A Unified Treatment of Partial Stragglers and Sparse Matrices in Coded Matrix Computation
The overall execution time of distributed matrix computations is often dominated by slow worker nodes (stragglers) over the clusters. Recently, different coding techniques have been utilized to mitigate the effect of stragglers where worker nodes are assigned the task of processing encoded submatric...
Saved in:
Published in | 2021 IEEE Information Theory Workshop (ITW) pp. 1 - 6 |
---|---|
Main Authors | , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
17.10.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The overall execution time of distributed matrix computations is often dominated by slow worker nodes (stragglers) over the clusters. Recently, different coding techniques have been utilized to mitigate the effect of stragglers where worker nodes are assigned the task of processing encoded submatrices of the original matrices. In many machine learning or optimization problems the relevant matrices are often sparse. Several coded computation methods operate with dense linear combinations of the original submatrices; this can significantly increase the worker node computation times and consequently the overall job execution time. Moreover, several existing techniques treat the stragglers as failures (erasures) and discard their computations. In this work, we present a coding approach which operates with limited encoding of the original submatrices and utilizes the partial computations done by the slower workers. Our scheme continues to have the optimal threshold of prior work. Extensive numerical experiments done in AWS (Amazon Web Services) cluster confirm that the proposed approach enhances the speed of the worker computations (and thus the whole process) significantly. |
---|---|
AbstractList | The overall execution time of distributed matrix computations is often dominated by slow worker nodes (stragglers) over the clusters. Recently, different coding techniques have been utilized to mitigate the effect of stragglers where worker nodes are assigned the task of processing encoded submatrices of the original matrices. In many machine learning or optimization problems the relevant matrices are often sparse. Several coded computation methods operate with dense linear combinations of the original submatrices; this can significantly increase the worker node computation times and consequently the overall job execution time. Moreover, several existing techniques treat the stragglers as failures (erasures) and discard their computations. In this work, we present a coding approach which operates with limited encoding of the original submatrices and utilizes the partial computations done by the slower workers. Our scheme continues to have the optimal threshold of prior work. Extensive numerical experiments done in AWS (Amazon Web Services) cluster confirm that the proposed approach enhances the speed of the worker computations (and thus the whole process) significantly. |
Author | Das, Anindya Bijoy Ramamoorthy, Aditya |
Author_xml | – sequence: 1 givenname: Anindya Bijoy surname: Das fullname: Das, Anindya Bijoy email: abd149@iastate.edu organization: Iowa State University,Department of Electrical and Computer Engineering,Ames,IA,USA,50011 – sequence: 2 givenname: Aditya surname: Ramamoorthy fullname: Ramamoorthy, Aditya email: adityarg@iastate.edu organization: Iowa State University,Department of Electrical and Computer Engineering,Ames,IA,USA,50011 |
