{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T11:41:22Z","timestamp":1790595682626,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-1900904"],"award-info":[{"award-number":["CCF-1900904"]}],"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":[[2023,10,28]]},"DOI":"10.1145\/3613424.3614265","type":"proceedings-article","created":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T17:22:15Z","timestamp":1702056135000},"page":"756-768","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["NAS-SE: Designing A Highly-Efficient In-Situ Neural Architecture Search Engine for Large-Scale Deployment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8529-5175","authenticated-orcid":false,"given":"Qiyu","family":"Wan","sequence":"first","affiliation":[{"name":"NVIDIA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7717-1199","authenticated-orcid":false,"given":"Lening","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Houston, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3653-7013","authenticated-orcid":false,"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Renmin University of China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8402-1436","authenticated-orcid":false,"given":"Shuaiwen Leon","family":"Song","sequence":"additional","affiliation":[{"name":"Microsoft, USA and University of Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9458-4769","authenticated-orcid":false,"given":"Xin","family":"Fu","sequence":"additional","affiliation":[{"name":"University of Houston, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,12,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304049"},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Machine Learning. PMLR, 550\u2013559","author":"Bender Gabriel","year":"2018","unstructured":"Gabriel Bender , Pieter-Jan Kindermans , Barret Zoph , Vijay Vasudevan , and Quoc Le . 2018 . Understanding and simplifying one-shot architecture search . In International Conference on Machine Learning. PMLR, 550\u2013559 . Gabriel Bender, Pieter-Jan Kindermans, Barret Zoph, Vijay Vasudevan, and Quoc Le. 2018. Understanding and simplifying one-shot architecture search. In International Conference on Machine Learning. PMLR, 550\u2013559."},{"key":"e_1_3_2_1_3_1","volume-title":"Smash: one-shot model architecture search through hypernetworks. arXiv preprint arXiv:1708.05344","author":"Brock Andrew","year":"2017","unstructured":"Andrew Brock , Theodore Lim , James\u00a0 M Ritchie , and Nick Weston . 2017. Smash: one-shot model architecture search through hypernetworks. arXiv preprint arXiv:1708.05344 ( 2017 ). Andrew Brock, Theodore Lim, James\u00a0M Ritchie, and Nick Weston. 2017. Smash: one-shot model architecture search through hypernetworks. arXiv preprint arXiv:1708.05344 (2017)."},{"key":"e_1_3_2_1_4_1","volume-title":"Once-for-all: Train one network and specialize it for efficient deployment. arXiv preprint arXiv:1908.09791","author":"Cai Han","year":"2019","unstructured":"Han Cai , Chuang Gan , Tianzhe Wang , Zhekai Zhang , and Song Han . 2019 . Once-for-all: Train one network and specialize it for efficient deployment. arXiv preprint arXiv:1908.09791 (2019). Han Cai, Chuang Gan, Tianzhe Wang, Zhekai Zhang, and Song Han. 2019. Once-for-all: Train one network and specialize it for efficient deployment. arXiv preprint arXiv:1908.09791 (2019)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proxylessnas: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332","author":"Cai Han","year":"2018","unstructured":"Han Cai , Ligeng Zhu , and Song Han . 2018 . Proxylessnas: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332 (2018). Han Cai, Ligeng Zhu, and Song Han. 2018. Proxylessnas: Direct neural architecture search on target task and hardware. arXiv preprint arXiv:1812.00332 (2018)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310400"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001140"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01202"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00378"},{"key":"e_1_3_2_1_14_1","volume-title":"Efficient multi-objective neural architecture search via lamarckian evolution. arXiv preprint arXiv:1804.09081","author":"Elsken Thomas","year":"2018","unstructured":"Thomas Elsken , Jan\u00a0Hendrik Metzen , and Frank Hutter . 2018. Efficient multi-objective neural architecture search via lamarckian evolution. arXiv preprint arXiv:1804.09081 ( 2018 ). Thomas Elsken, Jan\u00a0Hendrik Metzen, and Frank Hutter. 