for non-expert programmers. This work shows a new strategy for dynamically improving the performance of pipeline applications. We call this approach Dynamic Pipeline Mapping (DPM), and the key idea is to have free computational resources by gathering the pipeline’s fastest stages and then using these resources to replicate the slowest stages. We present two versions of this strategy, both with complexity O( N log ( N)) on the number of pipe stages, and we compare them to an optimal mapping algorithm and to the Binary Search Closest (BSC) algorithm [1]. Our results show that the DPM leads to significant performance improvements, increasing the application throughput up to 40% on average.
We propose to use knowledge about a parallel application's structure that was acquired with the use of a skeleton based development strategy to dynamically improve its performance. Parallel/distributed programming provides the possibility of solving highly demanding computational problems. However, this type of application requires support tools in all phases of the development cycle because the implementation is extremely difficult, especially for non-expert programmers. This work shows a new strategy for dynamically improving the performance of pipeline applications. We call this approach Dynamic Pipeline Mapping (DPM), and the key idea is to have free computational resources by gathering the pipeline's fastest stages and then using these resources to replicate the slowest stages. We present two versions of this strategy, both with complexity O(N log (N)) on the number of pipe stages, and we compare them to an optimal mapping algorithm and to the Binary Search Closest (BSC) algorithm [1]. Our results show that the DPM leads to significant performance improvements, increasing the application throughput up to 40% on average.
Author Cesar, E.
Margalef, T.
Moreno, A.
Guevara, A.
Sorribes, J.
Author_xml – sequence: 1
  givenname: A.
  surname: Moreno
  fullname: Moreno, A.
  email: amoreno@euss.cat
  organization: Escola Universitaria Salesiana de Sarria (EUSS), Passeig Sant Joan Bosco, 74, 08017 Barcelona, Spain
– sequence: 2
  givenname: E.
  surname: Cesar
  fullname: Cesar, E.
  email: eduardo.cesar@uab.cat
  organization: Departament Arquitectura de Computadors i Sistemes Operatius, Universitat Autonoma de Barcelona, 08193 Bellaterra, Spain
– sequence: 3
  givenname: A.
  surname: Guevara
  fullname: Guevara, A.
  email: alex.guevara@caos.uab.es
  organization: Departament Arquitectura de Computadors i Sistemes Operatius, Universitat Autonoma de Barcelona, 08193 Bellaterra, Spain
– sequence: 4
  givenname: J.
  surname: Sorribes
  fullname: Sorribes, J.
  email: joan.sorribes@uab.cat
  organization: Departament Arquitectura de Computadors i Sistemes Operatius, Universitat Autonoma de Barcelona, 08193 Bellaterra, Spain
– sequence: 5
  givenname: T.
  surname: Margalef
  fullname: Margalef, T.
  email: tomas.margalef@uab.cat
  organization: Departament Arquitectura de Computadors i Sistemes Operatius, Universitat Autonoma de Barcelona, 08193 Bellaterra, Spain
BookMark eNqFkL1OwzAURi1UJErhCVgysiTYceLYAwOq-JMqscBsOc51cZXaxk6ReHvclokBpCvd5Tu-n885mjnvAKErgiuCCbvZVEFF7asaE1LlwZicoDnhXV12lLIZmudUV3IiyBk6T2mDMWYNx3MkVl4NRa9G5bR168K64t1v_Roc-F0qgg0wWgc5kWAoVAij1Wqy3qULdGrUmODyZy_Q28P96_KpXL08Pi_vVqXOl6dSCdbQvuamZR0WAxdCc6KGVnFj-ob12rRAml6xmrBmIJTWrWJEGN4ZrEC3dIGuj--G6D92kCa5tUnDmBvvK8r8sUwJTFmOimNUR59SBCO1nQ5tp6jsKAmWe11yIw-65F6XzJN1ZZb-YkO0WxW__qFujxRkA58WokzagtMw2Ah6koO3f_LfHSiHBQ
CitedBy_id crossref_primary_10_1016_j_procs_2013_05_302
crossref_primary_10_3390_e16115677
crossref_primary_10_1002_cpe_4340
crossref_primary_10_1109_TPDS_2018_2817207
crossref_primary_10_1016_j_parco_2019_01_002
crossref_primary_10_1109_ACCESS_2018_2855064
crossref_primary_10_1145_3363815
crossref_primary_10_1007_s11227_017_1971_4
crossref_primary_10_1088_1742_6596_2032_1_012015
crossref_primary_10_1109_JETCAS_2014_2315883
Cites_doi 10.1006/jpdc.1999.1596
10.1016/j.jpdc.2009.08.008
10.1109/EMPDP.2005.22
10.1016/j.parco.2006.06.005
10.1016/j.jpdc.2007.11.004
10.1007/3-540-64359-1_759
10.1109/TPDS.2003.1178876
10.1109/78.218149
10.1016/S0166-5316(03)00069-5
ContentType Journal Article
Copyright 2011 Elsevier B.V.
