{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T23:25:19Z","timestamp":1773271519590,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"PRISM","award":["CC OTH 00541340 2022 TR"],"award-info":[{"award-number":["CC OTH 00541340 2022 TR"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3620666.3651347","type":"proceedings-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T12:08:21Z","timestamp":1713960501000},"page":"966-980","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["TAPA-CS: Enabling Scalable Accelerator Design on Distributed HBM-FPGAs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4866-0425","authenticated-orcid":false,"given":"Neha","family":"Prakriya","sequence":"first","affiliation":[{"name":"UCLA, Los Angeles, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5885-0425","authenticated-orcid":false,"given":"Yuze","family":"Chi","sequence":"additional","affiliation":[{"name":"UCLA, Los Angeles, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8301-8411","authenticated-orcid":false,"given":"Suhail","family":"Basalama","sequence":"additional","affiliation":[{"name":"UCLA, Los Angeles, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7450-2842","authenticated-orcid":false,"given":"Linghao","family":"Song","sequence":"additional","affiliation":[{"name":"UCLA, Los Angeles, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2887-6963","authenticated-orcid":false,"given":"Jason","family":"Cong","sequence":"additional","affiliation":[{"name":"UCLA, Los Angeles, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Alibaba FPGAs in the Cloud. https:\/\/www.alibabacloud.com\/help\/en\/fpga-based-ecs-instance."},{"key":"e_1_3_2_1_2_1","unstructured":"Alveo U55C High Performance Compute Card. https:\/\/www.xilinx.com\/products\/boards-and-kits\/alveo\/u55c.html#specifications."},{"key":"e_1_3_2_1_3_1","unstructured":"AlveoLink. https:\/\/github.com\/Xilinx\/AlveoLink."},{"key":"e_1_3_2_1_4_1","unstructured":"Amazon AQUA. https:\/\/aws.amazon.com\/redshift\/features\/."},{"key":"e_1_3_2_1_5_1","unstructured":"Amazon EC2 F1 Instances. https:\/\/aws.amazon.com\/ec2\/instance-types\/f1\/."},{"key":"e_1_3_2_1_6_1","unstructured":"AMD\/Xilinx UltraScale+ Devices Overview. https:\/\/docs.xilinx.com\/r\/en-US\/ug1120-alveo-platforms\/Overview."},{"key":"e_1_3_2_1_7_1","unstructured":"Baidu FPGAs in the Cloud. https:\/\/intl.cloud.baidu.com\/product\/bcc.html."},{"key":"e_1_3_2_1_8_1","unstructured":"Connectivity Options. https:\/\/docs.amd.com\/r\/en-US\/ug1393-vitis-application-acceleration\/connectivity-Options."},{"key":"e_1_3_2_1_9_1","unstructured":"Free Running Kernels in Vitis HLS. https:\/\/docs.amd.com\/r\/en-US\/ug1393-vitis-application-acceleration\/Free-Running-Kernels."},{"key":"e_1_3_2_1_10_1","unstructured":"Gurobi Solver. https:\/\/www.gurobi.com\/downloads\/gurobi-optimizer-eula\/."},{"key":"e_1_3_2_1_11_1","unstructured":"Huawei FPGAs in the Cloud."},{"key":"e_1_3_2_1_12_1","unstructured":"Intel HLS. https:\/\/www.intel.com\/content\/dam\/www\/central-libraries\/us\/en\/documents\/hls-production-brief.pdf."},{"key":"e_1_3_2_1_13_1","unstructured":"Intel Stratix 10."},{"key":"e_1_3_2_1_14_1","unstructured":"Python MIP. https:\/\/www.python-mip.com\/."},{"key":"e_1_3_2_1_15_1","volume-title":"HLS","author":"Vitis","year":"2022","unstructured":"Vitis HLS 2022.2. https:\/\/docs.xilinx.com\/r\/en-US\/ug1399-vitis-hls."},{"key":"e_1_3_2_1_16_1","unstructured":"Xilinx PCIe-Based P2P. https:\/\/xilinx.github.io\/XRT\/master\/html\/p2p.html."