{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T19:01:25Z","timestamp":1754161285952,"version":"3.41.2"},"publisher-location":"New York, NY, USA","reference-count":70,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3696630.3728529","type":"proceedings-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:08:09Z","timestamp":1753729689000},"page":"27-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["dl\u00b2: Detecting Communication Deadlocks in Deep Learning Jobs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1899-8561","authenticated-orcid":false,"given":"Yanjie","family":"Gao","sequence":"first","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4315-8061","authenticated-orcid":false,"given":"Jiyu","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9148-5861","authenticated-orcid":false,"given":"Haoxiang","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3063-9425","authenticated-orcid":false,"given":"Hongyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6663-4861","authenticated-orcid":false,"given":"Ming","family":"Wu","sequence":"additional","affiliation":[{"name":"Zero Gravity Labs, San Francisco, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6455-3898","authenticated-orcid":false,"given":"Mao","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). USENIX Association, Savannah, GA, 265\u2013283."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Gustaf Ahdritz Nazim Bouatta Christina Floristean Sachin Kadyan Qinghui Xia William Gerecke Timothy J O'Donnell Daniel Berenberg Ian Fisk Niccol\u00f2 Zanichelli Bo Zhang Arkadiusz Nowaczynski Bei Wang Marta M Stepniewska-Dziubinska Shang Zhang Adegoke Ojewole Murat Efe Guney Stella Biderman Andrew M Watkins Stephen Ra Pablo Ribalta Lorenzo Lucas Nivon Brian Weitzner Yih-En Andrew Ban Shiyang Chen Minjia Zhang Conglong Li Shuaiwen Leon Song Yuxiong He Peter K Sorger Emad Mostaque Zhao Zhang Richard Bonneau and Mohammed AlQuraishi. 2024. OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization. Nature Methods (2024) 1\u201311.","DOI":"10.1038\/s41592-024-02272-z"},{"key":"e_1_3_2_1_3_1","volume-title":"DLOS: Effective Static Detection of Deadlocks in OS Kernels. In 2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Bai Jia-Ju","year":"2022","unstructured":"Jia-Ju Bai, Tuo Li, and Shi-Min Hu. 2022. DLOS: Effective Static Detection of Deadlocks in OS Kernels. In 2022 USENIX Annual Technical Conference (USENIX ATC 22). USENIX Association, Carlsbad, CA, 367\u2013382. https:\/\/www.usenix.org\/conference\/atc22\/presentation\/bai"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 36th IEEE\/ACM International Conference on Automated Software Engineering","author":"Brotherston James","year":"2022","unstructured":"James Brotherston, Paul Brunet, Nikos Gorogiannis, and Max Kanovich. 2022. A compositional deadlock detector for Android Java. In Proceedings of the 36th IEEE\/ACM International Conference on Automated Software Engineering (Melbourne, Australia) (ASE '21). IEEE Press, 955\u2013966. 10.1109\/ASE51524.2021.9678572"},{"key":"e_1_3_2_1_5_1","article-title":"PaLM: scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2024","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sashank Tsvyashchenko, Joshua Maynez, Abhishek Rao, Parker Barnes, Yi Tay, Noam Shazeer, Vinodkumar Prabhakaran, Emily Reif, Nan Du, Ben Hutchinson, Reiner Pope, James Bradbury, Jacob Austin, Michael Isard, Guy Gur-Ari, Pengcheng Yin, Toju Duke, Anselm Levskaya, Sanjay Ghemawat, Sunipa Dev, Henryk Michalewski, Xavier Garcia, Vedant Misra, Kevin Robinson, Liam Fedus, Denny Zhou, Daphne Ippolito, David Luan, Hyeontaek Lim, Barret Zoph, Alexander Spiridonov, Ryan Sepassi, David Dohan, Shivani Agrawal, Mark Omernick, Andrew M. Dai, Thanumalayan Sankaranarayana Pillai, Marie Pellat, Aitor Lewkowycz, Erica Moreira, Rewon Child, Oleksandr Polozov, Katherine Lee, Zongwei Zhou, Xuezhi Wang, Brennan Saeta, Mark Diaz, Orhan Firat, Michele Catasta, Jason Wei, Kathy Meier-Hellstern, Douglas Eck, Jeff Dean, Slav Petrov, and Noah Fiedel. 