{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:16:50Z","timestamp":1792790210121,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":93,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759838","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:05:39Z","timestamp":1762963539000},"page":"349-367","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["ATLAHS: An Application-centric Network Simulator Toolchain for AI, HPC, and Distributed Storage"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0061-5072","authenticated-orcid":false,"given":"Siyuan","family":"Shen","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2345-473X","authenticated-orcid":false,"given":"Tommaso","family":"Bonato","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3385-8597","authenticated-orcid":false,"given":"Zhiyi","family":"Hu","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9814-0588","authenticated-orcid":false,"given":"Pasquale","family":"Jordan","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8071-2552","authenticated-orcid":false,"given":"Tiancheng","family":"Chen","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-9797","authenticated-orcid":false,"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"[n. d.]. Broadcom htsim repository. https:\/\/github.com\/Broadcom\/csg-htsim. Accessed: 2025-02-13."},{"key":"e_1_3_3_3_3_2","unstructured":"[n. d.]. Ultra Ethernet Consortium. https:\/\/ultraethernet.org\/. Accessed: 2025-01-13."},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"crossref","unstructured":"Helgi Adalsteinsson Scott Cranford David\u00a0A. Evensky Joseph\u00a0P. Kenny Jackson Mayo Ali Pinar and Curtis\u00a0L. Janssen. 2010. A Simulator for Large-Scale Parallel Computer Architectures. Int. J. Distrib. Syst. Technol. 1 2 (April 2010) 57\u201373.","DOI":"10.4018\/jdst.2010040104"},{"key":"e_1_3_3_3_5_2","volume-title":"ROCm Communication Collectives Library (RCCL) Documentation","author":"Inc. Advanced Micro Devices,","year":"2025","unstructured":"Advanced Micro Devices, Inc.2025. ROCm Communication Collectives Library (RCCL) Documentation. https:\/\/rocm.docs.amd.com\/projects\/rccl\/en\/latest\/what-is-rccl.html Accessed: 2025-01-28."},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/215399.215427"},{"key":"e_1_3_3_3_7_2","unstructured":"Jens Axboe. 2005. blktrace: A Block I\/O Tracing Mechanism for Linux. https:\/\/www.kernel.org\/doc\/Documentation\/block\/blktrace.txt. Accessed: February 04 2025; an open\u2010source tool for tracing block I\/O events in Linux."},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"crossref","unstructured":"Tal Ben-Nun and Torsten Hoefler. 2019. Demystifying Parallel and Distributed Deep Learning: An In-depth Concurrency Analysis. ACM Comput. Surv. 52 4 Article 65 (Aug. 2019) 43\u00a0pages.","DOI":"10.1145\/3320060"},{"key":"e_1_3_3_3_9_2","unstructured":"Maciej Besta Julia Barth Eric Schreiber Ales Kubicek Afonso Catarino Robert Gerstenberger Piotr Nyczyk Patrick Iff Yueling Li Sam Houliston Tomasz Sternal Marcin Copik Grzegorz Kwa\u015bniewski J\u00fcrgen M\u00fcller \u0141ukasz Flis Hannes Eberhard Hubert Niewiadomski and Torsten Hoefler. 2025. Reasoning Language Models: A Blueprint. arxiv:https:\/\/arXiv.org\/abs\/2501.11223\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2501.11223"},{"key":"e_1_3_3_3_10_2","unstructured":"Maciej Besta and Torsten Hoefler. 2023. Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis. arxiv:https:\/\/arXiv.org\/abs\/2205.09702\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2205.09702"},{"key":"e_1_3_3_3_11_2","unstructured":"Maciej Besta Marcel Schneider Salvatore\u00a0Di Girolamo Ankit Singla and Torsten Hoefler. 