{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:39:05Z","timestamp":1743071945400,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319219080"},{"type":"electronic","value":"9783319219097"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-21909-7_3","type":"book-chapter","created":{"date-parts":[[2015,7,24]],"date-time":"2015-07-24T06:16:04Z","timestamp":1437718564000},"page":"21-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Hierarchical Optimization of MPI Reduce Algorithms"],"prefix":"10.1007","author":[{"given":"Khalid","family":"Hasanov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Lastovetsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,7,25]]},"reference":[{"key":"3_CR1","unstructured":"Message passing interface forum. http:\/\/www.mpi-forum.org\/"},{"issue":"MPIDC99","key":"3_CR2","first-page":"77","volume":"1999","author":"R Rabenseifner","year":"1999","unstructured":"Rabenseifner, R.: Automatic MPI counter proling of all users: first results on a CRAY T3E 900\u2013512. Proceedings of the Message Passing Interface Developers and Users Conference 1999(MPIDC99), 77\u201385 (1999)","journal-title":"Proceedings of the Message Passing Interface Developers and Users Conference"},{"key":"3_CR3","doi-asserted-by":"publisher","unstructured":"Hasanov, K., Quintin, J.N., Lastovetsky, A.: Hierarchical approach to optimization of parallel matrix multiplication on large-scale platforms. J. Supercomputing., 24p. March 2014 (Springer). doi:10.1007\/s11227-014-1133-x","DOI":"10.1007\/s11227-014-1133-x"},{"issue":"4","key":"3_CR4","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2","volume":"9","author":"RA van de Geijn","year":"1997","unstructured":"van de Geijn, R.A., Watts, J.: SUMMA: scalable universal matrix multiplication algorithm. Concurrency: Practice and Experience 9(4), 255\u2013274 (1997)","journal-title":"Concurrency: Practice and Experience"},{"key":"3_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1007\/978-3-319-14313-2_35","volume-title":"Euro-Par 2014: Parallel Processing Workshops","author":"K Hasanov","year":"2014","unstructured":"Hasanov, K., Quintin, J.-N., Lastovetsky, A.: High-level topology-oblivious optimization of mpi broadcast algorithms on extreme-scale platforms. In: Lopes, L., \u017dilinskas, J., Costan, A., Cascella, R.G., Kecskemeti, G., Jeannot, E., Cannataro, M., Ricci, L., Benkner, S., Petit, S., Scarano, V., Gracia, J., Hunold, S., Scott, S.L., Lankes, S., Lengauer, C., Carretero, J., Breitbart, J., Alexander, M. (eds.) Euro-Par 2014, Part II. LNCS, vol. 8806, pp. 412\u2013424. Springer, Heidelberg (2014)"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Hasanov, K., Quintin, J.N., Lastovetsky, A.: Topology-oblivious optimization of MPI broadcast algorithms on extreme-scale platforms. Simulation Modelling Practice and Theory. 10p. April 2015. doi:10.1016\/j.simpat.2015.03.005","DOI":"10.1016\/j.simpat.2015.03.005"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Gabriel, E., Fagg, G., Bosilca, G., Angskun, T., Dongarra, J., et al.: Open MPI: goals, concept, and design of a next generation MPI implementation. In: Proceedings of the 11th European PVM\/MPI Users Group Meeting (2004)","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"3_CR8","unstructured":"Grid\u20195000. http:\/\/www.grid5000.fr"},{"issue":"2","key":"3_CR9","first-page":"154","volume":"6","author":"V Bala","year":"1995","unstructured":"Bala, V., Bruck, J., Cypher, R., Elustondo, P., Ho, C.-T., Ho, C.