{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T04:40:49Z","timestamp":1786509649071,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Research Council (ERC)","award":["101287293"],"award-info":[{"award-number":["101287293"]}]},{"name":"Federal Ministry of Research, Technology and Space (BMFTR)","award":["16DII141"],"award-info":[{"award-number":["16DII141"]}]},{"name":"National Science Foundation (NSF)","award":["2551372"],"award-info":[{"award-number":["2551372"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3829181","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"160-176","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Trivance: Latency-Optimal AllReduce by Shortcutting Multiport Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3194-9002","authenticated-orcid":false,"given":"Anton","family":"Juerss","sequence":"first","affiliation":[{"name":"Weizenbaum Institut Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0577-0413","authenticated-orcid":false,"given":"Vamsi","family":"Addanki","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7798-1711","authenticated-orcid":false,"given":"Stefan","family":"Schmid","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/762761.762787"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1088149.1088183"},{"key":"e_1_3_2_1_3_1","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, et al. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877\u20131901."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/181014.181756"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441620"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750499"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1122971.1122975"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00033"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.10.010"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532380"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698535"},{"key":"e_1_3_2_1_12_1","unstructured":"Google Cloud. 2026. TPU 8t and TPU 8i: Technical Deep Dive. Retrieved 2026-07-03 from https:\/\/cloud.google.com\/blog\/products\/compute\/tpu-8t-and-tpu-8i-technical-deep-dive"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(06)80021-9"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3623490"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810093"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.4018\/jdst.2010040104"},{"key":"e_1_3_2_1_17_1","unstructured":"Sylvain Jeaugey. 2025. PAT: a new algorithm for all-gather and reduce-scatter operations at scale. arXiv:2506.20252 [cs.DC] https:\/\/arxiv.org\/abs\/2506.20252"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2021.102812"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3789240.3822611"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750514"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672249"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"e_1_3_2_1_25_1","unstructured":"Rolf Rabenseifner. 2004. Automatic MPI counter profiling of all users: First results on a CRAY T3E 900-512. https:\/\/api.semanticscholar.org\/CorpusID:55365541"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24685-5_1"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2017.08.004"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2686882"},{"key":"e_1_3_2_1_29_1","volume-title":"Swing: Short-cutting Rings for Higher Bandwidth Allreduce. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Sensi Daniele De","year":"2024","unstructured":"Daniele De Sensi, Tommaso Bonato, David Saam, and Torsten Hoefler. 2024. Swing: Short-cutting Rings for Higher Bandwidth Allreduce. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, 1445\u20131462."},{"key":"e_1_3_2_1_30_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Shah Aashaka","year":"2023","unstructured":"Aashaka Shah, Vijay Chidambaram, Meghan Cowan, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Jacob Nelson, Olli Saarikivi, and Rachee Singh. 2023. TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, 593\u2013612."},{"key":"e_1_3_2_1_31_1","volume-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053","author":"Shoeybi Mohammad","year":"2019","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053 (2019)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00037"},{"key":"e_1_3_2_1_33_1","volume-title":"Google Cloud","author":"Vahdat Amin","year":"2023","unstructured":"Amin Vahdat and Mark Lohmeyer. 2023. Enabling next-generation AI workloads: Announcing TPU v5p and AI Hypercomputer. Google Cloud, December 6 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"TopoOpt: Co-optimizing Network Topology and Parallelization Strategy for Distributed Training Jobs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Wang Weiyang","year":"2023","unstructured":"Weiyang Wang, Moein Khazraee, Zhizhen Zhong, Manya Ghobadi, Zhihao Jia, Dheevatsa Mudigere, Ying Zhang, and Anthony Kewitsch. 2023. TopoOpt: Co-optimizing Network Topology and Parallelization Strategy for Distributed Training Jobs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, 739\u2013767."},{"key":"e_1_3_2_1_35_1","unstructured":"Liangyu Zhao Siddharth Pal Tapan Chugh Weiyang Wang Jason Fantl Prithwish Basu Joud Khoury and Arvind Krishnamurthy. 2025. Efficient Direct-Connect Topologies for Collective Communications. arXiv:2202.03356 [cs.NI]"},{"key":"e_1_3_2_1_36_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Zu Yazhou","year":"2024","unstructured":"Yazhou Zu, Alireza Ghaffarkhah, Hoang-Vu Dang, Brian Towles, Steven Hand, Safeen Huda, Adekunle Bello, Alexander Kolbasov, Arash Rezaei, Dayou Du, Steve Lacy, Hang Wang, Aaron Wisner, Chris Lewis, and Henri Bahini. 2024. Resiliency at Scale: Managing Google's TPUv4 Machine Learning Supercomputer. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 761\u2013774. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/zu"}],"event":{"name":"SIGCOMM '26: ACM SIGCOMM 2026 Conference","location":"Colorado Convention Center Denver CO USA","acronym":"SIGCOMM '26","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2026 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3789240.3829181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:35:44Z","timestamp":1786473344000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3829181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":36,"alternative-id":["10.1145\/3789240.3829181","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3829181","relation":{},"subject":[],"published":{"date-parts":[[2026,8,11]]},"assertion":[{"value":"2026-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}