{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T23:29:23Z","timestamp":1777937363251,"version":"3.51.4"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319738130","type":"print"},{"value":"9783319738147","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-73814-7_6","type":"book-chapter","created":{"date-parts":[[2018,1,9]],"date-time":"2018-01-09T09:59:13Z","timestamp":1515491953000},"page":"82-96","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Breadth First Search on Multi-GPU Systems Using GPU-Centric OpenSHMEM"],"prefix":"10.1007","author":[{"given":"Sreeram","family":"Potluri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anshuman","family":"Goswami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manjunath Gorentla","family":"Venkata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neena","family":"Imam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,1,10]]},"reference":[{"key":"6_CR1","unstructured":"http:\/\/graph500.org: Graph 500 benchmark specification 1.2 (2017). http:\/\/www.graph500.org\/"},{"key":"6_CR2","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1145\/2370036.2145832","volume":"47","author":"D Merrill","year":"2012","unstructured":"Merrill, D., Garland, M., Grimshaw, A.: Scalable GPU graph traversal. SIGPLAN Not. 47, 117\u2013128 (2012)","journal-title":"SIGPLAN Not."},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Bisson, M., Bernaschi, M., Mastrostefano, E.: Parallel distributed breadth first search on the Kepler architecture. CoRR abs\/1408.1605 (2014)","DOI":"10.1145\/2742854.2742887"},{"key":"6_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-319-26428-8_2","volume-title":"OpenSHMEM and Related Technologies. Experiences, Implementations, and Technologies","author":"S Potluri","year":"2015","unstructured":"Potluri, S., Rossetti, D., Becker, D., Poole, D., Gorentla Venkata, M., Hernandez, O., Shamis, P., Lopez, M.G., Baker, M., Poole, W.: Exploring openSHMEM model to program GPU-based extreme-scale systems. In: Gorentla Venkata, M., Shamis, P., Imam, N., Lopez, M.G. (eds.) OpenSHMEM 2014. LNCS, vol. 9397, pp. 18\u201335. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-26428-8_2"},{"key":"6_CR5","unstructured":"NVIDIA: GPUDirect (2015). https:\/\/developer.nvidia.com\/gpudirect"},{"key":"6_CR6","unstructured":"NVIDIA: GPUDirect RDMA (2015). http:\/\/docs.nvidia.com\/cuda\/gpudirect-rdma"},{"key":"6_CR7","unstructured":"Rossetti, D.: GPUDirect: integrating the GPU with a network interface. In: GPU Technology Conference (2015)"},{"key":"6_CR8","first-page":"257","volume":"26","author":"H Wang","year":"2011","unstructured":"Wang, H., Potluri, S., Luo, M., Singh, A.K., Sur, S., Panda, D.K.: MVAPICH2-GPU: optimized GPU to GPU communication for infiniband clusters. Comput. Sci. 26, 257\u2013266 (2011)","journal-title":"Comput. Sci."},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Potluri, S., Hamidouche, K., Venkatesh, A., Bureddy, D., Panda, D.K.: Efficient inter-node MPI communication using GPUDirect RDMA for infiniband clusters with NVIDIA GPUs. In: Proceedings of the 2013 42nd International Conference on Parallel Processing, ICPP 2013, Washington, DC, USA, pp. 80\u201389. IEEE Computer Society (2013)","DOI":"10.1109\/ICPP.2013.17"},{"key":"6_CR10","unstructured":"MVAPICH: MPI over infiniband, 10GigE\/iWARP and RoCE (2015). http:\/\/mvapich.cse.ohio-state.edu"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Aji, A.M., Dinan, J., Buntinas, D., Balaji, P., Feng, W.C., Bisset, K.R., Thakur, R.: MPI-ACC: an integrated and extensible approach to data movement in accelerator-based systems. In: 14th IEEE International Conference on High Performance Computing and Communications, Liverpool, UK (2012)","DOI":"10.1109\/HPCC.2012.92"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Potluri, S., Bureddy, D., Wang, H., Subramoni, H., Panda, D.K.: Extending openSHMEM for GPU computing. In: Proceedings of the 2013 IEEE 27th International Symposium on Parallel and Distributed Processing, IPDPS 2013, Washington, DC, USA, pp. 1001\u20131012. IEEE Computer Society (2013)","DOI":"10.1109\/IPDPS.2013.104"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Cunningham, D., Bordawekar, R., Saraswat, V.: GPU programming in a high level language: compiling X10 to CUDA. In: Proceedings of the 2011 ACM SIGPLAN X10 Workshop, X10 2011, pp. 8:1\u20138:10. ACM, New York (2011)","DOI":"10.1145\/2212736.2212744"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Miyoshi, T., Irie, H., Shima, K., Honda, H., Kondo, M., Yoshinaga, T.: Flat: a GPU programming framework to provide embedded MPI. In: Proceedings of the 5th Annual Workshop on General Purpose Processing with Graphics Processing Units, GPGPU-5, pp. 20\u201329. ACM, New York (2012)","DOI":"10.1145\/2159430.2159433"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Ueno, K., Suzumura, T.: Parallel distributed breadth first search on GPU. In: 20th Annual International Conference on High Performance Computing, HiPC 2013, Bengaluru (Bangalore), Karnataka, India, 18\u201321 December 2013, pp. 314\u2013323 (2013)","DOI":"10.1109\/HiPC.2013.6799136"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Matsuoka, S.: Making TSUBAME2.0, the world\u2019s greenest production supercomputer, even greener: challenges to the architects. In: Proceedings of the 2011 International Symposium on Low Power Electronics and Design, Fukuoka, Japan, 1\u20133 August 2011, pp. 367\u2013368 (2011)","DOI":"10.1109\/ISLPED.2011.5993666"},{"key":"6_CR17","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.1109\/TPDS.2015.2475270","volume":"27","author":"M Bisson","year":"2016","unstructured":"Bisson, M., Bernaschi, M., Mastrostefano, E.: Parallel distributed breadth first search on the Kepler architecture. IEEE Trans. Parallel Distrib. Syst. 27, 2091\u20132102 (2016)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"6_CR18","unstructured":"Pan, Y., Wang, Y., Wu, Y., Yang, C., Owens, J.D.: Multi-GPU graph analytics. CoRR abs\/1504.04804 (2015)"}],"container-title":["Lecture Notes in Computer Science","OpenSHMEM and Related Technologies. Big Compute and Big Data Convergence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-73814-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T01:06:37Z","timestamp":1660266397000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-73814-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319738130","9783319738147"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-73814-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}