{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T20:31:41Z","timestamp":1794429101427,"version":"4.9.1"},"publisher-location":"Berlin, Heidelberg","reference-count":25,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642328190","type":"print"},{"value":"9783642328206","type":"electronic"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","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":[[2012]]},"DOI":"10.1007\/978-3-642-32820-6_25","type":"book-chapter","created":{"date-parts":[[2012,8,23]],"date-time":"2012-08-23T08:26:25Z","timestamp":1345710385000},"page":"246-257","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["From Serial Loops to Parallel Execution on Distributed Systems"],"prefix":"10.1007","author":[{"given":"George","family":"Bosilca","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aurelien","family":"Bouteiller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony","family":"Danalis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Herault","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Ancourt, C., Irigoin, F.: Scanning polyhedra with do loops. In: Proceedings of ACM PPoPP 1991, Williamsburg, VA, pp. 39\u201350 (1991)","DOI":"10.1145\/109626.109631"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Baskaran, M.M., Vydyanathan, N., Bondhugula, U.K.R., Ramanujam, J., Rountev, A., Sadayappan, P.: Compiler-assisted dynamic scheduling for effective parallelization of loop nests on multicore processors. In: Proceedings of ACM PPoPP 2009, Raleigh, NC, pp. 219\u2013228 (2009)","DOI":"10.1145\/1594835.1504209"},{"key":"25_CR3","first-page":"7","volume-title":"Proceedings of IEEE PACT 2004","author":"C. Bastoul","year":"2004","unstructured":"Bastoul, C.: Code Generation in the Polyhedral Model Is Easier Than You Think. In: Proceedings of IEEE PACT 2004, pp. 7\u201316. Antibes Juan-les-Pins, France (2004)"},{"key":"25_CR4","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719642","volume-title":"ScaLAPACK Users\u2019 Guide","author":"L.S. Blackford","year":"1997","unstructured":"Blackford, L.S., Choi, J., Cleary, A., D\u2019Azevedo, E., Demmel, J., Dhillon, I., Dongarra, J., Hammarling, S., Henry, G., Petitet, A., Stanley, K., Walker, D., Whaley, R.C.: ScaLAPACK Users\u2019 Guide. Society for Industrial and Applied Mathematics, Philadelphia (1997)"},{"key":"25_CR5","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/2.546612","volume":"29","author":"W. Blume","year":"1996","unstructured":"Blume, W., Doallo, R., Eigenmann, R., Grout, J., Hoeflinger, J., Lawrence, T., Lee, J., Padua, D., Paek, Y., Pottenger, B., Rauchwerger, L., Tu, P.: Parallel programming with polaris. IEEE Computer\u00a029, 78\u201382 (1996)","journal-title":"IEEE Computer"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Bondhugula, U., Hartono, A., Ramanujam, J., Sadayappan, P.: A practical automatic polyhedral parallelizer and locality optimizer. In: Proceedings of ACM PLDI 2008, Tucson, AZ, pp. 101\u2013113 (2008)","DOI":"10.1145\/1379022.1375595"},{"key":"25_CR7","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Faverge, M., Haidar, H., Herault, T., Kurzak, J., Langou, J., Lemarinier, P., Ltaief, H., Luszczek, P., YarKhan, A., Dongarra, J.: Distributed-Memory Task Execution and Dependence Tracking within DAGuE and the DPLASMA Project. Tech. Rep. 232, LAWN (September 2010)"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Faverge, M., Haidar, A., Herault, T., Kurzak, J., Langou, J., Lemarinier, P., Ltaief, H., Luszczek, P., YarKhan, A., Dongarra, J.: Flexible development of dense linear algebra algorithms on massively parallel architectures with DPLASMA. In: IEEE PDSEC 2011, Anchorage, AK (2011)","DOI":"10.1109\/IPDPS.2011.299"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Herault, T., Lemarinier, P., Dongarra, J.: DAGuE: A generic distributed dag engine for high performance computing. In: HIPS 2011, Anchorage, AK (2011)","DOI":"10.1109\/IPDPS.2011.281"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Herault, T., Lemarinier, P., Dongarra, J.J.: DAGuE: A generic distributed DAG engine for high performance computing. Parallel Computing (2011) (to appear), \n                    \n                      http:\/\/dx.doi.org\/10.1016\/j.parco.2011.10.003","DOI":"10.1016\/j.parco.2011.10.003"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Bosilca, G., Bouteiller, A., H\u00e9rault, T., Lemarinier, P., Saengpatsa, N.O., Tomov, S., Dongarra, J.J.: Performance portability of a gpu enabled factorization with the dague framework. In: IEEE CLUSTER, pp. 395\u2013402 (2011)","DOI":"10.1109\/CLUSTER.2011.51"},{"key":"25_CR12","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.parco.2008.10.002","volume":"35","author":"A. Buttari","year":"2009","unstructured":"Buttari, A., Langou, J., Kurzak, J., Dongarra, J.J.: A class of parallel tiled linear algebra algorithms for multicore architectures. Parallel Comput. Syst. Appl.