Improving matrix-based dynamic programming on massively parallel accelerators
Dynamic programming techniques are well-established and employed by various practical algorithms, including the edit-distance algorithm or the dynamic time warping algorithm. These algorithms usually operate in an iteration-based manner where new values are computed from values of the previous itera...
Gespeichert in:
| Veröffentlicht in: | Information systems (Oxford) Jg. 64; S. 175 - 193 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Elsevier Ltd
01.03.2017
|
| Schlagworte: | |
| ISSN: | 0306-4379, 1873-6076 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Dynamic programming techniques are well-established and employed by various practical algorithms, including the edit-distance algorithm or the dynamic time warping algorithm. These algorithms usually operate in an iteration-based manner where new values are computed from values of the previous iteration. The data dependencies enforce synchronization which limits possibilities for internal parallel processing. In this paper, we investigate parallel approaches to processing matrix-based dynamic programming algorithms on modern multicore CPUs, Intel Xeon Phi accelerators, and general purpose GPUs. We address both the problem of computing a single distance on large inputs and the problem of computing a number of distances of smaller inputs simultaneously (e.g., when a similarity query is being resolved). Our proposed solutions yielded significant improvements in performance and achieved speedup of two orders of magnitude when compared to the serial baseline.
•Dynamic programming algorithms with matrix organization (e.g., Levenshtein distance).•Employing task parallelism and SIMD/SIMT vectorization.•Proposed hierarchical algorithm optimized for CPUs, Intel Xeon Phi devices, and GPUs.•Can be efficiently parallelized if inputs are large or many distances are computed.•Experiments also determine optimal configurations for current hardware. |
|---|---|
| AbstractList | Dynamic programming techniques are well-established and employed by various practical algorithms, including the edit-distance algorithm or the dynamic time warping algorithm. These algorithms usually operate in an iteration-based manner where new values are computed from values of the previous iteration. The data dependencies enforce synchronization which limits possibilities for internal parallel processing. In this paper, we investigate parallel approaches to processing matrix-based dynamic programming algorithms on modern multicore CPUs, Intel Xeon Phi accelerators, and general purpose GPUs. We address both the problem of computing a single distance on large inputs and the problem of computing a number of distances of smaller inputs simultaneously (e.g., when a similarity query is being resolved). Our proposed solutions yielded significant improvements in performance and achieved speedup of two orders of magnitude when compared to the serial baseline.
•Dynamic programming algorithms with matrix organization (e.g., Levenshtein distance).•Employing task parallelism and SIMD/SIMT vectorization.•Proposed hierarchical algorithm optimized for CPUs, Intel Xeon Phi devices, and GPUs.•Can be efficiently parallelized if inputs are large or many distances are computed.•Experiments also determine optimal configurations for current hardware. |
| Author | Brabec, Michal Bednárek, David Kruliš, Martin |