2021. Towards Million-Server Network Simulations on Just a Laptop. arxiv:https:\/\/arXiv.org\/abs\/2105.12663\u00a0[cs.NI] https:\/\/arxiv.org\/abs\/2105.12663"},{"key":"e_1_3_3_3_12_2","unstructured":"Tommaso Bonato Abdul Kabbani Ahmad Ghalayini Michael Papamichael Mohammad Dohadwala Lukas Gianinazzi Mikhail Khalilov Elias Achermann Daniele\u00a0De Sensi and Torsten Hoefler. 2025. REPS: Recycled Entropy Packet Spraying for Adaptive Load Balancing and Failure Mitigation. arxiv:https:\/\/arXiv.org\/abs\/2407.21625\u00a0[cs.NI] https:\/\/arxiv.org\/abs\/2407.21625"},{"key":"e_1_3_3_3_13_2","unstructured":"Tommaso Bonato Abdul Kabbani Daniele\u00a0De Sensi Rong Pan Yanfang Le Costin Raiciu Mark Handley Timo Schneider Nils Blach Ahmad Ghalayini Daniel Alves Michael Papamichael Adrian Caulfield and Torsten Hoefler. 2024. FASTFLOW: Flexible Adaptive Congestion Control for High-Performance Datacenters. arxiv:https:\/\/arXiv.org\/abs\/2404.01630\u00a0[cs.NI] https:\/\/arxiv.org\/abs\/2404.01630"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/PADS.2000.847144"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Henri Casanova Arnaud Giersch Arnaud Legrand Martin Quinson and Fr\u00e9d\u00e9ric Suter. 2025. Lowering entry barriers to developing custom simulators of distributed applications and platforms with SimGrid. Parallel Comput. 123 (2025) 103\u2013125. 10.1016\/j.parco.2025.103125","DOI":"10.1016\/j.parco.2025.103125"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/UKSIM.2008.28"},{"key":"e_1_3_3_3_17_2","first-page":"533","volume-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Chard Abhishek","year":"2018","unstructured":"Abhishek Chard, R.\u00a0G. Dreslinski, Thomas\u00a0F. Wenisch, Greg Ganger, and Andrew\u00a0A. Chien. 2018. On the Diversity of Cluster Workloads and Its Impact on Research Results. In 2018 USENIX Annual Technical Conference (USENIX ATC 18). 533\u2013546. https:\/\/www.pdl.cmu.edu\/ATLAS\/ Includes LANL Mustang, Trinity, and Two Sigma traces."},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC63097.2024.00012"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.69"},{"key":"e_1_3_3_3_20_2","unstructured":"Storage\u00a0Performance Council. 2025. SPC Trace File Format Specification. https:\/\/skulddata.cs.umass.edu\/traces\/storage\/SPC-Traces.pdf. Accessed: 2025-01-22."},{"key":"e_1_3_3_3_21_2","unstructured":"CSCS. [n. d.]. New Research Infrastructure: \u2019Alps\u2019 Supercomputer Inaugurated. Swiss National Supercomputing Center ([n. d.]). https:\/\/www.cscs.ch\/publications\/news\/2024\/new-research-infrastructure-alps-supercomputer-inaugurated"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","unstructured":"Daniele De\u00a0Sensi Tiziano De\u00a0Matteis Konstantin Taranov Salvatore Di\u00a0Girolamo Tobias Rahn and Torsten Hoefler. 2022. Noise in the Clouds: Influence of Network Performance Variability on Application Scalability. Proc. ACM Meas. Anal. Comput. Syst. 6 3 Article 49 (dec 2022) 27\u00a0pages. 10.1145\/3570609","DOI":"10.1145\/3570609"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00039"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","unstructured":"Ewa Deelman Rafael\u00a0Ferreira da Silva Gideon Juve Mats Rynge Karan Vahi and Miron Livny. 2022. WfCommons: A Framework for Enabling Scientific Workflow Research and Development. Future Generation Computer Systems 129 (2022) 166\u2013182. 10.1016\/j.future.2022.01.011","DOI":"10.1016\/j.future.2022.01.011"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","unstructured":"Wolfgang\u00a0E. Denzel Jian Li Peter Walker and Yuho Jin. 2010. A Framework for End-to-End Simulation of High-performance Computing Systems. SIMULATION 86 5-6 (2010) 331\u2013350. 