{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T22:42:29Z","timestamp":1781908949541,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2328972,2324864,2337454,2213701,2217003"],"award-info":[{"award-number":["2328972,2324864,2337454,2213701,2217003"]}],"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":[[2025,6,30]]},"DOI":"10.1145\/3716368.3735215","type":"proceedings-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T13:58:23Z","timestamp":1751032703000},"page":"442-449","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["ART: Customizing Accelerators for DNN-Enabled Real-Time Safety-Critical Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3429-4692","authenticated-orcid":false,"given":"Shixin","family":"Ji","sequence":"first","affiliation":[{"name":"Brown University, Providence, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4865-3708","authenticated-orcid":false,"given":"Xingzhen","family":"Chen","sequence":"additional","affiliation":[{"name":"Brown University, Providence, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3659-339X","authenticated-orcid":false,"given":"Jinming","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Brown University, Providence, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4590-6559","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Brown University, Providence, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7655-4080","authenticated-orcid":false,"given":"Zhuoping","family":"Yang","sequence":"additional","affiliation":[{"name":"Brown University, Providence, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2333-3416","authenticated-orcid":false,"given":"Sarah","family":"Schultz","sequence":"additional","affiliation":[{"name":"Brown University, Providence, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0634-1941","authenticated-orcid":false,"given":"Yukai","family":"Song","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Pittsburgh, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-4034","authenticated-orcid":false,"given":"Jingtong","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Pittsburgh, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7498-0206","authenticated-orcid":false,"given":"Alex","family":"Jones","sequence":"additional","affiliation":[{"name":"Syracuse University, Syracuse, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0692-7486","authenticated-orcid":false,"given":"Zheng","family":"Dong","sequence":"additional","affiliation":[{"name":"Wayne State University, Detroit, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0493-1844","authenticated-orcid":false,"given":"Peipei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Brown University, Providence, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,29]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Rafie M. Autonomous Vehicles Drive AI Advances for Edge Computing. https:\/\/www.3dincites.com\/2021\/07\/autonomous-vehicles-drive-ai-advances-for-edge-computing\/."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Nagamatsu Y. et\u00a0al. Basic implementation of FPGA-GPU dual SoC hybrid architecture for low-latency multi-DOF robot motion control. In IROS pages 7255\u20137260. IEEE 2020.","DOI":"10.1109\/IROS45743.2020.9341602"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Basir R. et\u00a0al. Fog computing enabling industrial internet of things: State-of-the-art and research challenges. Sensors 19(21):4807 2019.","DOI":"10.3390\/s19214807"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Fowers J. et\u00a0al. A Configurable Cloud-Scale DNN Processor for Real-Time AI. In ISCA pages 1\u201314 2018.","DOI":"10.1109\/ISCA.2018.00012"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"D\u00fcrre J. et\u00a0al. A HOG-based real-time and multi-scale pedestrian detector demonstration system on FPGA. In FPGA pages 163\u2013172 2018.","DOI":"10.1145\/3174243.3174249"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Zhang J. et\u00a0al. A low-latency FPGA implementation for real-time object detection. In ISCAS pages 1\u20135. IEEE 2021.","DOI":"10.1109\/ISCAS51556.2021.9401577"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Lyu Y. et\u00a0al. Chipnet: Real-time lidar processing for drivable region segmentation on an fpga. IEEE Transactions on Circuits and Systems I: Regular Papers 2018.","DOI":"10.1109\/TCSI.2018.2881162"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Gao