2018. Efficient multi-objective neural architecture search via lamarckian evolution. arXiv preprint arXiv:1804.09081 (2018)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.05.013"},{"key":"e_1_3_2_1_19_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard G","year":"2017","unstructured":"Andrew\u00a0 G Howard , Menglong Zhu , Bo Chen , Dmitry Kalenichenko , Weijun Wang , Tobias Weyand , Marco Andreetto , and Hartwig Adam . 2017 . Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017). Andrew\u00a0G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8621865"},{"key":"e_1_3_2_1_21_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 237\u2013240","author":"Ji Houxiang","year":"2018","unstructured":"Houxiang Ji , Linghao Song , Li Jiang , Hai Li , and Yiran Chen . 2018 . ReCom: An efficient resistive accelerator for compressed deep neural networks. In 2018 Design , Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 237\u2013240 . Houxiang Ji, Linghao Song, Li Jiang, Hai Li, and Yiran Chen. 2018. ReCom: An efficient resistive accelerator for compressed deep neural networks. In 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 237\u2013240."},{"key":"e_1_3_2_1_22_1","volume-title":"Evolutionary deep learning to identify galaxies in the zone of avoidance. arXiv preprint arXiv:1903.07461","author":"Jones David","year":"2019","unstructured":"David Jones , Anja Schroeder , and Geoff Nitschke . 2019. Evolutionary deep learning to identify galaxies in the zone of avoidance. arXiv preprint arXiv:1903.07461 ( 2019 ). David Jones, Anja Schroeder, and Geoff Nitschke. 2019. Evolutionary deep learning to identify galaxies in the zone of avoidance. arXiv preprint arXiv:1903.07461 (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"Reduced-precision strategies for bounded memory in deep neural nets. arXiv preprint arXiv:1511.05236","author":"Judd Patrick","year":"2015","unstructured":"Patrick Judd , Jorge Albericio , Tayler Hetherington , Tor Aamodt , Natalie\u00a0Enright Jerger , Raquel Urtasun , and Andreas Moshovos . 2015. Reduced-precision strategies for bounded memory in deep neural nets. arXiv preprint arXiv:1511.05236 ( 2015 ). Patrick Judd, Jorge Albericio, Tayler Hetherington, Tor Aamodt, Natalie\u00a0Enright Jerger, Raquel Urtasun, and Andreas Moshovos. 2015. Reduced-precision strategies for bounded memory in deep neural nets. arXiv preprint arXiv:1511.05236 (2015)."},{"key":"e_1_3_2_1_24_1","volume-title":"Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055","author":"Liu Hanxiao","year":"2018","unstructured":"Hanxiao Liu , Karen Simonyan , and Yiming Yang . 2018 . Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018). Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.29"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_3"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321729"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00067"},{"key":"e_1_3_2_1_30_1","volume-title":"Atomnas: Fine-grained end-to-end neural architecture search. arXiv preprint arXiv:1912.09640","author":"Mei Jieru","year":"2019","unstructured":"Jieru Mei , Yingwei Li , Xiaochen Lian , Xiaojie Jin , Linjie Yang , Alan Yuille , and Jianchao Yang . 2019 . Atomnas: Fine-grained end-to-end neural architecture search. arXiv preprint arXiv:1912.09640 (2019). Jieru Mei, Yingwei Li, Xiaochen Lian, Xiaojie Jin, Linjie Yang, Alan Yuille, and Jianchao Yang. 2019. Atomnas: Fine-grained end-to-end neural architecture search. arXiv preprint arXiv:1912.09640 (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.33"},{"key":"e_1_3_2_1_32_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703","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 , 2019 . Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019). Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"key":"e_1_3_2_1_35_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"e_1_3_2_1_37_1","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 481\u2013497","author":"Stamoulis Dimitrios","year":"2019","unstructured":"Dimitrios Stamoulis , Ruizhou Ding , Di Wang , Dimitrios Lymberopoulos , Bodhi Priyantha , Jie Liu , and Diana Marculescu . 2019 . Single-path nas: Designing hardware-efficient convnets in less than 4 hours . In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 481\u2013497 . Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, and Diana Marculescu. 2019. Single-path nas: Designing hardware-efficient convnets in less than 4 hours. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 481\u2013497."