{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:44:12Z","timestamp":1787017452411,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731098","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T12:43:11Z","timestamp":1750423391000},"page":"835-848","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Zettafly: A Network Topology with Flexible Non-blocking Regions for Large-scale AI and HPC Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6243-8479","authenticated-orcid":false,"given":"Dezun","family":"Dong","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6074-1199","authenticated-orcid":false,"given":"Ziyu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8614-933X","authenticated-orcid":false,"given":"Fei","family":"Lei","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2014. Fujitsu Laboratories Develops Technology to Reduce Network Switches in Cluster Supercomputers by 40%. https:\/\/www.fujitsu.com\/global\/about\/resources\/news\/press-releases\/2014\/0715-02.html"},{"key":"e_1_3_3_2_3_2","unstructured":"2023. DualToR Evolution: Active Active DualToR. https:\/\/drive.google.com\/file\/d\/1RtYYk1JHv7WnyABrUVj7FiRMZu2KEYtL\/view"},{"key":"e_1_3_3_2_4_2","unstructured":"2023. Meta\u2019s evolution of network for AI - presented by Meta. https:\/\/www.youtube.com\/watch?v=5gOOtFySrqA"},{"key":"e_1_3_3_2_5_2","unstructured":"2023. NVIDIA DGX SuperPOD. https:\/\/docs.nvidia.com\/https:\/docs.nvidia.com\/dgx-superpod-reference-architecture-dgx-h100.pdf"},{"key":"e_1_3_3_2_6_2","unstructured":"2024. 200G QSFP56 Transceiver. https:\/\/vitextech.com\/product\/200g-qsfp56\/"},{"key":"e_1_3_3_2_7_2","unstructured":"2024. AcmeTrace. https:\/\/github.com\/InternLM\/AcmeTrace"},{"key":"e_1_3_3_2_8_2","unstructured":"2024. Argonne Leadership Computing Facility. https:\/\/reports.alcf.anl.gov\/data\/index.html"},{"key":"e_1_3_3_2_9_2","unstructured":"2024. NVIDIA Ethernet Networking Accelerates World\u2019s Largest AI Supercomputer Built by xAI. Retrieved October 28 2024 from https:\/\/nvidianews.nvidia.com\/news\/spectrum-x-ethernet-networking-xai-colossus"},{"key":"e_1_3_3_2_10_2","unstructured":"2024. Polaris. https:\/\/www.alcf.anl.gov\/polaris"},{"key":"e_1_3_3_2_11_2","unstructured":"2024. QM8700 InfiniBand Series. https:\/\/www.nvidia.com\/en-au\/networking\/infiniband\/qm8700\/"},{"key":"e_1_3_3_2_12_2","unstructured":"2024. Theta\/ThetaGPU. https:\/\/www.alcf.anl.gov\/alcf-resources\/theta"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654101"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607089"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.34"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3275463"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00025"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356215"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356196"},{"key":"e_1_3_3_2_21_2","series-title":"(SC \u201920)","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"De\u00a0Sensi Daniele","year":"2020","unstructured":"Daniele De\u00a0Sensi, Salvatore Di\u00a0Girolamo, Kim\u00a0H. McMahon, Duncan Roweth, and Torsten Hoefler. 2020. An in-depth analysis of the slingshot interconnect. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (Atlanta, Georgia) (SC \u201920). IEEE Press, Article 35, 14\u00a0pages."},{"key":"e_1_3_3_2_22_2","series-title":"(SC \u201912)","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","author":"Faanes Greg","year":"2012","unstructured":"Greg Faanes, Abdulla Bataineh, Duncan Roweth, Tom Court, Edwin Froese, Bob Alverson, Tim Johnson, Joe Kopnick, Mike Higgins, and James Reinhard. 2012. Cray cascade: a scalable HPC system based on a Dragonfly network. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (Salt Lake City, Utah) (SC \u201912). IEEE Computer Society Press, Washington, DC, USA, Article 103, 9\u00a0pages."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593732"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-92040-5_15"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.78"},{"key":"e_1_3_3_2_26_2","series-title":"(SC \u201922)","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","author":"Hoefler Torsten","year":"2022","unstructured":"Torsten Hoefler, Tommaso Bonato, Daniele De\u00a0Sensi, Salvatore Di\u00a0Girolamo, Shigang Li, Marco Heddes, Jon Belk, Deepak Goel, Miguel Castro, and Steve Scott. 2022. HammingMesh: a network topology for large-scale deep learning. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (Dallas, Texas) (SC \u201922). IEEE Press, Article 11, 18\u00a0pages."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Torsten Hoefler Ariel Hendel and Duncan Roweth. 