Y. et\u00a0al. A Reconfigurable Architecture for Real-time Event-based Multi-Object Tracking. TRETS 16(4):1\u201326 2023.","DOI":"10.1145\/3593587"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Li C.J. et\u00a0al. Fixed-point FPGA Implementation of the FFT Accumulation Method for Real-time Cyclostationary Analysis. TRETS 16(3):1\u201328 2023.","DOI":"10.1145\/3567429"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Zhuang J. et\u00a0al. CHARM: Composing Heterogeneous AcceleRators for Matrix Multiply on Versal ACAP Architecture. In FPGA page 153\u2013164. ACM 2023.","DOI":"10.1145\/3543622.3573210"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Zhuang J. et\u00a0al. SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration. In FPGA. ACM 2024.","DOI":"10.1145\/3626202.3637569"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Dong P. et\u00a0al. EQ-ViT: Algorithm-Hardware Co-Design for End-to-End Acceleration of Real-Time Vision Transformer Inference on Versal ACAP Architecture. IEEE TCAD 2024.","DOI":"10.1109\/TCAD.2024.3443692"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Yang Z. et\u00a0al. AIM: Accelerating Arbitrary-precision Integer Multiplication on Heterogeneous Reconfigurable Computing Platform Versal ACAP. In ICCAD pages 1\u20139. IEEE 2023.","DOI":"10.1109\/ICCAD57390.2023.10323754"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Bertogna M. et\u00a0al. Preemption Points Placement for Sporadic Task Sets. In 2010 22nd Euromicro Conference on Real-Time Systems pages 251\u2013260 2010.","DOI":"10.1109\/ECRTS.2010.9"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Bertogna M. et\u00a0al. Optimal Selection of Preemption Points to Minimize Preemption Overhead. In ECRTS pages 217\u2013227 2011.","DOI":"10.1109\/ECRTS.2011.28"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Kim H. et\u00a0al. A server-based approach for predictable GPU access control. In RTCSA pages 1\u201310. IEEE 2017.","DOI":"10.1109\/RTCSA.2017.8046309"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Enright D. et\u00a0al. PAAM: A Framework for Coordinated and Priority-Driven Accelerator Management in ROS 2. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.06452 2024.","DOI":"10.1109\/RTAS61025.2024.00015"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Zahaf H.E. et\u00a0al. Design and analysis of programming platform for accelerated GPU-like architectures. In RTNS pages 1\u201310 2020.","DOI":"10.1145\/3394810.3394826"},{"key":"e_1_3_3_1_20_2","unstructured":"Han M. et\u00a0al. Microsecond-scale preemption for concurrent { GPU-accelerated}{ DNN} inferences. In OSDI pages 539\u2013558 2022."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Kim S. et\u00a0al. DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads. In ASPLOS pages 73\u201386 2023.","DOI":"10.1145\/3623278.3624753"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Choi Y. et\u00a0al. Prema: A predictive multi-task scheduling algorithm for preemptible neural processing units. In HPCA pages 220\u2013233. IEEE 2020.","DOI":"10.1109\/HPCA47549.2020.00027"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Ghodrati S. et\u00a0al. Planaria: Dynamic Architecture Fission for Spatial Multi-Tenant Acceleration of Deep Neural Networks. In MICRO pages 681\u2013697 2020.","DOI":"10.1109\/MICRO50266.2020.00062"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Wang C. et\u00a0al. CD-MSA: cooperative and deadline-aware scheduling for efficient multi-tenancy on DNN accelerators. TPDS 34(7):2091\u20132106 2023.","DOI":"10.1109\/TPDS.2023.3276759"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Gao C. et\u00a0al. Layer-Puzzle: Allocating and Scheduling Multi-task on Multi-core NPUs by Using Layer Heterogeneity. In DATE pages 1\u20136. IEEE 2023.","DOI":"10.23919\/DATE56975.2023.10137320"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Oh Y.H. et\u00a0al. Layerweaver: Maximizing resource utilization of neural processing units via layer-wise scheduling. In HPCA pages 584\u2013597. IEEE 2021.","DOI":"10.1109\/HPCA51647.2021.00056"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Kim S. et\u00a0al. MoCA: Memory-centric adaptive execution for multi-tenant deep neural networks. In HPCA pages 828\u2013841. IEEE 2023.","DOI":"10.1109\/HPCA56546.2023.10071035"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Zeng S. et\u00a0al. Serving multi-DNN workloads on FPGAs: A coordinated architecture scheduling and mapping perspective. IEEE Transactions on Computers 72(5):1314\u20131328 2022.","DOI":"10.1109\/TC.2022.3214113"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Jozwik K. et\u00a0al. Comparison of Preemption Schemes for Partially Reconfigurable FPGAs. IEEE Embedded Systems Letters 4(2):45\u201348 2012.","DOI":"10.1109\/LES.2012.2193660"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Rossi E. et\u00a0al. Preemption of the Partial Reconfiguration Process to Enable Real-Time Computing With FPGAs. 