{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T08:03:00Z","timestamp":1773734580141,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007000","name":"Laboratory Directed Research and Development","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007000","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Science Foundation","award":["CCF-2119069"],"award-info":[{"award-number":["CCF-2119069"]}]},{"name":"National Science Foundation","award":["CCF-2119352"],"award-info":[{"award-number":["CCF-2119352"]}]},{"name":"National Science Foundation","award":["CCF-2028851"],"award-info":[{"award-number":["CCF-2028851"]}]},{"name":"National Science Foundation","award":["CCF-2028921"],"award-info":[{"award-number":["CCF-2028921"]}]},{"name":"National Science Foundation","award":["CCF-2028958"],"award-info":[{"award-number":["CCF-2028958"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpds.2026.3661876","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:52:14Z","timestamp":1770411134000},"page":"1032-1047","source":"Crossref","is-referenced-by-count":0,"title":["Practical Machine Learning Autotuning for Large-Scale Collective Communication"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0806-1599","authenticated-orcid":false,"given":"Michael","family":"Wilkins","sequence":"first","affiliation":[{"name":"Cornelis Networks, Inc, Wayne, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3731-5423","authenticated-orcid":false,"given":"Yanfei","family":"Guo","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5532-3048","authenticated-orcid":false,"given":"Rajeev","family":"Thakur","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Dinda","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikos","family":"Hardavellas","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Efficient training of large language models on distributed infrastructures: A survey","author":"Duan","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PDP62718.2024.00020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00036"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2000.10024"},{"key":"ref5","first-page":"26","article-title":"Flexible collective communication tuning architecture applied to Open MPI","volume-title":"Proc. Euro PVM\/MPI","author":"Fagg","year":"2006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-007-0012-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2007.06.005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87475-1_30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS.2018.8641622"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ExaMPI54564.2021.00010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176345462"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2006.311904"},{"key":"ref16","article-title":"The MVAPICH project: Evolution and sustainability of an open source production quality MPI library for HPC","volume-title":"Proc. Workshop Sustain. Softw. Sci.: Pract. Experiences, held Conjunction Int\u2019l Conf. Supercomputing","author":"Panda","year":"2013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00033"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2018.00014"},{"issue":"1","key":"ref20","first-page":"1625","article-title":"Confidence intervals for random forests: The Jackknife and the infinitesimal Jackknife","volume":"15","author":"Wager","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3526967"},{"key":"ref22","article-title":"High performance computing application i\/o traces. in lawrence livermore national laboratory (LLNL) open data initiative","author":"Wang","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3093338.3093385"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref25","article-title":"OSU micro-benchmarks","year":"2002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1063\/5.0005188"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/mnras\/staf444"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1017\/pasa.2018.25"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPPS.1999.760522"},{"key":"ref31","article-title":"Accurate runtime selection of optimal MPI collective algorithms using analytical performance modelling","author":"Nuriyev","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER59578.2024.00017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW63119.2024.00141"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW63119.2024.00140"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00037"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06040-w"},{"key":"ref37","article-title":"Optimal parameters determination for the execution of MPI applications on parallel architectures","author":"Sartori","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1183401.1183431"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS56514.2022.00016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3149457.3149461"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2896993"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03770-2_26"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2015.29"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-019-02917-1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00035"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IC2EW.2016.35"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/11434582\/11373210-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11434582\/11373210.pdf?arnumber=11373210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:45:14Z","timestamp":1773726314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11373210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":43,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2026.3661876","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}