{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T12:57:20Z","timestamp":1755694640104,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,4,9]],"date-time":"2021-04-09T00:00:00Z","timestamp":1617926400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-#1755659, CNS-#1815619"],"award-info":[{"award-number":["CNS-#1755659, CNS-#1815619"]}],"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":[[2021,4,9]]},"DOI":"10.1145\/3427921.3450256","type":"proceedings-article","created":{"date-parts":[[2021,4,10]],"date-time":"2021-04-10T07:37:01Z","timestamp":1618040221000},"page":"249-256","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["PieSlicer: Dynamically Improving Response Time for Cloud-based CNN Inference"],"prefix":"10.1145","author":[{"given":"Samuel S.","family":"Ogden","sequence":"first","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangnan","family":"Kong","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Guo","sequence":"additional","affiliation":[{"name":"Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Qualcomm on Tour. https:\/\/www.anandtech.com\/show\/11201\/qualcomm-snapdragon-835-performance-preview\/5.  Qualcomm on Tour. https:\/\/www.anandtech.com\/show\/11201\/qualcomm-snapdragon-835-performance-preview\/5."},{"key":"e_1_3_2_1_2_1","unstructured":"NVIDIA Triton Inference Server. https:\/\/developer.nvidia.com\/nvidia-triton-inference-server.  NVIDIA Triton Inference Server. https:\/\/developer.nvidia.com\/nvidia-triton-inference-server."},{"key":"e_1_3_2_1_3_1","volume-title":"https:\/\/machinelearning.apple.com\/2017\/08\/06\/siri-voices.html","author":"Deep Learning","year":"2017","unstructured":"Deep Learning for Siri's Voice. https:\/\/machinelearning.apple.com\/2017\/08\/06\/siri-voices.html , 2017 . Deep Learning for Siri's Voice. https:\/\/machinelearning.apple.com\/2017\/08\/06\/siri-voices.html, 2017."},{"key":"e_1_3_2_1_4_1","volume-title":"https:\/\/en.wikipedia.org\/wiki\/Pixel_2","author":"Pixel","year":"2019","unstructured":"Pixel 2 - Wikipedia. https:\/\/en.wikipedia.org\/wiki\/Pixel_2 , 2019 . Pixel 2 - Wikipedia. https:\/\/en.wikipedia.org\/wiki\/Pixel_2, 2019."},{"key":"e_1_3_2_1_5_1","volume-title":"et al. Benchmark analysis of representative deep neural network architectures","author":"Bianco S.","year":"2018","unstructured":"Bianco , S. et al. Benchmark analysis of representative deep neural network architectures . 2018 . doi: 10.1109\/ACCESS.2018.2877890. 10.1109\/ACCESS.2018.2877890 Bianco, S. et al. Benchmark analysis of representative deep neural network architectures. 2018. doi: 10.1109\/ACCESS.2018.2877890."},{"key":"e_1_3_2_1_6_1","volume-title":"OSDI 18","author":"Chen T.","year":"2018","unstructured":"Chen , T. et al. TVM: An automated end-to-end optimizing compiler for deep learning . In OSDI 18 , 2018 . Chen, T. et al. TVM: An automated end-to-end optimizing compiler for deep learning. In OSDI 18, 2018."},{"key":"e_1_3_2_1_7_1","volume-title":"SenSys '15","author":"Chen T.Y.H.","year":"2015","unstructured":"Chen , T.Y.H. et al. Glimpse: Continuous, real-time object recognition on mobile devices . In SenSys '15 , 2015 . Chen, T.Y.H. et al. Glimpse: Continuous, real-time object recognition on mobile devices. In SenSys '15, 2015."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1966445.1966473"},{"key":"e_1_3_2_1_9_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation","author":"Crankshaw D.","year":"2017","unstructured":"Crankshaw , D. et al. Clipper: A low-latency online prediction serving system . In 14th USENIX Symposium on Networked Systems Design and Implementation , 2017 . Crankshaw, D. et al. Clipper: A low-latency online prediction serving system. In 14th USENIX Symposium on Networked Systems Design and Implementation, 2017."},{"key":"e_1_3_2_1_10_1","volume-title":"ACM MobiSys","author":"Cuervo E.","year":"2010","unstructured":"Cuervo , E. et al. Maui: Making smartphones last longer with code offload . In ACM MobiSys 2010 . Association for Computing Machinery, Inc. , June 2010. Cuervo, E. et al. Maui: Making smartphones last longer with code offload. In ACM MobiSys 2010. Association for Computing Machinery, Inc., June 2010."