10.1177\/0037549709340840 arXiv:https:\/\/doi.org\/10.1177\/0037549709340840","DOI":"10.1177\/0037549709340840"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","unstructured":"Jiangfei Duan Xiuhong Li Ping Xu Xingcheng Zhang Shengen Yan Yun Liang and Dahua Lin. 2024. Proteus: Simulating the Performance of Distributed DNN Training. IEEE Transactions on Parallel and Distributed Systems 35 10 (2024) 1867\u20131878. 10.1109\/TPDS.2024.3443255","DOI":"10.1109\/TPDS.2024.3443255"},{"key":"e_1_3_3_3_27_2","unstructured":"Jiangfei Duan Shuo Zhang Zerui Wang Lijuan Jiang Wenwen Qu Qinghao Hu Guoteng Wang Qizhen Weng Hang Yan Xingcheng Zhang Xipeng Qiu Dahua Lin Yonggang Wen Xin Jin Tianwei Zhang and Peng Sun. 2024. Efficient Training of Large Language Models on Distributed Infrastructures: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2407.20018\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2407.20018"},{"key":"e_1_3_3_3_28_2","unstructured":"Dror\u00a0G. Feitelson. [n. d.]. The Parallel Workloads Archive. https:\/\/www.cs.huji.ac.il\/labs\/parallel\/workload\/. Accessed: 2025-04-12."},{"key":"e_1_3_3_3_29_2","first-page":"731","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Feng Yinxiao","year":"2024","unstructured":"Yinxiao Feng, Yuchen Wei, Dong Xiang, and Kaisheng Ma. 2024. Evaluating Chiplet-based Large-Scale Interconnection Networks via Cycle-Accurate Packet-Parallel Simulation. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, CA, 731\u2013747. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/feng-yinxiao"},{"key":"e_1_3_3_3_30_2","unstructured":"Mackenzie Ferguson. 2025. Nvidia\u2019s Unstoppable Rise: Dominating the AI Chip Market. OpenTools.ai (2025). https:\/\/opentools.ai\/news\/nvidias-unstoppable-rise-dominating-the-ai-chip-market Accessed: 2025-01-28."},{"key":"e_1_3_3_3_31_2","unstructured":"Luigi Fusco Mikhail Khalilov Marcin Chrapek Giridhar Chukkapalli Thomas Schulthess and Torsten Hoefler. 2024. Understanding Data Movement in Tightly Coupled Heterogeneous Systems: A Case Study with the Grace Hopper Superchip. arxiv:https:\/\/arXiv.org\/abs\/2408.11556\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2408.11556"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","unstructured":"Markus Geimer Felix Wolf Brian J.\u00a0N. Wylie Erika \u00c1brah\u00e1m Daniel Becker and Bernd Mohr. 2010. The Scalasca performance toolset architecture. Concurrency and Computation: Practice and Experience 22 (4 2010) 702\u2013719. Issue 6. 10.1002\/cpe.1556","DOI":"10.1002\/cpe.1556"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS51919.2020.00016"},{"key":"e_1_3_3_3_34_2","first-page":"485","volume-title":"16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Gu Juncheng","year":"2019","unstructured":"Juncheng Gu, Mosharaf Chowdhury, Kang\u00a0G. Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang Liu, and Chuanxiong Guo. 2019. Tiresias: A GPU Cluster Manager for Distributed Deep Learning. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). USENIX Association, Boston, MA, 485\u2013500. https:\/\/www.usenix.org\/conference\/nsdi19\/presentation\/gu"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098825"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Thomas Henderson Sally Floyd and George Riley. 2006. ns3 Project Goals. Workshop on NS-2: the IP Network Simulator. (01 2006). 10.1145\/1190455.1190468","DOI":"10.1145\/1190455.1190468"},{"key":"e_1_3_3_3_37_2","unstructured":"Torsten Hoefler Tommaso Bonato Daniele\u00a0De Sensi Salvatore\u00a0Di Girolamo Shigang Li Marco Heddes Jon Belk Deepak Goel Miguel Castro and Steve Scott. 