-T., Kipnis, S., Snir, M.: CCL: a portable and tunable collective communication library for scalable parallel computers. IEEE TPDS 6(2), 154\u2013164 (1995)","journal-title":"IEEE TPDS"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Kielmann, T., Hofman, R.F.H., Bal, H.E., Plaat, A., Bhoedjang, R.A.F.: MagPIe MPIs collective communication operations for clustered wide area systems. In: Proceedings of PPoPP99, 34(8): 131\u2013140 (1999)","DOI":"10.1145\/329366.301116"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Vadhiyar, S.S., Fagg, G.E., Dongarra, J.: Automatically tuned collective communications. In: Proceedings of ACM\/IEEE Conference on Supercomputing (2000)","DOI":"10.1109\/SC.2000.10024"},{"key":"3_CR12","unstructured":"Chan, E.W., Heimlich, M.F., Purkayastha, A., Van de Geijn, R.A.: On optimizing collective communication. In: Proceedings of IEEE International Conference on Cluster Computing (2004)"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Rabenseifner, R.: Optimization of collective reduction operations. In: Proceddings of International Conference on Computational Science, June 2004","DOI":"10.1007\/978-3-540-24685-5_1"},{"issue":"12","key":"3_CR14","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1016\/j.parco.2009.09.001","volume":"35","author":"P Sanders","year":"2009","unstructured":"Sanders, P., Speck, J., Tr\u00e1ff, J.L.: Two-tree algorithms for full bandwidth broadcast. Reduct. Scan. Parallel Comput. 35(12), 581\u2013594 (2009)","journal-title":"Reduct. Scan. Parallel Comput."},{"key":"3_CR15","unstructured":"MPICH-A Portable Implementation of MPI. http:\/\/www.mpich.org\/"},{"key":"3_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/978-3-540-39924-7_38","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"R Thakur","year":"2003","unstructured":"Thakur, R., Gropp, W.D.: Improving the performance of collective operations in MPICH. In: Dongarra, J., Laforenza, D., Orlando, S. (eds.) EuroPVM\/MPI 2003. LNCS, vol. 2840, pp. 257\u2013267. Springer, Heidelberg (2003)"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Venkata, M.G., Shamis, P., Sampath, R., Graham, R.L.l, Ladd, J.S.: Optimizing blocking and nonblocking reduction operations for multicore systems: hierarchical design and implementation. In: Proceedings of IEEE Cluster, pp. 1\u20138 (2013)","DOI":"10.1109\/CLUSTER.2013.6702676"},{"issue":"3","key":"3_CR18","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/S0167-8191(06)80021-9","volume":"20","author":"RW Hockney","year":"1994","unstructured":"Hockney, R.W.: The communication challenge for MPP: intel paragon and Meiko CS-2. Parallel Comput. 20(3), 389\u2013398 (1994)","journal-title":"Parallel Comput."},{"key":"3_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-540-87475-1_32","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"A Lastovetsky","year":"2008","unstructured":"Lastovetsky, A., Rychkov, V., O\u2019Flynn, M.: MPIBlib: benchmarking MPI communications for parallel computing on homogeneous and heterogeneous clusters. In: Lastovetsky, A., Kechadi, T., Dongarra, J. (eds.) EuroPVM\/MPI 2008. LNCS, vol. 5205, pp. 227\u2013238. Springer, Heidelberg (2008)"},{"key":"3_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-15646-5_1","volume-title":"Recent Advances in the Message Passing Interface","author":"P Sack","year":"2010","unstructured":"Sack, P., Gropp, W.: A scalable MPI\\_comm\\_split algorithm for exascale computing. In: Keller, R., Gabriel, E., Resch, M., Dongarra, J. (eds.) EuroMPI 2010. LNCS, vol. 6305, pp. 1\u201310. Springer, Heidelberg (2010)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Moody, A., Ahn, D.H., de Supinski, B.R.: Exascale algorithms for generalized MPI\\_comm\\_split. In: Proceedings of the 18th European MPI Users\u2019 Group conference on Recent advances in the message passing interface (EuroMPI 2011) (2011)","DOI":"10.1007\/978-3-642-24449-0_4"}],"container-title":["Lecture Notes in Computer Science","Parallel Computing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-21909-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T17:35:47Z","timestamp":1675272947000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-21909-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319219080","9783319219097"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-21909-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"25 July 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}