{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T06:13:34Z","timestamp":1781244814639,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T00:00:00Z","timestamp":1624492800000},"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":[[2021,6,24]]},"DOI":"10.1145\/3458864.3467882","type":"proceedings-article","created":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T16:13:50Z","timestamp":1624378430000},"page":"81-93","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":162,"title":["nn-Meter"],"prefix":"10.1145","author":[{"given":"Li Lyna","family":"Zhang","sequence":"first","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihao","family":"Han","sequence":"additional","affiliation":[{"name":"Microsoft Research and Rose-Hulman Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyu","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Research and University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningxin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Cao","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqing","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,6,24]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322967"},{"key":"e_1_3_2_1_2_1","volume-title":"Eagle: Efficient and Agile Performance Estimator and Dataset. https:\/\/github.com\/thomasccp\/eagle.","author":"BRP-NAS","year":"2020","unstructured":"BRP-NAS authors. 2020 . Eagle: Efficient and Agile Performance Estimator and Dataset. https:\/\/github.com\/thomasccp\/eagle. BRP-NAS authors. 2020. Eagle: Efficient and Agile Performance Estimator and Dataset. https:\/\/github.com\/thomasccp\/eagle."},{"key":"e_1_3_2_1_3_1","unstructured":"Andrea Di Biagio. 2018. llvm-mca: a static performance analysis tool.  Andrea Di Biagio. 2018. llvm-mca: a static performance analysis tool."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the Ninth Asian Conference on Machine Learning (Proceedings of Machine Learning Research). PMLR, 622--637","author":"Cai Ermao","year":"2017","unstructured":"Ermao Cai , Da-Cheng Juan , Dimitrios Stamoulis , and Diana Marculescu . 2017 . NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks . In Proceedings of the Ninth Asian Conference on Machine Learning (Proceedings of Machine Learning Research). PMLR, 622--637 . Ermao Cai, Da-Cheng Juan, Dimitrios Stamoulis, and Diana Marculescu. 2017. NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks. In Proceedings of the Ninth Asian Conference on Machine Learning (Proceedings of Machine Learning Research). PMLR, 622--637."},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Cai Han","year":"2020","unstructured":"Han Cai , Chuang Gan , Tianzhe Wang , Zhekai Zhang , and Song Han . 2020 . Once-for-all: Train One Network and Specialize it for Efficient Deployment . In International Conference on Learning Representations (ICLR). Han Cai, Chuang Gan, Tianzhe Wang, Zhekai Zhang, and Song Han. 2020. Once-for-all: Train One Network and Specialize it for Efficient Deployment. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_7_1","volume-title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. In International Conference on Learning Representations (ICLR).","author":"Cai Han","year":"2019","unstructured":"Han Cai , Ligeng Zhu , and Song Han . 2019 . ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. In International Conference on Learning Representations (ICLR). Han Cai, Ligeng Zhu, and Song Han. 2019. ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_9_1","volume-title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Association","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 . 2018 . TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Association , Carlsbad, CA, 578--594. 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. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Association, Carlsbad, CA, 578--594."},{"key":"e_1_3_2_1_10_1","volume-title":"Learning to Optimize Tensor Programs (NIPS'18)","author":"Chen Tianqi","unstructured":"Tianqi Chen , Lianmin Zheng , Eddie Yan , Ziheng Jiang , Thierry Moreau , Luis Ceze , Carlos Guestrin , and Arvind Krishnamurthy . 2018. Learning to Optimize Tensor Programs (NIPS'18) . Curran Associates Inc., Red Hook, NY, USA , 3393--3404. Tianqi Chen, Lianmin Zheng, Eddie Yan, Ziheng Jiang, Thierry Moreau, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. Learning to Optimize Tensor Programs (NIPS'18). Curran Associates Inc., Red Hook, NY, USA, 3393--3404."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01166"},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Dong Xuanyi","year":"2020","unstructured":"Xuanyi Dong and Yi Yang . 