{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T04:07:04Z","timestamp":1781064424679,"version":"3.54.1"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T00:00:00Z","timestamp":1735084800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Spoke 1 (FutureHPC & BigData) of the Italian Research Center"},{"name":"MUR Mission 4 - Next Generation EU"},{"name":"Adaptive Tunability for Synthesis and Control via Autonomous Learning on Edge"},{"name":"Laboratory Directed Research and Development (LDRD) Initiative"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Reconfigurable Technol. Syst."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:p>\n            This article presents a methodology for the Synthesis of PARallel multi-Threaded Accelerators (SPARTA) from OpenMP annotated C\/C++ specifications. SPARTA extends an open-source HLS tool, enabling the generation of accelerators that provide latency tolerance for irregular memory accesses through multithreading, support fine-grained memory-level parallelism through a hot-potato deflection-based network-on-chip (NoC), support synchronization constructs, and can instantiate memory-side caches. Our approach is based on a custom runtime OpenMP library, providing flexibility and extensibility. Experimental results show high scalability when synthesizing irregular graph kernels. The accelerators generated with our approach are, on average, 2.29\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\times\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            faster than state-of-the-art HLS methodologies.\n          <\/jats:p>","DOI":"10.1145\/3677035","type":"journal-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T13:44:58Z","timestamp":1720791898000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["SPARTA: High-Level Synthesis of Parallel Multi-Threaded Accelerators"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6311-5458","authenticated-orcid":false,"given":"Giovanni","family":"Gozzi","sequence":"first","affiliation":[{"name":"Politecnico di Milano, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8675-6703","authenticated-orcid":false,"given":"Michele","family":"Fiorito","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8202-1627","authenticated-orcid":false,"given":"Serena","family":"Curzel","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7991-8554","authenticated-orcid":false,"given":"Claudio","family":"Barone","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, Richland, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3516-7903","authenticated-orcid":false,"given":"Vito Giovanni","family":"Castellana","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, Richland, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-1420","authenticated-orcid":false,"given":"Marco","family":"Minutoli","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, Richland, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9452-120X","authenticated-orcid":false,"given":"Antonino","family":"Tumeo","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, Richland, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0301-4419","authenticated-orcid":false,"given":"Fabrizio","family":"Ferrandi","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,25]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Graph500. 2023. Retrieved from https:\/\/graph500.org"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3529256"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_2_5_2","unstructured":"ARM Developers. 2020. AMBA AXI and ACE Protocol Specification. Retrieved from https:\/\/developer.arm.com\/documentation\/ihi0022\/e\/AMBA-AXI3-and-AXI4-Protocol-Specification"},{"key":"e_1_3_2_6_2","first-page":"373","volume-title":"Proceedings of the IEEE International Symposium on High Performance Computer Architecture (HPCA)","author":"Basak Abanti","year":"2019","unstructured":"Abanti Basak, Shuangchen Li, Xing Hu, Sang Min Oh, Xinfeng Xie, Li Zhao, Xiaowei Jiang, and Yuan Xie. 2019. Analysis and Optimization of the Memory Hierarchy for Graph Processing Workloads. In Proceedings of the IEEE International Symposium on High Performance Computer Architecture (HPCA). 