Copyright_xml – notice: 2011 Elsevier B.V.
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1016/j.parco.2011.11.001
DatabaseName CrossRef
Computer and Information Systems 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
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Computer and Information Systems Abstracts
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-7336
EndPage 139
ExternalDocumentID 10_1016_j_parco_2011_11_001
S0167819111001566
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
123
1B1
1~.
1~5
29O
4.4
457
4G.
5VS
6OB
7-5
71M
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABEFU
ABFNM
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
LG9
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SCC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
WH7
WUQ
XPP
ZMT
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c336t-a9643b28f56709d899c81ad5a8ffb46bcf5e14ba62164d13325a619f87f0aec53
ISICitedReferencesCount 11
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000300742800003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0167-8191
IngestDate Sun Sep 28 06:03:07 EDT 2025
Tue Nov 18 22:17:21 EST 2025
Sat Nov 29 08:08:08 EST 2025
Fri Feb 23 02:29:26 EST 2024
IsPeerReviewed true
IsScholarly true
Issue 3
Keywords Load balancing
Performance
Pipeline
Language English
License https://www.elsevier.com/tdm/userlicense/1.0
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c336t-a9643b28f56709d899c81ad5a8ffb46bcf5e14ba62164d13325a619f87f0aec53
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PQID 1671339036
PQPubID 23500
PageCount 15
ParticipantIDs proquest_miscellaneous_1671339036
crossref_citationtrail_10_1016_j_parco_2011_11_001
crossref_primary_10_1016_j_parco_2011_11_001
elsevier_sciencedirect_doi_10_1016_j_parco_2011_11_001
PublicationCentury 2000
PublicationDate 2012-03-01
PublicationDateYYYYMMDD 2012-03-01
PublicationDate_xml – month: 03
  year: 2012
  text: 2012-03-01
  day: 01
PublicationDecade 2010
PublicationTitle Parallel computing
PublicationYear 2012
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References A. Moreno, E. Cesar, A. Guevara, J. Sorribes, T. Margalef, E. Luque, Dynamic pipeline mapping (dpm), in: LNCS, vol. 5168, 2008, pp. 295–304.
Gilmore, Hillston, Kloul, Ribaudo (b0060) 2003; 54
A. Morajko, E. Cesar, P. Caymes-Scutari, T. Margalef, J. Sorribes, E. Luque, Automatic tuning of master/worker applications, in: Euro-Par 2005 Parallel Processing, Lecture Notes in Computer Science, vol. 3648, 2005, pp. 95–103.
Caymes-Scutari, Morajko, Margalef, Luque (b0070) 2010; 70
Benoit, Robert (b0005) 2008; 68
Cesar, Moreno, Sorribes, Luque (b0020) 2006; 32
M. Lee, W. Liu, V.K. Prasanna, A mapping methodology for designing software task pipelines for embedded signal processing, in: IPPS/SPDP Workshops, 1998, pp. 937–944.
Hoang, Rabaey (b0040) 1993; 41
Benoit, Cole, Gilmore, Hillston (b0065) 2004
Subhlok, Vondran (b0030) 2000; 60
Almeida, González, Moreno, Rodrı´guez (b0055) 2002
F. Guirado, A. Ripoll, C. Roig, E. Luque, Exploitation of parallelism for applications with an input data stream: optimal resource-throughput tradeoffs, in: 13th Euromicro Conference on Parallel, Distributed and Network-Based Processing, 2005, pp. 170–178.
E. Cesar, J. Sorribes, E. Luque, Modeling pipeline applications in poetries, in: Euro-Par 2005 Parallel Processing, Lecture Notes in Computer Science, vol. 3648, 2005, pp. 83–95.
Yang, Kasturi, Sivasubramaniam (b0045) 2003; 14
10.1016/j.parco.2011.11.001_b0025
Yang (10.1016/j.parco.2011.11.001_b0045) 2003; 14
10.1016/j.parco.2011.11.001_b0015
Hoang (10.1016/j.parco.2011.11.001_b0040) 1993; 41
Subhlok (10.1016/j.parco.2011.11.001_b0030) 2000; 60
10.1016/j.parco.2011.11.001_b0050
Caymes-Scutari (10.1016/j.parco.2011.11.001_b0070) 2010; 70
10.1016/j.parco.2011.11.001_b0035
Benoit (10.1016/j.parco.2011.11.001_b0005) 2008; 68
10.1016/j.parco.2011.11.001_b0010
Cesar (10.1016/j.parco.2011.11.001_b0020) 2006; 32
Benoit (10.1016/j.parco.2011.11.001_b0065) 2004
Almeida (10.1016/j.parco.2011.11.001_b0055) 2002
Gilmore (10.1016/j.parco.2011.11.001_b0060) 2003; 54
References_xml – volume: 54
  start-page: 79
  year: 2003
  end-page: 104
  ident: b0060
  article-title: Pepa nets: a structured performance modelling formalism
  publication-title: Perform Eval.
