{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:28:24Z","timestamp":1781022504962,"version":"3.54.1"},"reference-count":16,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Micro"],"published-print":{"date-parts":[[2021,5,1]]},"DOI":"10.1109\/mm.2021.3066343","type":"journal-article","created":{"date-parts":[[2021,3,17]],"date-time":"2021-03-17T20:14:00Z","timestamp":1616012040000},"page":"10-18","source":"Crossref","is-referenced-by-count":14,"title":["The Vision Behind MLPerf: Understanding AI Inference Performance"],"prefix":"10.1109","volume":"41","author":[{"given":"Vijay Janapa","family":"Reddi","sequence":"first","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christine","family":"Cheng","sequence":"additional","affiliation":[{"name":"Intel, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Kanter","sequence":"additional","affiliation":[{"name":"MLCommons, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5984-238X","authenticated-orcid":false,"given":"Peter","family":"Mattson","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guenther","family":"Schmuelling","sequence":"additional","affiliation":[{"name":"Microsoft Corp, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9032-7239","authenticated-orcid":false,"given":"Carole-Jean","family":"Wu","sequence":"additional","affiliation":[{"name":"Facebook Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"MLPerf training benchmark","author":"mattson","year":"0","journal-title":"Proc 3rd Conf Mach Learn Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2974843"},{"key":"ref12","article-title":"Deep learning recommendation model for personalization and recommendation systems","author":"naumov","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref14","article-title":"MLPerf mobile inference benchmark: Why mobile AI benchmarking is hard and what to do about it","author":"reddi","year":"0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref16","article-title":"Developing a recommendation benchmark for MLPerf training and inference","author":"wu","year":"2020"},{"key":"ref4","article-title":"Benchmarking TinyML systems: Challenges and direction","author":"banbury","year":"0"},{"key":"ref3","article-title":"A new version of the PTDaemon tool is now available","year":"0"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019"},{"key":"ref5","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00047"},{"key":"ref2","article-title":"Machine learning innovation to benefit everyone","author":"mlcommons","year":"2020"},{"key":"ref1","article-title":"Introducing the next generation of on-device vision models: MobileNetV3 and MobileNetEdgeTPU","year":"2019"},{"key":"ref9","article-title":"Google’s multilingual neural machine translation system: Enabling zero-shot translation","author":"johnson","year":"2017"}],"container-title":["IEEE Micro"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/40\/9440735\/09380984.pdf?arnumber=9380984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:57Z","timestamp":1652194257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9380984\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,1]]},"references-count":16,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/mm.2021.3066343","relation":{},"ISSN":["0272-1732","1937-4143"],"issn-type":[{"value":"0272-1732","type":"print"},{"value":"1937-4143","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,1]]}}}