373\u2013386."},{"key":"e_1_3_2_7_2","first-page":"12","volume-title":"Proceedings of the SC Conference on High Performance Computing Networking, Storage and Analysis (SC \u201912)","author":"Beamer Scott","year":"2012","unstructured":"Scott Beamer, Krste Asanovic, and David A. Patterson. 2012. Direction-Optimizing Breadth-First Search. In Proceedings of the SC Conference on High Performance Computing Networking, Storage and Analysis (SC \u201912). 12."},{"key":"e_1_3_2_8_2","unstructured":"Scott Beamer Krste Asanovic and David A. Patterson. 2015. The GAP Benchmark Suite. Retrieved from http:\/\/arxiv.org\/abs\/1508.03619"},{"key":"e_1_3_2_9_2","first-page":"8","volume-title":"Proceedings of the IEEE 23rd International Conference on Application-Specific Systems, Architectures and Processors (ASAP \u201912)","author":"Betkaoui B.","year":"2012","unstructured":"B. Betkaoui, Yu Wang, D.B. Thomas, and W. Luk. 2012. A Reconfigurable Computing Approach for Efficient and Scalable Parallel Graph Exploration. In Proceedings of the IEEE 23rd International Conference on Application-Specific Systems, Architectures and Processors (ASAP \u201912). 8\u201315."},{"key":"e_1_3_2_10_2","first-page":"1","volume-title":"Proceedings of the IEEE\/ACM International Conference on Computer Aided Design (ICCAD)","author":"Agostini Nicolas Bohm","year":"2022","unstructured":"Nicolas Bohm Agostini, Serena Curzel, Vinay Amatya, Cheng Tan, Marco Minutoli, Vito Giovanni Castellana, Joseph Manzano, David Kaeli, and Antonino Tumeo. 2022. An MLIR-based Compiler Flow for System-Level Design and Hardware Acceleration. In Proceedings of the IEEE\/ACM International Conference on Computer Aided Design (ICCAD). 1\u20139."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.5555\/2555729.2555747"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/2840819.2840865"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.5555\/355074"},{"key":"e_1_3_2_14_2","first-page":"69","volume-title":"Proceedings of the ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)","author":"Chen Xinyu","year":"2021","unstructured":"Xinyu Chen, Hongshi Tan, Yao Chen, Bingsheng He, Weng-Fai Wong, and Deming Chen. 2021. ThunderGP: HLS-Based Graph Processing Framework on FPGAs. In Proceedings of the ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA). 69\u201380."},{"key":"e_1_3_2_15_2","first-page":"204","volume-title":"Proceedings of the 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. 2021. Extending High-Level Synthesis for Task-Parallel Programs. In Proceedings of the IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). 204\u2013213."},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1109\/FPT.2013.6718365","volume-title":"Proceedings of the 2013 International Conference on Field-Programmable Technology (FPT)","author":"Choi Jongsok","year":"2013","unstructured":"Jongsok Choi, Stephen Brown, and Jason Anderson. 2013. From Software Threads to Parallel Hardware in High-Level Synthesis for FPGAs. In Proceedings of the 2013 International Conference on Field-Programmable Technology (FPT). 270\u2013277."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3530775"},{"key":"e_1_3_2_18_2","first-page":"54","volume-title":"Proceedings of the ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)","author":"Du Yixiao","year":"2022","unstructured":"Yixiao Du, Yuwei Hu, Zhongchun Zhou, and Zhiru Zhang. 2022. High-Performance Sparse Linear Algebra on HBM-Equipped FPGAs Using HLS: A Case Study on SpMV. In Proceedings of the ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA). 54\u201364."},{"key":"e_1_3_2_19_2","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/B978-155860852-8\/50010-9","volume-title":"Interconnection Networks: An Engineering Approach","author":"Duato Jos\u00e9","year":"2003","unstructured":"Jos\u00e9 Duato, Sudhakar Yalamanchili, and Lionel Ni. 2003. Interconnection Networks: An Engineering Approach. Morgan Kaufmann, 359\u2013444."