{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T12:40:50Z","timestamp":1769863250078,"version":"3.49.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["2023YFB3001904"],"award-info":[{"award-number":["2023YFB3001904"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A6007"],"award-info":[{"award-number":["U23A6007"]}],"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":[[2026,3]]},"DOI":"10.1109\/tpds.2025.3650515","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:54Z","timestamp":1767638514000},"page":"651-665","source":"Crossref","is-referenced-by-count":0,"title":["SMEStencil: Optimizing High-Order Stencils on ARM Multicore Using SME Unit"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8117-4425","authenticated-orcid":false,"given":"Yinuo","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6108-859X","authenticated-orcid":false,"given":"Tianqi","family":"Mao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3486-6016","authenticated-orcid":false,"given":"Lin","family":"Gan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5174-1832","authenticated-orcid":false,"given":"Wubing","family":"Wan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Song","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayu","family":"Fu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lanke","family":"He","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8842-6465","authenticated-orcid":false,"given":"Wenqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"National Supercomputing Center in Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6002-0028","authenticated-orcid":false,"given":"Zekun","family":"Yin","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9740-6581","authenticated-orcid":false,"given":"Wei","family":"Xue","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8673-8254","authenticated-orcid":false,"given":"Guangwen","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The landscape of parallel computing research: A view from Berkeley","volume":"EECS-2006-183","author":"Asanovic","year":"2006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1562764.1562783"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2013.10.026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2010.04.044"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compfluid.2013.12.007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2021.108063"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00043"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/gji\/ggu308"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3613209"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.earscirev.2018.02.008","article-title":"Reverse time migration: A prospect of seismic imaging methodology","volume":"179","author":"Zhou","year":"2018","journal-title":"Earth- Sci. Rev."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2017.02.011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19861-8_13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2467268"},{"key":"ref14","first-page":"1","article-title":"Reducing redundancy in data organization and arithmetic calculation for stencil computations","volume-title":"Proc. SC21, Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Li","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00069"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.103"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00049"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WOLFHPC.2016.08"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370316"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WOLFHPC.2016.06"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3271060"},{"key":"ref23","article-title":"Comparison of the effectiveness of shared memory optimizations for stencil computations on nvidia GPU architectures","author":"Verweij","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2014.7040968"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SYNASC.2014.70"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00073"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC.2018.00009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356210"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441598"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532392"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638476"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/sc41406.2024.00059"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3725798.3725803"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00035"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.jcp.2019.05.022","article-title":"Dispersion analysis of finite difference and discontinuous Galerkin schemes for Maxwell\u2019s equations in linear lorentz media","volume":"394","author":"Jiang","year":"2019","journal-title":"J. Comput. Phys."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/75.553055"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011180613990"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1190\/1.1444009"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1190\/segam2012-0128.1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1190\/geo2015-0384.1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/070693199"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063398"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3168824"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3368826.3377904"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593716"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00089"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11368703\/11328920.pdf?arnumber=11328920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T21:05:18Z","timestamp":1769807118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11328920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":47,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2025.3650515","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":[[2026,3]]}}}