| Author_xml | – sequence: 1 givenname: David surname: Bednárek fullname: Bednárek, David email: bednarek@ksi.mff.cuni.cz – sequence: 2 givenname: Michal surname: Brabec fullname: Brabec, Michal email: brabec@ksi.mff.cuni.cz – sequence: 3 givenname: Martin surname: Kruliš fullname: Kruliš, Martin email: krulis@ksi.mff.cuni.cz |
| BookMark | eNp9kM1qwzAQhEVJoUnae49-Absr2Zbt3kroH6T00p7FWtoEBdkKkgjN29chPRVaGNiFnW9hZsFmox-JsVsOBQcu73aFjYWYtgImAb9gc942ZS6hkTM2hxJkXpVNd8UWMe4AQNRdN2dvr8M--IMdt9mAKdivvMdIJjPHEQers-m4DTgMJ4MfJ0-M9kDumO0xoHPkMtSaHAVMPsRrdrlBF-nmZy7Z59Pjx-olX78_v64e1rkWXZXyGnmPVGmqeiOMlh0Q1pXmsiSBreA96K7kUEoNfStNW6NoemF4txGyBazKJYPzXx18jIE2ah_sgOGoOKhTHWqnbFSnOhRMAj4h8heibcJk_ZgCWvcfeH8GaQp0sBRU1JZGTcYG0kkZb_-GvwE96nzD |
| CitedBy_id | crossref_primary_10_1051_e3sconf_202131503012 crossref_primary_10_1016_j_jpdc_2021_04_014 crossref_primary_10_1007_s00158_017_1822_1 crossref_primary_10_1016_j_parco_2023_103019 crossref_primary_10_1016_j_knosys_2021_107793 crossref_primary_10_1007_s10766_020_00658_y |
| Cites_doi | 10.1007/978-3-319-25087-8_27 10.1109/ICDM.2010.21 10.1093/bioinformatics/btl582 10.1016/0022-2836(81)90087-5 10.1145/2597652.2597677 10.1016/0196-6774(85)90023-9 10.1007/978-3-319-23135-8_19 10.1145/321796.321811 10.1186/1471-2105-14-117 10.1016/j.procs.2013.05.067 10.1007/11758549_29 10.1109/JCSSE.2011.5930126 10.1111/j.1467-8659.2007.01012.x 10.1007/978-3-540-74048-3_4 10.1007/978-3-642-38718-0_38 10.1186/1471-2105-9-S2-S10 10.1016/j.jcp.2010.02.009 10.1145/316542.316550 10.1109/IPDPS.2009.5160931 10.1109/TC.1983.1676311 |
| ContentType | Journal Article |
| Copyright | 2016 Elsevier Ltd |
| Copyright_xml | – notice: 2016 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.is.2016.06.001 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1873-6076 |
| EndPage | 193 |
| ExternalDocumentID | 10_1016_j_is_2016_06_001 S0306437915301897 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 13V 1B1 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 63O 7-5 71M 77K 8P~ 9JN 9JO AAAKF AAAKG AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARIN AAXUO AAYFN ABBOA ABFNM ABKBG ABMAC ABMVD ABTAH ABUCO ABXDB ABYKQ ACDAQ ACGFS ACHRH ACNNM ACNTT ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD AEBSH AEKER AENEX AFFNX AFKWA AFTJW AGHFR AGJBL AGUBO AGUMN AGYEJ AHHHB AHZHX AI. AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALEQD ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNSAS CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HAMUX HF~ HLZ HVGLF HZ~ H~9 IHE J1W KOM LG9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SES SEW SPC SPCBC SSB SSD SSL SSV SSZ T5K TN5 UHS VH1 WUQ XSW ZCG ZY4 ~G- 77I 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABJNI ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO ADVLN AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c294t-5a1bae4ce4bd2dc690ea54c163e2a821b0c931036c0b86d85a27b2d19f2680a43 |
| ISICitedReferencesCount | 6 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000391900000014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0306-4379 |
| IngestDate | Sat Nov 29 06:20:17 EST 2025 Tue Nov 18 22:12:23 EST 2025 Fri Feb 23 02:35:56 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Multicore Edit distance Intel Xeon Phi Dynamic time warping Parallel Dynamic programming GPU |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c294t-5a1bae4ce4bd2dc690ea54c163e2a821b0c931036c0b86d85a27b2d19f2680a43 |
| PageCount | 19 |
| ParticipantIDs | crossref_primary_10_1016_j_is_2016_06_001 crossref_citationtrail_10_1016_j_is_2016_06_001 elsevier_sciencedirect_doi_10_1016_j_is_2016_06_001 |
