{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T18:47:12Z","timestamp":1768070832534,"version":"3.49.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"crossref","award":["732631"],"award-info":[{"award-number":["732631"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100006112","name":"Microsoft Research","doi-asserted-by":"crossref","award":["MRL contract number 2017-044"],"award-info":[{"award-number":["MRL contract number 2017-044"]}],"id":[{"id":"10.13039\/100006112","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2019,4,1]]},"DOI":"10.1109\/tc.2018.2876312","type":"journal-article","created":{"date-parts":[[2018,10,22]],"date-time":"2018-10-22T19:48:23Z","timestamp":1540237703000},"page":"484-497","source":"Crossref","is-referenced-by-count":52,"title":["A Scalable Near-Memory Architecture for Training Deep Neural Networks on Large In-Memory Datasets"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9923-5031","authenticated-orcid":false,"given":"Fabian","family":"Schuiki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3244-2693","authenticated-orcid":false,"given":"Michael","family":"Schaffner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank K.","family":"Gurkaynak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Benini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Artificial Intelligence Architecture | NVIDIA Volta","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744788"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2017.8050809"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2967011"},{"key":"ref31","article-title":"Average price of electricity to ultimate customers by end-use sector","year":"2017"},{"key":"ref30","article-title":"Measuring ddr4 power consumption","author":"angelini","year":"2014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001178"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1145\/2644865.2541967","article-title":"DianNao: A small-footprint high-throughput accelerator for ubiquitous machine-learning","volume":"49","author":"chen","year":"2014","journal-title":"ACM SIGPLAN Notices"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2682138"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2011.7477494"},{"key":"ref40","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2016"},{"key":"ref11","year":"2017"},{"key":"ref12","article-title":"Deep Learning Benchmarks of NVIDIA Tesla P100 PCIe, Tesla K80, and Tesla M40 GPUs","author":"murphy","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2016.2574353"},{"key":"ref14","first-page":"1740","article-title":"Flexpoint: An adaptive numerical format for efficient training of deep neural networks","author":"k\u00f6ster","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/378239.379016"},{"key":"ref17","article-title":"Thermal feasibility of die-stacked processing in memory","author":"eckert","year":"2014","journal-title":"Workshop on Near-Data Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2016.7936173"},{"key":"ref28","article-title":"Information technology – Data centres – Key performance indicators – Part 2: Power usage effectiveness (PUE)","year":"2016"},{"key":"ref4","first-page":"19","article-title":"Design and evaluation of a processing-in-memory architecture for the smart memory cube","author":"azarkhish","year":"2016","journal-title":"Proc 29th Int Conf Archit Comput Syst"},{"key":"ref27","article-title":"Deep image: Scaling up image recognition","author":"wu","year":"2015"},{"key":"ref3","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2017.2654506"},{"key":"ref29","article-title":"Machine learning applications for data center optimization","author":"gao","year":"2014","journal-title":"Google Inc White Paper"},{"key":"ref5","article-title":"Hybrid memory cube specification 2.1","year":"2015"},{"key":"ref8","article-title":"FD-SOI–Harnessing the power & a little spelunking into PPA","author":"tewell","year":"2016","journal-title":"53rd Des Automat Conf"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2752706"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref9","article-title":"IEDM 2013 preview","author":"davis","year":"2013"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref20","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref24","article-title":"CNN-benchmarks","author":"johnson","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967940"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1816038.1815998"},{"key":"ref25","article-title":"Optimizing performance of recurrent neural networks on GPUs","author":"appleyard","year":"2016"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/8664420\/08502059.pdf?arnumber=8502059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:06:47Z","timestamp":1657746407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8502059\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,1]]},"references-count":41,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tc.2018.2876312","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,1]]}}}