{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T04:05:27Z","timestamp":1746763527773,"version":"3.40.5"},"reference-count":12,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":[[2025,3]]},"DOI":"10.1109\/mm.2025.3534638","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:37:36Z","timestamp":1738089456000},"page":"26-35","source":"Crossref","is-referenced-by-count":0,"title":["Unified Collective Communication: A Unified Library for CPU, GPU, and DPU Collectives"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5282-1682","authenticated-orcid":false,"given":"Manjunath Gorentla","family":"Venkata","sequence":"first","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1551-3048","authenticated-orcid":false,"given":"Valentine","family":"Petrov","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0881-7299","authenticated-orcid":false,"given":"Sergey","family":"Lebedev","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4638-2456","authenticated-orcid":false,"given":"Devendar","family":"Bureddy","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4208-6493","authenticated-orcid":false,"given":"Ferrol","family":"Aderholdt","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7956-1387","authenticated-orcid":false,"given":"Joshua","family":"Ladd","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6224-9802","authenticated-orcid":false,"given":"Gil","family":"Bloch","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4388-7084","authenticated-orcid":false,"given":"Mike","family":"Dubman","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9318-9620","authenticated-orcid":false,"given":"Gilad","family":"Shainer","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]}],"member":"263","reference":[{"volume-title":"UCC specification","year":"2025","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/sc41405.2020.00039"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/mlhpc.2016.004"},{"article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","year":"2017","author":"Goyal","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ccgrid.2011.42"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/comhpc.2016.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"volume-title":"MiniAMR - A miniapp for adaptive mesh refinement","year":"2016","author":"Sasidharan","key":"ref8"},{"article-title":"Communication-efficient distributed deep learning: A comprehensive survey","year":"2020","author":"Tang","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/hoti63208.2024.00018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cluster.2013.6702676"},{"article-title":"On optimizing the communication of model parallelism","year":"2022","author":"Zhuang","key":"ref12"}],"container-title":["IEEE Micro"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/40\/10989057\/10856352.pdf?arnumber=10856352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T17:38:41Z","timestamp":1746725921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10856352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":12,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/mm.2025.3534638","relation":{},"ISSN":["0272-1732","1937-4143"],"issn-type":[{"type":"print","value":"0272-1732"},{"type":"electronic","value":"1937-4143"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}