{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T19:49:33Z","timestamp":1782589773082,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T00:00:00Z","timestamp":1701993600000},"content-version":"vor","delay-in-days":41,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"DARPA RTML","award":["FA8650-20-2-7006"],"award-info":[{"award-number":["FA8650-20-2-7006"]}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2238346, CCRI-2016662"],"award-info":[{"award-number":["CCF-2238346, CCRI-2016662"]}],"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\/3613424.3614280","type":"proceedings-article","created":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T12:22:15Z","timestamp":1702038135000},"page":"62-76","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["AuRORA: Virtualized Accelerator Orchestration for Multi-Tenant Workloads"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9581-1222","authenticated-orcid":false,"given":"Seah","family":"Kim","sequence":"first","affiliation":[{"name":"University of California, Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9307-2956","authenticated-orcid":false,"given":"Jerry","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0754-3975","authenticated-orcid":false,"given":"Krste","family":"Asanovic","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2324-1715","authenticated-orcid":false,"given":"Borivoje","family":"Nikolic","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1811-5407","authenticated-orcid":false,"given":"Yakun Sophia","family":"Shao","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,12,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. Compute Express Link Interconnect. https:\/\/www.computeexpresslink.org\/about-cxl"},{"key":"e_1_3_2_1_2_1","unstructured":"AXI AMBA and ACE\u00a0Protocol Specification. 2011. ARM. Cambridge UK (2011)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2996616"},{"key":"e_1_3_2_1_4_1","volume-title":"The rocket chip generator. EECS Department","author":"Asanovic Krste","year":"2016","unstructured":"Krste Asanovic, Rimas Avizienis, Jonathan Bachrach, Scott Beamer, David Biancolin, Christopher Celio, Henry Cook, Daniel Dabbelt, John Hauser, Adam Izraelevitz, 2016. The rocket chip generator. EECS Department, University of California, Berkeley, Tech. Rep. UCB\/EECS-2016-17 4 (2016)."},{"key":"e_1_3_2_1_5_1","unstructured":"Krste Asanovi\u0107 Rimas Avizienis Jonathan Bachrach Scott Beamer David Biancolin Christopher Celio Henry Cook Palmer Dabbelt John\u00a0R. Hauser Adam\u00a0M. Izraelevitz Sagar Karandikar Ben Keller Donggyu Kim Jack Koenig Yunsup Lee Eric Love Martin Maas Albert Magyar Howard Mao Miquel Moret\u00f3 Albert\u00a0J. Ou David\u00a0A. Patterson Brian\u00a0C. Richards Colin Schmidt Stephen Twigg Huy\u00a0D. Vo and Andrew Waterman. 2016. The Rocket Chip Generator."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228584"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872362.2872414"},{"key":"e_1_3_2_1_8_1","volume-title":"Benchmark Analysis of Representative Deep Neural Network Architectures. CoRR abs\/1810.00736","author":"Bianco Simone","year":"2018","unstructured":"Simone Bianco, R\u00e9mi Cad\u00e8ne, Luigi Celona, and Paolo Napoletano. 2018. Benchmark Analysis of Representative Deep Neural Network Architectures. CoRR abs\/1810.00736 (2018). arXiv:1810.00736http:\/\/arxiv.org\/abs\/1810.00736"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854350"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00568"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.39"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00027"},{"key":"e_1_3_2_1_13_1","unstructured":"Lauranne Choquin. 2020. Arm Custom Instructions: Enabling Innovation and Greater Flexibility on Arm. Technical Report. Arm Ltd."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228512"},{"key":"e_1_3_2_1_15_1","unstructured":"Henry\u00a0M Cook Andrew\u00a0S Waterman and Yunsup Lee. 2018. Sifive tilelink specification. Technical Report. tech. rep. SiFive Inc. 2018."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522311"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451157"},{"key":"e_1_3_2_1_18_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR abs\/1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR abs\/1810.04805 (2018). http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.44"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00062"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561747"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.848473"},{"key":"e_1_3_2_1_24_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arxiv:1512.03385\u00a0[cs.CV]"},{"key":"e_1_3_2_1_25_1","volume-title":"Hill and Vijay\u00a0Janapa Reddi","author":"D.","year":"2019","unstructured":"Mark\u00a0D. Hill and Vijay\u00a0Janapa Reddi. 2019. Accelerator-level Parallelism. CoRR abs\/1907.02064 (2019). arxiv:1907.02064http:\/\/arxiv.org\/abs\/1907.02064"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942048"},{"key":"e_1_3_2_1_27_1","unstructured":"Muhammad Huzaifa Rishi Desai Samuel Grayson Xutao Jiang Ying Jing Jae Lee Fang Lu Yihan Pang Joseph Ravichandran Finn Sinclair Boyuan Tian Hengzhi Yuan Jeffrey Zhang and Sarita\u00a0V. Adve. 2021. Exploring Extended Reality with ILLIXR: A new Playground for Architecture Research. arXiv:2004.04643\u00a0[cs.DC]"},{"key":"e_1_3_2_1_28_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size. CoRR abs\/1602.07360","author":"Iandola N.","year":"2016","unstructured":"Forrest\u00a0N. Iandola, Matthew\u00a0W. Moskewicz, Khalid Ashraf, Song Han, William\u00a0J. Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size. CoRR abs\/1602.07360 (2016). arxiv:1602.07360 http:\/\/arxiv.org\/abs\/1602.07360"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00065"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00014"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071035"},{"key":"e_1_3_2_1_32_1","volume-title":"DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads. arxiv:2212.03414","author":"Kim Seah","year":"2023","unstructured":"Seah Kim, Hyoukjun Kwon, Jinook Song, Jihyuck Jo, Yu-Hsin Chen, Liangzhen Lai, and Vikas Chandra. 