Exploiting memory allocations in clusterized many-core architectures
Power-efficient architectures have become the most important feature required for future embedded systems. Modern designs, like those released on mobile devices, reveal that clusterization is the way to improve energy efficiency. However, such architectures are still limited by the memory subsystem...
Saved in:
Published in | IET computers & digital techniques Vol. 13; no. 4; pp. 302 - 311 |
---|---|
Main Authors | , , , , , |
Format | Journal Article |
Language | English |
Published |
Institution of Engineering and Technology
01.07.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Power-efficient architectures have become the most important feature required for future embedded systems. Modern designs, like those released on mobile devices, reveal that clusterization is the way to improve energy efficiency. However, such architectures are still limited by the memory subsystem (i.e., memory latency problems). This work investigates an alternative approach that exploits on-chip data locality to a large extent, through distributed shared memory systems that permit efficient reuse of on-chip mapped data in clusterized many-core architectures. First, this work reviews the current literature on memory allocations and explore the limitations of cluster-based many-core architectures. Then, several memory allocations are introduced and benchmarked scalability, performance and energy-wise, compared to the conventional centralized shared memory solution to reveal which memory allocation is the most appropriate for future mobile architectures. Our results show that distributed shared memory allocations bring performance gains and opportunities to reduce energy consumption. |
---|---|
AbstractList | Power-efficient architectures have become the most important feature required for future embedded systems. Modern designs, like those released on mobile devices, reveal that clusterization is the way to improve energy efficiency. However, such architectures are still limited by the memory subsystem (i.e., memory latency problems). This work investigates an alternative approach that exploits on-chip data locality to a large extent, through distributed shared memory systems that permit efficient reuse of on-chip mapped data in clusterized many-core architectures. First, this work reviews the current literature on memory allocations and explore the limitations of cluster-based many-core architectures. Then, several memory allocations are introduced and benchmarked scalability, performance and energy-wise, compared to the conventional centralized shared memory solution to reveal which memory allocation is the most appropriate for future mobile architectures. Our results show that distributed shared memory allocations bring performance gains and opportunities to reduce energy consumption. |
Author | Garibotti, Rafael Reis, Ricardo Gamatié, Abdoulaye Ost, Luciano Sassatelli, Gilles Butko, Anastasiia |
Author_xml | – sequence: 1 givenname: Rafael surname: Garibotti fullname: Garibotti, Rafael organization: Pontifícia Universidade Católica do Rio Grande do Sul [Brasil] = Pontifical Catholic University of Rio Grande do Sul [Brazil] = Université catholique pontificale de Rio Grande do Sul [Brésil] – sequence: 2 givenname: Luciano surname: Ost fullname: Ost, Luciano organization: Loughborough University – sequence: 3 givenname: Anastasiia surname: Butko fullname: Butko, Anastasiia organization: Lawrence Berkeley National Laboratory [Berkeley] – sequence: 4 givenname: Ricardo orcidid: 0000-0001-5781-5858 surname: Reis fullname: Reis, Ricardo organization: Universidade Federal do Rio Grande do Sul [Porto Alegre] – sequence: 5 givenname: Abdoulaye orcidid: 0000-0002-8326-3257 surname: Gamatié fullname: Gamatié, Abdoulaye organization: ADAptive Computing – sequence: 6 givenname: Gilles orcidid: 0000-0002-6396-286X surname: Sassatelli fullname: Sassatelli, Gilles organization: ADAptive Computing |
BackLink | https://hal-lirmm.ccsd.cnrs.fr/lirmm-02100269$$DView record in HAL |
BookMark | eNqVyrtuwjAUgGELUancHqCbd5RwTmhCGFELysDYoZtlmdNykC_INoj06bsgdqb_G_6xGPrgSYg3hBLhfb1gyoU55LICbMsal81AjHBVY9E2-D18GPBVjFM6AdRNDe1IfG5vZxs4s_-VjlyIvdTWBqMzB58ke2nsJWWK_EcH6bTvCxMiSR3NkTOZfImUpuLlR9tEs3snYr7bfn10xVFbdY7sdOxV0Ky6zV5Zjs4pqBCgatZXXD53_wNGdUq_ |