2020 . NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search . In International Conference on Learning Representations (ICLR). Xuanyi Dong and Yi Yang. 2020. NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_13_1","volume-title":"Lin (Eds.)","volume":"33","author":"Dudziak Lukasz","year":"2020","unstructured":"Lukasz Dudziak , Thomas Chau , Mohamed Abdelfattah , Royson Lee , Hyeji Kim , and Nicholas Lane . 2020 . BRP-NAS: Prediction-based NAS using GCNs. In Advances in Neural Information Processing Systems (Neurips), H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H . Lin (Eds.) , Vol. 33 . Curran Associates, Inc., 10480--10490. https:\/\/proceedings.neurips.cc\/paper\/ 2020\/file\/768e78024aa8fdb9b8fe87be86f64745-Paper.pdf Lukasz Dudziak, Thomas Chau, Mohamed Abdelfattah, Royson Lee, Hyeji Kim, and Nicholas Lane. 2020. BRP-NAS: Prediction-based NAS using GCNs. In Advances in Neural Information Processing Systems (Neurips), H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 10480--10490. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/768e78024aa8fdb9b8fe87be86f64745-Paper.pdf"},{"key":"e_1_3_2_1_14_1","volume-title":"Trained Quantization and Huffman Coding. In International Conference on Learning Representations (ICLR).","author":"Han Song","unstructured":"Song Han , Huizi Mao , and William J. Dally . 2016. Deep Compression: Compressing Deep Neural Networks with Pruning , Trained Quantization and Huffman Coding. In International Conference on Learning Representations (ICLR). Song Han, Huizi Mao, and William J. Dally. 2016. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_15_1","volume-title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices. In European Conference on Computer Vision (ECCV).","author":"He Yihui","year":"2018","unstructured":"Yihui He , Ji Lin , Zhijian Liu , Hanrui Wang , Li-Jia Li , and Song Han . 2018 . AMC: AutoML for Model Compression and Acceleration on Mobile Devices. In European Conference on Computer Vision (ECCV). Yihui He, Ji Lin, Zhijian Liu, Hanrui Wang, Li-Jia Li, and Song Han. 2018. AMC: AutoML for Model Compression and Acceleration on Mobile Devices. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_16_1","unstructured":"Ling Huang Jinzhu Jia Bin Yu Byung-Gon Chun Petros Maniatis and Mayur Naik. 2010. Predicting Execution Time of Computer Programs Using Sparse Polynomial Regression. In Advances in Neural Information Processing Systems (NIPS).  Ling Huang Jinzhu Jia Bin Yu Byung-Gon Chun Petros Maniatis and Mayur Naik. 2010. Predicting Execution Time of Computer Programs Using Sparse Polynomial Regression. In Advances in Neural Information Processing Systems (NIPS)."},{"key":"e_1_3_2_1_17_1","unstructured":"Intel. 2019. Deploy High-Performance Deep Learning Inference Open-VINO. https:\/\/software.intel.com\/content\/www\/us\/en\/develop\/tools\/openvino-toolkit.html.  Intel. 2019. Deploy High-Performance Deep Learning Inference Open-VINO. https:\/\/software.intel.com\/content\/www\/us\/en\/develop\/tools\/openvino-toolkit.html."},{"key":"e_1_3_2_1_18_1","unstructured":"Gideon Stupp Israel Hirsh. 2019. Intel Architecture Code Analyzer.  Gideon Stupp Israel Hirsh. 2019. Intel Architecture Code Analyzer."},{"key":"e_1_3_2_1_19_1","volume-title":"Learned TPU Cost Model for XLA Tensor Programs. NeurIPS workshop.","author":"Kaufman Samuel J.","year":"2019","unstructured":"Samuel J. Kaufman , Phitchaya Mangpo Phothilimthana , and Mike Burrows . 2019 . Learned TPU Cost Model for XLA Tensor Programs. NeurIPS workshop. Samuel J. Kaufman, Phitchaya Mangpo Phothilimthana, and Mike Burrows. 2019. Learned TPU Cost Model for XLA Tensor Programs. NeurIPS workshop."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Breiman Leo. 2001. Random Forests. In Machine Learning. 5--32.  Breiman Leo. 2001. Random Forests. In Machine Learning. 5--32.","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_2_1_22_1","volume-title":"Pruning Filters for Efficient ConvNets. In The International Conference on Learning Representations (ICLR).","author":"Li Hao","year":"2017","unstructured":"Hao Li , Asim Kadav , Igor Durdanovic , Hanan Samet , and Hans Peter Graf . 2017 . Pruning Filters for Efficient ConvNets. In The International Conference on Learning Representations (ICLR). Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2017. Pruning Filters for Efficient ConvNets. In The International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_23_1","volume-title":"DARTS: Differentiable Architecture Search. In International Conference on Learning Representations (ICLR).","author":"Liu Hanxiao","year":"2019","unstructured":"Hanxiao Liu , Karen Simonyan , and Yiming Yang . 