2022. The Convergence of Hyperscale Data Center and High-Performance Computing Networks. Computer 55 7 (2022) 29\u201337. 10.1109\/MC.2022.3158437","DOI":"10.1109\/MC.2022.3158437"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.5555\/3691825.3691864"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555783"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3431379.3460650"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527389"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807652"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250679"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2008.19"},{"key":"e_1_3_3_2_36_2","series-title":"(SC \u201922)","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","author":"Lakhotia Kartik","year":"2022","unstructured":"Kartik Lakhotia, Maciej Besta, Laura Monroe, Kelly Isham, Patrick Iff, Torsten Hoefler, and Fabrizio Petrini. 2022. PolarFly: a cost-effective and flexible low-diameter topology. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (Dallas, Texas) (SC \u201922). IEEE Press, Article 12, 15\u00a0pages."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626183.3659975"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392747"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926275"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356151"},{"key":"e_1_3_3_2_41_2","series-title":"(OSDI\u201920)","volume-title":"Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation","author":"Narayanan Deepak","year":"2020","unstructured":"Deepak Narayanan, Keshav Santhanam, Fiodar Kazhamiaka, Amar Phanishayee, and Matei Zaharia. 2020. Heterogeneity-aware cluster scheduling policies for deep learning workloads. In Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation(OSDI\u201920). USENIX Association, USA, Article 27, 18\u00a0pages."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPINEB.2017.11"},{"key":"e_1_3_3_2_44_2","volume-title":"Load-balanced routing in interconnection networks","author":"Singh Arjun","year":"2005","unstructured":"Arjun Singh. 2005. Load-balanced routing in interconnection networks. Stanford University."},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Leslie\u00a0G. Valiant. 1982. A scheme for fast parallel communication. SIAM journal on computing 11 2 (1982) 350\u2013361.","DOI":"10.1137\/0211027"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Mark Wade Erik Anderson Shahab Ardalan Pavan Bhargava Sidney Buchbinder Michael L.\u00a0Davenport John Fini Haiwei Lu Chen Li Roy Meade Chandru Ramamurthy Michael Rust Forrest Sedgwick Vladimir Stojanovic Derek Van\u00a0Orden Chong Zhang Chen Sun Sergey\u00a0Y. Shumarayev Conor O\u2019Keeffe Tim\u00a0T. Hoang David Kehlet Ravi\u00a0V. Mahajan Matthew\u00a0T. Guzy Allen Chan and Tina Tran. 2020. TeraPHY: A Chiplet Technology for Low-Power High-Bandwidth In-Package Optical I\/O. IEEE Micro 40 2 (2020) 63\u201371. 10.1109\/MM.2020.2976067","DOI":"10.1109\/MM.2020.2976067"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593711"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386367.3431307"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Yuyang Wang Dezun Dong and Fei Lei. 2022. Understanding node connection modes in Multi-Rail Fat-tree. J. Parallel and Distrib. Comput. 167 (2022) 199\u2013210. 10.1016\/j.jpdc.2022.04.019","DOI":"10.1016\/j.jpdc.2022.04.019"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056051"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Ke Wu Dezun Dong and Weixia Xu. 2024. COER: A Network Interface Offloading Architecture for RDMA and Congestion Control Protocol Codesign. ACM Trans. Archit. Code Optim. 21 3 Article 49 (Sept. 2024) 26\u00a0pages. 10.1145\/3660525","DOI":"10.1145\/3660525"},{"key":"e_1_3_3_2_52_2","series-title":"(OSDI\u201920)","volume-title":"Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation","author":"Xiao Wencong","year":"2020","unstructured":"Wencong Xiao, Shiru Ren, Yong Li, Yang Zhang, Pengyang Hou, Zhi Li, Yihui Feng, Wei Lin, and Yangqing Jia. 2020. AntMan: dynamic scaling on GPU clusters for deep learning. In Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation(OSDI\u201920). USENIX Association, USA, Article 30, 16\u00a0pages."},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787484"}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","location":"Tokyo Japan","acronym":"SIGARCH '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T07:04:30Z","timestamp":1750489470000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731098"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":52,"alternative-id":["10.1145\/3695053.3731098","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731098","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}