{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T08:28:18Z","timestamp":1786523298478,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["CCF-2338077"],"award-info":[{"award-number":["CCF-2338077"]}]},{"name":"NNSA","award":["DE-NA0003966"],"award-info":[{"award-number":["DE-NA0003966"]}]},{"name":"DOE U.S. Department of Energy\/NNSA","award":["NA0003525"],"award-info":[{"award-number":["NA0003525"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767393","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:18:44Z","timestamp":1762532324000},"page":"479-488","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Scaling All-to-All Operations Across Emerging Many-Core Supercomputers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6583-7789","authenticated-orcid":false,"given":"Shannon Gayle","family":"Kinkead","sequence":"first","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, USA and University of New Mexico, Albuquerque, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4036-0442","authenticated-orcid":false,"given":"Jackson","family":"Wesley","sequence":"additional","affiliation":[{"name":"University of New Mexico, Albuquerque, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4955-2984","authenticated-orcid":false,"given":"Whit","family":"Schonbein","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-2811","authenticated-orcid":false,"given":"David","family":"DeBonis","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory (LANL), Los Alamos, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5141-9176","authenticated-orcid":false,"given":"Matthew","family":"Dosanjh","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8891-934X","authenticated-orcid":false,"given":"Amanda","family":"Bienz","sequence":"additional","affiliation":[{"name":"University of New Mexico, Albuquerque, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3555819.3555825"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Amanda Bienz William\u00a0D. Gropp and Luke\u00a0N. Olson. 2019. Node aware sparse matrix\u2013vector multiplication. J. Parallel and Distrib. Comput. 130 (2019) 166\u2013178. 10.1016\/j.jpdc.2019.03.016","DOI":"10.1016\/j.jpdc.2019.03.016"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ExaMPI49596.2019.00008"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"J. Bruck Ching-Tien Ho S. Kipnis E. Upfal and D. Weathersby. 1997. Efficient algorithms for all-to-all communications in multiport message-passing systems. IEEE Transactions on Parallel and Distributed Systems 8 11 (1997) 1143\u20131156. 10.1109\/71.642949","DOI":"10.1109\/71.642949"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00014"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624111"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2024.10528936"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2966884.2966919"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00032"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2010.5470853"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Qiao Kang Sunwoo Lee Kaiyuan Hou Robert Ross Ankit Agrawal Alok Choudhary and Wei-keng Liao. 2020. Improving MPI Collective I\/O for High Volume Non-Contiguous Requests With Intra-Node Aggregation. IEEE Transactions on Parallel and Distributed Systems 31 11 (2020) 2682\u20132695. 10.1109\/TPDS.2020.3000458","DOI":"10.1109\/TPDS.2020.3000458"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid51090.2021.00021"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.91"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Teng Ma George Bosilca Aurelien Bouteiller and Jack\u00a0J Dongarra. 2013. Kernel-assisted and topology-aware MPI collective communications on multicore\/many-core platforms. J. Parallel and Distrib. Comput. 73 7 (2013) 1000\u20131010.","DOI":"10.1016\/j.jpdc.2013.01.015"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2016.139"},{"key":"e_1_3_3_2_17_2","unstructured":"Evelyn Namugwanya Amanda Bienz Derek Schafer and Anthony Skjellum. 2023. Collective-Optimized FFTs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.16589 (2023)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145823"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607103"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2014.32"},{"key":"e_1_3_3_2_21_2","unstructured":"Jesper\u00a0Larsson Tr\u00e4ff. 2019. Decomposing Collectives for Exploiting Multi-lane Communication. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1910.13373 (2019)."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2642769.2642770"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-07312-0_1"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03770-2_41"}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/full\/10.1145\/3731599.3767393","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767393","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T07:41:05Z","timestamp":1786520465000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767393"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":23,"alternative-id":["10.1145\/3731599.3767393","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767393","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}