},{"volume-title":"Recurrent Networks for Guided Multi-Attention Classification. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'20)","author":"Dai X.","key":"e_1_3_2_1_11_1","unstructured":"Dai , X. et al . Recurrent Networks for Guided Multi-Attention Classification. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'20) . Dai, X. et al. Recurrent Networks for Guided Multi-Attention Classification. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'20)."},{"volume-title":"ImageNet: A Large-Scale Hierarchical Image Database. In CVPR'09","author":"Deng J.","key":"e_1_3_2_1_12_1","unstructured":"Deng , J. et al . ImageNet: A Large-Scale Hierarchical Image Database. In CVPR'09 . Deng, J. et al. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR'09."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3135974.3135993"},{"key":"e_1_3_2_1_15_1","volume-title":"OSDI'20","author":"Gujarati A.","year":"2020","unstructured":"Gujarati , A. et al. Serving DNNs like clockwork: Performance predictability from the bottom up . In OSDI'20 , 2020 . Gujarati, A. et al. Serving DNNs like clockwork: Performance predictability from the bottom up. In OSDI'20, 2020."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E.2018.00042"},{"volume-title":"CVPR'16","author":"He K.","key":"e_1_3_2_1_17_1","unstructured":"He , K. et al. Deep residual learning for image recognition . CVPR'16 . He, K. et al. Deep residual learning for image recognition. CVPR'16."},{"key":"e_1_3_2_1_18_1","volume-title":"et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. abs\/1704.04861","author":"Howard A.G.","year":"2017","unstructured":"Howard , A.G. et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. abs\/1704.04861 , 2017 . Howard, A.G. et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. abs\/1704.04861, 2017."},{"volume-title":"MobiSys '19","author":"Hu J.","key":"e_1_3_2_1_19_1","unstructured":"Hu , J. et al. Banner: An image sensor reconfiguration framework for seamless resolution-based tradeoffs . MobiSys '19 . Hu, J. et al. Banner: An image sensor reconfiguration framework for seamless resolution-based tradeoffs. MobiSys '19."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419215"},{"key":"e_1_3_2_1_21_1","volume-title":"et al. AI benchmark: All about deep learning on smartphones","author":"Ignatov A.","year":"2019","unstructured":"Ignatov , A. et al. AI benchmark: All about deep learning on smartphones in 2019 . CoRR, abs\/1910.06663, 2019. URL http:\/\/arxiv.org\/abs\/1910.06663. Ignatov, A. et al. AI benchmark: All about deep learning on smartphones in 2019. CoRR, abs\/1910.06663, 2019. URL http:\/\/arxiv.org\/abs\/1910.06663."},{"key":"e_1_3_2_1_22_1","volume-title":"et al. Serving deep learning models in a serverless platform. CoRR,abs\/1710.08460","author":"Ishakian V.","year":"2017","unstructured":"Ishakian , V. et al. Serving deep learning models in a serverless platform. CoRR,abs\/1710.08460 , 2017 . URL http:\/\/arxiv.org\/abs\/1710.08460. Ishakian, V. et al. Serving deep learning models in a serverless platform. CoRR,abs\/1710.08460, 2017. URL http:\/\/arxiv.org\/abs\/1710.08460."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303958"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2012.6195845"},{"key":"e_1_3_2_1_28_1","volume-title":"et al. Learning multiple layers of features from tiny images. Technical report","author":"Krizhevsky A.","year":"2009","unstructured":"Krizhevsky , A. et al. Learning multiple layers of features from tiny images. Technical report , 2009 . Krizhevsky, A. et al. Learning multiple layers of features from tiny images. Technical report, 2009."},{"key":"e_1_3_2_1_29_1","first-page":"66","volume-title":"IC2E'20","author":"LeMay M.","year":"2020","unstructured":"LeMay , M. et al. Perseus: Characterizing performance and cost of multi-tenant serving for cnn models . In IC2E'20 , pages 66 -- 72 . IEEE , 2020 . LeMay, M. et al. Perseus: Characterizing performance and cost of multi-tenant serving for cnn models. In IC2E'20, pages 66--72. IEEE, 2020."