{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T01:10:05Z","timestamp":1780708205304,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":77,"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-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-SC0021293"],"award-info":[{"award-number":["DE-SC0021293"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2312207"],"award-info":[{"award-number":["CNS-2312207"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2047516 (CAREER)"],"award-info":[{"award-number":["CCF-2047516 (CAREER)"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2146873"],"award-info":[{"award-number":["CCF-2146873"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2230944"],"award-info":[{"award-number":["CNS-2230944"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["III-2008557"],"award-info":[{"award-number":["III-2008557"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2341378"],"award-info":[{"award-number":["CNS-2341378"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2333895"],"award-info":[{"award-number":["CCF-2333895"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["OAC-2333899"],"award-info":[{"award-number":["OAC-2333899"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2334273"],"award-info":[{"award-number":["CCF-2334273"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3620666.3651384","type":"proceedings-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T12:08:21Z","timestamp":1713960501000},"page":"916-931","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2697-7042","authenticated-orcid":false,"given":"Wei","family":"Niu","sequence":"first","affiliation":[{"name":"University of Georgia, Athens, Georgia, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8431-3699","authenticated-orcid":false,"given":"Md Musfiqur Rahman","family":"Sanim","sequence":"additional","affiliation":[{"name":"University of Georgia, Athens, Georgia, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8749-7115","authenticated-orcid":false,"given":"Zhihao","family":"Shu","sequence":"additional","affiliation":[{"name":"University of Georgia, Athens, Georgia, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5274-9169","authenticated-orcid":false,"given":"Jiexiong","family":"Guan","sequence":"additional","affiliation":[{"name":"William & Mary, Williamsburg, Virginia, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-8010","authenticated-orcid":false,"given":"Xipeng","family":"Shen","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, North Carolina, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5554-5417","authenticated-orcid":false,"given":"Miao","family":"Yin","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, Texas, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2609-1428","authenticated-orcid":false,"given":"Gagan","family":"Agrawal","sequence":"additional","affiliation":[{"name":"University of Georgia, Athens, Georgia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4116-5237","authenticated-orcid":false,"given":"Bin","family":"Ren","sequence":"additional","affiliation":[{"name":"William & Mary, Williamsburg, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"265","volume-title":"OSDI 2016","author":"Abadi Martin","year":"2016","unstructured":"Martin 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. Tensor-flow: A system for large-scale machine learning. In OSDI 2016, pages 265--283, USA, 2016. USENIX Association."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3168805"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_4_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E Peters, and Arman Cohan. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150, 2020."},{"key":"e_1_3_2_1_5_1","first-page":"4","volume-title":"ICML","volume":"2","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. Is space-time attention all you need for video understanding? In ICML, volume 2, page 4, 2021."},{"key":"e_1_3_2_1_6_1","first-page":"2397","volume-title":"International Conference on Machine Learning","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O'Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, et al. Pythia: A suite for analyzing large language models across training and scaling. In International Conference on Machine Learning, pages 2397--2430. PMLR, 2023."