\u00a035, 38\u201353 (2009)","journal-title":"Parallel Comput. Syst. Appl."},{"issue":"9","key":"25_CR13","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1002\/cpe.728","volume":"15","author":"J.J. Dongarra","year":"2003","unstructured":"Dongarra, J.J., Luszczek, P., Petitet, A.: The LINPACK benchmark: Past, present and future. Concurrency Computat.: Pract. Exper.\u00a015(9), 803\u2013820 (2003)","journal-title":"Concurrency Computat.: Pract. Exper."},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"van Engelen, R.A., Birch, J., Shou, Y., Walsh, B., Gallivan, K.A.: A unified framework for nonlinear dependence testing and symbolic analysis. In: Proceedings of ACM ICS 2004, Malo, France, pp. 106\u2013115 (2004)","DOI":"10.1145\/1006209.1006226"},{"key":"25_CR15","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/BF01407931","volume":"20","author":"P. Feautrier","year":"1991","unstructured":"Feautrier, P.: Dataflow analysis of array and scalar references. International Journal of Parallel Programming\u00a020, 23\u201353 (1991), 10.1007\/BF01407931","journal-title":"International Journal of Parallel Programming"},{"issue":"2","key":"25_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1499096.1499100","volume":"36","author":"F.G. Gustavson","year":"2009","unstructured":"Gustavson, F.G., Karlsson, L., K\u00e5gstr\u00f6m, B.: Distributed SBP cholesky factorization algorithms with near-optimal scheduling. ACM Trans. Math. Softw.\u00a036(2), 1\u201325 (2009)","journal-title":"ACM Trans. Math. Softw."},{"key":"25_CR17","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/2.546613","volume":"29","author":"M.W. Hall","year":"1996","unstructured":"Hall, M.W., Anderson, J.M., Amarasinghe, S.P., Murphy, B.R., Liao, S.W., Bugnion, E., Lam, M.S.: Maximizing multiprocessor performance with the SUIF compiler. IEEE Computer\u00a029, 84\u201389 (1996)","journal-title":"IEEE Computer"},{"key":"25_CR18","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1023\/B:IJPP.0000035817.01263.d0","volume":"32","author":"K. Kyriakopoulos","year":"2004","unstructured":"Kyriakopoulos, K., Psarris, K.: Data dependence analysis techniques for increased accuracy and extracted parallelism. International Journal of Parallel Programming\u00a032, 317\u2013359 (2004)","journal-title":"International Journal of Parallel Programming"},{"key":"25_CR19","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1109\/TPDS.2008.131","volume":"20","author":"K. Kyriakopoulos","year":"2009","unstructured":"Kyriakopoulos, K., Psarris, K.: Nonlinear Symbolic Analysis for Advanced Program Parallelization. IEEE Transactions on Parallel and Distributed Systems\u00a020, 623\u2013640 (2009)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Maydan, D.E., Hennessy, J.L., Lam, M.S.: Efficient and exact data dependence analysis. In: Proceedings of ACM PLDI 1991, Toronto, Ontario, pp. 1\u201314 (1991)","DOI":"10.1145\/113446.113447"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Perez, J.M., Badia, R.M., Labarta, J.: A dependency-aware task-based programming environment for multi-core architectures. In: Proceedings of IEEE Cluster Computing, pp. 142\u2013151 (2008)","DOI":"10.1109\/CLUSTR.2008.4663765"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Pugh, W.: The omega test: a fast and practical integer programming algorithm for dependence analysis. In: Proceedings of the ACM\/IEEE SC 1991, pp. 4\u201313 (1991)","DOI":"10.1145\/125826.125848"},{"key":"25_CR23","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1023\/A:1007554627716","volume":"28","author":"F. Quiller\u00e9","year":"2000","unstructured":"Quiller\u00e9, F., Rajopadhye, S., Wilde, D.: Generation of efficient nested loops from polyhedra. Int. J. Parallel Program.\u00a028, 469\u2013498 (2000)","journal-title":"Int. J. Parallel Program."},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Song, F., YarKhan, A., Dongarra, J.: Dynamic task scheduling for linear algebra algorithms on distributed-memory multicore systems. In: Proceedings of ACM\/IEEE SC 2009 (2009)","DOI":"10.1145\/1654059.1654079"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Vasilache, N., Bastoul, C., Cohen, A., Girbal, S.: Violated dependence analysis. In: Proceedings of ACM ICS 2006, Cairns, Queensland, Australia, pp. 335\u2013344 (2006)","DOI":"10.1145\/1183401.1183448"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2012 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-32820-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,19]],"date-time":"2020-04-19T20:59:22Z","timestamp":1587329962000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-32820-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642328190","9783642328206"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-32820-6_25","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-642-32820-6","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}