{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T16:33:06Z","timestamp":1754152386336,"version":"3.41.2"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,7]]},"DOI":"10.1145\/3735358.3735369","type":"proceedings-article","created":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T23:08:27Z","timestamp":1752793707000},"page":"114-120","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Miniature: Fast AI Supercomputer Networks Simulation on FPGAs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2815-6408","authenticated-orcid":false,"given":"Yicheng","family":"Qian","sequence":"first","affiliation":[{"name":"Northeastern University, Boston, USA and Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2021-4917","authenticated-orcid":false,"given":"Ran","family":"Shu","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9611-5870","authenticated-orcid":false,"given":"Rui","family":"Ma","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7322-4062","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6762-4527","authenticated-orcid":false,"given":"Derek","family":"Chiou","sequence":"additional","affiliation":[{"name":"UT Austin, Austin, USA and Microsoft, Redmond, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9071-6621","authenticated-orcid":false,"given":"Nadeen","family":"Gebara","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0094-4960","authenticated-orcid":false,"given":"Luca","family":"Piccolboni","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5624-056X","authenticated-orcid":false,"given":"Miriam","family":"Leeser","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4175-0097","authenticated-orcid":false,"given":"Yongqiang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. The Beating Heart of the World\u2019s First Exascale Supercomputer - IEEE Spectrum. https:\/\/spectrum.ieee.org\/frontier-exascale-supercomputer."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Mohammad Alizadeh Adel Javanmard and Balaji Prabhakar. 2011. Analysis of DCTCP: stability convergence and fairness. ACM SIGMETRICS Performance Evaluation Review 39 1 (2011) 73\u201384.","DOI":"10.1145\/1993744.1993753"},{"key":"e_1_3_3_2_4_2","unstructured":"AMD. 2023. AMD Alveo U280 Data Center Accelerator Card User Guide. https:\/\/docs.amd.com\/r\/en-US\/ug1314-alveo-u280-reconfig-accel\/Introduction."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629574"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/1592681.1592693"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/2342356.2342426"},{"key":"e_1_3_3_2_8_2","unstructured":"P4 Consortium. 2024. P4 \u2013 Language Consortium. https:\/\/p4.org\/."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Miquel Ferriol-Galm\u00e9s Jordi Paillisse Jos\u00e9 Su\u00e1rez-Varela Krzysztof Rusek Shihan Xiao Xiang Shi Xiangle Cheng Pere Barlet-Ros and Albert Cabellos-Aparicio. 2023. RouteNet-Fermi: Network modeling with graph neural networks. IEEE\/ACM transactions on networking 31 6 (2023) 3080\u20133095.","DOI":"10.1109\/TNET.2023.3269983"},{"key":"e_1_3_3_2_10_2","first-page":"51","volume-title":"15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Firestone Daniel","year":"2018","unstructured":"Daniel Firestone, Andrew Putnam, Sambhrama Mundkur, Derek Chiou, Alireza Dabagh, Mike Andrewartha, Hari Angepat, Vivek Bhanu, Adrian Caulfield, Eric Chung, et\u00a0al. 2018. Azure accelerated networking: SmartNICs in the public cloud. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18). 51\u201366."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0M Fujimoto. 1990. Parallel discrete event simulation. Commun. ACM 33 10 (1990) 30\u201353.","DOI":"10.1145\/84537.84545"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604844"},{"key":"e_1_3_3_2_14_2","volume-title":"2024 International Conference on Field Programmable Technology (ICFPT)","author":"Han Zhaoyang","year":"2024","unstructured":"Zhaoyang Han, Yicheng Qian, Michael Zink, and Miriam Leeser. 2024. Memory-efficient Sketch Acceleration for Handling Large Network Flows on FPGAs. In 2024 International Conference on Field Programmable Technology (ICFPT). To appear. Preprint available at https:\/\/arxiv.org\/abs\/2504.16896."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293924"},{"key":"e_1_3_3_2_16_2","unstructured":"IEEE. 2010. 802.1Qbb \u2013 Priority-based Flow Control. https:\/\/1.ieee802.org\/dcb\/802-1qbb\/. [Accessed 27-06-2024]."},{"key":"e_1_3_3_2_17_2","unstructured":"Sylvain Jeaugey. 2019. Massively Scale Your Deep Learning Training with NCCL 2.4 | NVIDIA Technical Blog. https:\/\/developer.nvidia.com\/blog\/massively-scale-deep-learning-training-nccl-2-4\/."