{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T22:48:17Z","timestamp":1752101297700,"version":"3.37.3"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T00:00:00Z","timestamp":1705276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T00:00:00Z","timestamp":1705276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T00:00:00Z","timestamp":1705276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shaanxi Key Technology R&D Program","award":["2021ZDLGY07-01"],"award-info":[{"award-number":["2021ZDLGY07-01"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972302","61962019"],"award-info":[{"award-number":["61972302","61962019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["20199236325"],"award-info":[{"award-number":["20199236325"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2024,1,15]]},"DOI":"10.1109\/jiot.2023.3294253","type":"journal-article","created":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T17:26:54Z","timestamp":1689096414000},"page":"2964-2978","source":"Crossref","is-referenced-by-count":3,"title":["Performance Prediction for Deep Learning Models With Pipeline Inference Strategy"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3121-6299","authenticated-orcid":false,"given":"Zhenyi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4065-4052","authenticated-orcid":false,"given":"Pengfei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1857-0493","authenticated-orcid":false,"given":"Bowen","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"}]},{"given":"Linwei","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2276-053X","authenticated-orcid":false,"given":"Wenkai","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2138-3739","authenticated-orcid":false,"given":"Chengmin","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"}]},{"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6913-8604","authenticated-orcid":false,"given":"Quan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2944584"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00048"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2463209.2488949"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2644865.2541974"},{"volume-title":"NCNN: A high-performance neural network inference framework optimized for the mobile platform","year":"2022","key":"ref5"},{"volume-title":"Compute library: A software library for computer vision and machine learning","year":"2022","key":"ref6"},{"key":"ref7","first-page":"1","article-title":"MNN: A universal and efficient inference engine","volume-title":"Proc. MLSys","author":"Jiang"},{"volume-title":"Rockchip RK3399 datasheet","year":"2022","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DSD57027.2022.00051"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60939-9_2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-04580-6_9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3038908"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2020.2968258"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2020.2969171"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2946538"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2981684"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3527169"},{"key":"ref18","first-page":"181","article-title":"A deep learning based cost model for automatic code optimization","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Baghdadi"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP58684.2023.00039"},{"key":"ref20","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. 14th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Zheng"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3457388.3458666"},{"key":"ref22","first-page":"503","article-title":"Habitat: A runtime-based computational performance predictor for deep neural network training","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Yu"},{"key":"ref23","article-title":"Using graph neural networks to model the performance of deep neural networks","author":"Singh","year":"2021","journal-title":"arXiv:2108.12489"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888998214044"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref26","article-title":"NAS-bench-201: Extending the scope of reproducible neural architecture search","author":"Dong","year":"2020","journal-title":"arXiv:2001.00326"},{"key":"ref27","article-title":"Darts: Differentiable architecture search","author":"Liu","year":"2018","journal-title":"arXiv:1806.09055"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref33","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","author":"Iandola","year":"2016","journal-title":"arXiv:1602.07360"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554.PMC346238.PMID6953413"},{"key":"ref38","first-page":"1","article-title":"Boosting algorithms as gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Mason"},{"key":"ref39","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref40","first-page":"622","article-title":"NeuralPower: Predict and deploy energy-efficient convolutional neural networks","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Cai"},{"key":"ref41","first-page":"1","article-title":"Towards GPU utilization prediction for cloud deep learning","volume-title":"Proc. 12th USENIX Workshop Hot Topics Cloud Comput. (HotCloud)","author":"Yeung"},{"key":"ref42","first-page":"10480","article-title":"BRP-NAS: Prediction-based NAS using GCNs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Dudziak"},{"article-title":"Predicting future performance of convolutional neural networks in early training stages","year":"2019","author":"Xin","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942149"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2017.8167764"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3194554.3194565"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"ref49","article-title":"Design automation for efficient deep learning computing","author":"Han","year":"2019","journal-title":"arXiv:1904.10616"},{"key":"ref50","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"Cai","year":"2018","journal-title":"arXiv:1812.00332"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01166"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8341973"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CAHPC.2018.8645908"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/DASC\/PiCom\/DataCom\/CyberSciTec.2018.000-4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00062"},{"key":"ref56","article-title":"Pick the right edge device: Towards power and performance estimation of CUDA-based CNNs on GPGPUs","author":"Metz","year":"2021","journal-title":"arXiv:2102.02645"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5923"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3101936"},{"key":"ref59","first-page":"29","article-title":"Work-in-progress: Early power estimation of CUDA-based CNNs on GPGPUs","volume-title":"Proc. Int. Conf. Hardw.\/Softw. Codesign and Syst. Synth. (CODES+ISSS)","author":"Metz"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00068"},{"key":"ref61","first-page":"1","article-title":"PALEO: A performance model for deep neural networks","volume-title":"Proc. ICLR","author":"Qi"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2897634"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44534-8_1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10040520"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10384482\/10177988.pdf?arnumber=10177988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:16:53Z","timestamp":1705025813000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10177988\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,15]]},"references-count":64,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3294253","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"type":"electronic","value":"2327-4662"},{"type":"electronic","value":"2372-2541"}],"subject":[],"published":{"date-parts":[[2024,1,15]]}}}