{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T08:40:01Z","timestamp":1780994401931,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3620666.3651369","type":"proceedings-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T12:08:21Z","timestamp":1713960501000},"page":"301-316","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["EVT: Accelerating Deep Learning Training with Epilogue Visitor Tree"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9601-4586","authenticated-orcid":false,"given":"Zhaodong","family":"Chen","sequence":"first","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5708-0216","authenticated-orcid":false,"given":"Andrew","family":"Kerr","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5645-6718","authenticated-orcid":false,"given":"Richard","family":"Cai","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8812-7847","authenticated-orcid":false,"given":"Jack","family":"Kosaian","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0357-9049","authenticated-orcid":false,"given":"Haicheng","family":"Wu","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8716-5793","authenticated-orcid":false,"given":"Yufei","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California San Diego, San Diego, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2093-1788","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, HongKong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661197"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/773473.178257"},{"key":"e_1_3_2_1_3_1","volume-title":"Coconet: A collaborative convolutional network. arXiv preprint arXiv:1901.09886","author":"Chakraborti Tapabrata","year":"2019","unstructured":"Tapabrata Chakraborti, Brendan McCane, Steven Mills, and Umapada Pal. Coconet: A collaborative convolutional network. arXiv preprint arXiv:1901.09886, 2019."},{"key":"e_1_3_2_1_4_1","first-page":"579","volume-title":"Proceedings of the 13th USENIX conference on Operating Systems Design and Implementation","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Meghan Cowan, Haichen Shen, Leyuan Wang, Yuwei Hu, Luis Ceze, et al. Tvm: an automated end-to-end optimizing compiler for deep learning. In Proceedings of the 13th USENIX conference on Operating Systems Design and Implementation, pages 579--594, 2018."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476182"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171--4186, 2019."},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16\u00d716 words: Transformers for image recognition at scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2017.101"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"e_1_3_2_1_11_1","first-page":"448","volume-title":"International conference on machine learning","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, pages 448--456. pmlr, 2015."},{"key":"e_1_3_2_1_12_1","first-page":"14","article-title":"Restructuring batch normalization to accelerate cnn training","volume":"1","author":"Jung Wonkyung","year":"2019","unstructured":"Wonkyung Jung, Daejin Jung, Byeongho Kim, Sunjung Lee, Wonjong Rhee, and Jung Ho Ahn. Restructuring batch normalization to accelerate cnn training. Proceedings of Machine Learning and Systems, 1:14--26, 2019.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_13_1","volume-title":"An efficient heuristic procedure for partitioning graphs. The Bell system technical journal, 49(2):291--307","author":"Kernighan Brian W","year":"1970","unstructured":"Brian W Kernighan and Shen Lin. An efficient heuristic procedure for partitioning graphs. The Bell system technical journal, 49(2):291--307, 1970."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Learning Representations.","author":"Kipf Thomas N","unstructured":"Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","volume-title":"Mlir: A compiler infrastructure for the end of moore's law. arXiv preprint arXiv:2002.11054","author":"Lattner Chris","year":"2020","unstructured":"Chris Lattner, Mehdi Amini, Uday Bondhugula, Albert Cohen, Andy Davis, Jacques Pienaar, River Riddle, Tatiana Shpeisman, Nicolas Vasilache, and Oleksandr Zinenko. Mlir: A compiler infrastructure for the end of moore's law. arXiv preprint arXiv:2002.11054, 2020."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3030548"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080834"},{"key":"e_1_3_2_1_18_1","volume-title":"Integer programming formulation of traveling salesman problems. Journal of the ACM (JACM), 7(4):326--329","author":"Miller Clair E","year":"1960","unstructured":"Clair E Miller, Albert W Tucker, and Richard A Zemlin. Integer programming formulation of traveling salesman problems. Journal of the ACM (JACM), 7(4):326--329, 1960."