2022. HammingMesh: A Network Topology for Large-Scale Deep Learning. arxiv:https:\/\/arXiv.org\/abs\/2209.01346\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2209.01346"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.5555\/2401945.2402019"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.12"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/1851476.1851564"},{"key":"e_1_3_3_3_41_2","unstructured":"Torsten Hoefler Karen Schramm Eric Spada Keith Underwood Cedell Alexander Bob Alverson Paul Bottorff Adrian Caulfield Mark Handley Cathy Huang Costin Raiciu Abdul Kabbani Eugene Opsasnick Rong Pan Adee Ran and Rip Sohan. 2025. Ultra Ethernet\u2019s Design Principles and Architectural Innovations. arxiv:https:\/\/arXiv.org\/abs\/2508.08906\u00a0[cs.NI] https:\/\/arxiv.org\/abs\/2508.08906"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2009.70"},{"key":"e_1_3_3_3_43_2","unstructured":"Zhiyi Hu Siyuan Shen Tommaso Bonato Sylvain Jeaugey Cedell Alexander Eric Spada James Dinan Jeff Hammond and Torsten Hoefler. 2025. Demystifying NCCL: An In-depth Analysis of GPU Communication Protocols and Algorithms. arxiv:https:\/\/arXiv.org\/abs\/2507.04786\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2507.04786"},{"key":"e_1_3_3_3_44_2","volume-title":"Intel\u00ae oneAPI Collective Communications Library (oneCCL)","author":"Corporation Intel","year":"2024","unstructured":"Intel Corporation. 2024. Intel\u00ae oneAPI Collective Communications Library (oneCCL). https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/oneapi\/programming-guide\/2024-1\/intel-oneapi-collective-communications-library.html Accessed: 2025-01-28."},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.13"},{"key":"e_1_3_3_3_46_2","unstructured":"Albert\u00a0Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Emma\u00a0Bou Hanna Florian Bressand Gianna Lengyel Guillaume Bour Guillaume Lample L\u00e9lio\u00a0Renard Lavaud Lucile Saulnier Marie-Anne Lachaux Pierre Stock Sandeep Subramanian Sophia Yang Szymon Antoniak Teven\u00a0Le Scao Th\u00e9ophile Gervet Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William\u00a0El Sayed. 2024. Mixtral of Experts. arxiv:https:\/\/arXiv.org\/abs\/2401.04088\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.04088"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","unstructured":"Laxmikant\u00a0V. Kale and Sanjeev Krishnan. 1993. CHARM++: a portable concurrent object oriented system based on C++. SIGPLAN Not. 28 10 (oct 1993) 91\u2013108. 10.1145\/167962.165874","DOI":"10.1145\/167962.165874"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.115"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/11758525_71"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68564-7_9"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","unstructured":"Andreas Kn\u00fcpfer Markus Geimer Johannes Spazier Joseph Schuchart Michael Wagner Dominic Eschweiler and Matthias\u00a0S. M\u00fcller. 2010. A generic attribute extension to OTF and its use for MPI replay. Procedia Computer Science 1 1 (2010) 2115\u20132124. 10.1016\/j.procs.2010.04.237ICCS 2010.","DOI":"10.1016\/j.procs.2010.04.237"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31476-6_7"},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"crossref","unstructured":"Andreas Kn\u00fcpfer Ronny Brendel Holger Brunst Hartmut Mix and Wolfgang\u00a0E Nagel. 2006. LNCS 3992 - Introducing the Open Trace Format (OTF). https:\/\/doi.org\/doi:10.3233\/978-1-61499-041-3-481","DOI":"10.1007\/11758525_71"},{"key":"e_1_3_3_3_54_2","unstructured":"Greg Kramer. 2023. Direct Drive - Azure\u2019s next-generation block storage architecture. https:\/\/storagedeveloper.org\/events\/agenda\/session\/347. [Online]. Accessed: 2024-02-13."},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","unstructured":"Gautam Kumar Nandita Dukkipati Keon Jang Hassan Wassel Xian Wu Behnam Montazeri Yaogong Wang Kevin Springborn Christopher Alfeld Mike Ryan David\u00a0J. Wetherall and Amin Vahdat. 