11(2) 2018.","DOI":"10.1145\/3182183"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Zhou H. et\u00a0al. GPES: A preemptive execution system for GPGPU computing. In RTAS pages 87\u201397. IEEE 2015.","DOI":"10.1109\/RTAS.2015.7108420"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Tanasic I. et\u00a0al. Enabling preemptive multiprogramming on GPUs. ACM SIGARCH Computer Architecture News 42(3):193\u2013204 2014.","DOI":"10.1145\/2678373.2665702"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Li R. et\u00a0al. Rosgm: A real-time gpu management framework with plug-in policies for ros 2. In RTAS pages 93\u2013105. IEEE 2023.","DOI":"10.1109\/RTAS58335.2023.00015"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Jozwik K. et\u00a0al. A novel mechanism for effective hardware task preemption in dynamically reconfigurable systems. In FPL pages 352\u2013355. IEEE 2010.","DOI":"10.1109\/FPL.2010.76"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Attia S. et\u00a0al. Feel free to interrupt: Safe task stopping to enable FPGA checkpointing and context switching. TRETS 13(1):1\u201327 2020.","DOI":"10.1145\/3372491"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Rodriguez-Canal G. et\u00a0al. Programming Abstractions for Preemptive Scheduling on FPGAs Using Partial Reconfiguration. In Euro-Par. Springer 2022.","DOI":"10.1007\/978-3-031-31209-0_10"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Samardzic N. et\u00a0al. Bonsai: High-performance adaptive merge tree sorting. In ISCA pages 282\u2013294. IEEE 2020.","DOI":"10.1109\/ISCA45697.2020.00033"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Qiao W. et\u00a0al. TopSort: A high-performance two-phase sorting accelerator optimized on HBM-based FPGAs. IEEE Transactions on Emerging Topics in Computing 11(2):404\u2013419 2022.","DOI":"10.1109\/TETC.2022.3228575"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Bertogna M. et\u00a0al. Preemption Points Placement for Sporadic Task Sets. In 2010 22nd Euromicro Conference on Real-Time Systems pages 251\u2013260 2010.","DOI":"10.1109\/ECRTS.2010.9"},{"key":"e_1_3_3_1_40_2","unstructured":"Standaert B. et\u00a0al. A Limited-Preemption Scheduling Model Inspired by Security Considerations. 2024."},{"key":"e_1_3_3_1_41_2","unstructured":"Guan N. et\u00a0al. Industry Challenge. https:\/\/2021.rtss.org\/wp-content\/uploads\/2021\/12\/proceedings-1.pdf."},{"key":"e_1_3_3_1_42_2","unstructured":"Autoware Foundation. Autoware - the world\u2019s leading open-source software project for autonomous driving."},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Touvron H. et\u00a0al. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR 2021.","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"e_1_3_3_1_44_2","unstructured":"Tolstikhin I. et\u00a0al. MLP-mixer: an all-MLP architecture for vision. In NIPS Red Hook NY USA 2024. Curran Associates Inc."},{"key":"e_1_3_3_1_45_2","unstructured":"Qi C.R. et\u00a0al. Pointnet: Deep learning on point sets for 3d classification and segmentation. In CVPR pages 652\u2013660 2017."}],"event":{"name":"GLSVLSI '25: Great Lakes Symposium on VLSI 2025","location":"New Orleans LA USA","acronym":"GLSVLSI '25","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2025"],"original-title":[],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T14:37:10Z","timestamp":1751035030000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716368.3735215"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,29]]},"references-count":44,"alternative-id":["10.1145\/3716368.3735215","10.1145\/3716368"],"URL":"https:\/\/doi.org\/10.1145\/3716368.3735215","relation":{},"subject":[],"published":{"date-parts":[[2025,6,29]]},"assertion":[{"value":"2025-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}