2024. PaLM: scaling language modeling with pathways. J. Mach. Learn. Res. 24, 1, Article 240 (mar 2024), 113 pages.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/356586.356588"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3229060"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","volume":"2","author":"Cowan Meghan","year":"2023","unstructured":"Meghan Cowan, Saeed Maleki, Madanlal Musuvathi, Olli Saarikivi, and Yifan Xiong. 2023. MSCCLang: Microsoft Collective Communication Language. In Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2 (Vancouver, BC, Canada) (ASPLOS 2023). Association for Computing Machinery, New York, NY, USA, 502\u2013514. 10.1145\/3575693.3575724"},{"key":"e_1_3_2_1_9_1","unstructured":"DeepSeek-AI. 2024. DeepSeek-V3 Technical Report. arXiv:2412.19437 [cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_2_1_10_1","volume-title":"Symbolic Deadlock Analysis in Concurrent Libraries and Their Clients. In 2009 IEEE\/ACM International Conference on Automated Software Engineering. 480\u2013491","author":"Deshmukh Jyotirmoy","year":"2009","unstructured":"Jyotirmoy Deshmukh, E. Allen Emerson, and Sriram Sankaranarayanan. 2009. Symbolic Deadlock Analysis in Concurrent Libraries and Their Clients. In 2009 IEEE\/ACM International Conference on Automated Software Engineering. 480\u2013491. 10.1109\/ASE.2009.14"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles","author":"Engler Dawson","year":"2003","unstructured":"Dawson Engler and Ken Ashcraft. 2003. RacerX: effective, static detection of race conditions and deadlocks. In Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles (Bolton Landing, NY, USA) (SOSP '03). Association for Computing Machinery, New York, NY, USA, 237\u2013252. 10.1145\/945445.945468"},{"key":"e_1_3_2_1_12_1","volume-title":"An Empirical Study on Quality Issues of Deep Learning Platform. In 2023 IEEE\/ACM 45th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). 455\u2013466","author":"Gao Yanjie","year":"2023","unstructured":"Yanjie Gao, Xiaoxiang Shi, Haoxiang Lin, Hongyu Zhang, Hao Wu, Rui Li, and Mao Yang. 2023. An Empirical Study on Quality Issues of Deep Learning Platform. In 2023 IEEE\/ACM 45th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). 455\u2013466. 10.1109\/ICSE-SEIP58684.2023.00052"},{"key":"e_1_3_2_1_13_1","volume-title":"2011 USENIX Annual Technical Conference (USENIX ATC 11)","author":"Guo Zhenyu","year":"2011","unstructured":"Zhenyu Guo, Dong Zhou, Haoxiang Lin, Mao Yang, Fan Long, Chaoqiang Deng, Changshu Liu, and Lidong Zhou. 2011. G2: A Graph Processing System for Diagnosing Distributed Systems. In 2011 USENIX Annual Technical Conference (USENIX ATC 11). USENIX Association, Portland, OR. https:\/\/www.usenix.org\/conference\/usenixatc11\/g2-graph-processing-system-diagnosing-distributed-systems"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 15th Asia-Pacific Symposium on Internetware","author":"Hao Jiale","year":"2024","unstructured":"Jiale Hao, Meng Wang, and Hong Zhang. 2024. Efficient Deadlock Detection in MPI Programs with Path Compression and Focus Matching. In Proceedings of the 15th Asia-Pacific Symposium on Internetware (Macau, China) (Internetware '24). Association for Computing Machinery, New York, NY, USA, 467\u2013476. 10.1145\/3671016.3674822"},{"key":"e_1_3_2_1_15_1","volume-title":"Elliott Slaughter, Pinku Surana, Wen mei Hwu, William Gropp, and Alex Aiken.","author":"Hidayetoglu Mert","year":"2024","unstructured":"Mert Hidayetoglu, Simon Garcia de Gonzalo, Elliott Slaughter, Pinku Surana, Wen mei Hwu, William Gropp, and Alex Aiken. 