{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:56:56Z","timestamp":1772726216406,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Technology &amp; Engineering Solutions of Sandia, LLC"},{"DOI":"10.13039\/100006168","name":"National Nuclear Security Administration","doi-asserted-by":"publisher","award":["DE-NA0003525"],"award-info":[{"award-number":["DE-NA0003525"]}],"id":[{"id":"10.13039\/100006168","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002585","name":"Korea Aerospace University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002585","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,4,1]]},"DOI":"10.1109\/tpds.2021.3104240","type":"journal-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T19:54:07Z","timestamp":1628711647000},"page":"1002-1014","source":"Crossref","is-referenced-by-count":24,"title":["Evaluating Spatial Accelerator Architectures with Tiled Matrix-Matrix Multiplication"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4992-6181","authenticated-orcid":false,"given":"Gordon Euhyun","family":"Moon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9824-1352","authenticated-orcid":false,"given":"Hyoukjun","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6659-3927","authenticated-orcid":false,"given":"Geonhwa","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0974-4001","authenticated-orcid":false,"given":"Prasanth","family":"Chatarasi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5854-409X","authenticated-orcid":false,"given":"Sivasankaran","family":"Rajamanickam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5738-6942","authenticated-orcid":false,"given":"Tushar","family":"Krishna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295734"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840848"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3358198"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2928962"},{"key":"ref30","first-page":"579","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"Proc 12th USENIX Conf Operating Syst Des Implementation (OSDI)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536398"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00087-9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2011.6043234"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2021.3057203"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/292395.292412"},{"key":"ref40","article-title":"Cutlass: Fast linear algebra in cuda c++","author":"kerr","year":"2017","journal-title":"NVIDIA Developer Blog"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1377603.1377607"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492916000076"},{"key":"ref15","article-title":"Amesos2 and Belos: Direct and iterative solvers for large sparse linear systems","volume":"20","author":"bavier","year":"1970","journal-title":"Sci Program"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41321-1_2"},{"key":"ref17","article-title":"Employing multiple levels of parallelism for CFD at large scales on next generation high-performance computing platforms","author":"howard","year":"2018","journal-title":"Proc 10th Int Conf Comput Fluid Dyn"},{"key":"ref18","first-page":"1","article-title":"Designing vector-friendly compact BLAS and LAPACK kernels","author":"kim","year":"2017","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3130218.3130230"},{"key":"ref4","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS46596.2019.8964858"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIC.2018.8502276"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00040"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/SC41405.2020.00062","article-title":"Fast stencil-code computation on a wafer-scale processor","author":"rocki","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173176"},{"key":"ref2","article-title":"Accelerating DNNs with Xilinx alveo accelerator cards.","year":"0"},{"key":"ref9","article-title":"Using the graphcore IPU for traditional HPC applications","author":"louw","year":"2021"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2012.132"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.2172\/1808019","article-title":"Evaluating spatial accelerator architectures with tiled matrix-matrix multiplication","author":"moon","year":"2021"},{"key":"ref25","year":"2020"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/9575177\/9511786-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9575177\/09511786.pdf?arnumber=9511786","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T04:54:19Z","timestamp":1673067259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9511786\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,1]]},"references-count":41,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3104240","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":[[2022,4,1]]}}}