{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T15:30:27Z","timestamp":1773588627197,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","funder":[{"name":"NSF (National Science Foundation)","award":["2444537"],"award-info":[{"award-number":["2444537"]}]},{"name":"NSF (National Science Foundation)","award":["2139899"],"award-info":[{"award-number":["2139899"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,22]]},"DOI":"10.1145\/3779212.3790238","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:55:26Z","timestamp":1773150926000},"page":"1547-1565","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reconfigurable Torus Fabrics for Multi-tenant ML"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6599-3996","authenticated-orcid":false,"given":"Abhishek","family":"Vijaya Kumar","sequence":"first","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0232-9821","authenticated-orcid":false,"given":"Eric","family":"Ding","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2866-9824","authenticated-orcid":false,"given":"Arjun","family":"Devraj","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8218-5656","authenticated-orcid":false,"given":"Darius","family":"Bunandar","sequence":"additional","affiliation":[{"name":"Lightmatter, Mountain View, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8118-3026","authenticated-orcid":false,"given":"Rachee","family":"Singh","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. TPU v4 Documentation. https:\/\/cloud.google.com\/tpu\/docs\/v4. (2023). Accessed on 2024-05--29."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604878"},{"key":"e_1_3_2_1_3_1","volume-title":"Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Agrawal Amey","year":"2024","unstructured":"Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, and Ramachandran Ramjee. 2024. Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 117--134. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/agrawal"},{"key":"e_1_3_2_1_4_1","unstructured":"Meta AI. 2024. Llama 3.2: Multilingual Large Language Models. (2024). https:\/\/www.llama.com\/Accessed: 2025--1--20."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1402958.1402967"},{"key":"e_1_3_2_1_6_1","unstructured":"Amazon Web Services. 2024. Amazon EC2 Trn1\/Trn1n Architecture -- AWS Neuron Documentation. https:\/\/awsdocsneuron. readthedocs-hosted.com\/en\/latest\/general\/arch\/neuronhardware\/trn1-arch.html. (2024). Accessed: 2025-01--31."},{"key":"e_1_3_2_1_7_1","unstructured":"Amazon Web Services. 2024. Amazon EC2 UltraClusters. https:\/\/aws.amazon.com\/ec2\/ultraclusters\/. (2024). Accessed: 2025-01--31."},{"key":"e_1_3_2_1_8_1","unstructured":"Arista. 2026. Arista scale-up ethernet. (2026). https:\/\/blogs.arista.com\/blog\/the-sun-rises-on-scale-up-ethernet"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750510"},{"key":"e_1_3_2_1_10_1","unstructured":"Broadcom. 2026. Broadcom scale-up ethernet. (2026). https:\/\/docs.broadcom.com\/doc\/scale-up-ethernet-framework#page=5.17 Accessed: 2026-Jan-06."},{"key":"e_1_3_2_1_11_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma Albert Webson Shixiang Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Alex Castro-Ros Marie Pellat Kevin Robinson Dasha Valter Sharan Narang Gaurav Mishra Adams Yu Vincent Zhao Yanping Huang Andrew Dai Hongkun Yu Slav Petrov Ed H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc V. Le and Jason Wei. 2022. Scaling Instruction-Finetuned Language Models. (2022). arXiv:cs.LG\/2210.11416 https:\/\/arxiv.org\/abs\/2210.11416"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/52324.52336"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3772356.3772414"},{"key":"e_1_3_2_1_14_1","volume-title":"PipSwitch: A Circuit Switch Using Programmable Integrated Photonics. In Optical Fiber Conference (OFC 2025","author":"Ding Eric","year":"2025","unstructured":"Eric Ding and Rachee Singh. 