{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T15:06:02Z","timestamp":1783091162820,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":105,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,28]]},"DOI":"10.1145\/3774934.3786457","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:25:57Z","timestamp":1769613957000},"page":"81-94","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["DiggerBees: Depth First Search Leveraging Hierarchical Block-Level Stealing on GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7605-525X","authenticated-orcid":false,"given":"Yuyao","family":"Niu","sequence":"first","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"},{"name":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6387-8116","authenticated-orcid":false,"given":"Yuechen","family":"Lu","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2150-5759","authenticated-orcid":false,"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4564-2093","authenticated-orcid":false,"given":"Marc","family":"Casas","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"},{"name":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/341800.341801"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","unstructured":"Umut A. Acar Arthur Chargu\u00e9raud and Mike Rainey. 2015. A work-efficient algorithm for parallel unordered depth-first search. In SC \u201915. 1\u201312. https:\/\/doi.org\/10.1145\/2807591.2807651 10.1145\/2807591.2807651","DOI":"10.1145\/2807591.2807651"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","unstructured":"Alok Aggarwal and Richard Anderson. 1987. A random NC algorithm for depth first search. In STOC \u201987. 325\u2013334. https:\/\/doi.org\/10.1145\/28395.28430 10.1145\/28395.28430","DOI":"10.1145\/28395.28430"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","unstructured":"A. Aggarwal R. J. Anderson and M.-Y. Kao. 1989. Parallel depth-first search in general directed graphs. In STOC \u201989. 297\u2013308. https:\/\/doi.org\/10.1145\/73007.73035 10.1145\/73007.73035","DOI":"10.1145\/73007.73035"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","unstructured":"Matthew Agostini Francis O\u2019Brien and Tarek Abdelrahman. 2020. Balancing Graph Processing Workloads Using Work Stealing on Heterogeneous CPU-FPGA Systems. In ICPP \u201920. Article 50 12 pages. https:\/\/doi.org\/10.1145\/3404397.3404433 10.1145\/3404397.3404433","DOI":"10.1145\/3404397.3404433"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","unstructured":"Tetsuo Asano Taisuke Izumi Masashi Kiyomi Matsuo Konagaya Hirotaka Ono Yota Otachi Pascal Schweitzer Jun Tarui and Ryuhei Uehara. 2014. Depth-First Search Using Bits. In ISAAC \u201914. 553\u2013564. isbn:978-3-319-13074-3 https:\/\/doi.org\/10.1007\/978-3-319-13075-0_44 10.1007\/978-3-319-13075-0_44","DOI":"10.1007\/978-3-319-13075-0_44"},{"key":"e_1_3_2_2_7_1","unstructured":"Scott Beamer Krste Asanovi\u0107 and David Patterson. 2015. The GAP benchmark suite. arXiv preprint arXiv:1508.03619."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3155284.3018756"},{"key":"e_1_3_2_2_9_1","unstructured":"A Tarun Beri B Sorav Bansal and C Subodh Kumar. 2015. Locality aware work-stealing based scheduling in hybrid CPU-GPU clusters. In PDPTA \u201915. 48."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/324133.324234"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","unstructured":"Paolo Boldi Marco Rosa Massimo Santini and Sebastiano Vigna. 2011. Layered Label Propagation: A Multiresolution Coordinate-Free Ordering for Compressing Social Networks. In WWW \u201911. 587\u2013596. https:\/\/doi.org\/10.1145\/1963405.1963488 10.1145\/1963405.1963488","DOI":"10.1145\/1963405.1963488"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","unstructured":"Paolo Boldi and Sebastiano Vigna. 2004. The WebGraph Framework I: Compression Techniques. In WWW \u201904. 