| PublicationCentury | 2000 |
| PublicationDate | March 2017 2017-03-00 |
| PublicationDateYYYYMMDD | 2017-03-01 |
| PublicationDate_xml | – month: 03 year: 2017 text: March 2017 |
| PublicationDecade | 2010 |
| PublicationTitle | Information systems (Oxford) |
| PublicationYear | 2017 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | NVIDIA, Kepler GPU Architecture. URL Smith, Waterman (bib6) 1981; 147 Intel, Xeon Phi Coprocessor Manavski, Valle (bib20) 2008; 9 Wagner, Fischer (bib3) 1974; 21 J.D. Owens, D. Luebke, N. Govindaraju, M. Harris, J. Krüger, A.E. Lefohn, T.J. Purcell, A survey of general-purpose computation on graphics hardware, in: Computer Graphics Forum, vol. 26, Wiley Online Library, 2007, pp. 80–113. NVIDIA, Maxwell GPU architecture. URL D. Bednárek, M. Brabec, M. Kruliš, On parallel evaluation of matrix-based dynamic programming algorithms. Liu, Wirawan, Schmidt (bib23) 2013; 14 Farrar (bib17) 2007; 23 L. Ligowski, W. Rudnicki, An efficient implementation of smith waterman algorithm on gpu using cuda, for massively parallel scanning of sequence databases, in: IEEE International Symposium on Parallel & Distributed Processing, 2009, IPDPS 2009, IEEE, 2009, pp. 1–8. Ukkonen (bib12) 1985; 6 M. Zymbler, Best-match time series subsequence search on the intel many integrated core architecture, in: Advances in Databases and Information Systems, Springer, 2015, pp. 275–286. Myers (bib7) 1999; 46 T.R. Mathies, A fast parallel algorithm to determine edit distance. V.I. Levenshtein, Binary codes capable of correcting deletions, insertions and reversals, Sov. Phys. Dokl. 10 (1966) 707. Müller (bib5) 2007 G. Delgado, C. Aporntewan, Data dependency reduction in dynamic programming matrix, in: 2011 Eighth International Joint Conference on Computer Science and Software Engineering (JCSSE), IEEE, 2011, pp. 234–236. Y. Liu, W. Huang, J. Johnson, S. Vaidya, Gpu accelerated Smith–Waterman, in: Computational Science—ICCS 2006, Springer, 2006, pp. 188–195. A. Chacón, S. Marco-Sola, A. Espinosa, P. Ribeca, J.C. Moure, Thread-cooperative, bit-parallel computation of Levenshtein distance on GPU, in: Proceedings of the 28th ACM International Conference on Supercomputing, ACM, 2014, pp. 103–112. D. Sart, A. Mueen, W. Najjar, E. Keogh, V. Niennattrakul, Accelerating dynamic time warping subsequence search with gpus and fpgas, in: 2010 IEEE 10th International Conference on Data Mining (ICDM), IEEE, 2010, pp. 1001–1006. Khajeh-Saeed, Poole, Blair Perot (bib22) 2010; 229 . Weste, Burr, Ackland (bib15) 1983; 32 Reinders (bib27) 2007 M. Kruliš, D. Bednárek, M. Brabec, Improving parallel processing of matrix-based similarity measures on modern gpus, in: Similarity Search and Applications, Springer, 2015, pp. 283–294. A. Tomiyama, R. Suda, Automatic parameter optimization for edit distance algorithm on gpu, in: High Performance Computing for Computational Science-VECPAR 2012, Springer, 2013, pp. 420–434. Xu, Cui, Hu, Guo (bib13) 2013; 17 10.1016/j.is.2016.06.001_bib14 Myers (10.1016/j.is.2016.06.001_bib7) 1999; 46 Liu (10.1016/j.is.2016.06.001_bib23) 2013; 14 10.1016/j.is.2016.06.001_bib11 10.1016/j.is.2016.06.001_bib10 Ukkonen (10.1016/j.is.2016.06.001_bib12) 1985; 6 Wagner (10.1016/j.is.2016.06.001_bib3) 1974; 21 Müller (10.1016/j.is.2016.06.001_bib5) 2007 Smith (10.1016/j.is.2016.06.001_bib6) 1981; 147 Manavski (10.1016/j.is.2016.06.001_bib20) 2008; 9 10.1016/j.is.2016.06.001_bib19 10.1016/j.is.2016.06.001_bib18 Farrar (10.1016/j.is.2016.06.001_bib17) 2007; 23 10.1016/j.is.2016.06.001_bib16 10.1016/j.is.2016.06.001_bib25 10.1016/j.is.2016.06.001_bib24 Reinders (10.1016/j.is.2016.06.001_bib27) 2007 10.1016/j.is.2016.06.001_bib21 Weste (10.1016/j.is.2016.06.001_bib15) 1983; 32 10.1016/j.is.2016.06.001_bib4 10.1016/j.is.2016.06.001_bib8 10.1016/j.is.2016.06.001_bib9 Xu (10.1016/j.is.2016.06.001_bib13) 2013; 17 10.1016/j.is.2016.06.001_bib1 10.1016/j.is.2016.06.001_bib2 Khajeh-Saeed (10.1016/j.is.2016.06.001_bib22) 2010; 229 10.1016/j.is.2016.06.001_bib26 |