2020. Swift: Delay is Simple and Effective for Congestion Control in the Datacenter. 10.1145\/3387514.3406591","DOI":"10.1145\/3387514.3406591"},{"key":"e_1_3_3_3_56_2","unstructured":"Lawrence Livermore\u00a0National Laboratory. [n. d.]. Lawrence Livermore National Laboratory\u2019s El Capitan verified as world\u2019s fastest supercomputer. LLNL ([n. d.]). https:\/\/www.llnl.gov\/article\/52061\/lawrence-livermore-national-laboratorys-el-capitan-verified-worlds-fastest-supercomputer"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","unstructured":"Tian Li Jie Zhong Ji Liu Wentao Wu and Ce Zhang. 2018. Ease.ml: towards multi-tenant resource sharing for machine learning workloads. Proc. VLDB Endow. 11 5 (Oct. 2018) 607\u2013620. 10.1145\/3177732.3177737","DOI":"10.1145\/3177732.3177737"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342085"},{"key":"e_1_3_3_3_59_2","unstructured":"Ruofan Liang Bingsheng He Shengen Yan and Peng Sun. 2022. A Simulation Platform for Multi-tenant Machine Learning Services on Thousands of GPUs. arxiv:https:\/\/arXiv.org\/abs\/2201.03175\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2201.03175"},{"key":"e_1_3_3_3_60_2","unstructured":"Linux Kernel Documentation. 2025. Extended Berkeley Packet Filter (eBPF). https:\/\/www.kernel.org\/doc\/html\/latest\/bpf\/index.html. Accessed: February 04 2025. eBPF extends the classic BPF mechanism to run sandboxed programs in the Linux kernel for tracing networking and more.."},{"key":"e_1_3_3_3_61_2","first-page":"357","volume-title":"15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)","author":"Lu Yuanwei","year":"2018","unstructured":"Yuanwei Lu, Guo Chen, Bojie Li, Kun Tan, Yongqiang Xiong, Peng Cheng, Jiansong Zhang, Enhong Chen, and Thomas Moscibroda. 2018. Multi-Path Transport for RDMA in Datacenters. In 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18). USENIX Association, Renton, WA, 357\u2013371. https:\/\/www.usenix.org\/conference\/nsdi18\/presentation\/lu"},{"key":"e_1_3_3_3_62_2","volume-title":"Nvidia\u2019s AI market dominance: Can anyone mount a serious challenge?","author":"Maillard Dorian","year":"2024","unstructured":"Dorian Maillard. 2024. Nvidia\u2019s AI market dominance: Can anyone mount a serious challenge?https:\/\/www.techradar.com\/pro\/nvidias-ai-market-dominance-can-anyone-mount-a-serious-challenge Accessed: 2025-01-28."},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","unstructured":"Misbah Mubarak Christopher\u00a0D. Carothers Robert\u00a0B. Ross and Philip Carns. 2017. Enabling Parallel Simulation of Large-Scale HPC Network Systems. IEEE Transactions on Parallel and Distributed Systems 28 1 (2017) 87\u2013100. 10.1109\/TPDS.2016.2543725","DOI":"10.1109\/TPDS.2016.2543725"},{"key":"e_1_3_3_3_64_2","volume-title":"NVIDIA Collective Communications Library (NCCL) Documentation","author":"Corporation NVIDIA","year":"2025","unstructured":"NVIDIA Corporation. 2025. NVIDIA Collective Communications Library (NCCL) Documentation. https:\/\/docs.nvidia.com\/deeplearning\/nccl\/user-guide\/docs\/index.html Accessed: 2025-01-28."},{"key":"e_1_3_3_3_65_2","volume-title":"NVIDIA Nsight Systems","author":"Corporation NVIDIA","year":"2025","unstructured":"NVIDIA Corporation. 2025. NVIDIA Nsight Systems. https:\/\/developer.nvidia.com\/nsight-systems"},{"key":"e_1_3_3_3_66_2","first-page":"761","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Olteanu Vladimir","year":"2022","unstructured":"Vladimir Olteanu, Haggai Eran, Dragos Dumitrescu, Adrian Popa, Cristi Baciu, Mark Silberstein, Georgios Nikolaidis, Mark Handley, and Costin Raiciu. 2022. An edge-queued datagram service for all datacenter traffic. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA, 761\u2013777. https:\/\/www.usenix.org\/conference\/nsdi22\/presentation\/olteanu"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","unstructured":"T.\u00a0V. Pham C. Steger B. Rockel K. Keuler I. Kirchner M. Mertens D. Rieger G. Z\u00e4ngl and B. Fr\u00fch. 2021. ICON in Climate Limited-area Mode (ICON release version 2.6.1): a new regional climate model. Geoscientific Model Development 14 2 (2021) 985\u20131005. 10.5194\/gmd-14-985-2021","DOI":"10.5194\/gmd-14-985-2021"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/1868447.1868457"},{"key":"e_1_3_3_3_70_2","unstructured":"Saeed Rashidi Joongun Park Abhilash Kolluri and Taekyung Heo. 2024. Chakra Execution Trace Collection \u2013 A Comprehensive Guide on Merging PyTorch and Kineto Traces. https:\/\/github.com\/mlcommons\/chakra\/wiki\/Chakra-Execution-Trace-Collection-%E2%80%90-A-Comprehensive-Guide-on-Merging-PyTorch-and-Kineto-Traces. GitHub wiki page last edited on September 24 2024. Accessed on March 26 2025.."},{"key":"e_1_3_3_3_71_2","unstructured":"Thomas Rausch Waldemar Hummer and Vinod Muthusamy. 2020. PipeSim: Trace-driven Simulation of Large-Scale AI Operations Platforms. arxiv:https:\/\/arXiv.org\/abs\/2006.12587\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2006.12587"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391236"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12331-3_2"},{"key":"e_1_3_3_3_74_2","unstructured":"Alastair Robertson and contributors. 2025. bpftrace: A High-Level Tracing Language for Linux. https:\/\/github.com\/iovisor\/bpftrace Version 0.22.1; accessed February 04 2025; licensed under Apache-2.0."},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","unstructured":"Hongzhang Shan Filip Blagojevi\u0107 Seung-Jai Min Paul Hargrove Haoqiang Jin Karl Fuerlinger Alice Koniges and Nicholas\u00a0J. Wright. 2010. A programming model performance study using the NAS parallel benchmarks. Sci. Program. 18 3\u20134 (Aug. 2010) 153\u2013167. 10.1155\/2010\/715637","DOI":"10.1155\/2010\/715637"},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00070"},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"publisher","unstructured":"Sameer\u00a0S. Shende and Allen\u00a0D. Malony. 2006. The Tau Parallel Performance System. The International Journal of High Performance Computing Applications 20 (5 2006) 287\u2013311. Issue 2. 10.1177\/1094342006064482","DOI":"10.1177\/1094342006064482"},{"key":"e_1_3_3_3_78_2","unstructured":"Srinivas Sridharan Taekyung Heo Louis Feng Zhaodong Wang Matt Bergeron Wenyin Fu Shengbao Zheng Brian Coutinho Saeed Rashidi Changhai Man and Tushar Krishna. 2023. Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces. arxiv:https:\/\/arXiv.org\/abs\/2305.14516\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2305.14516"},{"key":"e_1_3_3_3_79_2","unstructured":"sstsimulator. 2025. SST-DUMPI Trace Library. https:\/\/github.com\/sstsimulator\/sst-dumpi. Accessed: 2025-02-14."},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","unstructured":"Chunqiang Tang. 2025. Meta\u2019s Hyperscale Infrastructure: Overview and Insights. Commun. ACM 68 2 (Jan. 2025) 52\u201363. 10.1145\/3701296","DOI":"10.1145\/3701296"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"publisher","unstructured":"A.\u00a0P. Thompson H.\u00a0M. Aktulga R. Berger D.\u00a0S. Bolintineanu W.\u00a0M. Brown P.\u00a0S. Crozier P.\u00a0J. in\u00a0\u2019t Veld A. Kohlmeyer S.\u00a0G. Moore T.\u00a0D. Nguyen R. Shan M.\u00a0J. Stevens J. Tranchida C. Trott and S.\u00a0J. Plimpton. 2022. LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic meso and continuum scales. Comp. Phys. Comm. 271 (2022) 108171. 