{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T08:27:32Z","timestamp":1786523252032,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767570","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:13:44Z","timestamp":1762532024000},"page":"2077-2087","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Efficient Load Balancing BFS on GPUs: One Code for AMD, Intel & Nvidia"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0351-2055","authenticated-orcid":false,"given":"Kaan","family":"Olgu","sequence":"first","affiliation":[{"name":"University of Bristol, Bristol, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5088-0267","authenticated-orcid":false,"given":"Tobias","family":"Kenter","sequence":"additional","affiliation":[{"name":"Paderborn University, Paderborn, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5153-5481","authenticated-orcid":false,"given":"Jose","family":"Nunez-Yanez","sequence":"additional","affiliation":[{"name":"Linkoping University, Linkoping, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5312-0378","authenticated-orcid":false,"given":"Simon","family":"McIntosh-Smith","sequence":"additional","affiliation":[{"name":"University of Bristol, Bristol, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6439-4171","authenticated-orcid":false,"given":"Tom","family":"Deakin","sequence":"additional","affiliation":[{"name":"University of Bristol, Bristol, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.46"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00107"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","unstructured":"Scott Beamer Krste Asanovi\u0107 and David Patterson. 2013. Direction-Optimizing Breadth-First Search. Scientific Programming 21 3-4 (2013) 702694. arXiv:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.3233\/SPR-13037010.3233\/SPR-130370","DOI":"10.3233\/SPR-130370"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","unstructured":"Massimo Bernaschi Mauro Bisson Enrico Mastrostefano and Flavio Vella. 2018. Multilevel Parallelism for the Exploration of Large-Scale Graphs. IEEE Transactions on Multi-Scale Computing Systems 4 3 (2018) 204\u2013216. 10.1109\/TMSCS.2018.2797195","DOI":"10.1109\/TMSCS.2018.2797195"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36036-7_14"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","unstructured":"Avery Ching Sergey Edunov Maja Kabiljo Dionysios Logothetis and Sambavi Muthukrishnan. 2015. One trillion edges: graph processing at Facebook-scale. Proc. VLDB Endow. 8 12 (Aug. 2015) 1804\u20131815. 10.14778\/2824032.2824077","DOI":"10.14778\/2824032.2824077"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","unstructured":"Jonas Dann Daniel Ritter and Holger Fr\u00f6ning. 2024. GraphScale: Scalable Processing on FPGAs for HBM and Large Graphs. ACM Trans. Reconfigurable Technol. Syst. 17 2 Article 22 (March 2024) 23\u00a0pages. 10.1145\/3616497","DOI":"10.1145\/3616497"},{"key":"e_1_3_3_3_9_2","unstructured":"RAPIDS Developers. 2024. RAPIDS cuGraph - GPU-accelerated Graph Analytics. https:\/\/github.com\/rapidsai\/cugraph\/tree\/main Accessed: 2024-12-01."},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656600"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.37"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.46"},{"key":"e_1_3_3_3_13_2","unstructured":"Graph500. 2024. Large-scale benchmarks. https:\/\/graph500.org\/"},{"key":"e_1_3_3_3_14_2","unstructured":"Intel. 2024. GPU Occupancy Calculator. https:\/\/oneapi-src.github.io\/oneAPI-samples\/Tools\/GPU-Occupancy-Calculator\/ Accessed: 2024-12-10."},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW59300.2023.00045"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSE-EUC-DCABES.2016.246"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/1810479.1810534"},{"key":"e_1_3_3_3_18_2","unstructured":"Jure Leskovec and Andrej Krevl. 2014. SNAP Datasets: Stanford Large Network Dataset Collection. http:\/\/snap.stanford.edu\/data."},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Enrico Mastrostefano and Massimo Bernaschi. 2013. Efficient breadth first search on multi-GPU systems. J. Parallel and Distrib. Comput. 73 (09 2013) 1292\u20131305. 10.1016\/j.jpdc.2013.05.007","DOI":"10.1016\/j.jpdc.2013.05.007"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","unstructured":"Duane Merrill Michael Garland and Andrew Grimshaw. 2012. Scalable GPU graph traversal. SIGPLAN Not. 47 8 (Feb. 2012) 117\u2013128. 10.1145\/2370036.2145832","DOI":"10.1145\/2370036.2145832"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","unstructured":"Takuji Mitsuishi Jun Suzuki Yuki Hayashi Masaki Kan and Hideharu Amano. 2016. Breadth First Search on Cost-efficient Multi-GPU Systems. SIGARCH Comput. Archit. News 43 4 (April 2016) 58\u201363. 10.1145\/2927964.2927975","DOI":"10.1145\/2927964.2927975"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","unstructured":"Koji Ueno Toyotaro Suzumura Naoya Maruyama Katsuki Fujisawa and Satoshi Matsuoka. 2017. Efficient Breadth-First Search on Massively Parallel and Distributed-Memory Machines. Data Sci. Eng. 2 1 (2017) 22\u201335. 10.1007\/S41019-016-0024-Y","DOI":"10.1007\/S41019-016-0024-Y"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCW63240.2024.00090"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2005.4"}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T07:33:24Z","timestamp":1786520004000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767570"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":24,"alternative-id":["10.1145\/3731599.3767570","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767570","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}