},{"key":"e_1_3_2_1_30_1","volume-title":"et al. AI on the edge: Rethinking AI-based IoT applications using specialized edge architectures. arXiv preprint arXiv:2003.12488","author":"Liang Q.","year":"2020","unstructured":"Liang , Q. et al. AI on the edge: Rethinking AI-based IoT applications using specialized edge architectures. arXiv preprint arXiv:2003.12488 , 2020 . Liang, Q. et al. AI on the edge: Rethinking AI-based IoT applications using specialized edge architectures. arXiv preprint arXiv:2003.12488, 2020."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 22nd Annual Conference on Computational Learning Theory","author":"List N.","year":"2009","unstructured":"List , N. et al. Svm-optimization and steepest-descent line search . In Proceedings of the 22nd Annual Conference on Computational Learning Theory , 2009 . List, N. et al. Svm-optimization and steepest-descent line search. In Proceedings of the 22nd Annual Conference on Computational Learning Theory, 2009."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3300116"},{"key":"e_1_3_2_1_33_1","first-page":"1","volume-title":"InDAC'18","author":"Liu Z.","year":"2018","unstructured":"Liu , Z. et al. Deep n-jpeg: a deep neural network favorable jpeg-based image compression framework . InDAC'18 , pages 1 -- 6 , 2018 . Liu, Z. et al. Deep n-jpeg: a deep neural network favorable jpeg-based image compression framework. InDAC'18, pages 1--6, 2018."},{"key":"e_1_3_2_1_34_1","volume-title":"USENIX Workshop on Hot Topics in Edge Computing (HotEdge 18)","author":"Ogden S.S.","year":"2018","unstructured":"Ogden , S.S. et al. MODI: Mobile deep inference made efficient by edge computing . In USENIX Workshop on Hot Topics in Edge Computing (HotEdge 18) , 2018 . Ogden, S.S. et al. MODI: Mobile deep inference made efficient by edge computing. In USENIX Workshop on Hot Topics in Edge Computing (HotEdge 18), 2018."},{"key":"e_1_3_2_1_35_1","first-page":"2020","article-title":"Mdinference: Balancing inference accuracy and latency for mobile applications","author":"Ogden S.S.","year":"2020","unstructured":"Ogden , S.S. . Mdinference: Balancing inference accuracy and latency for mobile applications . In IC2E 2020 , 2020 . Ogden, S.S. et al. Mdinference: Balancing inference accuracy and latency for mobile applications. In IC2E 2020, 2020.","journal-title":"IC2E"},{"key":"e_1_3_2_1_36_1","volume-title":"et al. Pieslicer. https:\/\/github.com\/cake-lab\/PieSlicer","author":"Ogden S.S.","year":"2020","unstructured":"Ogden , S.S. et al. Pieslicer. https:\/\/github.com\/cake-lab\/PieSlicer , 2020 . Ogden, S.S. et al. Pieslicer. https:\/\/github.com\/cake-lab\/PieSlicer, 2020."},{"key":"e_1_3_2_1_37_1","volume-title":"Workshop on ML Systems at NIPS 2017","author":"Olston C.","year":"2017","unstructured":"Olston , C. et al. Tensor flow-serving: Flexible, high-performance ml serving . In Workshop on ML Systems at NIPS 2017 , 2017 . Olston, C. et al. Tensor flow-serving: Flexible, high-performance ml serving. In Workshop on ML Systems at NIPS 2017, 2017."},{"key":"e_1_3_2_1_38_1","volume-title":"Advances in Neural Information Processing Systems 32.","author":"Paszke A.","year":"2019","unstructured":"Paszke , A. et al. Pytorch: An imperative style, high-performance deep learning library . In Advances in Neural Information Processing Systems 32. 2019 . Paszke, A. et al. Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems 32. 2019."},{"key":"e_1_3_2_1_39_1","volume-title":"IEEE Conference on Computer Communications","author":"Ran X.","year":"2018","unstructured":"Ran , X. et al. Deep decision: A mobile deep learning framework for edge video analytics . In IEEE Conference on Computer Communications , 2018 . Ran, X. et al. Deep decision: A mobile deep learning framework for edge video analytics. In IEEE Conference on Computer Communications, 2018."