595\u2013601. https:\/\/doi.org\/10.1145\/988672.988752 10.1145\/988672.988752","DOI":"10.1145\/988672.988752"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","unstructured":"Trevor Brown Faith Ellen and Eric Ruppert. 2014. A general technique for non-blocking trees. In PPoPP \u201914. 329\u2013342. https:\/\/doi.org\/10.1145\/2555243.2555267 10.1145\/2555243.2555267","DOI":"10.1145\/2555243.2555267"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","unstructured":"Trevor Brown and Joanna Helga. 2011. Non-blocking k-ary search trees. In OPODIS\u201911. 207\u2013221. https:\/\/doi.org\/10.1007\/978-3-642-25873-2_15 10.1007\/978-3-642-25873-2_15","DOI":"10.1007\/978-3-642-25873-2_15"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","unstructured":"Trevor Brown Aleksandar Prokopec and Dan Alistarh. 2020. Non-blocking interpolation search trees with doubly-logarithmic running time. In PPoPP \u201920. 276\u2013291. https:\/\/doi.org\/10.1145\/3332466.3374542 10.1145\/3332466.3374542","DOI":"10.1145\/3332466.3374542"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","unstructured":"Huanqi Cao Yuanwei Wang Haojie Wang Heng Lin Zixuan Ma Wanwang Yin and Wenguang Chen. 2022. Scaling graph traversal to 281 trillion edges with 40 million cores. In PPoPP \u201922. 234\u2013245. https:\/\/doi.org\/10.1145\/3503221.3508403 10.1145\/3503221.3508403","DOI":"10.1145\/3503221.3508403"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","unstructured":"Weichen Cao Ke Meng Zhiheng Lin and Guangming Tan. 2025. GLumin: Fast Connectivity Check Based on LUTs For Efficient Graph Pattern Mining. In PPoPP \u201925. 455\u2013468. https:\/\/doi.org\/10.1145\/3710848.3710889 10.1145\/3710848.3710889","DOI":"10.1145\/3710848.3710889"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","unstructured":"Xuhao Chen and Arvind. 2022. Efficient and scalable graph pattern mining on $GPUs$. In OSDI \u201922. 857\u2013877. https:\/\/doi.org\/10.1109\/PADSW.2018.8644869 10.1109\/PADSW.2018.8644869","DOI":"10.1109\/PADSW.2018.8644869"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","unstructured":"Guojing Cong Sreedhar Kodali Sriram Krishnamoorthy Doug Lea Vijay Saraswat and Tong Wen. 2008. Solving Large Irregular Graph Problems Using Adaptive Work-Stealing. In ICPP \u201908. 536\u2013545. https:\/\/doi.org\/10.1109\/ICPP.2008.88 10.1109\/ICPP.2008.88","DOI":"10.1109\/ICPP.2008.88"},{"key":"e_1_3_2_2_20_1","unstructured":"Thomas H Cormen Charles E Leiserson Ronald L Rivest and Clifford Stein. 2022. Introduction to algorithms."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759872"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1006\/jagm.1995.1025"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3087556.3087580"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3434393"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","unstructured":"James Dinan D. Brian Larkins P. Sadayappan Sriram Krishnamoorthy and Jarek Nieplocha. 2009. Scalable work stealing. In SC \u201909. 11 pages. https:\/\/doi.org\/10.1145\/1654059.1654113 10.1145\/1654059.1654113","DOI":"10.1145\/1654059.1654113"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","unstructured":"Xiaojun Dong Letong Wang Yan Gu and Yihan Sun. 2023. Provably Fast and Space-Efficient Parallel Biconnectivity. In PPoPP \u201923. 52\u201365. https:\/\/doi.org\/10.1145\/3572848.3577483 10.1145\/3572848.3577483","DOI":"10.1145\/3572848.3577483"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1980.1675681"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","unstructured":"Faith Ellen Panagiota Fatourou Joanna Helga and Eric Ruppert. 2014. The amortized complexity of non-blocking binary search trees. In PODC \u201914. 332\u2013340. https:\/\/doi.org\/10.1145\/2611462.2611486 10.1145\/2611462.2611486","DOI":"10.1145\/2611462.2611486"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","unstructured":"Faith Ellen Panagiota Fatourou Eric Ruppert and Franck van Breugel. 