{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T10:58:09Z","timestamp":1778583489831,"version":"3.51.4"},"reference-count":22,"publisher":"Elsevier BV","issue":"3","license":[{"start":{"date-parts":[[2003,8,1]],"date-time":"2003-08-01T00:00:00Z","timestamp":1059696000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Systems Architecture"],"published-print":{"date-parts":[[2003,8]]},"DOI":"10.1016\/s1383-7621(03)00059-6","type":"journal-article","created":{"date-parts":[[2003,7,16]],"date-time":"2003-07-16T16:18:16Z","timestamp":1058372296000},"page":"89-108","source":"Crossref","is-referenced-by-count":12,"title":["Efficient implementation of reduce-scatter in MPI"],"prefix":"10.1016","volume":"49","author":[{"given":"Massimo","family":"Bernaschi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giulio","family":"Iannello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mario","family":"Lauria","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S1383-7621(03)00059-6_BIB1","doi-asserted-by":"crossref","unstructured":"A. Alexandrov, M. Ionescu, K.E. Schauser, C. Scheiman, LogGP: incorporating long messages into the LogP model\u2013\u2013one step closer towards a realistic model of parallel computation, Proceedings of the 7th Annual ACM Symposium on Parallel Algorithms and Architectures, 17\u201319 July 1995, pp. 95\u2013105","DOI":"10.1145\/215399.215427"},{"issue":"2","key":"10.1016\/S1383-7621(03)00059-6_BIB2","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1109\/71.342126","article-title":"CCL: a portable and tunable collective communication library for scalable parallel computers","volume":"6","author":"Bala","year":"1995","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB3","series-title":"Proceedings of 7th International Parallel Processing Symposium, 13\u201316 April","first-page":"156","article-title":"Global combine on mesh architectures with wormhole","author":"Barnett","year":"1993"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB4","doi-asserted-by":"crossref","unstructured":"M. Barnett, S. Gupta, D.G. Payne, L. Shuler, R. van de Geijn, J. Watts, Building a high-performance collective communication library, Proceedings of Supercomputing \u201994, Washington, DC, 14\u201318 November 1994, pp. 107\u2013116","DOI":"10.1109\/SUPERC.1994.344270"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB5","doi-asserted-by":"crossref","unstructured":"A. Bar-Noy, S. Kipnis, Designing Broadcasting Algorithms in the Postal Model for Message-Passing Systems, Math. Systems Theory, vol. 27, no. 5, pp. 431\u2013452, 1994, also appeared in Proceedings of the 4th Annual ACM Symposium on Parallel Algorithms and Architectures, June 1992, pp. 11\u201322","DOI":"10.1007\/BF01184933"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB6","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/0166-218X(94)E0148-6","article-title":"Optimal computation of census functions in the postal model","volume":"58","author":"Bar-Noy","year":"1995","journal-title":"Discrete Applied Mathematics"},{"issue":"5","key":"10.1016\/S1383-7621(03)00059-6_BIB7","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1002\/(SICI)1096-9128(19980425)10:5<359::AID-CPE323>3.0.CO;2-7","article-title":"Collective communication operations: Experimental results vs. theory","volume":"10","author":"Bernaschi","year":"1998","journal-title":"Concurrency: Practice and Experience"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB8","doi-asserted-by":"crossref","unstructured":"J. Bruck, C.T. Ho, S. Knipis. D. Weathersby, Efficient Algorithms for All-to-All Communications in Multi-Port Message-Passing Systems, Proceedings of the 6th Annual ACM Symposium on Parallel Algorithms and Architectures, June 1994, pp. 298\u2013309","DOI":"10.1145\/181014.181756"},{"issue":"1","key":"10.1016\/S1383-7621(03)00059-6_BIB9","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1109\/40.342015","article-title":"Myrinet\u2013\u2013a gigabit-per-second local-area network","volume":"15","author":"Boden","year":"1995","journal-title":"IEEE Micro"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB10","doi-asserted-by":"crossref","unstructured":"S.H. Bokhari, H. Berryman, Complete exchange