| References_xml | – volume: 21 start-page: 168 year: 1974 end-page: 173 ident: bib3 article-title: The string-to-string correction problem publication-title: J. ACM (JACM) – reference: V.I. Levenshtein, Binary codes capable of correcting deletions, insertions and reversals, Sov. Phys. Dokl. 10 (1966) 707. – start-page: 69 year: 2007 end-page: 84 ident: bib5 article-title: Dynamic time warping publication-title: Inf. Retr. Music Motion – reference: D. Bednárek, M. Brabec, M. Kruliš, On parallel evaluation of matrix-based dynamic programming algorithms. – volume: 32 start-page: 731 year: 1983 end-page: 744 ident: bib15 article-title: Dynamic time warp pattern matching using an integrated multiprocessing array publication-title: IEEE Trans. Comput. – volume: 147 start-page: 195 year: 1981 end-page: 197 ident: bib6 article-title: Identification of common molecular subsequences publication-title: J. Mol. Biol. – reference: NVIDIA, Kepler GPU Architecture. URL 〈 – volume: 14 start-page: 117 year: 2013 ident: bib23 article-title: Cudasw++ 3.0 publication-title: BMC Bioinform. – volume: 6 start-page: 132 year: 1985 end-page: 137 ident: bib12 article-title: Finding approximate patterns in strings publication-title: J. Algorithms – reference: J.D. Owens, D. Luebke, N. Govindaraju, M. Harris, J. Krüger, A.E. Lefohn, T.J. Purcell, A survey of general-purpose computation on graphics hardware, in: Computer Graphics Forum, vol. 26, Wiley Online Library, 2007, pp. 80–113. – volume: 9 start-page: S10 year: 2008 ident: bib20 article-title: Cuda compatible gpu cards as efficient hardware accelerators for Smith–Waterman sequence alignment publication-title: BMC Bioinform. – reference: M. Zymbler, Best-match time series subsequence search on the intel many integrated core architecture, in: Advances in Databases and Information Systems, Springer, 2015, pp. 275–286. – volume: 23 start-page: 156 year: 2007 end-page: 161 ident: bib17 article-title: Striped Smith–Waterman speeds database searches six times over other SIMD implementations publication-title: Bioinformatics – reference: 〉. – reference: NVIDIA, Maxwell GPU architecture. URL 〈 – year: 2007 ident: bib27 article-title: Intel Threading Building Blocks: Outfitting C++ for Multi-core Processor Parallelism – reference: L. Ligowski, W. Rudnicki, An efficient implementation of smith waterman algorithm on gpu using cuda, for massively parallel scanning of sequence databases, in: IEEE International Symposium on Parallel & Distributed Processing, 2009, IPDPS 2009, IEEE, 2009, pp. 1–8. – volume: 17 start-page: 523 year: 2013 end-page: 529 ident: bib13 article-title: Bit-parallel multiple approximate string matching based on gpu publication-title: Proc. Comput. Sci. – reference: Intel, Xeon Phi Coprocessor, 〈 – reference: G. Delgado, C. Aporntewan, Data dependency reduction in dynamic programming matrix, in: 2011 Eighth International Joint Conference on Computer Science and Software Engineering (JCSSE), IEEE, 2011, pp. 234–236. – reference: A. Chacón, S. Marco-Sola, A. Espinosa, P. Ribeca, J.C. Moure, Thread-cooperative, bit-parallel