2024. HiCCL: A Hierarchical Collective Communication Library. arXiv:2408.05962 [cs.DC] https:\/\/arxiv.org\/abs\/2408.05962"},{"key":"e_1_3_2_1_16_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Dehao Chen, Mia Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V Le, Yonghui Wu, and zhifeng Chen. 2019. GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc., 10. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/093f65e080a295f8076b1c5722a46aa2-Paper.pdf"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering","author":"Huang Yu","year":"2021","unstructured":"Yu Huang, Benjamin Ogles, and Eric Mercer. 2021. A predictive analysis for detecting deadlock in MPI programs. In Proceedings of the 35th IEEE\/ACM International Conference on Automated Software Engineering (Virtual Event, Australia) (ASE '20). Association for Computing Machinery, New York, NY, USA, 18\u201328. 10.1145\/3324884.3416588"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Frank Hutter Lars Kotthoff and Joaquin Vanschoren (Eds.). 2019. Automated Machine Learning - Methods Systems Challenges. Springer.","DOI":"10.1007\/978-3-030-05318-5"},{"key":"e_1_3_2_1_19_1","unstructured":"Meta Incubator. 2024. Gloo: collective communications library with various primitives for multi-machine training. https:\/\/github.com\/facebookincubator\/gloo."},{"key":"e_1_3_2_1_20_1","unstructured":"Michael Kerrisk. 2024. ld.so(8) - Linux manual page. https:\/\/www.man7.org\/linux\/man-pages\/man8\/ld.so.8.html."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 31st IEEE\/ACM International Conference on Automated Software Engineering","author":"Kroening Daniel","year":"2016","unstructured":"Daniel Kroening, Daniel Poetzl, Peter Schrammel, and Bj\u00f6rn Wachter. 2016. Sound static deadlock analysis for C\/Pthreads. In Proceedings of the 31st IEEE\/ACM International Conference on Automated Software Engineering (Singapore, Singapore) (ASE '16). Association for Computing Machinery, New York, NY, USA, 379\u2013390. 10.1145\/2970276.2970309"},{"key":"e_1_3_2_1_22_1","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Lin Zhiqi","year":"2024","unstructured":"Zhiqi Lin, Youshan Miao, Quanlu Zhang, Fan Yang, Yi Zhu, Cheng Li, Saeed Maleki, Xu Cao, Ning Shang, Yilei Yang, Weijiang Xu, Mao Yang, Lintao Zhang, and Lidong Zhou. 2024. nnScaler: Constraint-Guided Parallelization Plan Generation for Deep Learning Training. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 347\u2013363. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/lin-zhiqi"},{"key":"e_1_3_2_1_23_1","volume-title":"Multilingual Denoising Pre-training for Neural Machine Translation. CoRR abs\/2001.08210","author":"Liu Yinhan","year":"2020","unstructured":"Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, and Luke Zettlemoyer. 2020. Multilingual Denoising Pre-training for Neural Machine Translation. CoRR abs\/2001.08210 (2020). arXiv:2001.08210 https:\/\/arxiv.org\/abs\/2001.08210"},{"key":"e_1_3_2_1_24_1","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 9992\u201310002","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 9992\u201310002. 10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_25_1","unstructured":"LlamaTeam. 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_26_1","volume-title":"MPI: A Message-Passing Interface Standard Version 4.1. https:\/\/www.mpi-forum.org\/docs\/mpi-4.1\/mpi41-report.pdf","author":"Interface Forum Message Passing","year":"2023","unstructured":"Message Passing Interface Forum. 2023. MPI: A Message-Passing Interface Standard Version 4.1. https:\/\/www.mpi-forum.org\/docs\/mpi-4.1\/mpi41-report.pdf"},{"key":"e_1_3_2_1_27_1","unstructured":"Microsoft. 2022. Swin Tiny Patch4 Window7 224 Model. https:\/\/huggingface.co\/microsoft\/swin-tiny-patch4-window7-224."},{"key":"e_1_3_2_1_28_1","unstructured":"Microsoft. 