{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:00:45Z","timestamp":1776931245085,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402411"],"award-info":[{"award-number":["62402411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Project","award":["2023QN10X252"],"award-info":[{"award-number":["2023QN10X252"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756057","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:21:19Z","timestamp":1760721679000},"page":"659-674","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing All-to-All Collective Communication with Fault Tolerance on Torus Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9861-0469","authenticated-orcid":false,"given":"Le","family":"Qin","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6805-7669","authenticated-orcid":false,"given":"Junwei","family":"Cui","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6369-6389","authenticated-orcid":false,"given":"Weilin","family":"Cai","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4951-4075","authenticated-orcid":false,"given":"Meng","family":"Niu","sequence":"additional","affiliation":[{"name":"Huawei, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5174-7788","authenticated-orcid":false,"given":"Yan","family":"Yang","sequence":"additional","affiliation":[{"name":"Huawei, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4011-6668","authenticated-orcid":false,"given":"Jiayi","family":"Huang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. AWS Trn1 Architecture \u2014 AWS Neuron Documentation \u2014 awsdocs-neuron.readthedocs-hosted.com. https:\/\/awsdocs-neuron.readthedocs-hosted.com\/en\/v2.3.0\/general\/arch\/neuron-hardware\/trn1-arch.html. [Accessed 17-11-2024]."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2002.10017"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919636"},{"key":"e_1_3_3_2_5_2","unstructured":"Mistral AI. [n. d.]. Mixtral of experts \u2014 mistral.ai. https:\/\/mistral.ai\/news\/mixtral-of-experts\/?trk=cndc-detail. [Accessed 24-06-2024]."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00090"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Yuichiro Ajima Shinji Sumimoto and Toshiyuki Shimizu. 2009. Tofu: A 6D mesh\/torus interconnect for exascale computers. Computer 42 11 (2009) 36\u201340.","DOI":"10.1109\/MC.2009.370"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Mohammad Al-Fares Alexander Loukissas and Amin Vahdat. 2008. A scalable commodity data center network architecture. ACM SIGCOMM computer communication review 38 4 (2008) 63\u201374.","DOI":"10.1145\/1402946.1402967"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3625549.3658656"},{"key":"e_1_3_3_2_11_2","unstructured":"Yoshua Bengio Geoffrey Hinton Andrew Yao Dawn Song Pieter Abbeel Yuval\u00a0Noah Harari Ya-Qin Zhang Lan Xue Shai Shalev-Shwartz Gillian Hadfield et\u00a0al. 2023. Managing ai risks in an era of rapid progress. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.17688 (2023)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781351104005-13"},{"key":"e_1_3_3_2_13_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/181014.181756"},{"key":"e_1_3_3_2_15_2","unstructured":"Weilin Cai Juyong Jiang Le Qin Junwei Cui Sunghun Kim and Jiayi Huang. 2024. Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts. arxiv:https:\/\/arXiv.org\/abs\/2404.05019\u00a0[cs.LG]"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716006"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441620"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063419"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_3_2_20_2","unstructured":"Peter Clark Isaac Cowhey Oren Etzioni Tushar Khot Ashish Sabharwal Carissa Schoenick and Oyvind Tafjord. 2018. Think you have solved question answering? try arc the ai2 reasoning challenge. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1803.05457 (2018)."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Charles Clos. 1953. A study of non-blocking switching networks. Bell System Technical Journal 32 2 (1953) 406\u2013424.","DOI":"10.1002\/j.1538-7305.1953.tb01433.x"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Dally and Seitz. 1987. Deadlock-free message routing in multiprocessor interconnection networks. IEEE Transactions on computers 100 5 (1987) 547\u2013553.","DOI":"10.1109\/TC.1987.1676939"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/2821589"},{"key":"e_1_3_3_2_25_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.04805 (2018)."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00056"},{"key":"e_1_3_3_2_27_2","volume-title":"Interconnection networks","author":"Duato Jose","year":"2003","unstructured":"Jose Duato, Sudhakar Yalamanchili, and Lionel Ni. 2003. Interconnection networks. Morgan Kaufmann."