2010. Non-blocking binary search trees. In PODC \u201910. 131\u2013140. https:\/\/doi.org\/10.1145\/1835698.1835736 10.1145\/1835698.1835736","DOI":"10.1145\/1835698.1835736"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","unstructured":"Naila Farooqui Rajkishore Barik Brian T. Lewis Tatiana Shpeisman and Karsten Schwan. 2016. Affinity-aware work-stealing for integrated CPU-GPU processors. In PPoPP \u201916. Article 30 2 pages. https:\/\/doi.org\/10.1145\/2851141.2851194 10.1145\/2851141.2851194","DOI":"10.1145\/2851141.2851194"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","unstructured":"Panagiota Fatourou Elias Papavasileiou and Eric Ruppert. 2019. Persistent Non-Blocking Binary Search Trees Supporting Wait-Free Range Queries. In SPAA \u201919. 275\u2013286. https:\/\/doi.org\/10.1145\/3323165.3323197 10.1145\/3323165.3323197","DOI":"10.1145\/3323165.3323197"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","unstructured":"Panagiota Fatourou and Eric Ruppert. 2025. Lock-Free Augmented Trees (Abstract). In HOPC \u201925. 1\u20133. https:\/\/doi.org\/10.1145\/3746238.3746251 10.1145\/3746238.3746251","DOI":"10.1145\/3746238.3746251"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/22719.24067"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","unstructured":"Anil Gaihre Zhenlin Wu Fan Yao and Hang Liu. 2019. XBFS: eXploring Runtime Optimizations for Breadth-First Search on GPUs. In HPDC \u201919. 121\u2013131. https:\/\/doi.org\/10.1145\/3307681.3326606 10.1145\/3307681.3326606","DOI":"10.1145\/3307681.3326606"},{"key":"e_1_3_2_2_36_1","volume-title":"Nicolas Maillard, and Bruno Raffin.","author":"Gautier Thierry","year":"2013","unstructured":"Thierry Gautier, Joao Vicente Ferreira Lima, Nicolas Maillard, and Bruno Raffin. 2013. Locality-aware work stealing on multi-CPU and multi-GPU architectures. In MULTIPROG \u201913."},{"key":"e_1_3_2_2_37_1","unstructured":"Mohsen Ghaffari Christoph Grunau and Jiahao Qu. 2023. Nearly Work-Efficient Parallel DFS in Undirected Graphs. In SPAA \u201923. 273\u2013283."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01937481"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/0890-5401(92)90033-C"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","unstructured":"Yan Gu Zachary Napier and Yihan Sun. 2022. Analysis of Work-Stealing and Parallel Cache Complexity. 46\u201360. https:\/\/doi.org\/10.1137\/1.9781611977059.4 10.1137\/1.9781611977059.4","DOI":"10.1137\/1.9781611977059.4"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1137\/0219047"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2017.41"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1137\/0217028"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2017.7975294"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/362248.362272"},{"key":"e_1_3_2_2_46_1","unstructured":"Masaharu Imai Yuuji Yoshida and Teruo Fukumura. 1979. A parallel searching scheme for multiprocessor systems and its application to combinatorial problems. In IJCAI\u201979. 416\u2013418."},{"key":"e_1_3_2_2_47_1","unstructured":"Virendra K Janakiram Dharma P Agrawal and Ravi Mehrotra. 1987. Randomized Parallel Algorithms for Prolog Programs and Backtracking Applications.. In ICPP \u201987. 278\u2013281."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/368996.369025"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0040373"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.313122"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600227"},{"key":"e_1_3_2_2_52_1","first-page":"1004","article-title":"Depth-first search","volume":"2","author":"Kumar Vipin","year":"1987","unstructured":"Vipin Kumar. 1987. Depth-first search. Encyclopaedia of Artificial Intelligence, 2 (1987), 1004\u20131005.","journal-title":"Encyclopaedia of Artificial Intelligence"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1994.1070"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01389001"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","unstructured":"Vipin Kumar and V. Nageshwara Rao. 1990. Scalable parallel formulations of depth-first search. 