},{"key":"e_1_3_2_1_17_1","volume-title":"Elastic-DF: Scaling Performance of DNN Inference in FPGA Clouds through Automatic Partitioning. ACM Trans. Reconfigurable Technol. Syst., 15(2), dec","author":"Alonso Tobias","year":"2021","unstructured":"Tobias Alonso, Lucian Petrica, Mario Ruiz, Jakoba Petri-Koenig, Yaman Umuroglu, Ioannis Stamelos, Elias Koromilas, Michaela Blott, and Kees Vissers. Elastic-DF: Scaling Performance of DNN Inference in FPGA Clouds through Automatic Partitioning. ACM Trans. Reconfigurable Technol. Syst., 15(2), dec 2021."},{"key":"e_1_3_2_1_18_1","first-page":"699","volume-title":"Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '20","author":"Balkind Jonathan","year":"2020","unstructured":"Jonathan Balkind, Katie Lim, Michael Schaffner, Fei Gao, Grigory Chirkov, Ang Li, Alexey Lavrov, Tri M. Nguyen, Yaosheng Fu, Florian Zaruba, Kunal Gulati, Luca Benini, and David Wentzlaff. BYOC: A \"Bring Your Own Core\" Framework for Heterogeneous-ISA Research. In Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '20, page 699--714, New York, NY, USA, 2020. Association for Computing Machinery."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00032"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00032"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242897"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1941487.1941507"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.1999.810667"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/43.945302"},{"key":"e_1_3_2_1_25_1","volume-title":"Doug Burger. A Cloud-Scale Acceleration Architecture. In Proceedings of the 49th Annual IEEE\/ACM International Symposium on Microarchitecture. IEEE Computer Society","author":"Caulfield Adrian","year":"2016","unstructured":"Adrian Caulfield, Eric Chung, Andrew Putnam, Hari Angepat, Jeremy Fowers, Michael Haselman, Stephen Heil, Matt Humphrey, Puneet Kaur, Joo-Young Kim, Daniel Lo, Todd Massengill, Kalin Ovtcharov, Michael Papamichael, Lisa Woods, Sitaram Lanka, Derek Chiou, and Doug Burger. A Cloud-Scale Acceleration Architecture. In Proceedings of the 49th Annual IEEE\/ACM International Symposium on Microarchitecture. IEEE Computer Society, October 2016."},{"key":"e_1_3_2_1_26_1","first-page":"204","volume-title":"Jason Cong. Extending High-Level Synthesis for Task-Parallel Programs. In 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","author":"Chi Yuze","year":"2021","unstructured":"Yuze Chi, Licheng Guo, Jason Lau, Young-kyu Choi, Jie Wang, and Jason Cong. Extending High-Level Synthesis for Task-Parallel Programs. In 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pages 204--213, 2021."},{"key":"e_1_3_2_1_27_1","volume-title":"Jie Wang, and Jason Cong. Extending High-Level Synthesis for Task-Parallel Programs","author":"Chi Yuze","year":"2021","unstructured":"Yuze Chi, Licheng Guo, Jason Lau, Young kyu Choi, Jie Wang, and Jason Cong. Extending High-Level Synthesis for Task-Parallel Programs, 2021."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575753"},{"key":"e_1_3_2_1_29_1","first-page":"116","volume-title":"Jason Cong. HBM Connect: High-Performance HLS Interconnect for FPGA HBM. In The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, FPGA '21","author":"Chi Yuze","year":"2021","unstructured":"Young-kyu Choi, Yuze Chi, Weikang Qiao, Nikola Samardzic, and Jason Cong. HBM Connect: High-Performance HLS Interconnect for FPGA HBM. In The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, FPGA '21, page 116--126, New York, NY, USA, 2021. Association for Computing Machinery."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"key":"e_1_3_2_1_31_1","first-page":"93","volume-title":"Shaochong Zhang. Understanding Performance Differences of FPGAs and GPUs. In 2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","author":"Cong Jason","year":"2018","unstructured":"Jason Cong, Zhenman Fang, Michael Lo, Hanrui Wang, Jingxian Xu, and Shaochong Zhang. Understanding Performance Differences of FPGAs and GPUs. In 2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pages 93--96, 2018."