{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T23:21:01Z","timestamp":1784762461616,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,7]]},"DOI":"10.1145\/3605573.3605596","type":"proceedings-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T16:21:16Z","timestamp":1694622076000},"page":"786-796","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Exploiting Subgraph Similarities for Efficient Auto-tuning of Tensor Programs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4115-9072","authenticated-orcid":false,"given":"Mingzhen","family":"Li","sequence":"first","affiliation":[{"name":"Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1101-7927","authenticated-orcid":false,"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6816-058X","authenticated-orcid":false,"given":"Shanjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0352-8700","authenticated-orcid":false,"given":"Fengwei","family":"Yu","sequence":"additional","affiliation":[{"name":"SenseTime Research, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0081-5395","authenticated-orcid":false,"given":"Ruihao","family":"Gong","sequence":"additional","affiliation":[{"name":"SenseTime Research, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1829-2817","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7186-0556","authenticated-orcid":false,"given":"Zhongzhi","family":"Luan","sequence":"additional","affiliation":[{"name":"Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-1473","authenticated-orcid":false,"given":"Depei","family":"Qian","sequence":"additional","affiliation":[{"name":"Beihang University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,9,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of Machine Learning and Systems 3","author":"Baghdadi Riyadh","year":"2021","unstructured":"Riyadh Baghdadi, Massinissa Merouani, Mohamed-Hicham Leghettas, Kamel Abdous, Taha Arbaoui, Karima Benatchba, 2021. A Deep Learning Based Cost Model for Automatic Code Optimization. Proceedings of Machine Learning and Systems 3 (2021)."},{"key":"e_1_3_2_2_2_1","volume-title":"13th { USENIX} Symposium on Operating Systems Design and Implementation ({ OSDI} 18). 578\u2013594.","author":"Chen Tianqi","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, 2018. { TVM} : An automated end-to-end optimizing compiler for deep learning. In 13th { USENIX} Symposium on Operating Systems Design and Implementation ({ OSDI} 18). 578\u2013594."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327144.3327258"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569682"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of Machine Learning and Systems 3","author":"Kaufman Sam","year":"2021","unstructured":"Sam Kaufman, Phitchaya Phothilimthana, Yanqi Zhou, Charith Mendis, Sudip Roy, Amit Sabne, and Mike Burrows. 2021. A Learned Performance Model for Tensor Processing Units. Proceedings of Machine Learning and Systems 3 (2021)."},{"key":"e_1_3_2_2_8_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis","author":"Lee Wonchan","year":"2018","unstructured":"Wonchan Lee, Elliott Slaughter, Michael Bauer, Sean Treichler, Todd Warszawski, Michael Garland, and Alex Aiken. 2018. Dynamic Tracing: Memoization of Task Graphs for Dynamic Task-Based Runtimes. In Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (Dallas, Texas) (SC \u201918). IEEE Press, Article 34, 13\u00a0pages."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3030548"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3497776.3517774"},{"key":"e_1_3_2_2_12_1","volume-title":"MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworks. arXiv preprint","author":"Ryu Jaehun","year":"2021","unstructured":"Jaehun Ryu and Hyojin Sung. 2021. MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworks. arXiv preprint (2021)."},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of Machine Learning and Systems 3","author":"Steiner Benoit","year":"2021","unstructured":"Benoit Steiner, Chris Cummins, Horace He, and Hugh Leather. 2021. Value learning for throughput optimization of deep learning workloads. Proceedings of Machine Learning and Systems 3 (2021)."},{"key":"e_1_3_2_2_14_1","unstructured":"TVM. 2022. MetaSchedule in TVM. https:\/\/github.com\/apache\/tvm-rfcs\/blob\/main\/rfcs\/0005-meta-schedule-autotensorir.md."},{"key":"e_1_3_2_2_15_1","volume-title":"15th { USENIX} Symposium on Operating Systems Design and Implementation ({ OSDI} 21). 37\u201354.","author":"Wang Haojie","unstructured":"Haojie Wang, Jidong Zhai, Mingyu Gao, Zixuan Ma, Shizhi Tang, Liyan Zheng, Yuanzhi Li, Kaiyuan Rong, Yuanyong Chen, and Zhihao Jia. 2021. { PET} : Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. In 15th { USENIX} Symposium on Operating Systems Design and Implementation ({ OSDI} 21). 37\u201354."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486973"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575737"},{"key":"e_1_3_2_2_18_1","volume-title":"DynaTune: Dynamic Tensor Program Optimization in Deep Neural Network Compilation. In International Conference on Learning Representations.","author":"Zhang Minjia","year":"2021","unstructured":"Minjia Zhang, Menghao Li, Chi Wang, and Mingqin Li. 2021. DynaTune: Dynamic Tensor Program Optimization in Deep Neural Network Compilation. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_19_1","volume-title":"Moses: Efficient Exploitation of Cross-device Transferable Features for Tensor Program Optimization. arXiv preprint","author":"Zhao Zhihe","year":"2022","unstructured":"Zhihe Zhao, Xian Shuai, Yang Bai, Neiwen Ling, Nan Guan, Zhenyu Yan, and Guoliang Xing. 2022. Moses: Efficient Exploitation of Cross-device Transferable Features for Tensor Program Optimization. arXiv preprint (2022)."},{"key":"e_1_3_2_2_20_1","volume-title":"Ansor: Generating high-performance tensor programs for deep learning. In 14th { USENIX} Symposium on Operating Systems Design and Implementation ({ OSDI} 20). 863\u2013879.","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody\u00a0Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, 2020. Ansor: Generating high-performance tensor programs for deep learning. In 14th { USENIX} Symposium on Operating Systems Design and Implementation ({ OSDI} 20). 863\u2013879."},{"key":"e_1_3_2_2_21_1","volume-title":"TenSet: A Large-scale Program Performance Dataset for Learned Tensor Compilers. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).","author":"Zheng Lianmin","year":"2021","unstructured":"Lianmin Zheng, Ruochen Liu, Junru Shao, Tianqi Chen, Joseph\u00a0E Gonzalez, Ion Stoica, and Ameer\u00a0Haj Ali. 2021. TenSet: A Large-scale Program Performance Dataset for Learned Tensor Compilers. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507723"},{"key":"e_1_3_2_2_24_1","volume-title":"ROLLER: Fast and Efficient Tensor Compilation for Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zhu Hongyu","year":"2022","unstructured":"Hongyu Zhu, Ruofan Wu, Yijia Diao, Shanbin Ke, Haoyu Li, Chen Zhang, Jilong Xue, Lingxiao Ma, Yuqing Xia, Wei Cui, Fan Yang, Mao Yang, Lidong Zhou, Asaf Cidon, and Gennady Pekhimenko. 2022. ROLLER: Fast and Efficient Tensor Compilation for Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). Carlsbad, CA, 233\u2013248."}],"event":{"name":"ICPP 2023: 52nd International Conference on Parallel Processing","location":"Salt Lake City UT USA","acronym":"ICPP 2023"},"container-title":["Proceedings of the 52nd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605596","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605573.3605596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:04Z","timestamp":1750182544000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605596"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":24,"alternative-id":["10.1145\/3605573.3605596","10.1145\/3605573"],"URL":"https:\/\/doi.org\/10.1145\/3605573.3605596","relation":{},"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-09-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}