1\u201341. https:\/\/doi.org\/10.1007\/978-1-4612-3390-9_1 10.1007\/978-1-4612-3390-9_1","DOI":"10.1007\/978-1-4612-3390-9_1"},{"key":"e_1_3_2_2_56_1","unstructured":"Vipin Kumar V. Nageshwara Rao and K. Ramesh. 1988. Parallel Depth First Search on the Ring Architecture."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","unstructured":"Jo\u00e3o V.F. Lima Thierry Gautier Nicolas Maillard and Vincent Danjean. 2012. Exploiting Concurrent GPU Operations for Efficient Work Stealing on Multi-GPUs. In SBAC-PAD \u201912. 75\u201382. https:\/\/doi.org\/10.1109\/SBAC-PAD.2012.28 10.1109\/SBAC-PAD.2012.28","DOI":"10.1109\/SBAC-PAD.2012.28"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","unstructured":"Heng Lin Xiaowei Zhu Bowen Yu Xiongchao Tang Wei Xue Wenguang Chen Lufei Zhang Torsten Hoefler Xiaosong Ma Xin Liu Weimin Zheng and Jingfang Xu. 2018. ShenTu: Processing Multi-Trillion Edge Graphs on Millions of Cores in Seconds. In SC \u201918. 706\u2013716. https:\/\/doi.org\/10.1109\/SC.2018.00059 10.1109\/SC.2018.00059","DOI":"10.1109\/SC.2018.00059"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","unstructured":"Hang Liu and H. Howie Huang. 2015. Enterprise: breadth-first graph traversal on GPUs. In SC \u201915. 1\u201312. https:\/\/doi.org\/10.1145\/2807591.2807594 10.1145\/2807591.2807594","DOI":"10.1145\/2807591.2807594"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10009-015-0382-1"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","unstructured":"Lijuan Luo Martin Wong and Wen-mei Hwu. 2010. An effective GPU implementation of breadth-first search. In DAC \u201910. 52\u201355. https:\/\/doi.org\/10.1145\/1837274.1837289 10.1145\/1837274.1837289","DOI":"10.1145\/1837274.1837289"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1177\/0165551513519212"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1492-2_6"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","unstructured":"Ke Meng Liang Geng Xue Li Qian Tao Wenyuan Yu and Jingren Zhou. 2023. Efficient Multi-GPU Graph Processing with Remote Work Stealing. In ICDE \u201923. 191\u2013204. https:\/\/doi.org\/10.1109\/ICDE55515.2023.00022 10.1109\/ICDE55515.2023.00022","DOI":"10.1109\/ICDE55515.2023.00022"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","unstructured":"Duane Merrill Michael Garland and Andrew Grimshaw. 2012. Scalable GPU graph traversal. In PPoPP \u201912. 117\u2013128. https:\/\/doi.org\/10.1145\/2370036.2145832 10.1145\/2370036.2145832","DOI":"10.1145\/2370036.2145832"},{"key":"e_1_3_2_2_66_1","unstructured":"Seung-Jai Min Costin Iancu and Katherine Yelick. 2011. Hierarchical work stealing on manycore clusters. In PGAS11 \u201911. 625."},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3633331"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.963420"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","unstructured":"Maxim Naumov Alysson Vrielink and Michael Garland. 2017. Parallel Depth-First Search for Directed Acyclic Graphs. In IA3\u201917. Article 4 8 pages. https:\/\/doi.org\/10.1145\/3149704.3149764 10.1145\/3149704.3149764","DOI":"10.1145\/3149704.3149764"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","unstructured":"Yuyao Niu and Marc Casas. 2025. BerryBees: Breadth First Search by Bit-Tensor-Cores. In PPoPP \u201925. 339\u2013354. https:\/\/doi.org\/10.1145\/3710848.3710859 10.1145\/3710848.3710859","DOI":"10.1145\/3710848.3710859"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","unstructured":"Yuyao Niu Yuechen Lu Weifeng Liu and Marc Casas. 2025. DiggerBees Artifact. https:\/\/doi.org\/10.5281\/zenodo.18072817 10.5281\/zenodo.18072817","DOI":"10.5281\/zenodo.18072817"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173180"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","unstructured":"Linshan Qiu Lu Chen Hailiang Jie Xiangyu Ke Yunjun Gao Yang Liu and Zetao Zhang. 