computation of Levenshtein distance on GPU, in: Proceedings of the 28th ACM International Conference on Supercomputing, ACM, 2014, pp. 103–112. – volume: 229 start-page: 4247 year: 2010 end-page: 4258 ident: bib22 article-title: Acceleration of the Smith–Waterman algorithm using single and multiple graphics processors publication-title: J. Comput. Phys. – reference: M. Kruliš, D. Bednárek, M. Brabec, Improving parallel processing of matrix-based similarity measures on modern gpus, in: Similarity Search and Applications, Springer, 2015, pp. 283–294. – volume: 46 start-page: 395 year: 1999 end-page: 415 ident: bib7 article-title: A fast bit-vector algorithm for approximate string matching based on dynamic programming publication-title: J. ACM (JACM) – reference: A. Tomiyama, R. Suda, Automatic parameter optimization for edit distance algorithm on gpu, in: High Performance Computing for Computational Science-VECPAR 2012, Springer, 2013, pp. 420–434. – reference: T.R. Mathies, A fast parallel algorithm to determine edit distance. – reference: Y. Liu, W. Huang, J. Johnson, S. Vaidya, Gpu accelerated Smith–Waterman, in: Computational Science—ICCS 2006, Springer, 2006, pp. 188–195. – reference: D. Sart, A. Mueen, W. Najjar, E. Keogh, V. Niennattrakul, Accelerating dynamic time warping subsequence search with gpus and fpgas, in: 2010 IEEE 10th International Conference on Data Mining (ICDM), IEEE, 2010, pp. 1001–1006. – ident: 10.1016/j.is.2016.06.001_bib2 doi: 10.1007/978-3-319-25087-8_27 – ident: 10.1016/j.is.2016.06.001_bib14 doi: 10.1109/ICDM.2010.21 – ident: 10.1016/j.is.2016.06.001_bib25 – ident: 10.1016/j.is.2016.06.001_bib4 – volume: 23 start-page: 156 issue: 2 year: 2007 ident: 10.1016/j.is.2016.06.001_bib17 article-title: Striped Smith–Waterman speeds database searches six times over other SIMD implementations publication-title: Bioinformatics doi: 10.1093/bioinformatics/btl582 – volume: 147 start-page: 195 issue: 1 year: 1981 ident: 10.1016/j.is.2016.06.001_bib6 article-title: Identification of common molecular subsequences publication-title: J. Mol. Biol. doi: 10.1016/0022-2836(81)90087-5 – ident: 10.1016/j.is.2016.06.001_bib11 doi: 10.1145/2597652.2597677 – volume: 6 start-page: 132 issue: 1 year: 1985 ident: 10.1016/j.is.2016.06.001_bib12 article-title: Finding approximate patterns in strings publication-title: J. Algorithms doi: 10.1016/0196-6774(85)90023-9 – ident: 10.1016/j.is.2016.06.001_bib16 doi: 10.1007/978-3-319-23135-8_19 – year: 2007 ident: 10.1016/j.is.2016.06.001_bib27 – volume: 21 start-page: 168 issue: 1 year: 1974 ident: 10.1016/j.is.2016.06.001_bib3 article-title: The string-to-string correction problem publication-title: J. ACM (JACM) doi: 10.1145/321796.321811 – volume: 14 start-page: 117 issue: 1 year: 2013 ident: 10.1016/j.is.2016.06.001_bib23 article-title: Cudasw++ 3.0 publication-title: BMC Bioinform. doi: 10.1186/1471-2105-14-117 – volume: 17 start-page: 523 year: 2013 ident: 10.1016/j.is.2016.06.001_bib13 article-title: Bit-parallel multiple approximate string matching based on gpu publication-title: Proc. Comput. Sci. doi: 10.1016/j.procs.2013.05.067 – ident: 10.1016/j.is.2016.06.001_bib18 doi: 10.1007/11758549_29 – ident: 10.1016/j.is.2016.06.001_bib26 – ident: 10.1016/j.is.2016.06.001_bib24 – ident: 10.1016/j.is.2016.06.001_bib9 – ident: 10.1016/j.is.2016.06.001_bib10 doi: 10.1109/JCSSE.2011.5930126 – ident: 10.1016/j.is.2016.06.001_bib19 doi: 10.1111/j.1467-8659.2007.01012.x – start-page: 69 year: 2007 ident: 10.1016/j.is.2016.06.001_bib5 