},{"key":"e_1_3_2_1_7_1","volume-title":"Efficientvit: Enhanced linear attention for high-resolution low-computation visual recognition. arXiv preprint arXiv:2205.14756","author":"Cai Han","year":"2022","unstructured":"Han Cai, Chuang Gan, and Song Han. Efficientvit: Enhanced linear attention for high-resolution low-computation visual recognition. arXiv preprint arXiv:2205.14756, 2022."},{"key":"e_1_3_2_1_8_1","first-page":"12270","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Chen Minghao","year":"2021","unstructured":"Minghao Chen, Houwen Peng, Jianlong Fu, and Haibin Ling. Auto-former: Searching transformers for visual recognition. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pages 12270--12280, October 2021."},{"key":"e_1_3_2_1_9_1","first-page":"8714","article-title":"Searching the search space of vision transformer","volume":"34","author":"Chen Minghao","year":"2021","unstructured":"Minghao Chen, Kan Wu, Bolin Ni, Houwen Peng, Bei Liu, Jianlong Fu, Hongyang Chao, and Haibin Ling. Searching the search space of vision transformer. Advances in Neural Information Processing Systems, 34:8714--8726, 2021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","first-page":"578","volume-title":"OSDI 2018","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. Tvm: An automated end-to-end optimizing compiler for deep learning. In OSDI 2018, pages 578--594, 2018."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00490"},{"key":"e_1_3_2_1_12_1","volume-title":"Coatnet: Marrying convolution and attention for all data sizes. Advances in neural information processing systems, 34:3965--3977","author":"Dai Zihang","year":"2021","unstructured":"Zihang Dai, Hanxiao Liu, Quoc V Le, and Mingxing Tan. Coatnet: Marrying convolution and attention for all data sizes. Advances in neural information processing systems, 34:3965--3977, 2021."},{"key":"e_1_3_2_1_13_1","volume-title":"Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691","author":"Dao Tri","year":"2023","unstructured":"Tri Dao. Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691, 2023."},{"key":"e_1_3_2_1_14_1","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems, 35:16344--16359, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_16_1","volume-title":"Beyond the safeguards: Exploring the security risks of chatgpt","author":"Derner Erik","year":"2023","unstructured":"Erik Derner and Kristina Batisti\u010d. Beyond the safeguards: Exploring the security risks of chatgpt, 2023."},{"key":"e_1_3_2_1_17_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, Minneapolis, Minnesota, 2019. Association for Computational Linguistics."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2994150"},{"key":"e_1_3_2_1_19_1","volume-title":"Cswin transformer: A general vision transformer backbone with cross-shaped windows","author":"Dong Xiaoyi","year":"2021","unstructured":"Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang, Nenghai Yu, Lu Yuan, Dong Chen, and Baining Guo. Cswin transformer: A general vision transformer backbone with cross-shaped windows, 2021."},{"key":"e_1_3_2_1_20_1","volume-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. An image is worth 16\u00d716 words: Transformers for image recognition at scale, 2020."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3576933"},{"key":"e_1_3_2_1_23_1","volume-title":"Tensorflow xla. https:\/\/www.tensorflow.org\/xla","year":"2023","unstructured":"Google. Tensorflow xla. https:\/\/www.tensorflow.org\/xla, 2023."},{"key":"e_1_3_2_1_24_1","first-page":"5036","volume-title":"21st Annual Conference of the International Speech Communication Association, Virtual Event","author":"Gulati Anmol","year":"2020","unstructured":"Anmol Gulati, James Qin, Chung-Cheng Chiu, Niki Parmar, Yu Zhang, Jiahui Yu, Wei Han, Shibo Wang, Zhengdong Zhang, Yonghui Wu, and Ruoming Pang. Conformer: Convolution-augmented transformer for speech recognition. In Helen Meng, Bo Xu, and Thomas Fang Zheng, editors, Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020, pages 5036--5040. ISCA, 2020."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Han Dongchen","year":"2023","unstructured":"Dongchen Han, Xuran Pan, Yizeng Han, Shiji Song, and Gao Huang. Flatten transformer: Vision transformer using focused linear attention. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 2023."