2025. PipSwitch: A Circuit Switch Using Programmable Integrated Photonics. In Optical Fiber Conference (OFC 2025). arXiv:cs.NI\/2501.18136 https:\/\/arxiv.org\/abs\/2501.18136"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851223"},{"key":"e_1_3_2_1_16_1","unstructured":"FS. [n.d.]. Intel E10GSFPLR Compatible 10GBASE-ER SFP 1550nm 40km DOM Duplex LC\/UPC SMF Optical Transceiver Module. ([n.d.]). https:\/\/www.fs.com\/products\/201345.html Accessed: 2025--1--20."},{"key":"e_1_3_2_1_17_1","unstructured":"FS. [n.d.]. Intel E10GSFPSR Compatible 10GBASE-SR SFP 850nm 300m DOM Duplex LC\/UPC MMF Optical Transceiver Module. ([n.d.]). https:\/\/www.fs.com\/products\/71385.html Accessed: 2025--1--20."},{"key":"e_1_3_2_1_18_1","unstructured":"FS. [n.d.]. Mini Unmanaged 1x 10GBase-X to 1x 10GBase-X 2SFP Slots 10Gigabit Fiber Media Converter American Plug Standard. ([n.d.]). https:\/\/www.fs.com\/products\/131590.html Accessed: 2025--1--20."},{"key":"e_1_3_2_1_19_1","unstructured":"Google Cloud. 2024. Run a Calculation with JAX on Cloud TPU VMs. Google Cloud Documentation. (2024). https:\/\/cloud.google.com\/tpu\/docs\/run-calculation-jax Accessed: 2025-01--31."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1592568.1592576"},{"key":"e_1_3_2_1_21_1","unstructured":"Gurobi Optimization LLC. 2023. Gurobi Optimizer Reference Manual. (2023). https:\/\/www.gurobi.com"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626328"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"HotChips 34. Accessed on 2023-05--26. Passage\u2014A Wafer-Scale Programmable Photonic Communication Substrate. https:\/\/hc34.hotchips.org\/assets\/program\/conference\/day1. (Accessed on 2023-05--26).","DOI":"10.1109\/HCS55958.2022.9895610"},{"key":"e_1_3_2_1_25_1","unstructured":"Intel. 2020. Intel Ethernet Network Adapter E810-XXVDA2. (2020). https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/189760\/intel-ethernet-network-adapter-e810xxvda2\/specifications.html Accessed: 2025--1--20."},{"key":"e_1_3_2_1_26_1","unstructured":"Intel Gaudi AI accelerator 2021. Intel Gaudi AI accelerator. (2021). https:\/\/habana.ai\/products\/gaudi\/."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810093"},{"key":"e_1_3_2_1_28_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","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 24). USENIX Association, Santa Clara, CA, 745--760. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/jiang-ziheng"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934904"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Norman P. Jouppi George Kurian Sheng Li Peter Ma Rahul Nagarajan Lifeng Nai Nishant Patil Suvinay Subramanian Andy Swing Brian Towles Cliff Young Xiang Zhou Zongwei Zhou and David Patterson. 2023. TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings. (2023). arXiv:cs.AR\/2304.01433","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472900"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2025.Th1F.2"},{"key":"e_1_3_2_1_33_1","unstructured":"Abhishek Vijaya Kumar Eric Ding Arjun Devraj and Rachee Singh. 2025. Morphlux. https:\/\/github.com\/cornell-sysphotonics\/Morphlux. (2025). GitHub repository."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01215349"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604836"},{"key":"e_1_3_2_1_36_1","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. (2019). arXiv:cs.CL\/1907.11692 https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTQE.2019.2948048"},{"key":"e_1_3_2_1_38_1","first-page":"2","article-title":"Co-Packaged Photonics For High Performance Computing: Status","volume":"40","author":"Mahajan Ravi","year":"2022","unstructured":"Ravi Mahajan, Xiaoqian Li, Joshua Fryman, Zhichao Zhang, Srikant Nekkanty, Pooya Tadayon, James Jaussi, Sergey Shumarayev, Ankur Agrawal, Susheel Jadhav, Kumar Abhishek Sing h, Andrew Alduino, Sushrutha Gujjula, Chia-Pin Chiu, Thomas Nordstog, Kaveh J. Hosseini, Sandeep Sane, Nitin Deshpande, Kemal Ayg\u00fcn, Arnab Sarkar, Priyanka Dobriyal, Suresh Pot hukuchi, Vanessa A. Pogue, and David Hui. 2022. Co-Packaged Photonics For High Performance Computing: Status, Challenges And Opportunities. J. Lightwave Technol. 