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"e_1_3_2_1_41_1","volume-title":"International conference on machine learning. PMLR, 6105\u20136114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le . 2019 . Efficientnet: Rethinking model scaling for convolutional neural networks . In International conference on machine learning. PMLR, 6105\u20136114 . Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105\u20136114."},{"key":"e_1_3_2_1_42_1","volume-title":"International Conference on Machine Learning. PMLR, 10096\u201310106","author":"Tan Mingxing","year":"2021","unstructured":"Mingxing Tan and Quoc Le . 2021 . Efficientnetv2: Smaller models and faster training . In International Conference on Machine Learning. PMLR, 10096\u201310106 . Mingxing Tan and Quoc Le. 2021. Efficientnetv2: Smaller models and faster training. In International Conference on Machine Learning. PMLR, 10096\u201310106."},{"key":"e_1_3_2_1_43_1","volume-title":"Mixconv: Mixed depthwise convolutional kernels. arXiv preprint arXiv:1907.09595","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc\u00a0 V Le . 2019 . Mixconv: Mixed depthwise convolutional kernels. arXiv preprint arXiv:1907.09595 (2019). Mingxing Tan and Quoc\u00a0V Le. 2019. Mixconv: Mixed depthwise convolutional kernels. arXiv preprint arXiv:1907.09595 (2019)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00030"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480120"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2836316"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2895748"},{"key":"e_1_3_2_1_48_1","volume-title":"Hat: Hardware-aware transformers for efficient natural language processing. arXiv preprint arXiv:2005.14187","author":"Wang Hanrui","year":"2020","unstructured":"Hanrui Wang , Zhanghao Wu , Zhijian Liu , Han Cai , Ligeng Zhu , Chuang Gan , and Song Han . 2020 . Hat: Hardware-aware transformers for efficient natural language processing. arXiv preprint arXiv:2005.14187 (2020). Hanrui Wang, Zhanghao Wu, Zhijian Liu, Han Cai, Ligeng Zhu, Chuang Gan, and Song Han. 2020. Hat: Hardware-aware transformers for efficient natural language processing. arXiv preprint arXiv:2005.14187 (2020)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465793"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"e_1_3_2_1_51_1","unstructured":"Xilinx. 2020. Xilinx Vivado. Retrieved June 8 2021 from https:\/\/www.xilinx.com\/support\/university\/vivado.html  Xilinx. 2020. Xilinx Vivado. Retrieved June 8 2021 from https:\/\/www.xilinx.com\/support\/university\/vivado.html"},{"key":"e_1_3_2_1_52_1","volume-title":"Pc-darts: Partial channel connections for memory-efficient architecture search. arXiv preprint arXiv:1907.05737","author":"Xu Yuhui","year":"2019","unstructured":"Yuhui Xu , Lingxi Xie , Xiaopeng Zhang , Xin Chen , Guo-Jun Qi , Qi Tian , and Hongkai Xiong . 2019 . Pc-darts: Partial channel connections for memory-efficient architecture search. arXiv preprint arXiv:1907.05737 (2019). Yuhui Xu, Lingxi Xie, Xiaopeng Zhang, Xin Chen, Guo-Jun Qi, Qi Tian, and Hongkai Xiong. 2019. Pc-darts: Partial channel connections for memory-efficient architecture search. arXiv preprint arXiv:1907.05737 (2019)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662395"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322271"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415640"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00207"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3459988"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00051"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507723"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00257"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"event":{"name":"MICRO '23: 56th Annual IEEE\/ACM International Symposium on Microarchitecture","location":"Toronto ON Canada","acronym":"MICRO '23","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["56th Annual IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613424.3614265","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613424.3614265","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613424.3614265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:21Z","timestamp":1750178781000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613424.3614265"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,28]]},"references-count":62,"alternative-id":["10.1145\/3613424.3614265","10.1145\/3613424"],"URL":"https:\/\/doi.org\/10.1145\/3613424.3614265","relation":{},"subject":[],"published":{"date-parts":[[2023,10,28]]},"assertion":[{"value":"2023-12-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}