10.1016\/j.cpc.2021.108171","DOI":"10.1016\/j.cpc.2021.108171"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCMP-UGC.2009.73"},{"key":"e_1_3_3_3_83_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arxiv:https:\/\/arXiv.org\/abs\/2302.13971\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_3_3_84_2","unstructured":"University of Massachusetts Amherst. 2016. UMass Trace Repository: Storage. https:\/\/traces.cs.umass.edu\/docs\/traces\/storage\/. Accessed: 4 February 2025. Copyright \u00a9 2016\u20132024 University of Massachusetts Amherst.."},{"key":"e_1_3_3_3_85_2","first-page":"407","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Vanini Erico","year":"2017","unstructured":"Erico Vanini, Rong Pan, Mohammad Alizadeh, Parvin Taheri, and Tom Edsall. 2017. Let It Flow: Resilient Asymmetric Load Balancing with Flowlet Switching. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). USENIX Association, Boston, MA, 407\u2013420. https:\/\/www.usenix.org\/conference\/nsdi17\/technical-sessions\/presentation\/vanini"},{"key":"e_1_3_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.4108\/ICST.SIMUTOOLS2008.3027"},{"key":"e_1_3_3_3_87_2","unstructured":"Kurt Wagner. [n. d.]. Meta Is Building New $800 Million AI-Focused Data Center in Indiana. Bloomberg ([n. d.]). https:\/\/www.bloomberg.com\/news\/articles\/2024-01-25\/meta-building-new-800-million-ai-focused-data-center-in-indiana?embedded-checkout=true"},{"key":"e_1_3_3_3_88_2","volume-title":"22nd 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, Chen Li, Heyang Zhou, Linkang Zheng, Sen Zhang, Yikai Zhu, Yang Liu, Pengcheng Zhang, Kun Qian, and Kunling He. 2025. SimAI: Unifying Architecture Design and Performance Tunning for Large-Scale Large Language Model Training with Scalability and Precision. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). USENIX Association."},{"key":"e_1_3_3_3_89_2","unstructured":"William Won Taekyung Heo Saeed Rashidi Srinivas Sridharan Sudarshan Srinivasan and Tushar Krishna. 2023. ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale. arxiv:https:\/\/arXiv.org\/abs\/2303.14006\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2303.14006"},{"key":"e_1_3_3_3_90_2","doi-asserted-by":"publisher","unstructured":"Feroz Zahid Ernst\u00a0Gunnar Gran Bartosz Bogda\u0144ski Bj\u00f8rn\u00a0Dag Johnsen and Tor Skeie. 2017. Efficient network isolation and load balancing in multi-tenant HPC clusters. Future Generation Computer Systems 72 (2017) 145\u2013162. 10.1016\/j.future.2016.04.003","DOI":"10.1016\/j.future.2016.04.003"},{"key":"e_1_3_3_3_91_2","unstructured":"Ben Zaitlen. 2021. NVIDIA Tools Extension API: An Annotation Tool for Profiling Code in Python and C\/C++. https:\/\/developer.nvidia.com\/blog\/nvidia-tools-extension-api-nvtx-annotation-tool-for-profiling-code-in-python-and-c-c\/ Accessed: 2025-01-28."},{"key":"e_1_3_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693493"},{"key":"e_1_3_3_3_93_2","first-page":"827","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Zhang Tianqi","year":"2022","unstructured":"Tianqi Zhang, Yanqi Zhang, Yuandong Tian, Lin Ma, Wei Lin, and Bin Cui. 2022. MLaaS in the Wild: Workload Analysis and Scheduling in Large-scale Heterogeneous GPU Clusters. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 827\u2013841. https:\/\/github.com\/alibaba\/clusterdata\/blob\/master\/cluster-trace-gpu-v2020\/README.md"},{"key":"e_1_3_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2004.1303013"}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:34:56Z","timestamp":1773254096000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759838"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":93,"alternative-id":["10.1145\/3712285.3759838","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759838","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"}}]}}