2024. GPU-Accelerated Batch-Dynamic Subgraph Matching. In ICDE \u201924\u2019. 3204\u20133216. https:\/\/doi.org\/10.1109\/ICDE60146.2024.00248 10.1109\/ICDE60146.2024.00248","DOI":"10.1109\/ICDE60146.2024.00248"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","unstructured":"Jean-No\u00ebl Quintin and Fr\u00e9d\u00e9ric Wagner. 2010. Hierarchical work-stealing. In Euro-Par \u201910. 217\u2013229. https:\/\/doi.org\/10.1007\/978-3-642-15277-1_21 10.1007\/978-3-642-15277-1_21","DOI":"10.1007\/978-3-642-15277-1_21"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","unstructured":"Stefan Radtke Jens Bargfrede and Walter Anheier. 1995. Distributed automatic test pattern generation with a parallel FAN algorithm. In ICCD \u201995. 698\u2013702. https:\/\/doi.org\/10.1109\/ICCD.1995.528944 10.1109\/ICCD.1995.528944","DOI":"10.1109\/ICCD.1995.528944"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01389000"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","unstructured":"V. Nageshwara Rao and Vipin Kumar. 1988. Superlinear speedup in parallel state-space search. In Foundations of Software Technology and Theoretical Computer Science. 161\u2013174. https:\/\/doi.org\/10.1007\/3-540-50517-2_79 10.1007\/3-540-50517-2_79","DOI":"10.1007\/3-540-50517-2_79"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.219757"},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(85)90024-9"},{"key":"e_1_3_2_2_80_1","doi-asserted-by":"publisher","unstructured":"A. Reinefeld and V. Schnecke. 1994. Work-load balancing in highly parallel depth-first search. In SHPCC \u201994. 773\u2013780. https:\/\/doi.org\/10.1109\/SHPCC.1994.296719 10.1109\/SHPCC.1994.296719","DOI":"10.1109\/SHPCC.1994.296719"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133900"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314626"},{"key":"e_1_3_2_2_83_1","unstructured":"Vikram A. Saletore and L. V. Kal\u00e9. 1990. Consistent linear speedups to a first solution in parallel state-space search. In AAAI\u201990. 227\u2013233."},{"key":"e_1_3_2_2_84_1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(88)90048-8"},{"key":"e_1_3_2_2_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"e_1_3_2_2_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCC.2015.8"},{"key":"e_1_3_2_2_87_1","doi-asserted-by":"publisher","DOI":"10.1137\/0215058"},{"key":"e_1_3_2_2_88_1","doi-asserted-by":"publisher","unstructured":"Daniele G. Spampinato Upasana Sridhar and Tze Meng Low. 2019. Linear algebraic depth-first search. In ARRAY \u201919. 93\u2013104. https:\/\/doi.org\/10.1145\/3315454.3329962 10.1145\/3315454.3329962","DOI":"10.1145\/3315454.3329962"},{"key":"e_1_3_2_2_89_1","doi-asserted-by":"publisher","unstructured":"Shixuan Sun Yulin Che Lipeng Wang and Qiong Luo. 2019. Efficient Parallel Subgraph Enumeration on a Single Machine. In ICDE \u201919. 232\u2013243. https:\/\/doi.org\/10.1109\/ICDE.2019.00029 10.1109\/ICDE.2019.00029","DOI":"10.1109\/ICDE.2019.00029"},{"key":"e_1_3_2_2_90_1","doi-asserted-by":"publisher","unstructured":"Shixuan Sun and Qiong Luo. 2018. Parallelizing Recursive Backtracking Based Subgraph Matching on a Single Machine. In ICPADS \u201918. 1\u20139. https:\/\/doi.org\/10.1109\/PADSW.2018.8644869 10.1109\/PADSW.2018.8644869","DOI":"10.1109\/PADSW.2018.8644869"},{"key":"e_1_3_2_2_91_1","doi-asserted-by":"publisher","DOI":"10.1137\/0201010"},{"key":"e_1_3_2_2_92_1","doi-asserted-by":"publisher","DOI":"10.1137\/0201010"},{"key":"e_1_3_2_2_93_1","unstructured":"Vasileios Trigonakis Jean-Pierre Lozi Tom\u00e1\u0161 Falt\u00edn Nicholas P. Roth Iraklis Psaroudakis Arnaud Delamare Vlad Haprian Calin Iorgulescu Petr Koupy Jinsoo Lee Sungpack Hong and Hassan Chafi. 2021. aDFS: An Almost Depth-First-Search Distributed Graph-Querying System. In USENIX ATC \u201921. 