2024. Microsoft Collective Communication Library (MSCCL). https:\/\/github.com\/microsoft\/msccl."},{"volume-title":"Proceedings of the Third Annual ACM Symposium on Principles of Distributed Computing","author":"Don","key":"e_1_3_2_1_29_1","unstructured":"Don P. Mitchell and Michael J. Merritt. 1984. A distributed algorithm for deadlock detection and resolution. In Proceedings of the Third Annual ACM Symposium on Principles of Distributed Computing (Vancouver, British Columbia, Canada) (PODC '84). Association for Computing Machinery, New York, NY, USA, 282\u2013284. 10.1145\/800222.806755"},{"key":"e_1_3_2_1_30_1","unstructured":"NetworkX. 2024. NetworkX is a Python package for the creation manipulation and study of the structure dynamics and functions of complex networks. https:\/\/networkx.org."},{"key":"e_1_3_2_1_31_1","unstructured":"NNI. 2018. NNI (Neural Network Intelligence): a lightweight but powerful toolkit to help users automate Feature Engineering Neural Architecture Search Hyper-parameter Tuning and Model Compression. https:\/\/github.com\/microsoft\/nni."},{"key":"e_1_3_2_1_32_1","unstructured":"NVIDIA. 2024. Collective Operations. https:\/\/docs.nvidia.com\/deeplearning\/nccl\/user-guide\/docs\/usage\/collectives.html."},{"key":"e_1_3_2_1_33_1","unstructured":"NVIDIA. 2024. CUDA Runtime API. https:\/\/docs.nvidia.com\/cuda\/cuda-runtime-api\/group__CUDART__EXECUTION.html."},{"key":"e_1_3_2_1_34_1","unstructured":"NVIDIA. 2024. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl."},{"key":"e_1_3_2_1_35_1","unstructured":"NVIDIA. 2024. NVIDIA CUDA Profiling Tools Interface. https:\/\/developer.nvidia.com\/cupti."},{"key":"e_1_3_2_1_36_1","unstructured":"NVIDIA. 2024. NVIDIA CUDA Toolkit. https:\/\/developer.nvidia.com\/cuda-toolkit."},{"key":"e_1_3_2_1_37_1","volume-title":"Olson and Dursun Delen","author":"David","year":"2008","unstructured":"David L. Olson and Dursun Delen. 2008. Advanced Data Mining Techniques (1st ed.). Springer Publishing Company, Incorporated."},{"key":"e_1_3_2_1_38_1","unstructured":"Lichen Pan Juncheng Liu Jinhui Yuan Rongkai Zhang Pengze Li and Zhen Xiao. 2023. OCCL: a Deadlock-free Library for GPU Collective Communication. arXiv:2303.06324 [cs.DC] https:\/\/arxiv.org\/abs\/2303.06324"},{"key":"e_1_3_2_1_39_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32, Vol. 32. Curran Associates, Inc., 8024\u20138035. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf"},{"key":"e_1_3_2_1_40_1","unstructured":"PyTorch. 2024. Automatic differentiation package - torch.autograd. https:\/\/pytorch.org\/docs\/stable\/autograd.html."},{"key":"e_1_3_2_1_41_1","unstructured":"PyTorch. 2024. Distributed communication package - torch.distributed. https:\/\/pytorch.org\/docs\/stable\/distributed.html."},{"key":"e_1_3_2_1_42_1","unstructured":"PyTorch. 2024. Distributed Data Parallel. https:\/\/pytorch.org\/docs\/stable\/notes\/ddp.html."},{"key":"e_1_3_2_1_43_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"Rasley Jeff","year":"2020","unstructured":"Jeff Rasley, Samyam Rajbhandari, Olatunji Ruwase, and Yuxiong He. 2020. Deep-Speed: System Optimizations Enable Training Deep Learning Models with Over 100 Billion Parameters. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Virtual Event, CA, USA) (KDD '20). Association for Computing Machinery, New York, NY, USA, 3505\u20133506. 10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_45_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Romero Joshua","year":"2022","unstructured":"Joshua Romero, Junqi Yin, Nouamane Laanait, Bing Xie, M. Todd Young, Sean Treichler, Vitalii Starchenko, Albina Borisevich, Alex Sergeev, and Michael Matheson. 2022. Accelerating Collective Communication in Data Parallel Training across Deep Learning Frameworks. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA, 1027\u20131040. https:\/\/www.usenix.org\/conference\/nsdi22\/presentation\/romero"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering","author":"Samak Malavika","year":"2014","unstructured":"Malavika Samak and Murali Ramanathan. 2014. Omen+: a precise dynamic deadlock detector for multithreaded Java libraries. In Proceedings of the 22nd ACM SIGSOFT International Symposium on Foundations of Software Engineering (Hong Kong, China) (FSE 2014). Association for Computing Machinery, New York, NY, USA, 735\u2013738. 10.1145\/2635868.2661670"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of the 19th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","author":"Samak Malavika","year":"2014","unstructured":"Malavika Samak and Murali Krishna Ramanathan. 2014. Trace Driven Dynamic Deadlock Detection and Reproduction. In Proceedings of the 19th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (Orlando, Florida, USA) (PPoPP '14). Association for Computing Machinery, New York, NY, USA, 29\u201342. 10.1145\/2555243.2555262"},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation","author":"Santhiar Anirudh","year":"2017","unstructured":"Anirudh Santhiar and Aditya Kanade. 2017. Static deadlock detection for asynchronous C# programs. In Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation (Barcelona, Spain) (PLDI 2017). Association for Computing Machinery, New York, NY, USA, 292\u2013305. 10.1145\/3062341.3062361"},{"key":"e_1_3_2_1_49_1","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow. CoRR abs\/1802.05799","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike Del Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. CoRR abs\/1802.05799 (2018). arXiv:1802.05799 http:\/\/arxiv.org\/abs\/1802.05799"},{"key":"e_1_3_2_1_50_1","volume-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. CoRR abs\/1909.08053","author":"Shoeybi Mohammad","year":"2019","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. CoRR abs\/1909.08053 (2019). arXiv:1909.08053 http:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_2_1_51_1","unstructured":"David Shriver. 2024. Intercepts allows you to intercept function calls in Python and handle them in any manner you choose. https:\/\/github.com\/dlshriver\/intercepts."},{"key":"e_1_3_2_1_52_1","volume-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1\u20139. 10","author":"Szegedy C.","year":"2015","unstructured":"C. Szegedy, Wei Liu, Yangqing Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. 2015. Going deeper with convolutions. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1\u20139. 10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_53_1","volume-title":"Multilayer perceptron (MLP). Geomatic approaches for modeling land change scenarios","author":"Taud Hind","year":"2018","unstructured":"Hind Taud and Jean-Franccois Mas. 2018. Multilayer perceptron (MLP). Geomatic approaches for modeling land change scenarios (2018), 451\u2013455."},{"key":"e_1_3_2_1_54_1","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:2302.13971 [cs.CL] https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_2_1_55_1","first-page":"10","volume-title":"Proc. ACM Program. Lang. 7, PLDI, Article 177 (jun","author":"Tun\u00e7 H\u00fcnkar Can","year":"2023","unstructured":"H\u00fcnkar Can Tun\u00e7, Umang Mathur, Andreas Pavlogiannis, and Mahesh Viswanathan. 2023. Sound Dynamic Deadlock Prediction in Linear Time. Proc. ACM Program. Lang. 7, PLDI, Article 177 (jun 2023), 26 pages. 10.1145\/3591291"},{"key":"e_1_3_2_1_56_1","unstructured":"GitHub User. 2022. Training hangs in the end while calling dist.barrier(). https:\/\/github.com\/huggingface\/transformers\/issues\/17478."},{"key":"e_1_3_2_1_57_1","unstructured":"GitHub User. 2023. Add validation for send\/recv sizes. https:\/\/github.com\/pytorch\/pytorch\/issues\/113376."