– volume: 68
  start-page: 790
  year: 2008
  end-page: 808
  ident: b0005
  article-title: Mapping pipeline skeletons onto heterogeneous platforms
  publication-title: J. Parallel Distrib. Comput.
– reference: E. Cesar, J. Sorribes, E. Luque, Modeling pipeline applications in poetries, in: Euro-Par 2005 Parallel Processing, Lecture Notes in Computer Science, vol. 3648, 2005, pp. 83–95.
– start-page: 299
  year: 2004
  end-page: 306
  ident: b0065
  article-title: Evaluating the performance of skeleton-based high level parallel programs
  publication-title: The International Conference on Computational Science (ICCS 2004), Part III
– start-page: 441
  year: 2002
  end-page: 449
  ident: b0055
  article-title: An analytical model for pipeline algorithms on heterogeneous clusters
  publication-title: Proceedings of the 9th European PVM/MPI Users’ Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
– volume: 60
  start-page: 297
  year: 2000
  end-page: 319
  ident: b0030
  article-title: Optimal use of mixed task and data parallelism for pipelined computations
  publication-title: J. Parallel Distrib. Comput.
– reference: A. Morajko, E. Cesar, P. Caymes-Scutari, T. Margalef, J. Sorribes, E. Luque, Automatic tuning of master/worker applications, in: Euro-Par 2005 Parallel Processing, Lecture Notes in Computer Science, vol. 3648, 2005, pp. 95–103.
– volume: 32
  start-page: 568
  year: 2006
  end-page: 589
  ident: b0020
  article-title: Modeling master/worker applications for automatic performance tuning
  publication-title: Parallel Comput.
– reference: M. Lee, W. Liu, V.K. Prasanna, A mapping methodology for designing software task pipelines for embedded signal processing, in: IPPS/SPDP Workshops, 1998, pp. 937–944.
– reference: A. Moreno, E. Cesar, A. Guevara, J. Sorribes, T. Margalef, E. Luque, Dynamic pipeline mapping (dpm), in: LNCS, vol. 5168, 2008, pp. 295–304.
– volume: 70
  start-page: 330
  year: 2010
  end-page: 337
  ident: b0070
  article-title: Scalable dynamic monitoring, analysis and tuning environment for parallel applications
  publication-title: J. Parallel Distrib. Comput.
– volume: 14
  start-page: 119
  year: 2003
  end-page: 130
  ident: b0045
  article-title: A pipeline-based approach for scheduling video processing algorithms on now
  publication-title: Trans. Parallel Distrib. Syst.
– reference: F. Guirado, A. Ripoll, C. Roig, E. Luque, Exploitation of parallelism for applications with an input data stream: optimal resource-throughput tradeoffs, in: 13th Euromicro Conference on Parallel, Distributed and Network-Based Processing, 2005, pp. 170–178.
– volume: 41
  start-page: 2225
  year: 1993
  end-page: 2235
  ident: b0040
  article-title: Scheduling of dsp programs onto multiprocessors for maximum throughput
  publication-title: IEEE Trans. Signal Process.
– volume: 60
  start-page: 297
  issue: 3
  year: 2000
  ident: 10.1016/j.parco.2011.11.001_b0030
  article-title: Optimal use of mixed task and data parallelism for pipelined computations
  publication-title: J. Parallel Distrib. Comput.
  doi: 10.1006/jpdc.1999.1596
– volume: 70
  start-page: 330
  year: 2010
  ident: 10.1016/j.parco.2011.11.001_b0070
  article-title: Scalable dynamic monitoring, analysis and tuning environment for parallel applications
  publication-title: J. Parallel Distrib. Comput.
  doi: 10.1016/j.jpdc.2009.08.008
– ident: 10.1016/j.parco.2011.11.001_b0050
  doi: 10.1109/EMPDP.2005.22
– volume: 32
  start-page: 568
  issue: 7
  year: 2006
  ident: 10.1016/j.parco.2011.11.001_b0020
  article-title: Modeling master/worker applications for automatic performance tuning
  publication-title: Parallel Comput.
  doi: 10.1016/j.parco.2006.06.005
– volume: 68
  start-page: 790
  issue: 6
  year: 2008
  ident: 10.1016/j.parco.2011.11.001_b0005
  article-title: Mapping pipeline skeletons onto heterogeneous platforms
  publication-title: J. Parallel Distrib. Comput.
