{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:39:30Z","timestamp":1766219970307,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3754598.3754615","type":"proceedings-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:34:32Z","timestamp":1766219672000},"page":"268-277","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SYgraph: A Portable Heterogeneous Graph Analytics Framework for GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9909-6440","authenticated-orcid":false,"given":"Antonio","family":"De Caro","sequence":"first","affiliation":[{"name":"University of Salerno, Fisciano, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9148-9769","authenticated-orcid":false,"given":"Gennaro","family":"Cordasco","sequence":"additional","affiliation":[{"name":"University of Salerno, Fisciano, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8869-6705","authenticated-orcid":false,"given":"Biagio","family":"Cosenza","sequence":"additional","affiliation":[{"name":"University of Salerno, Fisciano, Italy"}]}],"member":"320","published-online":{"date-parts":[[2025,12,20]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"GPU Memory; ROCm Documentation \u2014 rocm.docs.amd.com","year":"2024","unstructured":"AMD. 2024. GPU Memory; ROCm Documentation \u2014 rocm.docs.amd.com. https:\/\/rocm.docs.amd.com\/en\/latest\/conceptual\/gpu-memory.html"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15251-1_26"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00081"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971538"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.50"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018756"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/1963405.1963488"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988752"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Ulrik Brandes. 2001. A faster algorithm for betweenness centrality. Journal of mathematical sociology 25 2 (2001) 163\u2013177.","DOI":"10.1080\/0022250X.2001.9990249"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402918"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Federico Busato and Nicola Bombieri. 2015. An efficient implementation of the Bellman-Ford algorithm for Kepler GPU architectures. IEEE Transactions on Parallel and Distributed Systems 27 8 (2015) 2222\u20132233.","DOI":"10.1109\/TPDS.2015.2485994"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2018.8547541"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.43"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Laxman Dhulipala Guy\u00a0E Blelloch and Julian Shun. 2021. Theoretically efficient parallel graph algorithms can be fast and scalable. ACM Transactions on Parallel Computing (TOPC) 8 1 (2021) 1\u201370.","DOI":"10.1145\/3434393"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781003033707-22"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Alexandros\u00a0V Gerbessiotis and Leslie\u00a0G Valiant. 1994. Direct bulk-synchronous parallel algorithms. Journal of parallel and distributed computing 22 2 (1994) 251\u2013267.","DOI":"10.1006\/jpdc.1994.1085"},{"key":"e_1_3_3_2_18_2","volume-title":"SYCL 2020 Specification (revision 8) \u2014 registry.khronos.org","author":"Group The Khronos\u00ae SYCL\u2122\u00a0Working","year":"2023","unstructured":"The Khronos\u00ae SYCL\u2122\u00a0Working Group. 29-03-2023. SYCL 2020 Specification (revision 8) \u2014 registry.khronos.org. https:\/\/registry.khronos.org\/SYCL\/specs\/sycl-2020\/html\/sycl-2020.html"},{"key":"e_1_3_3_2_19_2","volume-title":"oneAPI Base Toolkit","year":"2024","unstructured":"Intel\u00ae. 2024. oneAPI Base Toolkit. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/base-toolkit.html"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Zhihao Jia Yongkee Kwon Galen Shipman Pat McCormick Mattan Erez and Alex Aiken. 2017. A distributed multi-GPU system for fast graph processing. Proc. VLDB Endow. 11 3 (Nov. 2017) 297\u2013310. 10.14778\/3157794.3157799","DOI":"10.14778\/3157794.3157799"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600227"},{"key":"e_1_3_3_2_22_2","volume-title":"Programming massively parallel processors: a hands-on approach","author":"Kirk David\u00a0B","year":"2016","unstructured":"David\u00a0B Kirk and W\u00a0Hwu Wen-Mei. 2016. Programming massively parallel processors: a hands-on approach. Morgan kaufmann."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295716"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"U. Meyer and P. Sanders. 2003. \u0394 -stepping: a parallelizable shortest path algorithm. Journal of Algorithms 49 1 (2003) 114\u2013152. 10.1016\/S0196-6774(03)00076-2","DOI":"10.1016\/S0196-6774(03)00076-2"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522739"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173180"},{"key":"e_1_3_3_2_27_2","volume-title":"NVIDIA Nsight Compute","year":"2024","unstructured":"NVIDIA. 2024. NVIDIA Nsight Compute. https:\/\/docs.nvidia.com\/nsight-compute\/NsightComputeCli\/index.html"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9277"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159696"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Narayanan Sundaram Nadathur Satish Md\u00a0Mostofa\u00a0Ali Patwary Subramanya\u00a0R. Dulloor Michael\u00a0J. Anderson Satya\u00a0Gautam Vadlamudi Dipankar Das and Pradeep Dubey. 2015. GraphMat: high performance graph analytics made productive. Proc. VLDB Endow. 8 11 (July 2015) 1214\u20131225. 10.14778\/2809974.2809983","DOI":"10.14778\/2809974.2809983"},{"key":"e_1_3_3_2_32_2","volume-title":"November 2024 | TOP500","year":"2024","unstructured":"TOP500.org. 2024. November 2024 | TOP500. https:\/\/top500.org\/lists\/top500\/2024\/11\/"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59419-0_21"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295733"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441605"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Pengyu Wang Jing Wang Chao Li Jianzong Wang Haojin Zhu and Minyi Guo. 2021. Grus: Toward Unified-memory-efficient High-performance Graph Processing on GPU. ACM Trans. Archit. Code Optim. 18 2 (Feb. 2021). 10.1145\/3444844","DOI":"10.1145\/3444844"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Zonghan Wu Shirui Pan Fengwen Chen Guodong Long Chengqi Zhang and Philip\u00a0S. Yu. 2021. A Comprehensive Survey on Graph Neural Networks. IEEE Transactions on Neural Networks and Learning Systems 32 1 (2021) 4\u201324. 10.1109\/TNNLS.2020.2978386","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Boyu Yang Weiguo Zheng Xiang Lian Yuzheng Cai and X\u00a0Sean Wang. 2024. HERO: A Hierarchical Set Partitioning and Join Framework for Speeding up the Set Intersection Over Graphs. Proceedings of the ACM on Management of Data 2 1 (2024) 1\u201325.","DOI":"10.1145\/3639284"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Carl Yang Ayd\u0131n Bulu\u00e7 and John\u00a0D. Owens. 2022. GraphBLAST: A High-Performance Linear Algebra-based Graph Framework on the GPU. ACM Trans. Math. Software 48 1 (Feb. 2022) 1:1\u20131:51. 10.1145\/3466795","DOI":"10.1145\/3466795"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Yunming Zhang Mengjiao Yang Riyadh Baghdadi Shoaib Kamil Julian Shun and Saman Amarasinghe. 2018. GraphIt: a high-performance graph DSL. Proc. ACM Program. Lang. 2 OOPSLA (Oct. 2018). 10.1145\/3276491","DOI":"10.1145\/3276491"}],"event":{"name":"ICPP '25: 54th International Conference on Parallel Processing","location":"San Diego CA USA","acronym":"ICPP '25"},"container-title":["Proceedings of the 54th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3754598.3754615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T08:35:06Z","timestamp":1766219706000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3754598.3754615"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":40,"alternative-id":["10.1145\/3754598.3754615","10.1145\/3754598"],"URL":"https:\/\/doi.org\/10.1145\/3754598.3754615","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-12-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}