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Tiziano De Matteis Johannes de Fine Licht Jakub Ber\u00e1nek and Torsten Hoefler. Streaming Message Interface: High-Performance Distributed Memory Programming on Reconfigurable Hardware. In Proceedings of the International Conference for High Performance Computing Networking Storage and Analysis SC '19 New York NY USA 2019. Association for Computing Machinery.","DOI":"10.1145\/3295500.3356201"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008373903657"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145694.2145725"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2015.46"},{"key":"e_1_3_2_1_36_1","volume-title":"Doug Burger. A Configurable Cloud-Scale DNN Processor for Real-Time AI. In Proceedings of the 45th International Symposium on Computer Architecture, 2018","author":"Fowers Jeremy","year":"2018","unstructured":"Jeremy Fowers, Kalin Ovtcharov, Michael Papamichael, Todd Massengill, Ming Liu, Daniel Lo, Shlomi Alkalay, Michael Haselman, Logan Adams, Mahdi Ghandi, Stephen Heil, Prerak Patel, Adam Sapek, Gabriel Weisz, Lisa Woods, Sitaram Lanka, Steve Reinhardt, Adrian Caulfield, Eric Chung, and Doug Burger. A Configurable Cloud-Scale DNN Processor for Real-Time AI. In Proceedings of the 45th International Symposium on Computer Architecture, 2018. ACM, June 2018."},{"key":"e_1_3_2_1_37_1","volume-title":"TAPA: A Scalable Task-Parallel Dataflow Programming Framework for Modern FPGAs with Co-Optimization of HLS and Physical Design. ACM Trans. Reconfigurable Technol. Syst., 16(4), dec","author":"Guo Licheng","year":"2023","unstructured":"Licheng Guo, Yuze Chi, Jason Lau, Linghao Song, Xingyu Tian, Moazin Khatti, Weikang Qiao, Jie Wang, Ecenur Ustun, Zhenman Fang, Zhiru Zhang, and Jason Cong. TAPA: A Scalable Task-Parallel Dataflow Programming Framework for Modern FPGAs with Co-Optimization of HLS and Physical Design. ACM Trans. Reconfigurable Technol. Syst., 16(4), dec 2023."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439289"},{"key":"e_1_3_2_1_39_1","first-page":"197","volume-title":"EasyNet: 100 Gbps Network for HLS","author":"He Zhenhao","year":"2021","unstructured":"Zhenhao He, Dario Korolija, and Gustavo Alonso. EasyNet: 100 Gbps Network for HLS. pages 197--203, 08 2021."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/H2RC54759.2021.00009"},{"key":"e_1_3_2_1_41_1","volume-title":"Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference. ACM Trans. Embed. Comput. Syst., 18(5s), oct","author":"Jiang Weiwen","year":"2019","unstructured":"Weiwen Jiang, Edwin H.-M. Sha, Xinyi Zhang, Lei Yang, Qingfeng Zhuge, Yiyu Shi, and Jingtong Hu. Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference. ACM Trans. Embed. Comput. Syst., 18(5s), oct 2019."},{"key":"e_1_3_2_1_42_1","first-page":"29","volume-title":"Krste Asanovic. FireSim: FPGA-Accelerated Cycle-Exact Scale-Out System Simulation in the Public Cloud. In 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA)","author":"Karandikar Sagar","year":"2018","unstructured":"Sagar Karandikar, Howard Mao, Donggyu Kim, David Biancolin, Alon Amid, Dayeol Lee, Nathan Pemberton, Emmanuel Amaro, Colin Schmidt, Aditya Chopra, Qijing Huang, Kyle Kovacs, Borivoje Nikolic, Randy Katz, Jonathan Bachrach, and Krste Asanovic. FireSim: FPGA-Accelerated Cycle-Exact Scale-Out System Simulation in the Public Cloud. In 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), pages 29--42, 2018."