{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T18:02:02Z","timestamp":1784656922719,"version":"3.55.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102141"],"award-info":[{"award-number":["62102141"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/tpds.2023.3277915","type":"journal-article","created":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T17:49:06Z","timestamp":1684518546000},"page":"2167-2179","source":"Crossref","is-referenced-by-count":4,"title":["COFFEE: Cross-Layer Optimization for Fast and Efficient Executions of Sinkhorn-Knopp Algorithm on HPC Systems"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1175-4081","authenticated-orcid":false,"given":"Chengyu","family":"Sun","sequence":"first","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2392-0267","authenticated-orcid":false,"given":"Huizhang","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1477-9751","authenticated-orcid":false,"given":"Hong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering Department, University of Texas at Arlington, Arlington, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7411-8923","authenticated-orcid":false,"given":"Jeff","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2635-7716","authenticated-orcid":false,"given":"Kenli","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Foresight of graph reinforcement learning latent permutations learnt by gumbel sinkhorn network","author":"shen","year":"2021"},{"key":"ref35","article-title":"Intel® intrinsics guide","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/gji\/ggw014"},{"key":"ref34","article-title":"Performance of SSE and AVX instruction sets","author":"jeong","year":"2012"},{"key":"ref15","first-page":"10039","article-title":"Sequential cooperative Bayesian inference","author":"wang","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-016-1779-7"},{"key":"ref14","first-page":"4869","article-title":"Supervised word mover's distance","author":"huang","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126954"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00057"},{"key":"ref30","author":"von luxburg","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00045"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1273442.1250746"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/060659624"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-010-0383-x"},{"key":"ref2","first-page":"1","article-title":"POT: Python optimal transport","volume":"22","author":"flamary","year":"2021","journal-title":"J Mach Learn Res"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703591"},{"key":"ref17","first-page":"2257","article-title":"Faster wasserstein distance estimation with the sinkhorn divergence","volume":"33","author":"chizat","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00019"},{"key":"ref16","first-page":"1367","article-title":"Computational optimal transport: Complexity by accelerated gradient descent is better than by sinkhorn's algorithm","author":"dvurechensky","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","first-page":"144","article-title":"Implication of inter-node and intra-node contention in creating large throughput photonic networks","author":"sato","year":"2014","journal-title":"Proc Int Conf Opt Netw Des Model"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662426"},{"key":"ref18","article-title":"A new parallel algorithm for sinkhorn word-movers distance and its performance on PIUMA and xeon CPU","author":"tithi","year":"2021"},{"key":"ref24","first-page":"1961","article-title":"Near-linear time approximation algorithms for optimal transport via sinkhorn iteration","author":"altschuler","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2213977.2214056"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF02242355"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3210754"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.31"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2017.2753825"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476217"},{"key":"ref28","first-page":"172","article-title":"Blink: Fast and generic collectives for distributed ML","volume":"2","author":"wang","year":"2020","journal-title":"Proc Mach Learn Syst"},{"key":"ref27","first-page":"216","article-title":"Hierarchical distributed-memory multi-leader MPI-allreduce for deep learning workloads","author":"nguyen","year":"2018","journal-title":"Proc IEEE 6th Int Symp Comput Netw Workshops"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IPCCC47392.2019.8958738"},{"key":"ref8","first-page":"7673","article-title":"On unbalanced optimal transport: An analysis of sinkhorn algorithm","author":"pham","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2615921"},{"key":"ref9","first-page":"2681","article-title":"Interpolating between optimal transport and MMD using sinkhorn divergences","author":"feydy","year":"2019","journal-title":"Proc 22nd Int Conf Artif Intell Statist"},{"key":"ref4","first-page":"1","article-title":"Sinkhorn networks: Using optimal transport techniques to learn permutations","volume":"3","author":"mena","year":"2017","journal-title":"Proc NIPS Workshop Optimal Transport Mach Learn"},{"key":"ref3","article-title":"Sinkhorn distances: Lightspeed computation of optimal transportation distances","author":"cuturi","year":"2013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2140\/pjm.1967.21.343"},{"key":"ref40","article-title":"GPU kernels for block-sparse weights","author":"gray","year":"2017"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10132303\/10129913.pdf?arnumber=10129913","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:50:40Z","timestamp":1687805440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10129913\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":41,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3277915","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":[[2023,7]]}}}