273\u2013287."},{"key":"e_1_3_2_2_94_1","doi-asserted-by":"publisher","unstructured":"Hao Wang Liang Geng Rubao Lee Kaixi Hou Yanfeng Zhang and Xiaodong Zhang. 2019. SEP-graph: finding shortest execution paths for graph processing under a hybrid framework on GPU. In PPoPP \u201919. 38\u201352. https:\/\/doi.org\/10.1145\/3293883.3295733 10.1145\/3293883.3295733","DOI":"10.1145\/3293883.3295733"},{"key":"e_1_3_2_2_95_1","doi-asserted-by":"publisher","unstructured":"Letong Wang Guy Blelloch Yan Gu and Yihan Sun. 2025. Parallel Cluster-BFS and Applications to Shortest Paths. In ALENEX \u201925. 42\u201355. https:\/\/doi.org\/10.1137\/1.9781611978339.4 10.1137\/1.9781611978339.4","DOI":"10.1137\/1.9781611978339.4"},{"key":"e_1_3_2_2_96_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"key":"e_1_3_2_2_97_1","doi-asserted-by":"publisher","unstructured":"Yihua Wei and Peng Jiang. 2022. STMatch: Accelerating Graph Pattern Matching on GPU with Stack-Based Loop Optimizations. In SC \u201922. 1\u201313. https:\/\/doi.org\/10.1109\/SC41404.2022.00058 10.1109\/SC41404.2022.00058","DOI":"10.1109\/SC41404.2022.00058"},{"key":"e_1_3_2_2_98_1","doi-asserted-by":"publisher","unstructured":"Hao Wen and Wei Zhang. 2019. Improving Parallelism of Breadth First Search (BFS) Algorithm for Accelerated Performance on GPUs. In HPEC \u201919. 1\u20137. https:\/\/doi.org\/10.1109\/HPEC.2019.8916551 10.1109\/HPEC.2019.8916551","DOI":"10.1109\/HPEC.2019.8916551"},{"key":"e_1_3_2_2_99_1","doi-asserted-by":"publisher","DOI":"10.14778\/3364324.3364329"},{"key":"e_1_3_2_2_100_1","doi-asserted-by":"publisher","DOI":"10.1145\/3567955.3567963"},{"key":"e_1_3_2_2_101_1","doi-asserted-by":"publisher","unstructured":"Lyuheng Yuan Da Yan Jiao Han Akhlaque Ahmad Yang Zhou and Zhe Jiang. 2024. Faster Depth-First Subgraph Matching on GPUs. In ICDE \u201924\u2019. 3151\u20133163. https:\/\/doi.org\/10.1109\/ICDE60146.2024.00244 10.1109\/ICDE60146.2024.00244","DOI":"10.1109\/ICDE60146.2024.00244"},{"key":"e_1_3_2_2_102_1","doi-asserted-by":"publisher","unstructured":"Yunming Zhang Vladimir Kiriansky Charith Mendis Saman Amarasinghe and Matei Zaharia. 2017. Making caches work for graph analytics. In Big Data \u201917. 293\u2013302. https:\/\/doi.org\/10.1109\/BigData.2017.8257937 10.1109\/BigData.2017.8257937","DOI":"10.1109\/BigData.2017.8257937"},{"key":"e_1_3_2_2_103_1","doi-asserted-by":"publisher","unstructured":"Ruohuang Zheng and Sreepathi Pai. 2021. Efficient Execution of Graph Algorithms on CPU with SIMD Extensions. In CGO \u201921. 262\u2013276. https:\/\/doi.org\/10.1109\/CGO51591.2021.9370326 10.1109\/CGO51591.2021.9370326","DOI":"10.1109\/CGO51591.2021.9370326"},{"key":"e_1_3_2_2_104_1","volume-title":"Gemini: A Computation-Centric Distributed Graph Processing System. In OSDI \u201916. 301\u2013316.","author":"Zhu Xiaowei","year":"2016","unstructured":"Xiaowei Zhu, Wenguang Chen, Weimin Zheng, and Xiaosong Ma. 2016. Gemini: A Computation-Centric Distributed Graph Processing System. In OSDI \u201916. 301\u2013316."},{"key":"e_1_3_2_2_105_1","unstructured":"Marinka Zitnik Rok Sosi\u010d Sagar Maheshwari and Jure Leskovec. 2018. BioSNAP Datasets: Stanford Biomedical Network Dataset Collection. http:\/\/snap.stanford.edu\/biodata"}],"event":{"name":"PPoPP '26: 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Sydney NSW Australia","acronym":"PPoPP '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774934.3786457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:28:55Z","timestamp":1769614135000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774934.3786457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":105,"alternative-id":["10.1145\/3774934.3786457","10.1145\/3774934"],"URL":"https:\/\/doi.org\/10.1145\/3774934.3786457","relation":{},"subject":[],"published":{"date-parts":[[2026,1,28]]},"assertion":[{"value":"2026-01-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}