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1987.13876"},{"key":"e_1_3_2_1_44_1","first-page":"1","volume-title":"Jean B\u00e9langer. Multi-FPGA Communication Interface for Electric Circuit Co-Simulation. In 2020 IEEE Electric Power and Energy Conference (EPEC)","author":"Lemaire Michel","year":"2020","unstructured":"Michel Lemaire, Daniel Massicotte, and Jean B\u00e9langer. Multi-FPGA Communication Interface for Electric Circuit Co-Simulation. In 2020 IEEE Electric Power and Energy Conference (EPEC), pages 1--6, 2020."},{"key":"e_1_3_2_1_45_1","unstructured":"Jure Leskovec and Andrej Krevl. SNAP Datasets: Stanford large network dataset collection. http:\/\/snap.stanford.edu\/data June 2014."},{"key":"e_1_3_2_1_46_1","first-page":"139","volume-title":"Lesley Shannon. CHIP-KNN: A Configurable and High-Performance K-Nearest Neighbors Accelerator on Cloud FPGAs. In 2020 International Conference on Field-Programmable Technology (ICFPT)","author":"Lu Alec","year":"2020","unstructured":"Alec Lu, Zhenman Fang, Nazanin Farahpour, and Lesley Shannon. CHIP-KNN: A Configurable and High-Performance K-Nearest Neighbors Accelerator on Cloud FPGAs. In 2020 International Conference on Field-Programmable Technology (ICFPT), pages 139--147, 2020."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00014"},{"key":"e_1_3_2_1_48_1","volume-title":"February","author":"Ovtcharov Kalin","year":"2015","unstructured":"Kalin Ovtcharov, Olatunji Ruwase, Joo-Young Kim, Jeremy Fowers, Karin Strauss, and Eric Chung. Accelerating Deep Convolutional Neural Networks Using Specialized Hardware, February 2015."},{"key":"e_1_3_2_1_49_1","volume-title":"The Web Conference","author":"Page Lawrence","year":"1999","unstructured":"Lawrence Page, Sergey Brin, Rajeev Motwani, and Terry Winograd. The PageRank Citation Ranking : Bringing Order to the Web. In The Web Conference, 1999."},{"key":"e_1_3_2_1_50_1","volume-title":"VLSI digital signal processing systems: design and implementation","author":"Parhi Keshab K","year":"2007","unstructured":"Keshab K Parhi. VLSI digital signal processing systems: design and implementation. In John Wiley & Sons, 2007."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.42"},{"key":"e_1_3_2_1_52_1","first-page":"220","volume-title":"ZRLMPI: A Unified Programming Model for Reconfigurable Heterogeneous Computing Clusters. In 2020 IEEE 28th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","author":"Ringlein Burkhard","year":"2020","unstructured":"Burkhard Ringlein, Francois Abel, Alexander Ditter, Beat Weiss, Christoph Hagleitner, and Dietmar Fey. ZRLMPI: A Unified Programming Model for Reconfigurable Heterogeneous Computing Clusters. In 2020 IEEE 28th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pages 220--220, 2020."},{"key":"e_1_3_2_1_53_1","first-page":"1","volume-title":"Saldana and Paul Chow. TMD-MPI: An MPI Implementation for Multiple Processors Across Multiple FPGAs. In 2006 International Conference on Field Programmable Logic and Applications","author":"Manuel","year":"2006","unstructured":"Manuel Saldana and Paul Chow. TMD-MPI: An MPI Implementation for Multiple Processors Across Multiple FPGAs. In 2006 International Conference on Field Programmable Logic and Applications, pages 1--6, 2006."},{"key":"e_1_3_2_1_54_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. Very Deep Convolutional Networks for Large-Scale Image Recognition, 2015."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694362"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.2877290"},{"key":"e_1_3_2_1_57_1","first-page":"239","volume-title":"Paul Chow. AIgean: An Open Framework for Machine Learning on Heterogeneous Clusters. In 2020 IEEE 28th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","author":"Tarafdar Naif","year":"2020","unstructured":"Naif Tarafdar, Giuseppe Di Guglielmo, Philip C Harris, Jeffrey D Krupa, Vladimir Loncar, Dylan S Rankin, Nhan Tran, Zhenbin Wu, Qianfeng Shen, and Paul Chow. AIgean: An Open Framework for Machine Learning on Heterogeneous Clusters. In 2020 IEEE 28th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pages 239--239, 2020."