{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T18:05:18Z","timestamp":1754157918799,"version":"3.41.2"},"reference-count":22,"publisher":"Emerald","issue":"4","license":[{"start":{"date-parts":[[2008,11,21]],"date-time":"2008-11-21T00:00:00Z","timestamp":1227225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,11,21]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-heading\">Purpose<\/jats:title><jats:p>The purpose of this paper is to explain one of the most important collective communication patterns used in scientific applications which is the complete exchange, also called All\u2010to\u2010All. Although efficient algorithms have been studied for specific networks, general solutions like those available in well\u2010known MPI distributions (e.g. the MPI_Alltoall operation) are strongly influenced by the congestion of network resources.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-heading\">Design\/methodology\/approach<\/jats:title><jats:p>In this paper we present an integrated approach to model the performance of the All\u2010to\u2010All collective operation, which consists in identifying a contention signature that characterizes a given network environment, using it to augment a contention\u2010free communication model.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-heading\">Findings<\/jats:title><jats:p>This approach, assessed by experimental results, allows an accurate prediction of the performance of the All\u2010to\u2010All operation over different network architectures with a small overhead.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-heading\">Practical implications<\/jats:title><jats:p>The paper discusses the problem of network contention in a grid environment, studying some strategies to minimize the impact of contention on the performance of an All\u2010to\u2010All operation.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-heading\">Originality\/value<\/jats:title><jats:p>The approach used, assessed by experimental results, allows an accurate prediction of the performance of the All\u2010to\u2010All operation over different network architectures with a small overhead. Also discussed is the problem of network contention in a grid environment and some strategies to minimize the impact of contention on the performance of an All\u2010to\u2010All operation.<\/jats:p><\/jats:sec>","DOI":"10.1108\/17427370810932187","type":"journal-article","created":{"date-parts":[[2009,1,17]],"date-time":"2009-01-17T07:25:31Z","timestamp":1232177131000},"page":"440-459","source":"Crossref","is-referenced-by-count":0,"title":["Assessing contention effects of all\u2010to\u2010all communications on clusters and grids"],"prefix":"10.1108","volume":"4","author":[{"given":"Luiz","family":"Angelo Steffenel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maxime","family":"Martinasso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denis","family":"Trystram","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","reference":[{"unstructured":"Adve, V. (1993), \u201cAnalysing the behavior and performance of parallel programs\u201d, PhD thesis, Computer Sciences Department, University of Wisconsin.","key":"key2022012920331867500_b1"},{"doi-asserted-by":"crossref","unstructured":"Bruck, J., Ho, C.\u2010T., Kipnis, S., Upfal, E. and Weathersby, D. (1997), \u201cEfficient algorithms for all\u2010to\u2010all communications in multiport message\u2010passing systems\u201d, IEEE Transactions on Parallel and Distributed Systems, Vol. 8 No. 11, pp. 1143\u201056.","key":"key2022012920331867500_b2","DOI":"10.1109\/71.642949"},{"doi-asserted-by":"crossref","unstructured":"Casanova, H. (2005), \u201cNetwork modeling issues for grid application scheduling\u201d, International Journal of Foundations of Computer Science, Vol. 16 No. 2, pp. 144\u201062.","key":"key2022012920331867500_b3","DOI":"10.1142\/S0129054105002929"},{"doi-asserted-by":"crossref","unstructured":"Christara, C., Ding, X. and Jackson, K. (1999), \u201cAn efficient transposition algorithm for distributed memory computers\u201d, Proceedings of the High Performance Computing Systems and Applications, pp. 349\u201068.","key":"key2022012920331867500_b4","DOI":"10.1007\/0-306-47015-2_38"},{"unstructured":"Chun, A.T.T. (2001), \u201cPerformance studies of high\u2010speed communication on commodity cluster\u201d, PhD thesis, University of Hong Kong.","key":"key2022012920331867500_b5"},{"unstructured":"Chun, A.T.T. and Wang, C.