{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T14:32:53Z","timestamp":1780410773899,"version":"3.54.1"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpds.2023.3322037","type":"journal-article","created":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T17:46:00Z","timestamp":1696441560000},"page":"3104-3116","source":"Crossref","is-referenced-by-count":6,"title":["Design and Implementation of Deep Learning 2D Convolutions on Modern CPUs"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9591-913X","authenticated-orcid":false,"given":"Vasilios","family":"Kelefouras","sequence":"first","affiliation":[{"name":"Department of Computing, Plymouth University, Plymouth, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0460-6061","authenticated-orcid":false,"given":"Georgios","family":"Keramidas","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering & Informatics, Aristoteleio Panepistemio Thessalonikes, Thessaloniki, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3171471"},{"key":"ref12","article-title":"High performance zero-memory overhead direct convolutions","author":"zhang","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3211346.3211354"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2010.70"},{"key":"ref11","article-title":"The indirect convolution algorithm","author":"dukhan","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178496"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IC3IOT53935.2022.9767990"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"ref17","article-title":"Ansor: Generating high-performance tensor programs for deep learning","author":"zheng","year":"2020","journal-title":"Proc 14th USENIX Conf Operating Syst Des Implementation"},{"key":"ref16","first-page":"579","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"Proc 13th USENIX Conf Operating Syst Des Implementation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3460945.3464955"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446759"},{"key":"ref24","article-title":"Towards effective depthwise convolutions on ARMv8 architecture","author":"hao","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC53243.2021.00029"},{"key":"ref26","article-title":"Performance profiling example","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-022-00734-5"},{"key":"ref20","article-title":"Efficient and generic 1D dilated convolution layer for deep learning","author":"narendra","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3290420.3290444"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW50202.2020.00097"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57675-2_16"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00175"},{"key":"ref9","article-title":"Deep tensor convolution on multicores","author":"budden","year":"2016"},{"key":"ref4","article-title":"Autotuning convolutions is easier than you think","volume":"20","author":"tollenaere","year":"2022","journal-title":"ACM Trans Archit Code Optim"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414655"},{"key":"ref6","article-title":"A survey of model compression and acceleration for deep neural networks","author":"cheng","year":"2017"},{"key":"ref5","article-title":"oneDNN v2.7.0 documentation, understanding memory formats","year":"2022"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10272650\/10271698.pdf?arnumber=10271698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T19:50:58Z","timestamp":1699300258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10271698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":26,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3322037","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}