{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T04:06:41Z","timestamp":1747109201855,"version":"3.40.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB4501702"],"award-info":[{"award-number":["2022YFB4501702"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U24B20151","61972408","61872294"],"award-info":[{"award-number":["U24B20151","61972408","61872294"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tc.2025.3543677","type":"journal-article","created":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T18:41:32Z","timestamp":1739990492000},"page":"1829-1843","source":"Crossref","is-referenced-by-count":0,"title":["nDirect2: A High-Performance Library for Direct Convolutions on Multicore CPUs"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7167-4086","authenticated-orcid":false,"given":"Weiling","family":"Yang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2805-0862","authenticated-orcid":false,"given":"Pengyu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3542-4869","authenticated-orcid":false,"given":"Jianbin","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6243-8479","authenticated-orcid":false,"given":"Dezun","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2046-5043","authenticated-orcid":false,"given":"Zhengbin","family":"Pang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6262-7865","authenticated-orcid":false,"given":"Runxi","family":"He","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8364-9793","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2883-6997","authenticated-orcid":false,"given":"Tao","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0317-8192","authenticated-orcid":false,"given":"Chun","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6906-4940","authenticated-orcid":false,"given":"Yonggang","family":"Che","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3183-7228","authenticated-orcid":false,"given":"Jie","family":"Ren","sequence":"additional","affiliation":[{"name":"Shaanxi Normal University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.02325"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2799562.2799641"},{"key":"ref5","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan","year":"2015"},{"year":"2023","key":"ref6","article-title":"oneDNN"},{"year":"2023","key":"ref7","article-title":"Acl"},{"key":"ref8","first-page":"1","article-title":"High performance convolutional neural networks for document processing","volume-title":"Proc. 10th Int. Workshop Front","author":"Chellapilla","year":"2006"},{"year":"2023","key":"ref9","article-title":"Openblas"},{"year":"2023","key":"ref10","article-title":"Intel mkl"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"ref13","first-page":"5771","article-title":"High performance zero-memory overhead direct convolutions","volume-title":"Proc. ICML","author":"Zhang","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538940"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3093336.3037745"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446759"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577435"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3570305"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00032"},{"year":"2023","key":"ref20","article-title":"MXNet"},{"year":"2023","key":"ref21","article-title":"PyTorch"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1145\/3458817.3476206","article-title":"Tensor processing primitives: A programming abstraction for efficiency and portability in deep learning workloads","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal. (SC)","author":"Georganas","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ipdpsw50202.2020.00154"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228858"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071762"},{"key":"ref26","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. OSDI","author":"Zheng","year":"2020"},{"key":"ref27","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. OSDI","author":"Chen","year":"2018"},{"key":"ref28","first-page":"70:1","article-title":"Optimizing direct convolutions on ARM multi-cores","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal. (SC)","author":"Wang","year":"2023"},{"year":"2024","key":"ref29","article-title":"nDIRECT2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref31","first-page":"1","article-title":"Fast training of convolutional networks through FFTs","volume-title":"Proc. ICLR","author":"Mathieu","year":"2014"},{"year":"2023","key":"ref32","article-title":"XNNPACK"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.83"},{"issue":"4","key":"ref34","first-page":"43:1","article-title":"SCP: Shared cache partitioning for high-performance GEMM","volume-title":"ACM TACO","volume":"15","author":"Su","year":"2019"},{"key":"ref35","article-title":"Intel Xeon Gold 6252N"},{"article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"ref36"},{"key":"ref37","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"year":"2023","key":"ref39","article-title":"Kunpeng-920"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS48598.2019.9188171"},{"year":"2023","key":"ref41","article-title":"Raspberry-pi-4-model-b"},{"article-title":"Yolov3: An incremental improvement","year":"2018","author":"Redmon","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-85665-6_15"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071018"},{"article-title":"Bolt: Bridging the gap between auto-tuners and hardware-native performance","volume-title":"Proc. MLSys","author":"Xing","key":"ref45"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/10994769\/10892335.pdf?arnumber=10892335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T17:43:55Z","timestamp":1747071835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10892335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":45,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tc.2025.3543677","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"type":"print","value":"0018-9340"},{"type":"electronic","value":"1557-9956"},{"type":"electronic","value":"2326-3814"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}