\u2010L. (1999), \u201cRealistic communication model for parallel computing on cluster\u201d, Proceedings of the International Workshop on Cluster Computing, pp. 92\u2010101.","key":"key2022012920331867500_b6"},{"doi-asserted-by":"crossref","unstructured":"Clement, M., Steed, M. and Crandall, P. (1996), \u201cNetwork performance modelling for PM clusters\u201d, Proceedings of Supercomputing.","key":"key2022012920331867500_b7","DOI":"10.1145\/369028.369040"},{"unstructured":"de Supinski, B.R. and Karonis, N.T. (1999), \u201cAccurately measuring MPI broadcasts in a computational grid\u201d, Proceedings of the IEEE International Symposium on High Performance Distributed Computing (HPDC'99), August 1999.","key":"key2022012920331867500_b8"},{"unstructured":"Gabriel, E., Resch, M., Beisel, T. and Keller, R. (1998), \u201cDistributed computing in a heterogenous computing environment\u201d, EuroPVMMPI'98, number 1497 in LNCS, Liverpool, September 1998, Springer\u2010Verlag, New York, NY.","key":"key2022012920331867500_b9"},{"unstructured":"Grove, D. (2003), \u201cPerformance modelling of message\u2010passing parallel programs\u201d, PhD thesis, University of Adelaide.","key":"key2022012920331867500_b10"},{"doi-asserted-by":"crossref","unstructured":"Hockney, R.W. (1994), \u201cThe communication challenge for MPP: Intelparagon and meiko cs\u20102\u201d, Parallel Computing, Vol. 20, pp. 389\u201098.","key":"key2022012920331867500_b11","DOI":"10.1016\/S0167-8191(06)80021-9"},{"doi-asserted-by":"crossref","unstructured":"Jeannot, E. and Steffenel, L.A. (2007), \u201cFast and efficient total exchange on two clusters\u201d, Proceedings of the 13th International Conference on Parallel Computing (EURO\u2010PAR2007), LNCS 4641, pages 848\u2010857.","key":"key2022012920331867500_b12","DOI":"10.1007\/978-3-540-74466-5_91"},{"unstructured":"Jeannot, E. and Wagner, F. (2004), \u201cTwo fast and efficient message scheduling algorithms for data redistribution through a backbone\u201d, Proceedings of the IPDPS, IPDPS.","key":"key2022012920331867500_b13"},{"doi-asserted-by":"crossref","unstructured":"Johnssonn, S.L. and Ho, C.\u2010T. (1989), \u201cOptimum broad\u2010casting and personalized communication in hypercubes\u201d, IEEE Transactions on Computers, Vol. 38 No. 9, pp. 1249\u201068.","key":"key2022012920331867500_b14","DOI":"10.1109\/12.29465"},{"doi-asserted-by":"crossref","unstructured":"Kielmann, T., Bal, H. and Verstoep, K. (2000), \u201cFast measurement of LogP parameters for message passing platforms\u201d, Proceedings of the 4th Workshop on Runtime Systems for Parallel Programming, LNCS, Vol. 1800, pp. 1176\u201083.","key":"key2022012920331867500_b15","DOI":"10.1007\/3-540-45591-4_162"},{"doi-asserted-by":"crossref","unstructured":"Kielmann, T., Bal, H., Gorlatch, S., Verstoep, K. and Hofman, R. (2001), \u201cNetwork performance\u2010aware collective communication for clustered wide area systems\u201d, Parallel Computing, Vol. 27 No. 11, pp. 1431\u201056.","key":"key2022012920331867500_b16","DOI":"10.1016\/S0167-8191(01)00098-9"},{"doi-asserted-by":"crossref","unstructured":"K\u00f6nig, J.\u2010C., Rao, P.S. and Trystram, D. (1998), \u201cAnalysis of gossiping algorithms with restricted buffers\u201d, Parallel Algorithms and Applications, Vol. 13 No. 2, pp. 117\u201033.","key":"key2022012920331867500_b17","DOI":"10.1080\/01495739808947363"},{"doi-asserted-by":"crossref","unstructured":"Labarta, J., Girona, S., Pillet, V., Cortes, T. and Gregoris, L. (1996), \u201cDiP: a parallel program development environment\u201d, Proceedings of the 2nd Euro\u2010Par Conference, Vol. 2, pp. 665\u201074.","key":"key2022012920331867500_b18","DOI":"10.1007\/BFb0024763"},{"unstructured":"Midorikawa, E.T., Oliveira, H.M. and Laine, J.M. (2004), \u201cPEMPIs: a new methodology for modeling and prediction of MPI programs performance\u201d, Proceedings of the SBAC\u2010PAD 2004, IEEE Computer Society\/Brazilian Computer Society, pp. 254\u201061.","key":"key2022012920331867500_b19"},{"doi-asserted-by":"crossref","unstructured":"Moritz, C.A. and Frank, M.I. (2001), \u201cLoGPC: Modeling network contention in message\u2010passing programs\u201d, IEEE Trans\u2010actions on Parallel and Distributed Systems, Vol. 12 No. 4, pp. 404\u201015.","key":"key2022012920331867500_b20","DOI":"10.1109\/71.920589"},{"unstructured":"Pjesivac\u2010Grbovic, J., Angskun, T., Bosilca, G., Fagg, G.E., Gabriel, E. and Dongarra, J.J. (2005), \u201cPerformance analysis of MPI collective operations\u201d, Proceedings of the Workshop on Performance Modeling, Evaluation and Optimisation for Parallel and Distributed Systems (PMEO), in IPDPS (2005).","key":"key2022012920331867500_b21"},{"doi-asserted-by":"crossref","unstructured":"Steffenel, L.A. (2006), \u201cModeling network contention effects on alltoall operations\u201d, Proceedings of the IEEE Conference on Cluster Computing (CLUSTER 2006), Barcelona, Spain, September 2006, IEEE Computer Society, Washington DC.","key":"key2022012920331867500_b22","DOI":"10.1109\/CLUSTR.2006.311889"}],"container-title":["International Journal of Pervasive Computing and Communications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.emeraldinsight.com\/doi\/full-xml\/10.1108\/17427370810932187","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/17427370810932187\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/17427370810932187\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T00:24:12Z","timestamp":1753403052000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ijpcc\/article\/4\/4\/440-459\/162733"}},"subtitle":[],"editor":[{"given":"Jean\u2010Marc","family":"Pierson","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2008,11,21]]},"references-count":22,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2008,11,21]]}},"alternative-id":["10.1108\/17427370810932187"],"URL":"https:\/\/doi.org\/10.1108\/17427370810932187","relation":{},"ISSN":["1742-7371"],"issn-type":[{"type":"print","value":"1742-7371"}],"subject":[],"published":{"date-parts":[[2008,11,21]]}}}