on a circuit switched mesh, Proceedings of Scalable high Performance Computing Conference, 1992, pp. 300\u2013306","DOI":"10.1109\/SHPCC.1992.232628"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB11","doi-asserted-by":"crossref","unstructured":"D.E. Culler, R.M. Karp, D.A. Patterson, A. Sahay, K.E. Schauser, E. Santos, R. Subramonian, T. von Eicken, LogP: towards a realistic model of parallel computation, Proceedings of the 4th SIGPLAN Symposium on Principles and Practices of Parallel Programming. ACM, May 1993, pp. 1\u201312","DOI":"10.1145\/155332.155333"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB12","series-title":"Concrete Mathematics: A Foundation for Computer Science","author":"Graham","year":"1988"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB13","unstructured":"W. Gropp, E. Lusk, N. Doss, A. Skjellum, A High Performance, Portable Implementation of the MPI Message Passing Interface Standard, Tech. Rep. Argonne National Laboratories, Available at: http:\/\/www.mcs.anl.gov\/mpi\/mpicharticle\/paper.html"},{"issue":"9","key":"10.1016\/S1383-7621(03)00059-6_BIB14","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1109\/71.615442","article-title":"Efficient algorithms for the reduce-scatter operation in LogGP","volume":"8","author":"Iannello","year":"1997","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB15","unstructured":"R. Blackmore, Algorithms Development Group, IBM Poughkeepsie, personal communication, February 1998"},{"issue":"1","key":"10.1016\/S1383-7621(03)00059-6_BIB16","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1006\/jpdc.1996.1264","article-title":"MPI-FM: High performance MPI on workstation clusters","volume":"40","author":"Lauria","year":"1997","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB17","unstructured":"Message Passing Interface Forum, Document for standard message-passing interface, Tech. Rep. CS-93-214, University of Tennessee, November 1993"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB18","doi-asserted-by":"crossref","unstructured":"H. Franke, C.E. Wu, M. Riviere, P. Pattnik, M. Snir, MPI Programming Environment for IBM SP1\/SP2, Proceedings of the International Symposium on Computer Architecture, 1995, pp. 127\u2013135","DOI":"10.1109\/ICDCS.1995.500011"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB19","doi-asserted-by":"crossref","unstructured":"R.M. Karp, A. Sahay, E.E. Santos, K.E. Schauser, Optimal Broadcast and Summation in the LogP Model, Proceedings of the 5th Annual ACM Symposium on Parallel Algorithms and Architectures, June 1993, pp. 142\u2013153","DOI":"10.1145\/165231.165250"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB20","unstructured":"IBM AIX PVMe User\u2019s Guide and Subroutine Reference, SH23-0019-01"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB21","unstructured":"S. Bae, D. Kim, S. Ranka. Vector Prefix and Reduction Computation on Coarse-Grained, Distributed-Memory Parallel Machines. In: Proc. of the First Merged International, Parallel Processing Symposium and Symposium on Parallel and Distributed Processing, IPPS\/SPDP 1998, Orlando, FL, April 1998, pp. 321\u2013325"},{"key":"10.1016\/S1383-7621(03)00059-6_BIB22","doi-asserted-by":"crossref","unstructured":"N.S. Sundar, D.N. Jayasimha, D.K. Panda, P. Sadayappan, Complete Exchange in 2D Meshes, Proceedings of Scalable High Performance Computing Conference, Knoxville, Tennessee, 23\u201325 May 1994, pp. 406\u2013413","DOI":"10.1109\/SHPCC.1994.296672"}],"container-title":["Journal of Systems Architecture"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762103000596?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762103000596?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T18:27:04Z","timestamp":1585074424000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1383762103000596"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,8]]},"references-count":22,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2003,8]]}},"alternative-id":["S1383762103000596"],"URL":"https:\/\/doi.org\/10.1016\/s1383-7621(03)00059-6","relation":{},"ISSN":["1383-7621"],"issn-type":[{"value":"1383-7621","type":"print"}],"subject":[],"published":{"date-parts":[[2003,8]]}}}