2019 . DARTS: Differentiable Architecture Search. In International Conference on Learning Representations (ICLR). Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2019. DARTS: Differentiable Architecture Search. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Liu Zechun","year":"2019","unstructured":"Zechun Liu , Haoyuan Mu , Xiangyu Zhang , Zichao Guo , Tim Kwang-Ting Cheng Xin Yang , and Jian Sun . 2019 . MetaPruning: Meta Learning for Automatic Neural Architecture Channel Pruning . In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). Zechun Liu, Haoyuan Mu, Xiangyu Zhang, Zichao Guo, Tim Kwang-Ting Cheng Xin Yang, and Jian Sun. 2019. MetaPruning: Meta Learning for Automatic Neural Architecture Channel Pruning. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML). 4505--4515","author":"Mendis Charith","year":"2019","unstructured":"Charith Mendis , Alex Renda , Saman Amarasinghe , and Michael Carbin . 2019 . Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks . In Proceedings of the 36th International Conference on Machine Learning (ICML). 4505--4515 . Charith Mendis, Alex Renda, Saman Amarasinghe, and Michael Carbin. 2019. Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks. In Proceedings of the 36th International Conference on Machine Learning (ICML). 4505--4515."},{"key":"e_1_3_2_1_26_1","unstructured":"Microsoft. 2019. Neural Network Intelligence. https:\/\/github.com\/microsoft\/nni.  Microsoft. 2019. Neural Network Intelligence. https:\/\/github.com\/microsoft\/nni."},{"key":"e_1_3_2_1_27_1","volume-title":"Paleo: A Performance Model for Deep Neural Networks. In International Conference on Learning Representations (ICLR).","author":"Qi Hang","year":"2017","unstructured":"Hang Qi , Evan R. Sparks , and Ameet Talwalkar . 2017 . Paleo: A Performance Model for Deep Neural Networks. In International Conference on Learning Representations (ICLR). Hang Qi, Evan R. Sparks, and Ameet Talwalkar. 2017. Paleo: A Performance Model for Deep Neural Networks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_28_1","volume-title":"Precious: Resource-Demand Estimation for Embedded Neural Network Accelerators. In First International Workshop on Benchmarking Machine Learning Workloads on Emerging Hardware.","author":"Reif Stefan","year":"2020","unstructured":"Stefan Reif , Judith Hemp Benedict Herzog , Timo H\u00f6nig , and Wolfgang Schr\u00f6der-Preikschat . 2020 . Precious: Resource-Demand Estimation for Embedded Neural Network Accelerators. In First International Workshop on Benchmarking Machine Learning Workloads on Emerging Hardware. Stefan Reif, Judith Hemp Benedict Herzog, Timo H\u00f6nig, and Wolfgang Schr\u00f6der-Preikschat. 2020. Precious: Resource-Demand Estimation for Embedded Neural Network Accelerators. In First International Workshop on Benchmarking Machine Learning Workloads on Emerging Hardware."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"e_1_3_2_1_31_1","unstructured":"Iulia Turc Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. Well-Read Students Learn Better: On the Importance of Pre-training Compact Models. arXiv:1908.08962 [cs.CL]  Iulia Turc Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. Well-Read Students Learn Better: On the Importance of Pre-training Compact Models. arXiv:1908.08962 [cs.CL]"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313591"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00354"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"}],"event":{"name":"MobiSys '21: The 19th Annual International Conference on Mobile Systems, Applications, and Services","location":"Virtual Event Wisconsin","acronym":"MobiSys '21","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3458864.3467882","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3458864.3467882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:55Z","timestamp":1750195495000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3458864.3467882"}},"subtitle":["towards accurate latency prediction of deep-learning model inference on diverse edge devices"],"short-title":[],"issued":{"date-parts":[[2021,6,24]]},"references-count":35,"alternative-id":["10.1145\/3458864.3467882","10.1145\/3458864"],"URL":"https:\/\/doi.org\/10.1145\/3458864.3467882","relation":{},"subject":[],"published":{"date-parts":[[2021,6,24]]},"assertion":[{"value":"2021-06-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}