},{"key":"e_1_3_2_1_40_1","volume-title":"Exp. Psychol. Hum. Percept. Perform.","author":"Rayner K.","year":"1981","unstructured":"Rayner , K. et al. Masking of foveal and parafoveal vision during eye fixations in reading. J . Exp. Psychol. Hum. Percept. Perform. , 1981 . Rayner, K. et al. Masking of foveal and parafoveal vision during eye fixations in reading. J. Exp. Psychol. Hum. Percept. Perform., 1981."},{"key":"e_1_3_2_1_41_1","first-page":"446","volume-title":"ISCA'20","author":"Reddi V.J.","unstructured":"Reddi , V.J. et al. Mlperf inference benchmark . In ISCA'20 , pages 446 -- 459 . Reddi, V.J. et al. Mlperf inference benchmark. In ISCA'20, pages 446--459."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2010.07.005"},{"key":"e_1_3_2_1_43_1","volume-title":"et al. Infaas: Managed & model-less inference serving. CoRR, abs\/1905.13348","author":"Romero F.","year":"2019","unstructured":"Romero , F. et al. Infaas: Managed & model-less inference serving. CoRR, abs\/1905.13348 , 2019 . URL http:\/\/arxiv.org\/abs\/1905.13348. Romero, F. et al. Infaas: Managed & model-less inference serving. CoRR, abs\/1905.13348, 2019. URL http:\/\/arxiv.org\/abs\/1905.13348."},{"key":"e_1_3_2_1_44_1","volume-title":"2019 USENIX Conference on Operational Machine Learning (OpML 19)","author":"Soifer J.","year":"2019","unstructured":"Soifer , J. et al. Deep learning inference service at Microsoft . In 2019 USENIX Conference on Operational Machine Learning (OpML 19) , 2019 . Soifer, J. et al. Deep learning inference service at Microsoft. In 2019 USENIX Conference on Operational Machine Learning (OpML 19), 2019."},{"key":"e_1_3_2_1_45_1","volume-title":"et al. Rethinking the inception architecture for computer vision. CoRR, abs\/1512.00567","author":"Szegedy C.","year":"2015","unstructured":"Szegedy , C. et al. Rethinking the inception architecture for computer vision. CoRR, abs\/1512.00567 , 2015 . Szegedy, C. et al. Rethinking the inception architecture for computer vision. CoRR, abs\/1512.00567, 2015."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.226"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/30.125072"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00048"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345448"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313591"},{"volume-title":"2019 USENIX Annual Technical Conference.","author":"Zhang C.","key":"e_1_3_2_1_51_1","unstructured":"Zhang , C. et al. Mark: Exploiting cloud services for cost-effective, slo-aware machine learning inference serving . In 2019 USENIX Annual Technical Conference. Zhang, C. et al. Mark: Exploiting cloud services for cost-effective, slo-aware machine learning inference serving. In 2019 USENIX Annual Technical Conference."},{"key":"e_1_3_2_1_52_1","volume-title":"et al. Learning transferable architectures for scalable image recognition. CoRR, abs\/1707.07012","author":"Zoph B.","year":"2017","unstructured":"Zoph , B. et al. Learning transferable architectures for scalable image recognition. CoRR, abs\/1707.07012 , 2017 . URL http:\/\/arxiv.org\/abs\/1707.07012. Zoph, B. et al. Learning transferable architectures for scalable image recognition. CoRR, abs\/1707.07012, 2017. URL http:\/\/arxiv.org\/abs\/1707.07012."}],"event":{"name":"ICPE '21: ACM\/SPEC International Conference on Performance Engineering","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Virtual Event France","acronym":"ICPE '21"},"container-title":["Proceedings of the ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3427921.3450256","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3427921.3450256","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3427921.3450256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:23Z","timestamp":1750195463000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3427921.3450256"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,9]]},"references-count":52,"alternative-id":["10.1145\/3427921.3450256","10.1145\/3427921"],"URL":"https:\/\/doi.org\/10.1145\/3427921.3450256","relation":{},"subject":[],"published":{"date-parts":[[2021,4,9]]},"assertion":[{"value":"2021-04-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}