{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T13:53:46Z","timestamp":1770990826442,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2020,11,30]],"date-time":"2020-11-30T00:00:00Z","timestamp":1606694400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,11,30]],"date-time":"2020-11-30T00:00:00Z","timestamp":1606694400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004054","name":"King Abdulaziz University","doi-asserted-by":"publisher","award":["RG-6-611-40"],"award-info":[{"award-number":["RG-6-611-40"]}],"id":[{"id":"10.13039\/501100004054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s11227-020-03489-3","type":"journal-article","created":{"date-parts":[[2020,11,30]],"date-time":"2020-11-30T14:02:51Z","timestamp":1606744971000},"page":"6313-6355","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["DIESEL: A novel deep learning-based tool for SpMV computations and solving sparse linear equation systems"],"prefix":"10.1007","volume":"77","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4767-4147","authenticated-orcid":false,"given":"Thaha","family":"Mohammed","sequence":"first","affiliation":[]},{"given":"Aiiad","family":"Albeshri","sequence":"additional","affiliation":[]},{"given":"Iyad","family":"Katib","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4997-5322","authenticated-orcid":false,"given":"Rashid","family":"Mehmood","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,30]]},"reference":[{"key":"3489_CR1","doi-asserted-by":"publisher","unstructured":"AlAhmadi S, Muhammed T, Mehmood R, Albeshri A (2020) Performance characteristics for sparse matrix-vector multiplication on GPUs. Springer International Publishing, Cham, pp 409\u2013426. https:\/\/doi.org\/10.1007\/978-3-030-13705-2_17","DOI":"10.1007\/978-3-030-13705-2_17"},{"key":"3489_CR2","doi-asserted-by":"publisher","unstructured":"Alyahya H, Mehmood R, Katib I (2020) Parallel iterative solution of large sparse linear equation systems on the intel MIC architecture. Springer International Publishing, Cham, pp 377\u2013407. https:\/\/doi.org\/10.1007\/978-3-030-13705-2_16","DOI":"10.1007\/978-3-030-13705-2_16"},{"key":"3489_CR3","unstructured":"Asanovic K, Bodik R, Catanzaro BC, Gebis JJ, Husbands P, Keutzer K, Patterson DA, Plishker WL, Shalf J, Williams SW, Yelick KA (2006) The landscape of parallel computing research: a view from Berkeley. Tech. Rep. UCB\/EECS-2006-183, EECS Department, University of California, Berkeley, http:\/\/www.eecs.berkeley.edu\/Pubs\/TechRpts\/2006\/EECS-2006-183.html"},{"key":"3489_CR4","unstructured":"Baskaran MM, Bordawekar R (2009) Optimizing sparse matrix-vector multiplication on GPUs. Tech. Rep. RC24704 (W0812-047), IBM Research"},{"key":"3489_CR5","unstructured":"Bell N, Garland M (2008) Efficient sparse matrix-vector multiplication on CUDA. Tech. rep., Nvidia Technical Report NVR-2008-004, Nvidia Corporation"},{"key":"3489_CR6","doi-asserted-by":"publisher","unstructured":"Benatia A, Ji W, Wang Y, Shi F (2016) Sparse matrix format selection with multiclass SVM for SpMV on GPU. In: 2016 45th International Conference on Parallel Processing (ICPP), pp 496\u2013505. https:\/\/doi.org\/10.1109\/ICPP.2016.64","DOI":"10.1109\/ICPP.2016.64"},{"key":"3489_CR7","doi-asserted-by":"publisher","unstructured":"Benatia A, Ji W, Wang Y, Shi F (2018) Bestsf: a sparse meta-format for optimizing SpMV on GPU. ACM Trans Archit Code Optim 15(3). https:\/\/doi.org\/10.1145\/3226228","DOI":"10.1145\/3226228"},{"issue":"1","key":"3489_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000006","volume":"2","author":"Y Bengio","year":"2009","unstructured":"Bengio Y (2009) Learning deep architectures for ai. Found Trends Mach Learn 2(1):1\u2013127. https:\/\/doi.org\/10.1561\/2200000006","journal-title":"Found Trends Mach Learn"},{"issue":"8","key":"3489_CR9","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35(8):1798\u20131828. https:\/\/doi.org\/10.1109\/TPAMI.2013.50","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"3489_CR10","doi-asserted-by":"publisher","first-page":"C53","DOI":"10.1137\/15M1027826","volume":"38","author":"M Bernaschi","year":"2016","unstructured":"Bernaschi M, Bisson M, Fantozzi C, Janna C (2016) A factored sparse approximate inverse preconditioned conjugate gradient solver on graphics processing units. SIAM J Sci Comput 38(1):C53\u2013C72. https:\/\/doi.org\/10.1137\/15M1027826","journal-title":"SIAM J Sci Comput"},{"key":"3489_CR11","doi-asserted-by":"crossref","unstructured":"Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:27:1\u201327:27, software available at http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvm","DOI":"10.1145\/1961189.1961199"},{"key":"3489_CR12","doi-asserted-by":"publisher","unstructured":"Choi JW, Singh