{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T04:18:27Z","timestamp":1748405907926,"version":"3.41.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319174723"},{"type":"electronic","value":"9783319174730"}],"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\/978-3-319-17473-0_18","type":"book-chapter","created":{"date-parts":[[2015,4,30]],"date-time":"2015-04-30T09:59:39Z","timestamp":1430387979000},"page":"268-283","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Static Approximation of MPI Communication Graphs for Optimized Process Placement"],"prefix":"10.1007","author":[{"given":"Andrew J.","family":"McPherson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vijay","family":"Nagarajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcelo","family":"Cintra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,5,1]]},"reference":[{"key":"18_CR1","unstructured":"GCC: GNU compiler collection. http:\/\/gcc.gnu.org"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Agarwal, T., Sharma, A., Laxmikant, A., Kal\u00e9, L.V.: Topology-aware task mapping for reducing communication contention on large parallel machines. In: IPDPS (2006)","DOI":"10.1109\/IPDPS.2006.1639379"},{"key":"18_CR3","first-page":"906","volume-title":"Compilers: Principles, Techniques, and Tools","author":"AV Aho","year":"2006","unstructured":"Aho, A.V., Lam, M.S., Sethi, R., Ullman, J.D.: Compilers: Principles, Techniques, and Tools, 2nd edn, pp. 906\u2013908. Addison-Wesley Longman Publishing Co., Inc, Boston (2006)","edition":"2"},{"issue":"3","key":"18_CR4","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1177\/109434209100500306","volume":"5","author":"DH Bailey","year":"1991","unstructured":"Bailey, D.H., Barszcz, E., Barton, J.T., Browning, D.S., Carter, R.L., Dagum, L., Fatoohi, R.A., Frederickson, P.O., Lasinski, T.A., Schreiber, R., Simon, H.D., Venkatakrishnan, V., Weeratunga, S.: The NAS parallel benchmarks. IJHPCA 5(3), 63\u201373 (1991). doi:10.1177\/109434209100500306","journal-title":"IJHPCA"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Bronevetsky, G.: Communication-sensitive static dataflow for parallel message passing applications. In: CGO, pp. 1\u201312 (2009)","DOI":"10.1109\/CGO.2009.32"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Cappello, F., Guermouche, A., Snir, M.: On communication determinism in parallel HPC applications. In: ICCCN, pp. 1\u20138 (2010)","DOI":"10.1109\/ICCCN.2010.5560143"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Chen, W., Huang, J., Robert, B., Kuhn, H.: MPIPP: an automatic profile-guided parallel process placement toolset for SMP clusters and multiclusters. In: ICS, pp. 353\u2013360 (2006)","DOI":"10.1145\/1183401.1183451"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Danalis, A., Pollock, L.L., Swany, D.M., Cavazos, J.: MPI-aware compiler optimizations for improving communication-computation overlap. In: ICS, pp. 316\u2013325 (2009)","DOI":"10.1145\/1542275.1542321"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Duesterwald, E., Gupta, R., Soffa, M.L.: Demand-driven computation of interprocedural data flow. In: POPL, pp. 37\u201348 (1995)","DOI":"10.1145\/199448.199461"},{"key":"18_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/978-3-540-30218-6_19","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"E Gabriel","year":"2004","unstructured":"Gabriel, E., et al.: Open MPI: goals, concept, and design of a next generation MPI implementation. In: Dongarra, J., Kacsuk, P., Kranzlm\u00fcller, D. (eds.) EuroPVM\/MPI 2004. LNCS, vol. 3241, pp. 97\u2013104. Springer, Heidelberg (2004)"},{"key":"18_CR11","unstructured":"Faraj, A., Yuan, X.,: Communication characteristics in the NAS parallel benchmarks. In: IASTED PDCS, pp. 724\u2013729 (2002)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Grove, D., Torczon, L.: Interprocedural constant propagation: a study of jump function implementations. In: PLDI, pp. 90\u201399 (1993)","DOI":"10.1145\/173262.155099"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, R., Soffa, M.L.: A framework for partial data flow analysis. In: ICSM, pp. 4\u201313 (1994)","DOI":"10.1109\/ICSM.1994.336794"},{"key":"18_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1007\/3-540-57659-2_30","volume-title":"Languages and Compilers for Parallel Computing","author":"MW Hall","year":"1994","unstructured":"Hall, M.W., Mellor-Crummey, J.M., Carle, A., Rodr\u00edguez, R.G.: FIAT: a framework for interprocedural analysis and transformation. In: Banerjee, U., Gelernter, D., Nicolau, Alexandru, Padua, David A. (eds.) LCPC 1993. LNCS, vol. 768, pp. 522\u2013545. Springer, Heidelberg (1994)"},{"key":"18_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1007\/978-3-540-24644-2_20","volume-title":"Languages and Compilers for Parallel Computing","author":"C Huang","year":"2004","unstructured":"Huang, C., Lawlor, O.S., Kal\u00e9, L.V.: Adaptive MPI. In: Rauchwerger, Lawrence (ed.) LCPC 2003. LNCS, vol. 2958, pp. 306\u2013322. Springer, Heidelberg (2004)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Huang, C., Zheng, G., Kal\u00e9, L.V., Kumar, S.: Performance evaluation of adaptive MPI. In: PPOPP, pp. 12\u201321 (2006)","DOI":"10.1145\/1122971.1122976"},{"issue":"1","key":"18_CR17","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1002\/j.1538-7305.1970.tb01770.x","volume":"49","author":"BW Kernighan","year":"1970","unstructured":"Kernighan, B.W., Lin, S.: An efficient heuristic procedure for partitioning graphs. Bell Syst. Tech. J. 49(1), 291\u2013307 (1970)","journal-title":"Bell Syst. Tech. J."