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531468"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"e_1_3_3_2_30_2","unstructured":"Jiaao He Jiezhong Qiu Aohan Zeng Zhilin Yang Jidong Zhai and Jie Tang. 2021. Fastmoe: A fast mixture-of-expert training system. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2103.13262 (2021)."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508418"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00023"},{"key":"e_1_3_3_2_34_2","unstructured":"Changho Hwang Wei Cui Yifan Xiong Ziyue Yang Ze Liu Han Hu Zilong Wang Rafael Salas Jithin Jose Prabhat Ram et\u00a0al. 2023. Tutel: Adaptive mixture-of-experts at scale. Proceedings of Machine Learning and Systems 5 (2023)."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810093"},{"key":"e_1_3_3_2_36_2","unstructured":"Albert\u00a0Q Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier et\u00a0al. 2023. Mistral 7B. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.06825 (2023)."},{"key":"e_1_3_3_2_37_2","unstructured":"Chenyu Jiang Ye Tian Zhen Jia Shuai Zheng Chuan Wu and Yida Wang. 2024. Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapping. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.19429 (2024)."},{"key":"e_1_3_3_2_38_2","first-page":"745","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, et\u00a0al. 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). 745\u2013760."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Norman\u00a0P Jouppi Doe\u00a0Hyun Yoon George Kurian Sheng Li Nishant Patil James Laudon Cliff Young and David Patterson. 2020. A domain-specific supercomputer for training deep neural networks. Commun. ACM 63 7 (2020) 67\u201378.","DOI":"10.1145\/3360307"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid51090.2021.00021"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey\u00a0E Hinton. 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60 6 (2017) 84\u201390.","DOI":"10.1145\/3065386"},{"key":"e_1_3_3_2_43_2","unstructured":"Sameer Kumar and Norm Jouppi. 2020. Highly Available Data Parallel ML training on Mesh Networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2011.03605 (2020)."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2008.83"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Chi\u00a0Chung Lam C-H Huang and P Sadayappan. 1997. Optimal algorithms for all-to-all personalized communication on rings and two dimensional tori. J. Parallel and Distrib. Comput. 43 1 (1997) 3\u201313.","DOI":"10.1006\/jpdc.1997.1328"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00069"},{"key":"e_1_3_3_2_47_2","unstructured":"Dmitry Lepikhin HyoukJoong Lee Yuanzhong Xu Dehao Chen Orhan Firat Yanping Huang Maxim Krikun Noam Shazeer and Zhifeng Chen. 2020. Gshard: Scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2006.16668 (2020)."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Ang Li Shuaiwen\u00a0Leon Song Jieyang Chen Jiajia Li Xu Liu Nathan\u00a0R Tallent and Kevin\u00a0J Barker. 2019. Evaluating modern gpu interconnect: Pcie nvlink nv-sli nvswitch and gpudirect. IEEE Transactions on Parallel and Distributed Systems 31 1 (2019) 94\u2013110.","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"e_1_3_3_2_49_2","unstructured":"Graphcore Ltd. [n. d.]. IPU-POD64 \u2014 graphcore.ai. https:\/\/www.graphcore.ai\/products\/mk2\/ipu-pod64. [Accessed 17-11-2024]."},{"key":"e_1_3_3_2_50_2","unstructured":"Kiwan Maeng Shivam Bharuka Isabel Gao Mark Jeffrey Vikram Saraph Bor-Yiing Su Caroline Trippel Jiyan Yang Mike Rabbat Brandon Lucia et\u00a0al. 2021. Understanding and improving failure tolerant training for deep learning recommendation with partial recovery. Proceedings of Machine Learning and Systems 3 (2021) 637\u2013651."},{"key":"e_1_3_3_2_51_2","unstructured":"Timothy\u00a0Prickett Morgan. [n. d.]. Deep Dive On Google\u2019s Exascale TPUv4 AI Systems \u2014 nextplatform.com. https:\/\/www.nextplatform.com\/2022\/10\/11\/deep-dive-on-googles-exascale-tpuv4-ai-systems\/. [Accessed 15-11-2024]."},{"key":"e_1_3_3_2_52_2","unstructured":"Maxim Naumov Dheevatsa Mudigere Hao-Jun\u00a0Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole-Jean Wu Alisson\u00a0G Azzolini et\u00a0al. 2019. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1906.00091 (2019)."},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPCW57629.2022.00008"},{"key":"e_1_3_3_2_54_2","unstructured":"Dylan Patel. [n. d.]. GPT-4 Architecture Infrastructure Training Dataset Costs Vision MoE \u2014 semianalysis.com. https:\/\/www.semianalysis.com\/p\/gpt-4-architecture-infrastructure. [Accessed 25-06-2024]."