},{"key":"e_1_3_2_1_58_1","volume-title":"SASA: A Scalable and Automatic Stencil Acceleration Framework for Optimized Hybrid Spatial and Temporal Parallelism on HBM-Based FPGAs. ACM Trans. Reconfigurable Technol. Syst., 16(2), apr","author":"Tian Xingyu","year":"2023","unstructured":"Xingyu Tian, Zhifan Ye, Alec Lu, Licheng Guo, Yuze Chi, and Zhenman Fang. SASA: A Scalable and Automatic Stencil Acceleration Framework for Optimized Hybrid Spatial and Temporal Parallelism on HBM-Based FPGAs. ACM Trans. Reconfigurable Technol. Syst., 16(2), apr 2023."},{"key":"e_1_3_2_1_59_1","volume-title":"Kees Vissers. FINN. In Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays. ACM, feb","author":"Umuroglu Yaman","year":"2017","unstructured":"Yaman Umuroglu, Nicholas J. Fraser, Giulio Gambardella, Michaela Blott, Philip Leong, Magnus Jahre, and Kees Vissers. FINN. In Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays. ACM, feb 2017."},{"key":"e_1_3_2_1_60_1","first-page":"93","volume-title":"Jason Cong. AutoSA: A Polyhedral Compiler for High-Performance Systolic Arrays on FPGA. In The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, FPGA '21","author":"Wang Jie","year":"2021","unstructured":"Jie Wang, Licheng Guo, and Jason Cong. AutoSA: A Polyhedral Compiler for High-Performance Systolic Arrays on FPGA. In The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, FPGA '21, page 93--104, New York, NY, USA, 2021. Association for Computing Machinery."},{"key":"e_1_3_2_1_61_1","first-page":"845","volume-title":"Zha and Jing Li. Virtualizing FPGAs in the Cloud. In Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '20","author":"Yue","year":"2020","unstructured":"Yue Zha and Jing Li. Virtualizing FPGAs in the Cloud. In Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS '20, page 845--858, New York, NY, USA, 2020. Association for Computing Machinery."},{"key":"e_1_3_2_1_62_1","first-page":"470","volume-title":"Zha and Jing Li. Hetero-ViTAL: A Virtualization Stack for Heterogeneous FPGA Clusters. In 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA)","author":"Yue","year":"2021","unstructured":"Yue Zha and Jing Li. Hetero-ViTAL: A Virtualization Stack for Heterogeneous FPGA Clusters. In 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA), pages 470--483, 2021."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446699"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2934644"},{"key":"e_1_3_2_1_65_1","first-page":"1241","volume-title":"Automation and Test in Europe Conference and Exhibition (DATE)","author":"Zhang Wentai","year":"2019","unstructured":"Wentai Zhang, Jiaxi Zhang, Minghua Shen, Guojie Luo, and Nong Xiao. An Efficient Mapping Approach to Large-Scale DNNs on Multi-FPGA Architectures. In 2019 Design, Automation and Test in Europe Conference and Exhibition (DATE), pages 1241--1244, 2019."}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","location":"La Jolla CA USA","acronym":"ASPLOS '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651347","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:43Z","timestamp":1750291423000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":65,"alternative-id":["10.1145\/3620666.3651347","10.1145\/3620666"],"URL":"https:\/\/doi.org\/10.1145\/3620666.3651347","relation":{},"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2024-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}