{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T18:10:03Z","timestamp":1746727803073,"version":"3.40.5"},"reference-count":19,"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.2025.3547363","type":"journal-article","created":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T18:48:30Z","timestamp":1741200510000},"page":"46-55","source":"Crossref","is-referenced-by-count":0,"title":["Toward a Standardized Representation for Deep Learning Collective Algorithms"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0487-1693","authenticated-orcid":false,"given":"Jinsun","family":"Yoo","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1715-9144","authenticated-orcid":false,"given":"William","family":"Won","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1052-0179","authenticated-orcid":false,"given":"Meghan","family":"Cowan","sequence":"additional","affiliation":[{"name":"Nvidia, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3530-5631","authenticated-orcid":false,"given":"Nan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Nvidia, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7657-3049","authenticated-orcid":false,"given":"Benjamin","family":"Klenk","sequence":"additional","affiliation":[{"name":"Nvidia, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0651-370X","authenticated-orcid":false,"given":"Srinivas","family":"Sridharan","sequence":"additional","affiliation":[{"name":"Nvidia, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5738-6942","authenticated-orcid":false,"given":"Tushar","family":"Krishna","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Huang","year":"2019"},{"key":"ref2","article-title":"ZeRO: Extremely efficient collective communication for giant model training","volume-title":"Proc. 12th Int. Conf. Learn. Representations (ICLR)","author":"Wang","year":"2024"},{"article-title":"Communication-efficient distributed deep learning: A comprehensive survey","year":"2023","author":"Tang","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/isca45697.2020.00085"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/isca52012.2021.00049"},{"key":"ref6","first-page":"785","article-title":"Scaling distributed machine learning with in-network aggregation","volume-title":"Proc. 18th USENIX Symp. Netw. Syst. Des. Implementation (NSDI)","author":"Sapio","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ispass61541.2024.00028"},{"volume-title":"NVIDIA collective communications library (NCCL)","year":"2025","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref10","first-page":"593","article-title":"TACCL: Guiding collective algorithm synthesis using communication sketches","volume-title":"Proc. 20th USENIX Symp. Netw. Syst. Des. Implementation (NSDI)","author":"Shah","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/micro61859.2024.00068"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575724"},{"article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","year":"2020","author":"Shoeybi","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"},{"article-title":"Chakra: Advancing performance benchmarking and co-design using standardized execution traces","year":"2023","author":"Sridharan","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ispass57527.2023.00035"},{"volume-title":"Chakra","year":"2025","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3567955.3567959"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50743-5_3"}],"container-title":["IEEE Micro"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/40\/10989057\/10910230.pdf?arnumber=10910230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T17:38:38Z","timestamp":1746725918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10910230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":19,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/mm.2025.3547363","relation":{},"ISSN":["0272-1732","1937-4143"],"issn-type":[{"type":"print","value":"0272-1732"},{"type":"electronic","value":"1937-4143"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}