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3081333.3081360"},{"key":"e_1_3_2_1_29_1","first-page":"711","article-title":"Data movement is all you need: A case study on optimizing transformers","volume":"3","author":"Ivanov Andrei","year":"2021","unstructured":"Andrei Ivanov, Nikoli Dryden, Tal Ben-Nun, Shigang Li, and Torsten Hoefler. Data movement is all you need: A case study on optimizing transformers. Proceedings of Machine Learning and Systems, 3:711--732, 2021.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538948"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538932"},{"key":"e_1_3_2_1_32_1","first-page":"1","article-title":"Mnn: A universal and efficient inference engine","volume":"2","author":"Jiang Xiaotang","year":"2020","unstructured":"Xiaotang Jiang, Huan Wang, Yiliu Chen, Ziqi Wu, Lichuan Wang, Bin Zou, Yafeng Yang, Zongyang Cui, Yu Cai, Tianhang Yu, et al. Mnn: A universal and efficient inference engine. Proceedings of Machine Learning and Systems, 2:1--13, 2020.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_33_1","volume-title":"Ultralytics yolov8","author":"Jocher Glenn","year":"2023","unstructured":"Glenn Jocher, Ayush Chaurasia, and Jing Qiu. Ultralytics yolov8, 2023."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/290940.290999"},{"key":"e_1_3_2_1_36_1","volume-title":"Architecture and System Support for Transformer Models (ASSYST@ ISCA","author":"Kim Sehoon","year":"2023","unstructured":"Sehoon Kim, Coleman Hooper, Thanakul Wattanawong, Minwoo Kang, Ruohan Yan, Hasan Genc, Grace Dinh, Qijing Huang, Kurt Keutzer, Michael W Mahoney, et al. Full stack optimization of transformer inference. In Architecture and System Support for Transformer Models (ASSYST@ ISCA 2023), 2023."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/2959355.2959378"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2750858.2804262"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345455"},{"key":"e_1_3_2_1_41_1","volume-title":"The 28th Annual International Conference On Mobile Computing And Networking (MobiCom 2022","author":"Liang Rendong","year":"2022","unstructured":"Rendong Liang, Ting Cao, Jicheng Wen, Manni Wang, Yang Wang, Jianhua Zou, and Yunxin Liu. Romou: Rapidly generate high-performance tensor kernels for mobile gpus. In The 28th Annual International Conference On Mobile Computing And Networking (MobiCom 2022). ACM, February 2022."},{"key":"e_1_3_2_1_42_1","volume-title":"Piotr Doll'a r, and C. Lawrence Zitnick. Microsoft COCO: common objects in context. CoRR, abs\/1405.0312","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge J. Belongie, Lubomir D. Bourdev, Ross B. Girshick, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll'a r, and C. Lawrence Zitnick. Microsoft COCO: common objects in context. CoRR, abs\/1405.0312, 2014."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568520"},{"key":"e_1_3_2_1_45_1","first-page":"1025","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Liu Yizhi","year":"2019","unstructured":"Yizhi Liu, Yao Wang, Ruofei Yu, Mu Li, Vin Sharma, and Yida Wang. Optimizing {CNN} model inference on {CPUs}. In 2019 USENIX Annual Technical Conference (USENIX ATC 19), pages 1025--1040, 2019."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278773"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.577265"},{"key":"e_1_3_2_1_50_1","volume-title":"June","author":"Ni Hui","year":"2017","unstructured":"Hui Ni and The ncnn contributors. ncnn, June 2017."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454083"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.2001.1815"},{"key":"e_1_3_2_1_53_1","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","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 K\u00f6pf, 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 Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pages 8024--8035, 2019."},{"key":"e_1_3_2_1_54_1","unstructured":"PyTorch. TorchInductor January 2022."},{"key":"e_1_3_2_1_55_1","volume-title":"https:\/\/www.qualcomm.com\/products\/snapdragon-835-mobile-platform","author":"Snapdragon","year":"2016","unstructured":"Qualcomm. Snapdragon 835. https:\/\/www.qualcomm.com\/products\/snapdragon-835-mobile-platform, 2016."},{"key":"e_1_3_2_1_56_1","volume-title":"https:\/\/en.wikipedia.org\/wiki\/List_of_Qualcomm_Snapdragon_systems_on_chips","author":"Snapdragon","year":"2017","unstructured":"Qualcomm. Snapdragon 845. https:\/\/en.wikipedia.org\/wiki\/List_of_Qualcomm_Snapdragon_systems_on_chips, 2017."