{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T05:36:15Z","timestamp":1706765775642},"reference-count":12,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021,1,1]]},"DOI":"10.1109\/mm.2020.3039835","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T02:51:40Z","timestamp":1606272700000},"page":"15-22","source":"Crossref","is-referenced-by-count":2,"title":["Distributed Deep Learning With GPU-FPGA Heterogeneous Computing"],"prefix":"10.1109","volume":"41","author":[{"given":"Kenji","family":"Tanaka","sequence":"first","affiliation":[{"name":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Arikawa","sequence":"additional","affiliation":[{"name":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsuyoshi","family":"Ito","sequence":"additional","affiliation":[{"name":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazutaka","family":"Morita","sequence":"additional","affiliation":[{"name":"NTT Software Innovation Center, NTT Corporation, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naru","family":"Nemoto","sequence":"additional","affiliation":[{"name":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiko","family":"Terada","sequence":"additional","affiliation":[{"name":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junji","family":"Teramoto","sequence":"additional","affiliation":[{"name":"NTT Software Innovation Center, NTT Corporation, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takeshi","family":"Sakamoto","sequence":"additional","affiliation":[{"name":"NTT Device Technology Labs., NTT Corporation, Kanagawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126970"},{"key":"ref3","article-title":"Developing a linux kernel module using rdma for GPUdirect","year":"2020"},{"key":"ref10","article-title":"NVIDIA Collective Communications Library (NCCL)","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref11","article-title":"InfiniBand In-Network Computing Technology and Roadmap","author":"shainer","year":"2018","journal-title":"BoF SC18"},{"key":"ref5","article-title":"Dissecting the NVIDIA volta GPU architecture via microbenchmarking","author":"jia","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303979"},{"key":"ref8","article-title":"Optimizing network performance for distributed DNN training on GPU clusters: ImageNet\/AlexNet training in 1.5 minutes","author":"sun","year":"2019"},{"key":"ref7","article-title":"Image Classification at Supercomputer Scale","author":"yingm","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"ref9","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"sergeev","year":"2018"},{"key":"ref1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"}],"container-title":["IEEE Micro"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/40\/9336732\/09269435.pdf?arnumber=9269435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:43Z","timestamp":1652194243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9269435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,1]]},"references-count":12,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/mm.2020.3039835","relation":{},"ISSN":["0272-1732","1937-4143"],"issn-type":[{"value":"0272-1732","type":"print"},{"value":"1937-4143","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,1]]}}}