ContentType | Journal Article |
Copyright | Distributed under a Creative Commons Attribution 4.0 International License |
Copyright_xml | – notice: Distributed under a Creative Commons Attribution 4.0 International License |
DBID | 1XC |
DOI | 10.1049/iet-cdt.2018.5136 |
DatabaseName | Hyper Article en Ligne (HAL) |
DatabaseTitleList | |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Computer Science |
EISSN | 1751-861X |
EndPage | 311 |
ExternalDocumentID | oai_HAL_lirmm_02100269v1 |
GroupedDBID | .DC 0R~ 0ZK 1OC 1XC 24P 29I 3V. 4.4 4IJ 5GY 6IK 8FE 8FG 8VB 96U AAHHS AAHJG AAJGR ABJCF ABQXS ABUWG ACCFJ ACESK ACGFS ACIWK ACXQS ADEYR AEEZP AEGXH AENEX AEQDE AFAZI AFKRA AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN ARAPS AVUZU AZQEC BENPR BGLVJ BPHCQ CCPQU CS3 DU5 DWQXO EBS EJD ESX F8P GNUQQ GOZPB GROUPED_DOAJ GRPMH HCIFZ HZ~ IAO IFIPE IPLJI ITC JAVBF K1G K6V K7- L6V LAI M0N M43 M7S MCNEO MS~ NADUK NXXTH O9- OCL OK1 P2P P62 PQQKQ PROAC PTHSS QWB RIE RNS ROL RUI U5U UNMZH ZL0 ~ZZ |
ID | FETCH-hal_primary_oai_HAL_lirmm_02100269v13 |
ISSN | 1751-8601 |
IngestDate | Tue Oct 15 15:06:46 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 4 |
Keywords | multiprocessing systems power aware computing resource allocation energy conservation distributed shared memory systems |
Language | English |
License | Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0 |
LinkModel | OpenURL |
MergedId | FETCHMERGED-hal_primary_oai_HAL_lirmm_02100269v13 |
ORCID | 0000-0001-5781-5858 0000-0002-6396-286X 0000-0002-8326-3257 0000-0002-8326-3257 0000-0001-5781-5858 0000-0002-6396-286X |
ParticipantIDs | hal_primary_oai_HAL_lirmm_02100269v1 |
PublicationCentury | 2000 |
PublicationDate | 2019-07 |
PublicationDateYYYYMMDD | 2019-07-01 |
PublicationDate_xml | – month: 07 year: 2019 text: 2019-07 |
PublicationDecade | 2010 |
PublicationTitle | IET computers & digital techniques |
PublicationYear | 2019 |
Publisher | Institution of Engineering and Technology |
Publisher_xml | – name: Institution of Engineering and Technology |
SSID | ssj0056508 |
Score | 4.4361343 |
Snippet | Power-efficient architectures have become the most important feature required for future embedded systems. Modern designs, like those released on mobile... |
SourceID | hal |
SourceType | Open Access Repository |
StartPage | 302 |
SubjectTerms | Computer Science Embedded Systems Hardware Architecture Software Engineering |
Title | Exploiting memory allocations in clusterized many-core architectures |
URI | https://hal-lirmm.ccsd.cnrs.fr/lirmm-02100269 |
Volume | 13 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8JAEN4QvOjBB2p8Zw_cSNHSB-VIBCyKhCAm3JqyXbQRioHWRH6cv83Z3bYsggl6achCNm3nY3Ye38wglAdQwDmtGsoQzioFtB9RXLXiKqbhUVcllIgOfI9t037W7_tGP5P5klhLUTgokvnaupL_SBXWQK6sSvYPkk03hQX4DPKFK0gYrhvJmBPofE5cHjPG7GeBpdElfjgZRawRgj8Hs3IMf3uFNa0syMmDmWydNus9zjFnYx5mHBSe_8KmihTSVq-pCX4HTjYbQ8bZAF13mHDvWcBW1JG0IhYxmaQOfxS-iZqawAWTdOb76YnQpaLTQRcQM_UmciSCFz_JkYiE3RAbulI_RZ4H-ZEqEOq2bKiKZcabUHmND9JZ6GhNwqIuKVztpiSd3ZpQ3CvHArhBIEufhgrxGIFWtYqGqq1pwW1Xn5xOreG0mu2H5W_TXtx2teWM_Ol47DB3GVzYygd431ulcsVglNKS3kksAYNZv7wgN37KNKteuV65F7BtXpNYPrdtevtoN3ZKcFUg7ABlaJBDe8nADxzr_xzakd72Iaot4IcF_LAEP-wHWIIfTuGHl-B3hAqNeu_WVuC2nHfR-sT57QVoxygbTAJ6gjD4C9awTEjZG6i6a7kDi9ISdS3dMj1qWuQU5TfZ8Wyzn52j7QUUL1A2nEb0EszEcHDFZfENpuRz1g |
link.rule.ids | 230,315,786,790,891,27955,27956 |
linkProvider | Wiley-Blackwell |
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=Exploiting+memory+allocations+in+clusterized+many-core+architectures&rft.jtitle=IET+computers+%26+digital+techniques&rft.au=Garibotti%2C+Rafael&rft.au=Ost%2C+Luciano&rft.au=Butko%2C+Anastasiia&rft.au=Reis%2C+Ricardo&rft.date=2019-07-01&rft.pub=Institution+of+Engineering+and+Technology&rft.issn=1751-8601&rft.eissn=1751-861X&rft.volume=13&rft.issue=4&rft.spage=302&rft.epage=311&rft_id=info:doi/10.1049%2Fiet-cdt.2018.5136&rft.externalDBID=HAS_PDF_LINK&rft.externalDocID=oai_HAL_lirmm_02100269v1 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-8601&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-8601&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-8601&client=summon |