},{"key":"e_1_3_2_20_2","first-page":"1327","volume-title":"Proceedings of the 58th ACM\/IEEE Design Automation Conference (DAC)","author":"Ferrandi F.","year":"2021","unstructured":"F. Ferrandi, V. G. Castellana, S. Curzel, P. Fezzardi, M. Fiorito, M. Lattuada, M. Minutoli, C. Pilato, and A. Tumeo. 2021. Bambu: An Open-Source Research Framework for the High-Level Synthesis of Complex Applications. In Proceedings of the 58th ACM\/IEEE Design Automation Conference (DAC). 1327\u20131330."},{"key":"e_1_3_2_21_2","first-page":"1","volume-title":"Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE)","author":"Gao Yingxue","year":"2023","unstructured":"Yingxue Gao, Teng Wang, Lei Gong, Chao Wang, Xi Li, and Xuehai Zhou. 2023. FastRW: A Dataflow-Efficient and Memory-Aware Accelerator for Graph Random Walk on FPGAs. In Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE). 1\u20136."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.121"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-019-1914-z"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.websem.2005.06.005"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.5555\/2555729.2555732"},{"key":"e_1_3_2_26_2","first-page":"1","volume-title":"Proceedings of the IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Ham T. J.","year":"2016","unstructured":"T. J. Ham, L. Wu, N. Sundaram, N. Satish, and M. Martonosi. 2016. Graphicionado: A high-Performance and Energy-Efficient Accelerator for Graph Analytics. In Proceedings of the IEEE\/ACM International Symposium on Microarchitecture (MICRO). 1\u201313."},{"key":"e_1_3_2_27_2","first-page":"1","volume-title":"Proceedings of the IEEE\/ACM International Conference on Computer Aided Design (ICCAD)","author":"Hu Yuwei","year":"2021","unstructured":"Yuwei Hu, Yixiao Du, Ecenur Ustun, and Zhiru Zhang. 2021. GraphLily: Accelerating Graph Linear Algebra on HBM-Equipped FPGAs. In Proceedings of the IEEE\/ACM International Conference on Computer Aided Design (ICCAD). 1\u20139."},{"key":"e_1_3_2_28_2","first-page":"1","volume-title":"Proceedings of the International Conference on Field Programmable Logic and Applications (FPL)","author":"Huthmann J.","year":"2014","unstructured":"J. Huthmann, J. Oppermann, and A. Koch. 2014. Automatic High-Level Synthesis of Multi-Threaded Hardware Accelerators. In Proceedings of the International Conference on Field Programmable Logic and Applications (FPL). 1\u20134."},{"key":"e_1_3_2_29_2","unstructured":"Data Vortex Inc. 2023. Data Vortex Network on Chip IP Block. Retrieved from https:\/\/www.datavortex.com\/dv-noc-brief"},{"key":"e_1_3_2_30_2","first-page":"411","volume-title":"Proceedings of the ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA)","author":"Jun Sang-Woo","year":"2018","unstructured":"Sang-Woo Jun, Andy Wright, Sizhuo Zhang, Shuotao Xu, and Arvind. 2018. GraFBoost: Using Accelerated Flash Storage for External Graph Analytics. In Proceedings of the ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA). 411\u2013424."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2015.7293956"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3027486"},{"key":"e_1_3_2_33_2","unstructured":"Khronos Group. [n. d.]. OpenCL - Open Standard for Parallel Programming of Heterogeneous Systems. Retrieved from https:\/\/www.khronos.org\/opencl\/"},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1145\/3293883.3299108","volume-title":"Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming","author":"Lakhotia Kartik","year":"2019","unstructured":"Kartik Lakhotia, Rajgopal Kannan, Sourav Pati, and Viktor Prasanna. 2019. GPOP: A Cache and Memory-Efficient Framework for Graph Processing over Partitions. In Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming. 393\u2013394."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2007.913739"},{"key":"e_1_3_2_36_2","unstructured":"LLVM developers. [n. d.]. LLVM OpenMP Runtime Library. Retrieved from https:\/\/raw.githubusercontent.com\/llvm\/llvm-project\/main\/openmp\/runtime\/doc\/Reference.pdf"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2015.03.003"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2019.00030"},{"key":"e_1_3_2_39_2","first-page":"519","volume-title":"Proceedings of the IEEE 28th International Parallel and Distributed Processing Symposium (IPDPS)","author":"Manne Fredrik","year":"2014","unstructured":"Fredrik Manne and Mahantesh Halappanavar. 