  doi: 10.1016/j.jpdc.2007.11.004
– ident: 10.1016/j.parco.2011.11.001_b0015
– ident: 10.1016/j.parco.2011.11.001_b0035
  doi: 10.1007/3-540-64359-1_759
– volume: 14
  start-page: 119
  issue: 2
  year: 2003
  ident: 10.1016/j.parco.2011.11.001_b0045
  article-title: A pipeline-based approach for scheduling video processing algorithms on now
  publication-title: Trans. Parallel Distrib. Syst.
  doi: 10.1109/TPDS.2003.1178876
– ident: 10.1016/j.parco.2011.11.001_b0010
– volume: 41
  start-page: 2225
  issue: 6
  year: 1993
  ident: 10.1016/j.parco.2011.11.001_b0040
  article-title: Scheduling of dsp programs onto multiprocessors for maximum throughput
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/78.218149
– ident: 10.1016/j.parco.2011.11.001_b0025
– start-page: 299
  year: 2004
  ident: 10.1016/j.parco.2011.11.001_b0065
  article-title: Evaluating the performance of skeleton-based high level parallel programs
– start-page: 441
  year: 2002
  ident: 10.1016/j.parco.2011.11.001_b0055
  article-title: An analytical model for pipeline algorithms on heterogeneous clusters
– volume: 54
  start-page: 79
  issue: 2
  year: 2003
  ident: 10.1016/j.parco.2011.11.001_b0060
  article-title: Pepa nets: a structured performance modelling formalism
  publication-title: Perform Eval.
  doi: 10.1016/S0166-5316(03)00069-5
SSID ssj0006480
Score 2.016701
Snippet We propose to use knowledge about a parallel application’s structure that was acquired with the use of a skeleton based development strategy to dynamically...
We propose to use knowledge about a parallel application's structure that was acquired with the use of a skeleton based development strategy to dynamically...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 125
SubjectTerms Algorithms
Computation
Load balancing
Mapping
Optimization
Performance enhancement
Phases
Pipeline
Pipelines
Strategy
Title Load balancing in homogeneous pipeline based applications
URI https://dx.doi.org/10.1016/j.parco.2011.11.001
https://www.proquest.com/docview/1671339036
Volume 38
WOSCitedRecordID wos000300742800003&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-7336
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0006480
  issn: 0167-8191
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3da9swEBdd0oe9dGu70uwLDfrWOdiWPx_LSLeGUgJrIW9GkmWakNrG-aB__k5frtuwsD7sxQQhK7bufPc76ac7hM7SIGac59ShqUcdufHmUAACjucxHsrkIb5wVbGJ-OYmmU7TiaHyLlU5gbgsk8fHtP6vooY2ELY8OvsKcbeDQgP8BqHDFcQO138S_HVFAVRKxiI351Xuq4cKugvJdq1ntVDIUrqv_Ly7f93FqRPayCIrC0U5X6-sf9PsXFHqszHDdgNDLDVPe9Q2_VyLDW3o836_q6aZMW2YxsPugoNkbljGlV2DBNsq47yuESVJR1lIxyJ6-lyzca6ezly0Zbf1EsJ8WIPIK51YVeZWNX_7LEv2C-_VcgotXW2eqUEyOQjEN5K09wb1_ThMkx7qX1yNpuPWVUeBKq3XvpFNS6UIgFvP8jfo8sKJK2Ry-x4dmJACX2hVOER7ojxC72y5Dmys9zFKpWbgVjPwrMQdzcBWM7DSDNzVjA_o7nJ0--OXYypnOJyQaAUfHgBN5idFKNPz5RBT88SjeUiTomBBxHgRCi9gNPIhWs49QvyQQiRdJHHhUsFDcoJ6ZVWKU4QDV8CYBSlyQgLGOOOU-HHuu9xNCUQTA-TbScm4SSsvq5sssh0CGaDv7U21zqqyu3tkZzszwFADvgz0Z_eN36xsMjCbci-MqjnNQOLw2ingt4-ve5ZP6O3TR_EZ9VbNWnxB-3yzmi2br0bB_gDm448L
linkProvider Elsevier
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=Load+balancing+in+homogeneous+pipeline+based+applications&rft.jtitle=Parallel+computing&rft.au=Moreno%2C+A.&rft.au=Cesar%2C+E.&rft.au=Guevara%2C+A.&rft.au=Sorribes%2C+J.&rft.date=2012-03-01&rft.issn=0167-8191&rft.volume=38&rft.issue=3&rft.spage=125&rft.epage=139&rft_id=info:doi/10.1016%2Fj.parco.2011.11.001&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_parco_2011_11_001
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-8191&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-8191&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-8191&client=summon