},{"key":"e_1_3_3_2_18_2","first-page":"745","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024, Santa Clara, CA, April 15-17, 2024","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, and Xin Liu. 2024. MegaScale: Scaling Large Language Model Training to More Than 10, 000 GPUs. In 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024, Santa Clara, CA, April 15-17, 2024, Laurent Vanbever and Irene Zhang (Eds.). USENIX Association, 745\u2013760. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/jiang-ziheng"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00014"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3286062.3286083"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934897"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672243"},{"key":"e_1_3_3_2_23_2","unstructured":"OpenSim Ltd. 2024. OMNeT++ Discrete Event Simulator. https:\/\/omnetpp.org\/."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Rui Ma Jia-Ching Hsu Ali Mansoorshahi Joseph Garvey Michael Kinsner Deshanand Singh and Derek Chiou. 2024. Primate: A Framework to Automatically Generate Soft Processors for Network Applications. IEEE Computer Architecture Letters 23 1 (2024) 57\u201360. https:\/\/doi.org\/10.1109\/LCA.2024.3358839","DOI":"10.1109\/LCA.2024.3358839"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/347059.347421"},{"key":"e_1_3_3_2_26_2","unstructured":"nsnam. 2024. ns-3 | a discrete-event network simulator for internet systems. https:\/\/www.nsnam.org\/."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/MEMCOD.2011.5970513"},{"key":"e_1_3_3_2_28_2","unstructured":"Dylan Patel and Daniel Nishball. 2024. 100k H100 Clusters: Power Network Topology Ethernet vs InfiniBand Reliability Failures Checkpointing. https:\/\/www.semianalysis.com\/p\/100000-h100-clusters-power-network."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Krzysztof Rusek Jos\u00e9 Su\u00e1rez-Varela Paul Almasan Pere Barlet-Ros and Albert Cabellos-Aparicio. 2020. RouteNet: Leveraging graph neural networks for network modeling and optimization in SDN. IEEE Journal on Selected Areas in Communications 38 10 (2020) 2260\u20132270.","DOI":"10.1109\/JSAC.2020.3000405"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2018.00019"},{"key":"e_1_3_3_2_32_2","unstructured":"Martin Treiber. 2023. The Secrets of GPT-4 Leaked? https:\/\/www.ikangai.com\/the-secrets-of-gpt-4-leaked\/. [Accessed 27-06-2024]."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3050220.3050234"},{"key":"e_1_3_3_2_34_2","first-page":"541","volume-title":"USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Wang Xizheng","year":"2025","unstructured":"Xizheng Wang, Qingxu Li, Yichi Xu, Gang Lu, Dan Li, Li Chen, Heyang Zhou, Linkang Zheng, Sen Zhang, Yikai Zhu, et\u00a0al. 2025. SimAI: Unifying Architecture Design and Performance Tunning for Large-Scale Large Language Model Training with Scalability and Precision. In USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). 541\u2013558."},{"key":"e_1_3_3_2_35_2","unstructured":"xAI. 2025. Grok 3 Beta \u2014 The Age of Reasoning Agents. https:\/\/x.ai\/news\/grok-3."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544248"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Hui Zhang. 1995. Service disciplines for guaranteed performance service in packet-switching networks. Proc. IEEE 83 10 (1995) 1374\u20131396.","DOI":"10.1109\/5.469298"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472926"},{"key":"e_1_3_3_2_39_2","first-page":"685","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Zhao Kevin","year":"2023","unstructured":"Kevin Zhao, Prateesh Goyal, Mohammad Alizadeh, and Thomas\u00a0E Anderson. 2023. Scalable tail latency estimation for data center networks. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 685\u2013702."}],"event":{"name":"APNET 2025: The 9th Asia-Pacific Workshop on Networking","acronym":"APNET 2025","location":"Shang Hai China"},"container-title":["Proceedings of the 9th Asia-Pacific Workshop on Networking"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3735358.3735369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T05:09:22Z","timestamp":1753160962000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3735358.3735369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":38,"alternative-id":["10.1145\/3735358.3735369","10.1145\/3735358"],"URL":"https:\/\/doi.org\/10.1145\/3735358.3735369","relation":{},"subject":[],"published":{"date-parts":[[2025,8,6]]},"assertion":[{"value":"2025-08-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}