{"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":1784762461225,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T00:00:00Z","timestamp":1677024000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Research Grants Council (RGC)-General Research Fund","award":["14209619"],"award-info":[{"award-number":["14209619"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,22]]},"DOI":"10.1145\/3572864.3580330","type":"proceedings-article","created":{"date-parts":[[2023,2,14]],"date-time":"2023-02-14T00:18:37Z","timestamp":1676333917000},"page":"22-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Moses"],"prefix":"10.1145","author":[{"given":"Zhihe","family":"Zhao","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xian","family":"Shuai","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neiwen","family":"Ling","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Guan","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Yan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoliang","family":"Xing","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,2,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Tensorflow: A system for large-scale machine learning. CoRR, abs\/1605.08695","author":"Mart\u00edn Abadi","year":"2016","unstructured":"Mart\u00edn Abadi et al. Tensorflow: A system for large-scale machine learning. CoRR, abs\/1605.08695, 2016."},{"key":"e_1_3_2_1_2_1","volume-title":"Chameleon: Adaptive code optimization for expedited deep neural network compilation. CoRR, abs\/2001.08743","author":"Ahn Byung Hoon","year":"2020","unstructured":"Byung Hoon Ahn, Prannoy Pilligundla, Amir Yazdanbakhsh, and Hadi Esmaeilzadeh. Chameleon: Adaptive code optimization for expedited deep neural network compilation. CoRR, abs\/2001.08743, 2020."},{"key":"e_1_3_2_1_3_1","volume-title":"A deep learning based cost model for automatic code optimization. CoRR, abs\/2104.04955","author":"Baghdadi Riyadh","year":"2021","unstructured":"Riyadh Baghdadi, Massinissa Merouani, Mohamed-Hicham Leghettas, Kamel Abdous, Taha Arbaoui, Karima Benatchba, and Saman P. Amarasinghe. A deep learning based cost model for automatic code optimization. CoRR, abs\/2104.04955, 2021."},{"key":"e_1_3_2_1_4_1","volume-title":"A deep learning based cost model for automatic code optimization. CoRR, abs\/2104.04955","author":"Baghdadi Riyadh","year":"2021","unstructured":"Riyadh Baghdadi, Massinissa Merouani, Mohamed-Hicham Leghettas, Kamel Abdous, Taha Arbaoui, Karima Benatchba, and Saman P. Amarasinghe. A deep learning based cost model for automatic code optimization. CoRR, abs\/2104.04955, 2021."},{"key":"e_1_3_2_1_5_1","volume-title":"Learning to optimize tensor programs. CoRR, abs\/1805.08166","author":"Tianqi Chen","year":"2018","unstructured":"Tianqi Chen et al. Learning to optimize tensor programs. CoRR, abs\/1805.08166, 2018."},{"key":"e_1_3_2_1_6_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Tianqi","year":"2018","unstructured":"Tianqi Chen et al. TVM: An automated end-to-end optimizing compiler for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18), October 2018."},{"key":"e_1_3_2_1_7_1","volume-title":"Bayesian nonparametric space partitions: A survey. arXiv preprint arXiv:2002.11394","author":"Xuhui Fan","year":"2020","unstructured":"Xuhui Fan et al. Bayesian nonparametric space partitions: A survey. arXiv preprint arXiv:2002.11394, 2020."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Learning Representations","author":"Jonathan","year":"2019","unstructured":"Jonathan Frankle et al. The lottery ticket hypothesis: Finding sparse, trainable neural networks. In International Conference on Learning Representations, 2019."},{"key":"e_1_3_2_1_9_1","volume-title":"Learning transferable parameters for unsupervised domain adaptation. arXiv preprint arXiv:2108.06129","author":"Han Zhongyi","year":"2021","unstructured":"Zhongyi Han, Haoliang Sun, and Yilong Yin. Learning transferable parameters for unsupervised domain adaptation. arXiv preprint arXiv:2108.06129, 2021."},{"key":"e_1_3_2_1_10_1","volume-title":"Intel mkl-dnn. https:\/\/oneapi-src.github.io\/oneDNN\/v0\/index.html","year":"2022","unstructured":"Intel. Intel mkl-dnn. https:\/\/oneapi-src.github.io\/oneDNN\/v0\/index.html, 2022."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454038"},{"key":"e_1_3_2_1_13_1","volume-title":"Yanqi Zhou, Charith Mendis, Sudip Roy, Amit Sabne, and Mike Burrows. A learned performance model for tensor processing units. arXiv preprint arXiv:2008.01040","author":"Kaufman Samuel J","year":"2020","unstructured":"Samuel J Kaufman, Phitchaya Mangpo Phothilimthana, Yanqi Zhou, Charith Mendis, Sudip Roy, Amit Sabne, and Mike Burrows. A learned performance model for tensor processing units. arXiv preprint arXiv:2008.01040, 2020."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358280"},{"key":"e_1_3_2_1_15_1","first-page":"14807","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Li Menghao","year":"2020","unstructured":"Menghao Li, Minjia Zhang, Chi Wang, and Mingqin Li. Adatune: Adaptive tensor program compilation made efficient. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 14807--14819. Curran Associates, Inc., 2020."},{"key":"e_1_3_2_1_16_1","volume-title":"The deep learning compiler: A comprehensive survey. CoRR, abs\/2002.03794","author":"Li Mingzhen","year":"2020","unstructured":"Mingzhen Li, Yi Liu, Xiaoyan Liu, Qingxiao Sun, Xin You, Hailong Yang, Zhongzhi Luan, and Depei Qian. The deep learning compiler: A comprehensive survey. CoRR, abs\/2002.03794, 2020."},{"issue":"4","key":"e_1_3_2_1_17_1","volume":"37","author":"Li Tzu-Mao","year":"2018","unstructured":"Tzu-Mao Li et al. Differentiable programming for image processing and deep learning in halide. ACM Trans. Graph., 37(4), July 2018.","journal-title":"ACM Trans. Graph."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485938"},{"key":"e_1_3_2_1_19_1","volume-title":"Domain adaptation: Learning bounds and algorithms. arXiv preprint arXiv:0902.3430","author":"Yishay Mansour","year":"2009","unstructured":"Yishay Mansour et al. Domain adaptation: Learning bounds and algorithms. arXiv preprint arXiv:0902.3430, 2009."},{"key":"e_1_3_2_1_20_1","volume-title":"H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc","author":"Mendis Charith","year":"2019","unstructured":"Charith Mendis, Cambridge Yang, Yewen Pu, Dr.Saman Amarasinghe, and Michael Carbin. Compiler auto-vectorization with imitation learning. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454083"},{"key":"e_1_3_2_1_22_1","volume-title":"Nvidia cudnn. https:\/\/docs.nvidia.com\/deeplearning\/cudnn\/api\/index.html","author":"NVIDIA.","year":"2022","unstructured":"NVIDIA. Nvidia cudnn. https:\/\/docs.nvidia.com\/deeplearning\/cudnn\/api\/index.html, 2022."},{"key":"e_1_3_2_1_23_1","volume-title":"Metatune: Meta-learning based cost model for fast and efficient auto-tuning frameworks. CoRR, abs\/2102.04199","author":"Ryu Jaehun","year":"2021","unstructured":"Jaehun Ryu and Hyojin Sung. Metatune: Meta-learning based cost model for fast and efficient auto-tuning frameworks. CoRR, abs\/2102.04199, 2021."},{"key":"e_1_3_2_1_24_1","volume-title":"Tlp: A deep learning-based cost model for tensor program tuning. arXiv preprint arXiv:2211.03578","author":"Zhai Yi","year":"2022","unstructured":"Yi Zhai, Yu Zhang, Shuo Liu, Xiaomeng Chu, Jie Peng, Jianmin Ji, and Yanyong Zhang. Tlp: A deep learning-based cost model for tensor program tuning. arXiv preprint arXiv:2211.03578, 2022."},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Learning Representations","author":"Zhang Minjia","year":"2021","unstructured":"Minjia Zhang, Menghao Li, Chi Wang, and Mingqin Li. Dynatune: Dynamic tensor program optimization in deep neural network compilation. In International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3275199"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450268.3453520"},{"key":"e_1_3_2_1_28_1","first-page":"859","volume-title":"Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '20","author":"Flextensor Zheng","year":"2020","unstructured":"Zheng et al. Flextensor: An automatic schedule exploration and optimization framework for tensor computation on heterogeneous system. In Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '20, page 859--873, New York, NY, USA, 2020. Association for Computing Machinery."},{"key":"e_1_3_2_1_29_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Lianmin","year":"2020","unstructured":"Lianmin Zheng et al. Ansor: Generating high-performance tensor programs for deep learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), November 2020."},{"key":"e_1_3_2_1_30_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)","author":"Lianmin","year":"2021","unstructured":"Lianmin Zheng et al. 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), 2021."}],"event":{"name":"HotMobile '23: The 24th International Workshop on Mobile Computing Systems and Applications","location":"Newport Beach California","acronym":"HotMobile '23","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the 24th International Workshop on Mobile Computing Systems and Applications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572864.3580330","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3572864.3580330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:10Z","timestamp":1750183690000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572864.3580330"}},"subtitle":["Exploiting Cross-Device Transferable Features for on-Device Tensor Program Optimization"],"short-title":[],"issued":{"date-parts":[[2023,2,22]]},"references-count":30,"alternative-id":["10.1145\/3572864.3580330","10.1145\/3572864"],"URL":"https:\/\/doi.org\/10.1145\/3572864.3580330","relation":{},"subject":[],"published":{"date-parts":[[2023,2,22]]},"assertion":[{"value":"2023-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}