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom57177.2022.00058"},{"key":"e_1_3_3_2_56_2","unstructured":"Nicole\u00a0Hemsoth Prickett. [n. d.]. The AI Training Chip Tencent Has an Eye On \u2014 nextplatform.com. https:\/\/www.nextplatform.com\/2021\/08\/26\/the-ai-training-chip-tencent-has-an-eye-on\/. [Accessed 17-11-2024]."},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465434"},{"key":"e_1_3_3_2_58_2","unstructured":"Kishore Punniyamurthy Khaled Hamidouche and Bradford\u00a0M Beckmann. 2023. Optimizing Distributed ML Communication with Fused Computation-Collective Operations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.06942 (2023)."},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731025"},{"key":"e_1_3_3_2_60_2","first-page":"18332","volume-title":"International conference on machine learning","author":"Rajbhandari Samyam","year":"2022","unstructured":"Samyam Rajbhandari, Conglong Li, Zhewei Yao, Minjia Zhang, Reza\u00a0Yazdani Aminabadi, Ammar\u00a0Ahmad Awan, Jeff Rasley, and Yuxiong He. 2022. Deepspeed-moe: Advancing mixture-of-experts inference and training to power next-generation ai scale. In International conference on machine learning. PMLR, 18332\u201318346."},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00018"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527382"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"crossref","unstructured":"Robert\u00a0R Schaller. 1997. Moore\u2019s law: past present and future. IEEE spectrum 34 6 (1997) 52\u201359.","DOI":"10.1109\/6.591665"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2006.40"},{"key":"e_1_3_3_2_65_2","first-page":"593","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). 593\u2013612."},{"key":"e_1_3_3_2_66_2","unstructured":"Noam Shazeer Azalia Mirhoseini Krzysztof Maziarz Andy Davis Quoc Le Geoffrey Hinton and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1701.06538 (2017)."},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"crossref","unstructured":"Young-Joo Suh and Kang\u00a0G Shin. 2001. All-to-all personalized communication in multidimensional torus and mesh networks. IEEE Transactions on Parallel and Distributed Systems 12 1 (2001) 38\u201359.","DOI":"10.1109\/71.899938"},{"key":"e_1_3_3_2_68_2","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc\u00a0V Le. 2014. Sequence to sequence learning with neural networks. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"crossref","unstructured":"Rajeev Thakur Rolf Rabenseifner and William Gropp. 2005. Optimization of collective communication operations in MPICH. The International Journal of High Performance Computing Applications 19 1 (2005) 49\u201366.","DOI":"10.1177\/1094342005051521"},{"key":"e_1_3_3_2_70_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.5555\/370049.370055"},{"key":"e_1_3_3_2_72_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI63208.2024.00013"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"e_1_3_3_2_75_2","unstructured":"Lilian Weng. 2021. How to Train Really Large Models on Many GPUs?lilianweng.github.io (Sep 2021). https:\/\/lilianweng.github.io\/posts\/2021-09-25-train-large\/"},{"key":"e_1_3_3_2_76_2","unstructured":"William Won Midhilesh Elavazhagan Sudarshan Srinivasan Ajaya Durg Swati Gupta and Tushar Krishna. 2023. TACOS: Topology-aware collective algorithm synthesizer for distributed training. arXiv preprint arXiv 2304 (2023)."},{"key":"e_1_3_3_2_77_2","unstructured":"Chris Ying Sameer Kumar Dehao Chen Tao Wang and Youlong Cheng. 2018. Image classification at supercomputer scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1811.06992 (2018)."},{"key":"e_1_3_3_2_78_2","unstructured":"Barret Zoph Irwan Bello Sameer Kumar Nan Du Yanping Huang Jeff Dean Noam Shazeer and William Fedus. 2022. St-moe: Designing stable and transferable sparse expert models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2202.08906 (2022)."},{"key":"e_1_3_3_2_79_2","first-page":"761","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, et\u00a0al. 2024. Resiliency at Scale: Managing { Google\u2019s}{ TPUv4} Machine Learning Supercomputer. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 761\u2013774."}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756057","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:48:40Z","timestamp":1769464120000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756057"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":78,"alternative-id":["10.1145\/3725843.3756057","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756057","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}