2014. New Effective Multithreaded Matching Algorithms. In Proceedings of the IEEE 28th International Parallel and Distributed Processing Symposium (IPDPS). 519\u2013528."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3057860"},{"key":"e_1_3_2_41_2","volume-title":"Proceedings of the 35th International Conference on Computer-Aided Design (ICCAD)","author":"Minutoli Marco","year":"2016","unstructured":"Marco Minutoli, Vito Giovanni Castellana, Antonino Tumeo, Marco Lattuada, and Fabrizio Ferrandi. 2016. Efficient Synthesis Of Graph Methods: A Dynamically Scheduled Architecture. In Proceedings of the 35th International Conference on Computer-Aided Design (ICCAD)."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555781"},{"key":"e_1_3_2_43_2","first-page":"1591","volume-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","volume":"35","author":"Nane Razvan","year":"2016","unstructured":"Razvan Nane, Vlad Mihai Sima, Christian Pilato, Jongsok Choi, Blair Fort, Andrew Canis, Yu Ting Chen, Hsuan Hsiao, Stephen Dean Brown, Fabrizio Ferrandi, Jason Helge Anderson, and Koen Bertels. 2016. A Survey and Evaluation of FPGA High-Level Synthesis Tools. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 35, 10 (2016), 1591\u20131604."},{"key":"e_1_3_2_44_2","first-page":"661","volume-title":"Proceedings of the IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","author":"Nguyen Tan","year":"2016","unstructured":"Tan Nguyen, Yao Cheny, Kyle Rupnow, Swathi Gurumani, and Deming Chen. 2016. SoC, NoC and Hierarchical Bus Implementations of Applications on FPGAs Using the FCUDA Flow. In Proceedings of the IEEE Computer Society Annual Symposium on VLSI (ISVLSI). 661\u2013666."},{"key":"e_1_3_2_45_2","first-page":"25","volume-title":"Proceedings of the IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM)","author":"Nurvitadhi E.","year":"2014","unstructured":"E. Nurvitadhi, G. Weisz, Y. Wang, S. Hurkat, M. Nguyen, J. C. Hoe, J. F. Mart\u00ednez, and C. Guestrin. 2014. GraphGen: An FPGA Framework for Vertex-Centric Graph Computation. In Proceedings of the IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM). 25\u201328."},{"key":"e_1_3_2_46_2","first-page":"111","volume-title":"Proceedings of the ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)","author":"Oguntebi Tayo","year":"2016","unstructured":"Tayo Oguntebi and Kunle Olukotun. 2016. GraphOps: A Dataflow Library for Graph Analytics Acceleration. In Proceedings of the ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA). 111\u2013117."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530681"},{"key":"e_1_3_2_48_2","volume-title":"Proceedings of the International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS)","author":"Podobas Artur","year":"2016","unstructured":"Artur Podobas and Mats Brorsson. 2016. Empowering OpenMP with Automatically Generated Hardware. In Proceedings of the International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS). IEEE."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2014.6983050"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.5555\/829576"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530409"},{"key":"e_1_3_2_52_2","first-page":"1","volume-title":"Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)","author":"Sommer L.","year":"2017","unstructured":"L. Sommer, J. Oppermann, J. Hofmann, and A. Koch. 2017. Synthesis of Interleaved Multithreaded Accelerators from OpenMP Loops. In Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig). 1\u20137."},{"key":"e_1_3_2_53_2","first-page":"531","volume-title":"Proceedings of the IEEE International Symposium on High Performance Computer Architecture (HPCA)","author":"Song Linghao","year":"2018","unstructured":"Linghao Song, Youwei Zhuo, Xuehai Qian, Hai Li, and Yiran Chen. 2018. GraphR: Accelerating Graph Processing Using ReRAM. In Proceedings of the IEEE International Symposium on High Performance Computer Architecture (HPCA). 