},{"issue":"8","key":"e_1_3_2_1_57_1","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.","journal-title":"OpenAI blog"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_60_1","first-page":"208","article-title":"Efficiently compiling dynamic neural networks for model inference","volume":"3","author":"Shen Haichen","year":"2021","unstructured":"Haichen Shen, Jared Roesch, Zhi Chen, Wei Chen, Yong Wu, Mu Li, Vin Sharma, Zachary Tatlock, and Yida Wang. Nimble: Efficiently compiling dynamic neural networks for model inference. Proceedings of Machine Learning and Systems, 3:208--222, 2021.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_61_1","first-page":"3","volume-title":"International Workshop on Languages and Compilers for Parallel Computing","author":"Shirako Jun","year":"2020","unstructured":"Jun Shirako and Vivek Sarkar. An affine scheduling framework for integrating data layout and loop transformations. In International Workshop on Languages and Compilers for Parallel Computing, pages 3--19. Springer, 2020."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460945.3464953"},{"key":"e_1_3_2_1_63_1","first-page":"865","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Sung Hsin-Hsuan","year":"2023","unstructured":"Hsin-Hsuan Sung, Jou-An Chen, Wei Niu, Jiexiong Guan, Bin Ren, and Xipeng Shen. Decentralized {Application-Level} adaptive scheduling for {Multi-Instance}{DNNs} on open mobile devices. In 2023 USENIX Annual Technical Conference (USENIX ATC 23), pages 865--877, 2023."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3412382.3458272"},{"key":"e_1_3_2_1_65_1","volume-title":"Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023."},{"key":"e_1_3_2_1_66_1","volume-title":"Convertlayout pass","author":"Apache","year":"2020","unstructured":"Apache TVM. Convertlayout pass, 2020."},{"key":"e_1_3_2_1_67_1","volume-title":"Attention is all you need. Advances in neural information processing systems, 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_68_1","first-page":"108","volume-title":"European conference on computer vision","author":"Wang Huiyu","year":"2020","unstructured":"Huiyu Wang, Yukun Zhu, Bradley Green, Hartwig Adam, Alan Yuille, and Liang-Chieh Chen. Axial-deeplab: Stand-alone axial-attention for panoptic segmentation. In European conference on computer vision, pages 108--126. Springer, 2020."},{"key":"e_1_3_2_1_69_1","volume-title":"International Conference on Learning Representations, ICLR","author":"Wang Wenxiao","year":"2022","unstructured":"Wenxiao Wang, Lu Yao, Long Chen, Binbin Lin, Deng Cai, Xiaofei He, and Wei Liu. Crossformer: A versatile vision transformer hinging on cross-scale attention. In International Conference on Learning Representations, ICLR, 2022."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00042"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241563"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"e_1_3_2_1_75_1","first-page":"351","volume-title":"Proceedings of the 26th International Conference on World Wide Web, WWW 2017","author":"Yao Shuochao","year":"2017","unstructured":"Shuochao Yao, Shaohan Hu, Yiran Zhao, Aston Zhang, and Tarek F. Abdelzaher. Deepsense: A unified deep learning framework for time-series mobile sensing data processing. In Rick Barrett, Rick Cummings, Eugene Agichtein, and Evgeniy Gabrilovich, editors, Proceedings of the 26th International Conference on World Wide Web, WWW 2017, Perth, Australia, April 3-7, 2017, pages 351--360. ACM, 2017."},{"key":"e_1_3_2_1_76_1","volume-title":"A survey of large language models. arXiv preprint arXiv:2303.18223","author":"Zhao Wayne Xin","year":"2023","unstructured":"Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, et al. A survey of large language models. arXiv preprint arXiv:2303.18223, 2023."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"}],"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\/3620666.3651384","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3620666.3651384","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"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\/3620666.3651384"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":77,"alternative-id":["10.1145\/3620666.3651384","10.1145\/3620666"],"URL":"https:\/\/doi.org\/10.1145\/3620666.3651384","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"}}]}}