},{"key":"18_CR18","unstructured":"Kreaseck, B., Strout, M.M., Hovland, P.: Depth analysis of MPI programs. In: AMP (2010)"},{"key":"18_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/978-3-642-24449-0_7","volume-title":"Recent Advances in the Message Passing Interface","author":"G Mercier","year":"2011","unstructured":"Mercier, G., Jeannot, E.: Improving MPI applications performance on multicore clusters with rank reordering. In: Cotronis, Y., Danalis, A., Dongarra, J., Nikolopoulos, D.S. (eds.) EuroMPI 2011. LNCS, vol. 6960, pp. 39\u201349. Springer, Heidelberg (2011)"},{"key":"18_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1007\/978-3-540-45209-6_177","volume-title":"Euro-Par 2003 Parallel Processing","author":"B Mohr","year":"2003","unstructured":"Mohr, B., Wolf, F.: KOJAK \u2013 a tool set for automatic performance analysis of parallel programs. In: B\u00f6sz\u00f6rm\u00e9nyi, L., Hellwagner, H., Kosch, H. (eds.) Euro-Par 2003. LNCS, vol. 2790, pp. 1301\u20131304. Springer, Heidelberg (2003)"},{"key":"18_CR21","first-page":"69","volume":"12","author":"WE Nagel","year":"1996","unstructured":"Nagel, W.E., Arnold, A., Weber, M., Hoppe, H.-C., Solchenbach, K.: VAMPIR: visualization and analysis of MPI resources. Supercomputer 12, 69\u201380 (1996)","journal-title":"Supercomputer"},{"key":"18_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-540-69389-5_29","volume-title":"Computational Science \u2013 ICCS 2008","author":"R Preissl","year":"2008","unstructured":"Preissl, R., Schulz, M., Kranzlm\u00fcller, D., de Supinski, B.R., Quinlan, D.J.: Using MPI communication patterns to guide source code transformations. In: Bubak, M., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) ICCS 2008, Part III. LNCS, vol. 5103, pp. 253\u2013260. Springer, Heidelberg (2008)"},{"issue":"2","key":"18_CR23","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1177\/1094342006064482","volume":"20","author":"SS Sameer","year":"2006","unstructured":"Sameer, S.S., Malony, A.D.: The TAU parallel performance system. Int. J. High Perform. Comput. Appl. 20(2), 287\u2013311 (2006)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"18_CR24","unstructured":"Shires, D.R., Pollock, L.L., Sprenkle, S.: Program flow graph construction for static analysis of MPI programs. In: PDPTA, pp. 1847\u20131853 (1999)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Strout, M.M., Kreaseck, B., Hovland, P.D.: Data-flow analysis for MPI programs. In: ICPP, pp. 175\u2013184 (2006)","DOI":"10.1109\/ICPP.2006.32"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Vetter, J.S., McCracken, M.O.: Statistical scalability analysis of communication operations in distributed applications. In: PPOPP, pp. 123\u2013132 (2001)","DOI":"10.1145\/568014.379590"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Xue, R., Liu, X., Wu, M., Guo, Z., Chen, W., Zheng, W., Zhang, Z., Voelker, G.M.: MPIWiz: subgroup reproducible replay of MPI applications. In: PPOPP, pp. 251\u2013260 (2009)","DOI":"10.1145\/1594835.1504213"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Zhai, J., Sheng, T., He, J., Chen, W., Zheng, W.: FACT: fast communication trace collection for parallel applications through program slicing. In: SC (2009)","DOI":"10.1145\/1654059.1654087"},{"key":"18_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/978-3-642-03869-3_11","volume-title":"Euro-Par 2009 Parallel Processing","author":"J Zhang","year":"2009","unstructured":"Zhang, J., Zhai, J., Chen, W., Zheng, W.: Process mapping for MPI collective communications. In: Sips, H., Epema, D., Lin, H. (eds.) Euro-Par 2009. LNCS, vol. 5704, pp. 81\u201392. Springer, Heidelberg (2009)"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-17473-0_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T18:35:37Z","timestamp":1748370937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-17473-0_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319174723","9783319174730"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-17473-0_18","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":"1 May 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}