{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T09:57:06Z","timestamp":1753437426756,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030787127"},{"type":"electronic","value":"9783030787134"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-78713-4_16","type":"book-chapter","created":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T23:06:15Z","timestamp":1623884775000},"page":"291-309","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["iPUG: Accelerating Breadth-First Graph\u00a0Traversals Using Manycore Graphcore\u00a0IPUs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8019-7047","authenticated-orcid":false,"given":"Luk","family":"Burchard","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7664-9517","authenticated-orcid":false,"given":"Johannes","family":"Moe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0125-5243","authenticated-orcid":false,"given":"Daniel Thilo","family":"Schroeder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7993-1769","authenticated-orcid":false,"given":"Konstantin","family":"Pogorelov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4200-511X","authenticated-orcid":false,"given":"Johannes","family":"Langguth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,17]]},"reference":[{"key":"16_CR1","unstructured":"Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2016), pp. 265\u2013283 (2016)"},{"key":"16_CR2","unstructured":"Abu-Khzam, F.N., Collins, R.L., Fellows, M.R., Langston, M.A., Suters, W.H., Symons, C.T.: Kernelization algorithms for the vertex cover problem (2017)"},{"key":"16_CR3","volume-title":"Compilers, Principles, Techniques, and Tools","author":"AV Aho","year":"1986","unstructured":"Aho, A.V., Sethi, R., Ullman, J.D.: Compilers, Principles, Techniques, and Tools. Addison-Wesley Pub. Co., Boston (1986)"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Azad, A., Bulu\u00e7, A.: Distributed-memory algorithms for maximum cardinality matching in bipartite graphs. In: 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 32\u201342. IEEE (2016)","DOI":"10.1109\/IPDPS.2016.103"},{"key":"16_CR5","unstructured":"Bader, D.A., Madduri, K.: Designing multithreaded algorithms for breadth-first search and ST-connectivity on the cray MTA-2. In: 2006 International Conference on Parallel Processing (ICPP 2006), pp. 523\u2013530. IEEE (2006)"},{"key":"16_CR6","unstructured":"Beamer, S., Asanovi\u0107, K., Patterson, D.: The gap benchmark suite. arXiv preprint arXiv:1508.03619 (2015)"},{"key":"16_CR7","unstructured":"Beamer, S., Asanovic, K., Patterson, D., Beamer, S., Patterson, D.: Searching for a parent instead of fighting over children: a fast breadth-first search implementation for graph500. EECS Department, University of California, Berkeley, Technical report UCB\/EECS-2011-117 (2011)"},{"key":"16_CR8","unstructured":"Bulu\u00e7, A., Beamer, S., Madduri, K., Asanovic, K., Patterson, D.: Distributed-memory breadth-first search on massive graphs. arXiv preprint arXiv:1705.04590 (2017)"},{"issue":"4","key":"16_CR9","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1177\/1094342011403516","volume":"25","author":"A Bulu\u00e7","year":"2011","unstructured":"Bulu\u00e7, A., Gilbert, J.R.: The combinatorial BLAS: design, implementation, and applications. Int. J. High Perf. Comput. Appl. 25(4), 496\u2013509 (2011)","journal-title":"Int. J. High Perf. Comput. Appl."},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Bulu\u00e7, A., Madduri, K.: Parallel breadth-first search on distributed memory systems. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312 (2011)","DOI":"10.1145\/2063384.2063471"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Chakrabarti, D., Zhan, Y., Faloutsos, C.: R-MAT: a recursive model for graph mining. In: Proceedings of the 2004 SIAM International Conference on Data Mining, pp. 442\u2013446. SIAM (2004)","DOI":"10.1137\/1.9781611972740.43"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Checconi, F., Petrini, F.: Traversing trillions of edges in real time: graph exploration on large-scale parallel machines. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp. 425\u2013434. IEEE (2014)","DOI":"10.1109\/IPDPS.2014.52"},{"issue":"6","key":"16_CR13","first-page":"1152","volume":"57","author":"Z Chenglong","year":"2020","unstructured":"Chenglong, Z., Huawei, C., Guobo, W., Qinfen, H., Yang, Z., Xiaochun, Y., Dongrui, F.: Efficient optimization of graph computing on high-throughput computer. J. Comput. Res. Dev. 57(6), 1152 (2020)","journal-title":"J. Comput. Res. Dev."},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Gaihre, A., Wu, Z., Yao, F., Liu, H.: XBFS: exploring runtime optimizations for breadth-first search on GPUs. In: Proceedings of the 28th International Symposium on High-Performance Parallel and Distributed Computing, pp. 121\u2013131 (2019)","DOI":"10.1145\/3307681.3326606"},{"issue":"1\u20134","key":"16_CR15","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1080\/00207168408803413","volume":"15","author":"RK Ghosh","year":"1984","unstructured":"Ghosh, R.K., Bhattacharjee, G.: Parallel breadth-first search algorithms for trees and graphs. Int. J. Comput. Math. 15(1\u20134), 255\u2013268 (1984)","journal-title":"Int. J. Comput. Math."},{"issue":"10","key":"16_CR16","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1145\/1103845.1094844","volume":"40","author":"D Gregor","year":"2005","unstructured":"Gregor, D., Lumsdaine, A.: Lifting sequential graph algorithms for distributed-memory parallel computation. ACM SIGPLAN Not. 40(10), 423\u2013437 (2005)","journal-title":"ACM SIGPLAN Not."},{"key":"16_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/978-3-540-77220-0_21","volume-title":"High Performance Computing \u2013 HiPC 2007","author":"P Harish","year":"2007","unstructured":"Harish, P., Narayanan, P.J.: Accelerating large graph algorithms on the GPU using CUDA. In: Aluru, S., Parashar, M., Badrinath, R., Prasanna, V.K. (eds.) HiPC 2007. LNCS, vol. 4873, pp. 197\u2013208. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-77220-0_21"},{"issue":"2","key":"16_CR18","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1145\/3282307","volume":"62","author":"JL Hennessy","year":"2019","unstructured":"Hennessy, J.L., Patterson, D.A.: A new golden age for computer architecture. Commun. ACM 62(2), 48\u201360 (2019)","journal-title":"Commun. ACM"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Hong, S., Oguntebi, T., Olukotun, K.: Efficient parallel graph exploration on multi-core CPU and GPU. In: 2011 International Conference on Parallel Architectures and Compilation Techniques, pp. 78\u201388. IEEE (2011)","DOI":"10.1109\/PACT.2011.14"},{"key":"16_CR20","unstructured":"Jia, Z., Tillman, B., Maggioni, M., Scarpazza, D.P.: Dissecting the graphcore ipu architecture via microbenchmarking. arXiv preprint arXiv:1912.03413 (2019)"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Kaya, K., Langguth, J., Panagiotas, I., U\u00e7ar, B.: Karp-Sipser based kernels for bipartite graph matching. In: 2020 Proceedings of the Twenty-Second Workshop on Algorithm Engineering and Experiments (ALENEX), pp. 134\u2013145. SIAM (2020)","DOI":"10.1137\/1.9781611976007.11"},{"issue":"35","key":"16_CR22","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.21105\/joss.01244","volume":"4","author":"SP Kolodziej","year":"2019","unstructured":"Kolodziej, S.P., et al.: The suitesparse matrix collection website interface. J. Open Source Softw. 4(35), 1244 (2019)","journal-title":"J. Open Source Softw."},{"key":"16_CR23","unstructured":"Korf, R.E., Schultze, P.: Large-scale parallel breadth-first search. In: AAAI, vol. 5, pp. 1380\u20131385 (2005)"},{"issue":"7","key":"16_CR24","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.parco.2014.03.004","volume":"40","author":"J Langguth","year":"2014","unstructured":"Langguth, J., Azad, A., Halappanavar, M., Manne, F.: On parallel push-relabel based algorithms for bipartite maximum matching. Parallel Comput. 40(7), 289\u2013308 (2014)","journal-title":"Parallel Comput."},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Langguth, J., Cai, X., Sourouri, M.: Memory bandwidth contention: communication vs computation tradeoffs in supercomputers with multicore architectures. In: 2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS), pp. 497\u2013506. IEEE (2018)","DOI":"10.1109\/PADSW.2018.8644601"},{"issue":"12","key":"16_CR26","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1016\/j.parco.2011.09.004","volume":"37","author":"J Langguth","year":"2011","unstructured":"Langguth, J., Patwary, M.M.A., Manne, F.: Parallel algorithms for bipartite matching problems on distributed memory computers. Parallel Comput. 37(12), 820\u2013845 (2011)","journal-title":"Parallel Comput."},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Liu, H., Huang, H.H.: Enterprise: breadth-first graph traversal on GPUs. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312 (2015)","DOI":"10.1145\/2807591.2807594"},{"key":"16_CR28","first-page":"45","volume":"19","author":"RC Murphy","year":"2010","unstructured":"Murphy, R.C., Wheeler, K.B., Barrett, B.W., Ang, J.A.: Introducing the graph 500. Cray Users Group (CUG) 19, 45\u201374 (2010)","journal-title":"Cray Users Group (CUG)"},{"issue":"2","key":"16_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2450142.2450149","volume":"60","author":"C Seshadhri","year":"2013","unstructured":"Seshadhri, C., Pinar, A., Kolda, T.G.: An in-depth analysis of stochastic Kronecker graphs. J. ACM (JACM) 60(2), 1\u201332 (2013)","journal-title":"J. ACM (JACM)"},{"issue":"8","key":"16_CR30","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/79173.79181","volume":"33","author":"LG Valiant","year":"1990","unstructured":"Valiant, L.G.: A bridging model for parallel computation. Commun. ACM 33(8), 103\u2013111 (1990)","journal-title":"Commun. ACM"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Y., Davidson, A., Pan, Y., Wu, Y., Riffel, A., Owens, J.D.: Gunrock: a high-performance graph processing library on the GPU. In: Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 1\u201312 (2016)","DOI":"10.1145\/2851141.2851145"},{"key":"16_CR32","unstructured":"Yang, C., Buluc, A., Owens, J.D.: GraphBLAST: a high-performance linear algebra-based graph framework on the GPU (2020)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Yasui, Y., Fujisawa, K., Goto, K.: NUMA-optimized parallel breadth-first search on multicore single-node system. In: 2013 IEEE International Conference on Big Data, pp. 394\u2013402. IEEE (2013)","DOI":"10.1109\/BigData.2013.6691600"},{"key":"16_CR34","doi-asserted-by":"publisher","unstructured":"Yoo, A., Chow, E., Henderson, K., McLendon, W., Hendrickson, B., Catalyurek, U.: A scalable distributed parallel breadth-first search algorithm on BlueGene\/L. In: SC 2005: Proceedings of the 2005 ACM\/IEEE Conference on Supercomputing, p. 25. IEEE, November 2005. https:\/\/doi.org\/10.1109\/SC.2005.4","DOI":"10.1109\/SC.2005.4"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-78713-4_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T07:07:00Z","timestamp":1680073620000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-78713-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030787127","9783030787134"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-78713-4_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"17 June 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"74","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.28","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.13","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"In the ISC High Performance Workshop, there were 49 submissions, out of which 35  were accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}