{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:48:33Z","timestamp":1783612113735,"version":"3.55.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["ZERO-ARM P3"],"award-info":[{"award-number":["ZERO-ARM P3"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC05-76RL01830"],"award-info":[{"award-number":["DE-AC05-76RL01830"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1109\/tpds.2022.3217824","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:51:05Z","timestamp":1667523065000},"page":"246-261","source":"Crossref","is-referenced-by-count":53,"title":["Dissecting Tensor Cores via Microbenchmarks: Latency, Throughput and Numeric Behaviors"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2873-6418","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"first","affiliation":[{"name":"Electronic System Group, Eindhoven University of Technology, Eindhoven, AZ, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3734-9137","authenticated-orcid":false,"given":"Ang","family":"Li","sequence":"additional","affiliation":[{"name":"Physical and Computational Sciences Directorate, Pacific Northwest National Laboratory, Richland, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3644-2922","authenticated-orcid":false,"given":"Tong","family":"Geng","sequence":"additional","affiliation":[{"name":"Physical and Computational Sciences Directorate, Pacific Northwest National Laboratory, Richland, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2518-6847","authenticated-orcid":false,"given":"Sander","family":"Stuijk","sequence":"additional","affiliation":[{"name":"Electronic System Group, Eindhoven University of Technology, Eindhoven, AZ, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4506-5732","authenticated-orcid":false,"given":"Henk","family":"Corporaal","sequence":"additional","affiliation":[{"name":"Electronic System Group, Eindhoven University of Technology, Eindhoven, AZ, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926273"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2871189"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2699470"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2018.06.009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.330"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441599"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476157"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293906"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH48897.2020.00029"},{"key":"ref12","first-page":"21099","article-title":"Accelerated sparse neural training: A provable and efficient method to find n: M transposable masks","author":"Hubara","year":"2021","journal-title":"Adv. Neural Informat. Process. Syst."},{"key":"ref13","article-title":"Dissecting the nvidia turing T4 GPU via microbenchmarking","author":"Jia","year":"2019"},{"key":"ref14","article-title":"Dissecting the nvidia volta GPU architecture via microbenchmarking","author":"Jia","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref16","volume-title":"Programming Massively Parallel Processors: A Hands-on Approach","author":"Kirk","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00085"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3045828"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3472473"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10549-5_35"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2549523"},{"key":"ref26","article-title":"Mixed precision training","author":"Micikevicius","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508431"},{"key":"ref28","article-title":"cublas"},{"key":"ref29","article-title":"Cutlass"},{"key":"ref30","article-title":"Nvidia ampere architecture white paper"},{"key":"ref31","article-title":"Nvidia hopper architecture white paper"},{"key":"ref32","article-title":"Nvidia turing architecture white paper"},{"key":"ref33","article-title":"Nvidia volta architecture white paper"},{"key":"ref34","article-title":"Nvidiansight"},{"key":"ref35","article-title":"PTX ISA"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374521"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00016"},{"key":"ref40","first-page":"20721","article-title":"Dominosearch: Find layer-wise fine-grained n: M sparse schemes from dense neural networks","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Sun"},{"key":"ref41","article-title":"TC-GNN: Accelerating sparse graph neural network computation via dense tensor core on GPUs","author":"Wang","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295701"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3090328"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00071"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374520"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018755"},{"key":"ref48","article-title":"Learning N: M fine-grained structured sparse neural networks from scratch","author":"Zhou","year":"2021"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/9956797\/9931992-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9956797\/09931992.pdf?arnumber=9931992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T17:33:48Z","timestamp":1717004028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9931992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":46,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2022.3217824","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":[[2023,1,1]]}}}