BookMark | eNotj11LwzAYhSPohZv-AhHyB1rz5mvp5Sh-DCYKq4hXIyRvRqBNSxpB_73D7epwHjgPnAW5TGNCQu6B1QCsedh0n9I0QteccagbDSAZuyAL0FpJJoCba_K1ph8phoiedhltGTAVOgb6bnOJtqe7ku3h0GOeqU2e7iabZ6SvtuTocKYx0Xb0x_E_-TmWYfoutsQx3ZCrYPsZb8-5JN3TY9e-VNu350273lYRwJRKaKZC0CCVbhw0jqHh3nHppbEIagV8paUJzDklQTfAkEmngkDhZdBcLMndSRsRcT_lONj8uz-fFX-wRE4t |
ContentType | Conference Proceeding |
DBID | 6IE 6IL CBEJK RIE RIL |
DOI | 10.1109/ITW48936.2021.9611400 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Xplore IEEE Proceedings Order Plans (POP All) 1998-Present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEL url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
EISBN | 1665403128 9781665403122 |
EndPage | 6 |
ExternalDocumentID | 9611400 |
Genre | orig-research |
GrantInformation_xml | – fundername: National Science Foundation funderid: 10.13039/100000001 |
GroupedDBID | 6IE 6IL CBEJK RIE RIL |
ID | FETCH-LOGICAL-i118t-3605ff614569c19c0e82dc24d48ae157127648f0cc5416910e04c5f3e3d4f623 |
IEDL.DBID | RIE |
IngestDate | Thu Jun 29 18:37:52 EDT 2023 |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-i118t-3605ff614569c19c0e82dc24d48ae157127648f0cc5416910e04c5f3e3d4f623 |
PageCount | 6 |
ParticipantIDs | ieee_primary_9611400 |
PublicationCentury | 2000 |
PublicationDate | 2021-Oct.-17 |
PublicationDateYYYYMMDD | 2021-10-17 |
PublicationDate_xml | – month: 10 year: 2021 text: 2021-Oct.-17 day: 17 |
PublicationDecade | 2020 |
PublicationTitle | 2021 IEEE Information Theory Workshop (ITW) |
PublicationTitleAbbrev | ITW |
PublicationYear | 2021 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
Score | 1.8415073 |
Snippet | The overall execution time of distributed matrix computations is often dominated by slow worker nodes (stragglers) over the clusters. Recently, different... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 1 |
SubjectTerms | Conferences Encoding Machine learning Optimization Sparse matrices Task analysis Web services |
Title | A Unified Treatment of Partial Stragglers and Sparse Matrices in Coded Matrix Computation |
URI | https://ieeexplore.ieee.org/document/9611400 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PS8MwFA5zJ08qm_ibHDzaLmmTtjnKcExhMrDiPI0mfRnD0Q7tQPzrfWnrRPHgLYSUtnml3_fa932PkMvQtYuWWnk6Cq0neAw40pGXBNZYhLisUfFP7qPxo7ibyVmHXG21MABQF5-B74b1v_y8NBv3qWygImTvDBP0nYQFjVarFeVwpga36ZNzUnF1BwH327U_mqbUmDHaI5OvszWlIi_-ptK--fhlxPjfy9kn_W91Hp1uceeAdKDokedrivTRIqGk6VftOC0tnbpHI1tR50K7WKyQ7NGsyOnDGhNaoJPaoB_e6LKgwzLHg-uZd9o0e6ij1ifp6CYdjr22bYK3xGyh8kLMUKxF2JWRMlwZBkmQm0DkIsmAy5gHcSQSy4yRwlnlMGDCSBtCmAuLbOiQdIuygCNCw8gGMmNGxApvVLIMQolLuNIaeKLYMem5XZmvG2OMebshJ39Pn5JdFxn34ufxGelWrxs4R0Sv9EUdyk8-J6Dg |
link.rule.ids | 310,311,786,790,795,796,802,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PS8MwFA5jHvSksom_zcGj3ZI26Y-jDMem6xhYcZ5Gm76M4WiHdiD-9b603UTx4C2EhLZ5he977fu-R8i1Y9pFyySwEtfRluAe4ChxLd_WSiPExZWKPxy7gydxP5XTBrnZamEAoCw-g44Zlv_y01ytzaeybuAie2eYoO8gzjOvUmvVshzOgu4wejZeKqbywOadevWPtiklavT3Sbi5XlUs8tpZF0lHff6yYvzvDR2Q9rc-j062yHNIGpC1yMstRQKpkVLSaFM9TnNNJ-bliJfU-NDO50ukezTOUvq4wpQWaFha9MM7XWS0l6e4uZz5oFW7hzJubRL176LewKobJ1gLzBcKy8EcRWsEXukGigeKgW-nyhap8GPg0uO25wpfM6WkMGY5DJhQUjvgpEIjHzoizSzP4JhQx9W2jJkSXoAPKlkMjsQlPEgS4H7ATkjLnMpsVVljzOoDOf17-orsDqJwNBsNxw9nZM9EycAA985Js3hbwwXie5FclmH9AujcpDQ |
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%3Abook&rft.genre=proceeding&rft.title=2021+IEEE+Information+Theory+Workshop+%28ITW%29&rft.atitle=A+Unified+Treatment+of+Partial+Stragglers+and+Sparse+Matrices+in+Coded+Matrix+Computation&rft.au=Das%2C+Anindya+Bijoy&rft.au=Ramamoorthy%2C+Aditya&rft.date=2021-10-17&rft.pub=IEEE&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FITW48936.2021.9611400&rft.externalDocID=9611400 |