{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:47:44Z","timestamp":1768031264500,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&#x0026;D Program of China","award":["2022YFB4501702"],"award-info":[{"award-number":["2022YFB4501702"]}]},{"name":"Excellent Youth Foundation of Hunan Province","award":["2021JJ10050"],"award-info":[{"award-number":["2021JJ10050"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972408"],"award-info":[{"award-number":["61972408"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872294"],"award-info":[{"award-number":["61872294"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tpds.2024.3350368","type":"journal-article","created":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T20:14:19Z","timestamp":1704917659000},"page":"439-454","source":"Crossref","is-referenced-by-count":7,"title":["Optimizing Full-Spectrum Matrix Multiplications on ARMv8 Multi-Core CPUs"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7167-4086","authenticated-orcid":false,"given":"Weiling","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3542-4869","authenticated-orcid":false,"given":"Jianbin","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6243-8479","authenticated-orcid":false,"given":"Dezun","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7514-1495","authenticated-orcid":false,"given":"Xing","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7858-6238","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwest University, Xi&#x2019;an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.83"},{"key":"ref2","first-page":"1","article-title":"High performance convolutional neural networks for document processing","volume-title":"Proc. 10th Int. Workshop Front. Handwriting Recognit.","author":"Chellapilla"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00032"},{"key":"ref5","first-page":"684","article-title":"Model-driven level 3 BLAS performance optimization on loongson 3A processor","volume-title":"Proc. IEEE 18th Int. Conf. Parallel Distrib. Syst.","author":"Zhang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1377603.1377607"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.29"},{"issue":"4","key":"ref10","first-page":"43:1","article-title":"SCP: Shared cache partitioning for high-performance GEMM","volume":"15","author":"Su","year":"2019","journal-title":"ACM Trans. Architecture Code Optim."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330355"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014118"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2021.02.013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3210754"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3378671"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2016.7936203"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00051"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-020-0741-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS48598.2019.9188171"},{"key":"ref27","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476217"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2925987"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/1094342020965661"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178496"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2939785"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.110"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01454-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446759"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.06.033"},{"key":"ref39","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. 14th USENIX Conf. Operating Syst. Des. Implementation","author":"Zheng"},{"key":"ref40","article-title":"The MOMMS family of matrix multiplication algorithms","author":"Smith","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807673"},{"key":"ref43","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref44","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref45","first-page":"55:1","article-title":"Designing vector-friendly compact BLAS and LAPACK kernels","volume-title":"Proc. Int. Conf. High Perform. Comput. Netw. Storage Anal.","author":"Kim"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545032"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99372-6_7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2018.10.003"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SC.1998.10004"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10411979\/10387717.pdf?arnumber=10387717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T23:42:43Z","timestamp":1707867763000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10387717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":44,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2024.3350368","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":[[2024,3]]}}}