{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:03:50Z","timestamp":1782950630616,"version":"3.54.5"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T00:00:00Z","timestamp":1684281600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T00:00:00Z","timestamp":1684281600000},"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":[],"published-print":{"date-parts":[[2023,5,17]]},"DOI":"10.1109\/infocom53939.2023.10228956","type":"proceedings-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T17:40:43Z","timestamp":1693330843000},"page":"1-10","source":"Crossref","is-referenced-by-count":21,"title":["Enabling Switch Memory Management for Distributed Training with In-Network Aggregation"],"prefix":"10.1109","author":[{"given":"Bohan","family":"Zhao","sequence":"first","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbo","family":"Dong","sequence":"additional","affiliation":[{"name":"Alibaba Group,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Cao","sequence":"additional","affiliation":[{"name":"Alibaba Group,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Nie","sequence":"additional","affiliation":[{"name":"Shenzhen University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenfei","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/BigCom51056.2020.00029"},{"key":"ref35","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","author":"jeon","year":"2019","journal-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2017.7947053"},{"key":"ref34","article-title":"Imagenet is an image database organized according to the wordnet hierarchy","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref37","first-page":"829","article-title":"In-network aggregation for shared machine learning clusters","volume":"3","author":"gebara","year":"2021","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"ref31","article-title":"Scaling distributed machine learning with in-network aggregation","author":"sapio","year":"2019"},{"key":"ref30","article-title":"Flexpipe","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934888"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2377677.2377710"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2377677.2377709"},{"key":"ref32","first-page":"155","article-title":"NetVRM: Virtual register memory for programmable networks","author":"zhu","year":"2022","journal-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)"},{"key":"ref2","article-title":"Language models are few-shot learners","author":"brown","year":"2020"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486422"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"ref16","first-page":"289","article-title":"Themis: Fair and efficient GPU cluster scheduling","author":"mahajan","year":"2020","journal-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI20)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476178"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322259"},{"key":"ref18","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","author":"lao","year":"0"},{"key":"ref24","article-title":"Barefoot tofino","year":"2020"},{"key":"ref23","first-page":"829","article-title":"In-network aggregation for shared machine learning clusters","volume":"3","author":"gebara","year":"2021","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486978"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362719"},{"key":"ref20","article-title":"Network-accelerated distributed machine learning using mlfabric","author":"viswanathan","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"ref21","article-title":"Netreduce: Rdma-compatible in-network reduction for distributed dnn training acceleration","author":"liu","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626334"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2931558"},{"key":"ref29","article-title":"One silicon, one experience, multiple roles","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2377677.2377710"},{"key":"ref7","first-page":"721","article-title":"Elastic resource sharing for distributed deep learning","author":"hwang","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2043164.2018443"},{"key":"ref4","article-title":"Deeptraffic: Driving fast through dense traffic with deep reinforcement learning","author":"fridman","year":"2018"},{"key":"ref3","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref6","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.phymed.2018.09.179"},{"key":"ref40","article-title":"Supplement to infiniband architecture specification volume 1 release 1.2.1 annex a17: Rocev2","year":"2014"}],"event":{"name":"IEEE INFOCOM 2023 - IEEE Conference on Computer Communications","location":"New York City, NY, USA","start":{"date-parts":[[2023,5,17]]},"end":{"date-parts":[[2023,5,20]]}},"container-title":["IEEE INFOCOM 2023 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10228851\/10228852\/10228956.pdf?arnumber=10228956","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T17:45:27Z","timestamp":1695059127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10228956\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,17]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/infocom53939.2023.10228956","relation":{},"subject":[],"published":{"date-parts":[[2023,5,17]]}}}