A, Vuduc RW (2010) Model-driven autotuning of sparse matrix-vector multiply on GPUs. In: Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, Association for Computing Machinery, New York, NY, USA, PPoPP \u201910, pp 115 \u2013 126. https:\/\/doi.org\/10.1145\/1693453.1693471","DOI":"10.1145\/1693453.1693471"},{"key":"3489_CR13","doi-asserted-by":"publisher","unstructured":"Davis TA, Hu Y (2011) The university of Florida sparse matrix collection. ACM Trans Math Softw 38(1):1:1\u20131:25. https:\/\/doi.org\/10.1145\/2049662.2049663","DOI":"10.1145\/2049662.2049663"},{"key":"3489_CR14","unstructured":"Dhar S, Guo J, Liu J, Tripathi S, Kurup U, Shah M (2020) On-device machine learning: an algorithms and learning theory perspective. 1911.00623"},{"key":"3489_CR15","doi-asserted-by":"crossref","unstructured":"Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115\u2013118. http:\/\/dx.doi.org\/10.1038\/nature21056, letter","DOI":"10.1038\/nature21056"},{"issue":"4","key":"3489_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3017994","volume":"43","author":"S Filippone","year":"2017","unstructured":"Filippone S, Cardellini V, Barbieri D, Fanfarillo A (2017) Sparse matrix-vector multiplication on GPGPUs. ACM Trans Math Softw 43(4):1\u201349. https:\/\/doi.org\/10.1145\/3017994","journal-title":"ACM Trans Math Softw"},{"key":"3489_CR17","doi-asserted-by":"crossref","unstructured":"Golub GH, Van\u00a0Loan CF (2012) Matrix computations, vol\u00a03. JHU Press","DOI":"10.56021\/9781421407944"},{"key":"3489_CR18","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, http:\/\/www.deeplearningbook.org"},{"key":"3489_CR19","unstructured":"Grimes RG, Kincaid DR, Young DM (1979) ITPACK 2.0 user\u2019s guide. Center for Numerical Analysis, The University of Texas at Austin"},{"key":"3489_CR20","unstructured":"Grossman M, Thiele C, Araya-Polo M, Frank F, Alpak FO, Sarkar V (2016) A survey of sparse matrix-vector multiplication performance on large matrices. ArXiv abs\/1608.00636"},{"issue":"5","key":"3489_CR21","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.1109\/TPDS.2013.123","volume":"25","author":"P Guo","year":"2014","unstructured":"Guo P, Wang L, Chen P (2014) A performance modeling and optimization analysis tool for sparse matrix-vector multiplication on GPUs. IEEE Trans Parallel Distrib Syst 25(5):1112\u20131123. https:\/\/doi.org\/10.1109\/TPDS.2013.123","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"1","key":"3489_CR22","doi-asserted-by":"publisher","first-page":"C72","DOI":"10.1137\/140956026","volume":"37","author":"C Janna","year":"2015","unstructured":"Janna C, Ferronato M, Gambolati G (2015) The use of supernodes in factored sparse approximate inverse preconditioning. SIAM J Sci Comput 37(1):C72\u2013C94. https:\/\/doi.org\/10.1137\/140956026","journal-title":"SIAM J Sci Comput"},{"key":"3489_CR23","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. CoRR abs\/1412.6980,"},{"key":"3489_CR24","unstructured":"Kirk DB, Wen-Mei WH (2016) Programming massively parallel processors: a hands-on approach. Morgan kaufmann"},{"key":"3489_CR25","doi-asserted-by":"crossref","unstructured":"Kreutzer M, Hager G, Wellein G, Fehske H, Basermann A, Bishop AR (2012) Sparse matrix-vector multiplication on GPGPU clusters: a new storage format and a scalable implementation. In: Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW), 2012 IEEE 26th International, IEEE, pp 1696\u20131702","DOI":"10.1109\/IPDPSW.2012.211"},{"issue":"1","key":"3489_CR26","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/TPDS.2014.2308221","volume":"26","author":"K Li","year":"2015","unstructured":"Li K, Yang W, Li K (2015) Performance analysis and optimization for SpMV on GPU using probabilistic modeling. IEEE Trans Parallel Distrib Syst 26(1):196\u2013205. https:\/\/doi.org\/10.1109\/TPDS.2014.2308221","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"2","key":"3489_CR27","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/s11227-012-0825-3","volume":"63","author":"R Li","year":"2013","unstructured":"Li R, Saad Y (2013) GPU-accelerated preconditioned iterative linear solvers. J Supercomput 63(2):443\u2013466. https:\/\/doi.org\/10.1007\/s11227-012-0825-3","journal-title":"J Supercomput"},{"issue":"1","key":"3489_CR28","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s10994-011-5273-4","volume":"87","author":"L van der Maaten","year":"2012","unstructured":"van der Maaten L, Hinton G (2012) Visualizing non-metric similarities in multiple maps. Mach Learn 87(1):33\u201355. https:\/\/doi.org\/10.1007\/s10994-011-5273-4","journal-title":"Mach Learn"},{"key":"3489_CR29","unstructured":"Maaten Lvd, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(Nov):2579\u20132605"},{"key":"3489_CR30","unstructured":"Mehmood