{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T15:06:46Z","timestamp":1764688006948,"version":"3.37.3"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpds.2022.3171471","type":"journal-article","created":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T19:42:59Z","timestamp":1651261379000},"page":"3800-3815","source":"Crossref","is-referenced-by-count":12,"title":["Design and Implementation of 2D Convolution on x86\/x64 Processors"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9591-913X","authenticated-orcid":false,"given":"Vasilios","family":"Kelefouras","sequence":"first","affiliation":[{"name":"School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0460-6061","authenticated-orcid":false,"given":"Georgios","family":"Keramidas","sequence":"additional","affiliation":[{"name":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2021","article-title":"Intel intrinsics guide","key":"ref33"},{"year":"2019","author":"meng","article-title":"Efficient winograd convolution via integer arithmetic","key":"ref32"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/TPDS.2010.70"},{"year":"2021","article-title":"OneAPI deep neural network library (OneDNN)","key":"ref30"},{"year":"2021","author":"fog","article-title":"Optimizing subroutines in assembly language. An optimization guide for x86 platforms","key":"ref34"},{"year":"2021","article-title":"Developer reference for Intel OneAPI math kernel library - C","key":"ref10"},{"year":"2021","article-title":"Developer reference for Intel OneAPI math kernel library - C","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/AISP.2017.8324097"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/MVIP49855.2020.9116883"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/2508148.2485925"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1145\/3290420.3290444"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CVPRW.2019.00175"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1016\/j.future.2018.01.048"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1145\/2568058.2568067"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.3390\/app8081235"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/IPDPSW50202.2020.00097"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1007\/978-3-030-57675-2_16"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/HPEC43674.2020.9286183"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/IJCNN.2019.8852012"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1145\/3178487.3178496"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1145\/3404397.3404407"},{"key":"ref5","first-page":"615","article-title":"Deep tensor convolution on multicores","volume":"70","author":"budden","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/IISWC.2006.302723"},{"year":"2018","author":"zhang","article-title":"High performance zero-memory overhead direct convolutions","key":"ref7"},{"year":"2019","author":"dukhan","article-title":"The indirect convolution algorithm","key":"ref2"},{"year":"2021","article-title":"Image filtering functions","key":"ref9"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/SC.2018.00069"},{"key":"ref20","article-title":"IIR Gaussian blur filter implementation using Intel advanced vector extensions","author":"bharti","year":"2015","journal-title":"Intel Tech Rep"},{"key":"ref22","first-page":"1230","article-title":"High performance 2D convolution utilizing the avx512on a multi-core architecture","volume":"43","author":"isamail","year":"2021","journal-title":"Songklanakarin J Sci Technol"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/IPDPSW.2013.207"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1007\/s11227-013-1049-x"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1609\/aaai.v29i1.9488"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1145\/3140582.3081039"},{"year":"2021","author":"narendra","article-title":"Efficient and generic 1D dilated convolution layer for deep learning","key":"ref25"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9790018\/09765671.pdf?arnumber=9765671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T19:50:04Z","timestamp":1661197804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9765671\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":34,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2022.3171471","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}