},{"key":"e_1_3_2_1_19_1","volume-title":"A branch-and-bound algorithm for the acyclic partitioning problem. Computers & operations research, 41:174--184","author":"Nossack Jenny","year":"2014","unstructured":"Jenny Nossack and Erwin Pesch. A branch-and-bound algorithm for the acyclic partitioning problem. Computers & operations research, 41:174--184, 2014."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577479"},{"key":"e_1_3_2_1_21_1","volume-title":"A simple and elegant mathematical formulation for the acyclic dag partitioning problem. arXiv preprint arXiv:2207.13638","author":"Yusuf \u00d6zkaya M","year":"2022","unstructured":"M Yusuf \u00d6zkaya and \u00dcmit V \u00c7ataly\u00fcrek. A simple and elegant mathematical formulation for the acyclic dag partitioning problem. arXiv preprint arXiv:2207.13638, 2022."},{"key":"e_1_3_2_1_22_1","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems 32","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. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9 Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems 32, pages 8024--8035. Curran Associates, Inc., 2019. URL: http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf."},{"key":"e_1_3_2_1_23_1","volume-title":"Gpu-initiated fine-grained overlap of collective communication with computation. arXiv preprint arXiv:2305.06942","author":"Punniyamurthy Kishore","year":"2023","unstructured":"Kishore Punniyamurthy, Bradford M Beckmann, and Khaled Hamidouche. Gpu-initiated fine-grained overlap of collective communication with computation. arXiv preprint arXiv:2305.06942, 2023."},{"issue":"9","key":"e_1_3_2_1_24_1","article-title":"Weisfeiler-lehman graph kernels","volume":"12","author":"Shervashidze Nino","year":"2011","unstructured":"Nino Shervashidze, Pascal Schweitzer, Erik Jan Van Leeuwen, Kurt Mehlhorn, and Karsten M Borgwardt. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research, 12(9), 2011.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_25_1","first-page":"1","author":"Thakkar Vijay","year":"2023","unstructured":"Vijay Thakkar, Pradeep Ramani, Cris Cecka, Aniket Shivam, Honghao Lu, Ethan Yan, Jack Kosaian, Mark Hoemmen, Haicheng Wu, Andrew Kerr, Matt Nicely, Duane Merrill, Dustyn Blasig, Fengqi Qiao, Piotr Majcher, Paul Springer, Markus Hohnerbach, Jin Wang, and Manish Gupta. CUTLASS, 1 2023. URL: https:\/\/github.com\/NVIDIA\/cutlass.","journal-title":"CUTLASS"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_2_1_27_1","volume-title":"Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions. arXiv preprint arXiv:1802.04730","author":"Vasilache Nicolas","year":"2018","unstructured":"Nicolas Vasilache, Oleksandr Zinenko, Theodoros Theodoridis, Priya Goyal, Zachary DeVito, William S Moses, Sven Verdoolaege, Andrew Adams, and Albert Cohen. Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions. arXiv preprint arXiv:1802.04730, 2018."},{"key":"e_1_3_2_1_28_1","first-page":"344","volume-title":"Physical and Social Computing","author":"Wang Guibin","year":"2010","unstructured":"Guibin Wang, YiSong Lin, and Wei Yi. Kernel fusion: An effective method for better power efficiency on multithreaded gpu. In 2010 IEEE\/ACM Int'l Conference on Green Computing and Communications & Int'l Conference on Cyber, Physical and Social Computing, pages 344--350. IEEE, 2010."},{"key":"e_1_3_2_1_29_1","first-page":"204","article-title":"Bridging the gap between auto-tuners and hardware-native performance","volume":"4","author":"Xing Jiarong","year":"2022","unstructured":"Jiarong Xing, Leyuan Wang, Shang Zhang, Jack Chen, Ang Chen, and Yibo Zhu. Bolt: Bridging the gap between auto-tuners and hardware-native performance. Proceedings of Machine Learning and Systems, 4:204--216, 2022.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_30_1","first-page":"10","author":"Xu Bing","year":"2022","unstructured":"Bing Xu, Ying Zhang, Hao Lu, Yang Chen, Terry Chen, Mike Iovine, Mu-Chu Lee, and Zhijing Li. AITemplate, 10 2022. URL: https:\/\/github.com\/facebookincubator\/AITemplate.","journal-title":"AITemplate"},{"key":"e_1_3_2_1_31_1","first-page":"863","volume-title":"Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, et al. Ansor: Generating high-performance tensor programs for deep learning. In Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation, pages 863--879, 2020."}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","location":"La Jolla CA USA","acronym":"ASPLOS '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651369","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:43Z","timestamp":1750291423000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":31,"alternative-id":["10.1145\/3620666.3651369","10.1145\/3620666"],"URL":"https:\/\/doi.org\/10.1145\/3620666.3651369","relation":{},"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2024-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}