2023. DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads. arxiv:2212.03414"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 25th International Conference on Neural Information Processing Systems -","volume":"1105","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey\u00a0E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1(NIPS\u201912). Curran Associates Inc., Red Hook, NY, USA, 1097\u20131105."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00016"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 5th Machine Learning and Systems Conference (MLSys 2023)","author":"Kwon Hyoukjun","year":"2023","unstructured":"Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo, Jason Yik, Debabrata Mohapatra, Dongyuan Zhan, Jinook Song, Peter Capak, Peizhao Zhang, Peter Vajda, Colby Banbury, Mark Mazumder, Liangzhen Lai, Ashish Sirasao, Tushar Krishna, Harshit Khaitan, Vikas Chandra, and Vijay\u00a0Janapa Reddi. 2023. XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse. In Proceedings of the 5th Machine Learning and Systems Conference (MLSys 2023)(MLSys 2023). Miami, FL, USA. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/hash\/baf570e47e7f4e314a9ffb72c4a5459c-Abstract-mlsys2023.html"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586312"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362694"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00458"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744876"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507752"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2086696.2086727"},{"key":"e_1_3_2_1_42_1","volume-title":"End-to-end Global to Local CNN Learning for Hand Pose Recovery in Depth data. CoRR abs\/1705.09606","author":"Madadi Meysam","year":"2017","unstructured":"Meysam Madadi, Sergio Escalera, Xavier Bar\u00f3, and Jordi Gonz\u00e0lez. 2017. End-to-end Global to Local CNN Learning for Hand Pose Recovery in Depth data. CoRR abs\/1705.09606 (2017). arXiv:1705.09606http:\/\/arxiv.org\/abs\/1705.09606"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415753"},{"key":"e_1_3_2_1_44_1","unstructured":"NVIDIA. 2018. TensorRT Inference Server User Guide."},{"key":"e_1_3_2_1_45_1","unstructured":"NVIDIA. 2022. Multi-Instance GPU User Guide. https:\/\/docs.nvidia.com\/datacenter\/tesla\/mig-user-guide\/index.html"},{"key":"e_1_3_2_1_46_1","unstructured":"NVIDIA Corporation. [n. d.]. Triton Inference Server: An Optimized Cloud and Edge Inferencing Solution. https:\/\/github.com\/triton-inference-server\/server"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3264265"},{"key":"e_1_3_2_1_48_1","volume-title":"YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers. CoRR abs\/1811.05588","author":"Pedoeem Jonathan","year":"2018","unstructured":"Jonathan Pedoeem and Rachel Huang. 2018. YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers. CoRR abs\/1811.05588 (2018). arXiv:1811.05588http:\/\/arxiv.org\/abs\/1811.05588"},{"key":"e_1_3_2_1_49_1","unstructured":"pytorch. [n. d.]. Running TorchServe. https:\/\/pytorch.org\/serve\/server.html"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"e_1_3_2_1_52_1","volume-title":"Faster, Stronger. CoRR abs\/1612.08242","author":"Redmon Joseph","year":"2016","unstructured":"Joseph Redmon and Ali Farhadi. 2016. YOLO9000: Better, Faster, Stronger. CoRR abs\/1612.08242 (2016). arXiv:1612.08242http:\/\/arxiv.org\/abs\/1612.08242"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"e_1_3_2_1_54_1","volume-title":"Wishbone bus architecture-a survey and comparison. arXiv preprint arXiv:1205.1860","author":"Sharma Mohandeep","year":"2012","unstructured":"Mohandeep Sharma and Dilip Kumar. 2012. Wishbone bus architecture-a survey and comparison. arXiv preprint arXiv:1205.1860 (2012)."},{"key":"e_1_3_2_1_55_1","volume-title":"Going Deeper with Convolutions. CoRR abs\/1409.4842","author":"Szegedy Christian","year":"2014","unstructured":"Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott\u00a0E. Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2014. Going Deeper with Convolutions. CoRR abs\/1409.4842 (2014). arxiv:1409.4842http:\/\/arxiv.org\/abs\/1409.4842"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2259016.2259018"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2490301.2451126"},{"key":"e_1_3_2_1_58_1","volume-title":"Deep Residual Learning for Small-Footprint Keyword Spotting. CoRR abs\/1710.10361","author":"Tang Raphael","year":"2017","unstructured":"Raphael Tang and Jimmy Lin. 2017. Deep Residual Learning for Small-Footprint Keyword Spotting. CoRR abs\/1710.10361 (2017). arXiv:1710.10361http:\/\/arxiv.org\/abs\/1710.10361"},{"key":"e_1_3_2_1_59_1","unstructured":"TensorFlow. [n. d.]. Tensorflow Guide Architecture. https:\/\/www.tensorflow.org\/tfx\/serving\/architecture"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/NoCArc57472.2022.9911299"},{"key":"e_1_3_2_1_62_1","volume-title":"SonicBOOM: The 3rd Generation Berkeley Out-of-Order Machine. (May","author":"Zhao Jerry","year":"2020","unstructured":"Jerry Zhao, Ben Korpan, Abraham Gonzalez, and Krste Asanovic. 2020. SonicBOOM: The 3rd Generation Berkeley Out-of-Order Machine. (May 2020)."}],"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\/3613424.3614280","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613424.3614280","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613424.3614280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:19:44Z","timestamp":1755890384000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613424.3614280"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,28]]},"references-count":62,"alternative-id":["10.1145\/3613424.3614280","10.1145\/3613424"],"URL":"https:\/\/doi.org\/10.1145\/3613424.3614280","relation":{},"subject":[],"published":{"date-parts":[[2023,10,28]]},"assertion":[{"value":"2023-12-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}