R, Crowcroft J (2005) Parallel iterative solution method for large sparse linear equation systems. University of Cambridge, Computer Laboratory"},{"key":"3489_CR31","unstructured":"Mohammed T (2017) A novel deep learning based iterative solver for large sparse linear equation systems. Master\u2019s thesis, King Abdulaziz University. https:\/\/kaupp.sa\/Details\/Thesis\/133000"},{"issue":"5","key":"3489_CR32","doi-asserted-by":"publisher","first-page":"947","DOI":"10.3390\/app9050947","volume":"9","author":"T Muhammed","year":"2019","unstructured":"Muhammed T, Mehmood R, Albeshri A, Katib I (2019) SURAA: a novel method and tool for loadbalanced and coalesced SpMV computations on GPUs. Appl Sci 9(5):947. https:\/\/doi.org\/10.3390\/app9050947","journal-title":"Appl Sci"},{"key":"3489_CR33","doi-asserted-by":"publisher","unstructured":"Nisa I, Siegel C, Rajam AS, Vishnu A, Sadayappan P (2018) Effective machine learning based format selection and performance modeling for SpMV on GPUs. In: 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp 1056\u20131065. https:\/\/doi.org\/10.1109\/IPDPSW.2018.00164","DOI":"10.1109\/IPDPSW.2018.00164"},{"key":"3489_CR34","doi-asserted-by":"publisher","unstructured":"Saad Y, van der Vorst HA (2000) Iterative solution of linear systems in the 20th century. J Comput Appl Math 123(1\u20132):1\u201333. https:\/\/doi.org\/10.1016\/S0377-0427(00)00412-X, http:\/\/www.sciencedirect.com\/science\/article\/pii\/ S037704270000412X, numerical Analysis 2000. Vol. III: Linear Algebra","DOI":"10.1016\/S0377-0427(00)00412-X"},{"key":"3489_CR35","doi-asserted-by":"publisher","unstructured":"Sedaghati N, Mu T, Pouchet LN, Parthasarathy S, Sadayappan P (2015) Automatic selection of sparse matrix representation on GPUs. In: Proceedings of the 29th ACM on International Conference on Supercomputing, ACM, New York, NY, USA, ICS \u201915, pp 99\u2013108. https:\/\/doi.org\/10.1145\/2751205.2751244","DOI":"10.1145\/2751205.2751244"},{"key":"3489_CR36","doi-asserted-by":"publisher","unstructured":"Tan G, Liu J, Li J (2018) Design and implementation of adaptive SpMV library for multicore and many-core architecture. ACM Trans Math Softw 44(4). https:\/\/doi.org\/10.1145\/3218823","DOI":"10.1145\/3218823"},{"key":"3489_CR37","doi-asserted-by":"publisher","first-page":"81279","DOI":"10.1109\/ACCESS.2019.2923565","volume":"7","author":"S Usman","year":"2019","unstructured":"Usman S, Mehmood R, Katib I, Albeshri A (2019a) ZAKI+: a machine learning based process mapping tool for SpMV computations on distributed memory architectures. IEEE Access 7:81279\u201381296. https:\/\/doi.org\/10.1109\/ACCESS.2019.2923565","journal-title":"IEEE Access"},{"key":"3489_CR38","doi-asserted-by":"crossref","unstructured":"Usman S, Mehmood R, Katib I, Albeshri A, Altowaijri S (2019b) ZAKI: a smart method and tool for automatic performance optimization of parallel SpMV computations on distributed memory machines. Mobile Netw Appl","DOI":"10.1007\/s11036-019-01318-3"},{"key":"3489_CR39","doi-asserted-by":"publisher","unstructured":"Usman S, Mehmood R, Katib I (2020) Big data and HPC convergence for smart infrastructures: a review and proposed architecture. Springer International Publishing, Cham, pp 561\u2013586. https:\/\/doi.org\/10.1007\/978-3-030-13705-2_23","DOI":"10.1007\/978-3-030-13705-2_23"},{"key":"3489_CR40","doi-asserted-by":"publisher","unstructured":"Verschoor M, Jalba AC (2012) Analysis and performance estimation of the Conjugate Gradient method on multiple GPUs. Parallel Comput 38(10\u201311):552\u2013575. https:\/\/doi.org\/10.1016\/j.parco.2012.07.002, http:\/\/www.sciencedirect.com\/science\/article\/pii\/ S0167819112000609","DOI":"10.1016\/j.parco.2012.07.002"},{"key":"3489_CR41","doi-asserted-by":"crossref","unstructured":"Zardoshti P, Khunjush F, Sarbazi-Azad H (2015) Adaptive sparse matrix representation for efficient matrix\u2013vector multiplication. J Supercomput pp 1\u201321","DOI":"10.1007\/s11227-015-1571-0"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03489-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-020-03489-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03489-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,14]],"date-time":"2023-10-14T07:26:25Z","timestamp":1697268385000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-020-03489-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,30]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["3489"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03489-3","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,30]]},"assertion":[{"value":"23 October 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 November 2020","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}