},{"key":"e_1_3_2_1_58_1","unstructured":"GitHub User. 2023. all_to_all_single stuck when using output_split_sizes = [1 3] and input_split_sizes = [1 3]. https:\/\/github.com\/pytorch\/pytorch\/issues\/117486."},{"key":"e_1_3_2_1_59_1","unstructured":"GitHub User. 2023. [Bug] dist.broadcast with multi GPU only works on torch.float32 but errors on int64 int32 and hangs on float16. https:\/\/github.com\/pytorch\/pytorch\/issues\/118696."},{"key":"e_1_3_2_1_60_1","unstructured":"GitHub User. 2023. Distributed hangs when doing hierarchical communication. https:\/\/github.com\/pytorch\/pytorch\/issues\/130102."},{"key":"e_1_3_2_1_61_1","unstructured":"GitHub User. 2023. FSDP hangs when combining MoE architecture. https:\/\/github.com\/pytorch\/pytorch\/issues\/126616."},{"key":"e_1_3_2_1_62_1","unstructured":"GitHub User. 2023. Interleaved isend and irecv causes hang. https:\/\/github.com\/pytorch\/pytorch\/issues\/109401."},{"key":"e_1_3_2_1_63_1","unstructured":"GitHub User. 2023. P2P operations hang when mixing the usage of default and non-default communication groups. https:\/\/github.com\/pytorch\/pytorch\/issues\/116590."},{"key":"e_1_3_2_1_64_1","unstructured":"GitHub User. 2024. For AllReduce communications with a shape mismatch some cases will hang while others will not. https:\/\/github.com\/NVIDIA\/nccl\/issues\/1417."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_66_1","unstructured":"Unified Communication X. 2024. Unified Collective Communication (UCC). https:\/\/github.com\/openucx\/ucc."},{"key":"e_1_3_2_1_67_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei Huan Lin Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jingren Zhou Junyang Lin Kai Dang Keming Lu Keqin Bao Kexin Yang Le Yu Mei Li Mingfeng Xue Pei Zhang Qin Zhu Rui Men Runji Lin Tianhao Li Tianyi Tang Tingyu Xia Xingzhang Ren Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yu Wan Yuqiong Liu Zeyu Cui Zhenru Zhang and Zihan Qiu. 2025. Qwen2.5 Technical Report. arXiv:2412.15115 [cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_2_1_68_1","volume-title":"OneFlow: Redesign the Distributed Deep Learning Framework from Scratch. CoRR abs\/2110.15032","author":"Yuan Jinhui","year":"2021","unstructured":"Jinhui Yuan, Xinqi Li, Cheng Cheng, Juncheng Liu, Ran Guo, Shenghang Cai, Chi Yao, Fei Yang, Xiaodong Yi, Chuan Wu, Haoran Zhang, and Jie Zhao. 2021. OneFlow: Redesign the Distributed Deep Learning Framework from Scratch. CoRR abs\/2110.15032 (2021). arXiv:2110.15032 https:\/\/arxiv.org\/abs\/2110.15032"},{"key":"e_1_3_2_1_69_1","unstructured":"Yu Zhang Kaiwen Zhang and Guanjun Liu. 2024. Static Deadlock Detection for Rust Programs. arXiv:2401.01114 [cs.PL] https:\/\/arxiv.org\/abs\/2401.01114"},{"key":"e_1_3_2_1_70_1","volume-title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zheng Lianmin","year":"2022","unstructured":"Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric P. Xing, Joseph E. Gonzalez, and Ion Stoica. 2022. Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA, 559\u2013578. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/zheng-lianmin"}],"event":{"name":"FSE Companion '25: 33rd ACM International Conference on the Foundations of Software Engineering","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Clarion Hotel Trondheim Trondheim Norway","acronym":"FSE Companion '25"},"container-title":["Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696630.3728529","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:12:05Z","timestamp":1753729925000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696630.3728529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":70,"alternative-id":["10.1145\/3696630.3728529","10.1145\/3696630"],"URL":"https:\/\/doi.org\/10.1145\/3696630.3728529","relation":{},"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"2025-07-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}