531\u2013543."},{"key":"e_1_3_2_54_2","first-page":"78","volume-title":"Proceedings of the IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)","author":"Tan Mingxing","year":"2015","unstructured":"Mingxing Tan, Gai Liu, Ritchie Zhao, Steve Dai, and Zhiru Zhang. 2015. ElasticFlow: A Complexity-Effective Approach for Pipelining Irregular Loop Nests. In Proceedings of the IEEE\/ACM International Conference on Computer-Aided Design (ICCAD). 78\u201385."},{"key":"e_1_3_2_55_2","first-page":"127","volume-title":"Proceedings of the 18th IEEE Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","author":"Villarreal J.","year":"2010","unstructured":"J. Villarreal, A. Park, W. Najjar, and R. Halstead. 2010. Designing Modular Hardware Accelerators in C with ROCCC 2.0. In Proceedings of the 18th IEEE Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). 127\u2013134."},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.5555\/2840819.2840866"},{"key":"e_1_3_2_57_2","first-page":"199","volume-title":"Proceedings of the IEEE International Symposium on High-Performance Computer Architecture (HPCA)","author":"Yao Pengcheng","year":"2022","unstructured":"Pengcheng Yao, Long Zheng, Yu Huang, Qinggang Wang, Chuangyi Gui, Zhen Zeng, Xiaofei Liao, Hai Jin, and Jingling Xue. 2022. ScalaGraph: A Scalable Accelerator for Massively Parallel Graph Processing. In Proceedings of the IEEE International Symposium on High-Performance Computer Architecture (HPCA). 199\u2013212."},{"key":"e_1_3_2_58_2","first-page":"741","volume-title":"Proceedings of the IEEE International Symposium on High-Performance Computer Architecture (HPCA)","author":"Ye Hanchen","year":"2022","unstructured":"Hanchen Ye, Cong Hao, Jianyi Cheng, Hyunmin Jeong, Jack Huang, Stephen Neuendorffer, and Deming Chen. 2022. ScaleHLS: A New Scalable High-Level Synthesis Framework on Multi-Level Intermediate Representation. In Proceedings of the IEEE International Symposium on High-Performance Computer Architecture (HPCA). 741\u2013755."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021737"},{"key":"e_1_3_2_60_2","first-page":"1","volume-title":"Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)","author":"Zhou Shijie","year":"2015","unstructured":"Shijie Zhou, Charalampos Chelmis, and Viktor K. Prasanna. 2015. Optimizing Memory Performance for FPGA Implementation of Pagerank. In Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig). 1\u20136."},{"key":"e_1_3_2_61_2","first-page":"2249","volume-title":"IEEE Transactions on Parallel and Distributed Systems","volume":"30","author":"Zhou Shijie","year":"2019","unstructured":"Shijie Zhou, Rajgopal Kannan, Viktor K. Prasanna, Guna Seetharaman, and Qing Wu. 2019. HitGraph: High-Throughput Graph Processing Framework on FPGA. IEEE Transactions on Parallel and Distributed Systems 30, 10 (2019), 2249\u20132264."},{"key":"e_1_3_2_62_2","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1145\/3203217.3203233","volume-title":"Proceedings of the ACM International Conference on Computing Frontiers (CF)","author":"Zhou Shijie","year":"2018","unstructured":"Shijie Zhou, Rajgopal Kannan, Hanqing Zeng, and Viktor K. Prasanna. 2018. An FPGA Framework for Edge-Centric Graph Processing. In Proceedings of the ACM International Conference on Computing Frontiers (CF). 69\u201377."}],"container-title":["ACM Transactions on Reconfigurable Technology and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677035","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:16Z","timestamp":1750294696000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677035"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,25]]},"references-count":61,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3,31]]}},"alternative-id":["10.1145\/3677035"],"URL":"https:\/\/doi.org\/10.1145\/3677035","relation":{},"ISSN":["1936-7406","1936-7414"],"issn-type":[{"value":"1936-7406","type":"print"},{"value":"1936-7414","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,25]]},"assertion":[{"value":"2023-12-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}