40, 2 (Jan 2022), 379--392. https:\/\/opg.optica.org\/jlt\/abstract.cfm?URI=jlt-40--2--379","journal-title":"Challenges And Opportunities. J. Lightwave Technol."},{"key":"e_1_3_2_1_39_1","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Mellette William M.","year":"2020","unstructured":"William M. Mellette, Rajdeep Das, Yibo Guo, Rob McGuinness, Alex C. Snoeren, and George Porter. 2020. Expanding across time to deliver bandwidth efficiency and low latency. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). USENIX Association, Santa Clara, CA, 1--18. https:\/\/www.usenix.org\/conference\/nsdi20\/presentation\/mellette"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098838"},{"key":"e_1_3_2_1_41_1","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer Sentinel Mixture Models. (2016). arXiv:cs.CL\/1609.07843"},{"key":"e_1_3_2_1_42_1","unstructured":"Meta. 2024. The LLaMA 3 Herd of Models. (2024). https:\/\/ai.meta.com\/research\/publications\/the-llama-3-herd-of-models\/ Accessed: 2024--11--10."},{"key":"e_1_3_2_1_43_1","volume-title":"Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies (FAST 21)","author":"Mohan Jayashree","year":"2021","unstructured":"Jayashree Mohan, Amar Phanishayee, and Vijay Chidambaram. 2021. CheckFreq: Frequent, Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies (FAST 21). USENIX Association, 203--216. https:\/\/www.usenix.org\/conference\/fast21\/presentation\/mohan"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230560"},{"key":"e_1_3_2_1_45_1","unstructured":"Nvidia. 2022. Doubling all2all Performance with NVIDIA Collective Communication Library 2.12. (2022). https: \/\/developer.nvidia.com\/blog\/doubling-all2all-performance-withnvidia- collective-communication-library-2--12\/ Accessed: 2024--11--16."},{"key":"e_1_3_2_1_46_1","unstructured":"NVIDIA. 2022. NVIDIA RTX 6000 Ada Generation Graphics Card. (2022). https:\/\/www.nvidia.com\/en-us\/design-visualization\/rtx-6000\/ Accessed: 2025--1--20."},{"key":"e_1_3_2_1_47_1","volume-title":"https:\/\/www.nvidia.com\/enus\/ data-center\/gb200-nvl72\/ Accessed: 2026-Jan-06","author":"NVIDIA.","year":"2024","unstructured":"NVIDIA. 2024. GB200 NVL72. (2024). https:\/\/www.nvidia.com\/enus\/ data-center\/gb200-nvl72\/ Accessed: 2026-Jan-06."},{"key":"e_1_3_2_1_48_1","unstructured":"Nvidia DGX Systems 2021. Nvidia DGX Systems. (2021). https:\/\/www.nvidia.com\/en-us\/data-center\/dgx-systems\/."},{"key":"e_1_3_2_1_49_1","unstructured":"Nvidia NVLink 2021. Nvidia NVLink and NVSwitch. (2021). https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1515\/nanoph-2018-0051"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544265"},{"key":"e_1_3_2_1_52_1","volume-title":"CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Rajasekaran Sudarsanan","year":"2024","unstructured":"Sudarsanan Rajasekaran, Manya Ghobadi, and Aditya Akella. 2024. CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 1403--1420. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/ rajasekaran"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1364\/NETWORKS.2022.NeTu1D.1"},{"key":"e_1_3_2_1_54_1","unstructured":"Thomas Rothvoss. 2012. A simpler proof for O(congestion dilation) packet routing. (2012). arXiv:cs.DS\/1206.3718"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2686882"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJSSCS.2024.3507754"},{"key":"e_1_3_2_1_57_1","unstructured":"Semianalysis. 2024. GB200 NVL72 Rack visual. (2024). https:\/\/newsletter.semianalysis.com\/p\/gb200-hardware-architectureand- component Accessed: 2026-Jan-06."},{"key":"e_1_3_2_1_58_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, Santa Clara, CA, 1445--1462. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/de-sensi"},{"key":"e_1_3_2_1_59_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, Boston, MA, 593--612. https:\/\/www.usenix.org\/conference\/ nsdi23\/presentation\/shah"},{"key":"e_1_3_2_1_60_1","volume-title":"Shoal: A Network Architecture for Disaggregated Racks. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Shrivastav Vishal","year":"2019","unstructured":"Vishal Shrivastav, Asaf Valadarsky, Hitesh Ballani, Paolo Costa, Ki Suh Lee, Han Wang, Rachit Agarwal, and Hakim Weatherspoon. 2019. Shoal: A Network Architecture for Disaggregated Racks. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). USENIX Association, Boston, MA, 255--270. https: \/\/www.usenix.org\/conference\/nsdi19\/presentation\/shrivastav"},{"key":"e_1_3_2_1_61_1","volume-title":"Operating System Concepts","author":"Silberschatz Abraham","unstructured":"Abraham Silberschatz, Peter B. Galvin, and Greg Gagne. 2018. Operating System Concepts (10th ed.). Wiley.","edition":"10"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787508"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472895"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230570"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2519390"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.451760"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3210534"},{"key":"e_1_3_2_1_68_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. (2023). arXiv:cs.CL\/2307.09288 https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_1_69_1","volume-title":"TSMC: Leading Semiconductor Manufacturing. https:\/\/www.tsmc.com.","author":"Manufacturing Taiwan Semiconductor","year":"2025","unstructured":"Taiwan Semiconductor Manufacturing Company (TSMC). 2025. TSMC: Leading Semiconductor Manufacturing. https:\/\/www.tsmc.com. (2025). Accessed: 2025-01--31."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696348.3696856"},{"key":"e_1_3_2_1_72_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, Boston, MA, 739--767. https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/wang-weiyang"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2023.W1G.1"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.497372"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1090\/qam\/253822"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2013.OW3A.5"},{"key":"e_1_3_2_1_77_1","volume-title":"Amazon EC2 Trn2 Instances and Trn2 UltraServers for AI\/ML Training and Inference are Now Available. AWS News Blog. (December","author":"Yun Channy","year":"2024","unstructured":"Channy Yun. 2024. Amazon EC2 Trn2 Instances and Trn2 UltraServers for AI\/ML Training and Inference are Now Available. AWS News Blog. (December 2024). https:\/\/aws.amazon.com\/blogs\/aws\/amazonec2-trn2-instances-and-trn2-ultraservers-for-aiml-training-andinference-is-now-available\/ Accessed: 2025-01--31."},{"key":"e_1_3_2_1_78_1","unstructured":"Liangyu Zhao Saeed Maleki Ziyue Yang Hossein Pourreza Aashaka Shah Changho Hwang and Arvind Krishnamurthy. 2024. Forest-Coll: Efficient Collective Communications on Heterogeneous Network Fabrics. (2024). arXiv:cs.NI\/2402.06787"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472921"},{"key":"e_1_3_2_1_80_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--774. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/zu"}],"event":{"name":"ASPLOS '26: 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Pittsburgh PA USA","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T13:58:47Z","timestamp":1773583127000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779212.3790238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":80,"alternative-id":["10.1145\/3779212.3790238","10.1145\/3779212"],"URL":"https:\/\/doi.org\/10.1145\/3779212.3790238","relation":{},"subject":[],"published":{"date-parts":[[2026,3,22]]},"assertion":[{"value":"2026-03-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}