article-title: Dynamic time warping publication-title: Inf. Retr. Music Motion doi: 10.1007/978-3-540-74048-3_4 – ident: 10.1016/j.is.2016.06.001_bib1 – ident: 10.1016/j.is.2016.06.001_bib8 doi: 10.1007/978-3-642-38718-0_38 – volume: 9 start-page: S10 issue: Suppl 2 year: 2008 ident: 10.1016/j.is.2016.06.001_bib20 article-title: Cuda compatible gpu cards as efficient hardware accelerators for Smith–Waterman sequence alignment publication-title: BMC Bioinform. doi: 10.1186/1471-2105-9-S2-S10 – volume: 229 start-page: 4247 issue: 11 year: 2010 ident: 10.1016/j.is.2016.06.001_bib22 article-title: Acceleration of the Smith–Waterman algorithm using single and multiple graphics processors publication-title: J. Comput. Phys. doi: 10.1016/j.jcp.2010.02.009 – volume: 46 start-page: 395 issue: 3 year: 1999 ident: 10.1016/j.is.2016.06.001_bib7 article-title: A fast bit-vector algorithm for approximate string matching based on dynamic programming publication-title: J. ACM (JACM) doi: 10.1145/316542.316550 – ident: 10.1016/j.is.2016.06.001_bib21 doi: 10.1109/IPDPS.2009.5160931 – volume: 32 start-page: 731 issue: 8 year: 1983 ident: 10.1016/j.is.2016.06.001_bib15 article-title: Dynamic time warp pattern matching using an integrated multiprocessing array publication-title: IEEE Trans. Comput. doi: 10.1109/TC.1983.1676311 |
| SSID | ssj0002599 |
| Score | 2.1716766 |
| Snippet | Dynamic programming techniques are well-established and employed by various practical algorithms, including the edit-distance algorithm or the dynamic time... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 175 |
| SubjectTerms | Dynamic programming Dynamic time warping Edit distance GPU Intel Xeon Phi Multicore Parallel |
| Title | Improving matrix-based dynamic programming on massively parallel accelerators |
| URI | https://dx.doi.org/10.1016/j.is.2016.06.001 |
| Volume | 64 |
| WOSCitedRecordID | wos000391900000014&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: 1873-6076 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002599 issn: 0306-4379 databaseCode: AIEXJ dateStart: 19950301 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Jb9UwELbglQMcWiggWhb5wAVVhsRxFh9LVcQiKg5FerfIsR2pW1olj-r9_I7XZ1qK6IFLFEWxY2U-ecYz38wg9JZzmfVSMULBuCCM95JwKhTpGas1GAxC9MI2m6gPDpr5nP_wEdPJthOoh6FZLvnFfxU1PANhm9TZO4g7TgoP4B6EDlcQO1z_SfArN8GZKb-_JEZRqR3lWs8HQtaZZTsP8M5kCOzGxyFG01fldEdICbrIht-n1Hb1mUsWMK4AtPXYupTDxKPwUavBxt_zUZ9c483b4D0INDL2I8Hj22gytfdKGOZziEJRcO-TAD0XSVkhFyuriKl0mO6zFUs2ytz1S_E6N3ddEm9s586zcAyTGhJe9d5FjlaqK4Trr2m0yDMMFLbj9mhqzQytY_HdR2u0LutshtZ2v-zPv0bdDYdB7uJObv0-sO0Ygb-v4s-GTGKcHD5G6_5UgXcdGp6ge3rYRBuhYwf2G_gmepSUn3yKvkeo4BQq2EMFJ1DB5wOOUMEBKjiFyjP089P-4d5n4ttrEEk5W5BS5J3QTGrWKapkxTMtSibBQNdUNDTvMslNF7pKZl1TqaYUtO6oynlPqyYTrHiOZsP5oF8gLPvaholYrzUrqIRTgwbVUYqiK4qKsy30IfyrVvra86YFyml7m4S20Ls44sLVXfnLu0X4_a23G5092AKObh21fYcvvEQPVzB_hWaL8Zd-jR7Iy8XRNL7xILoClHeMpQ |
| 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=Improving+matrix-based+dynamic+programming+on+massively+parallel+accelerators&rft.jtitle=Information+systems+%28Oxford%29&rft.au=Bedn%C3%A1rek%2C+David&rft.au=Brabec%2C+Michal&rft.au=Kruli%C5%A1%2C+Martin&rft.date=2017-03-01&rft.issn=0306-4379&rft.volume=64&rft.spage=175&rft.epage=193&rft_id=info:doi/10.1016%2Fj.is.2016.06.001&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_is_2016_06_001 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0306-4379&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0306-4379&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0306-4379&client=summon |