{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T11:19:23Z","timestamp":1768994363109,"version":"3.49.0"},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642038686","type":"print"},{"value":"9783642038693","type":"electronic"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"vor","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":[[2009]]},"DOI":"10.1007\/978-3-642-03869-3_79","type":"book-chapter","created":{"date-parts":[[2009,8,22]],"date-time":"2009-08-22T04:04:48Z","timestamp":1250913888000},"page":"851-862","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":59,"title":["An Extension of the StarSs Programming Model for Platforms with Multiple GPUs"],"prefix":"10.1007","author":[{"given":"Eduard","family":"Ayguad\u00e9","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rosa M.","family":"Badia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francisco D.","family":"Igual","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jes\u00fas","family":"Labarta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Mayo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"79_CR1","volume-title":"LAPACK Users\u2019 Guide","author":"E. Anderson","year":"1992","unstructured":"Anderson, E., Bai, Z., Demmel, J., Dongarra, J.E., DuCroz, J., Greenbaum, A., Hammarling, S., McKenney, A.E., Ostrouchov, S., Sorensen, D.: LAPACK Users\u2019 Guide. SIAM, Philadelphia (1992)"},{"key":"79_CR2","series-title":"Lecture Notes in Computer Science","volume-title":"Evolving OpenMP in an Age of Extreme Parallelism. 5th International Workshop on OpenMP, IWOMP 2009","author":"E. Ayguade","year":"2009","unstructured":"Ayguade, E., Badia, R.M., Cabrera, D., Duran, A., Gonzalez, M., Igual, F.D., Jimenez, D., Labarta, J., Martorell, X., Mayo, R., Perez, J.M., Quintana-Ort\u00ed, E.S.: A proposal to extend the OpenMP tasking model for heterogeneous architectures. In: Evolving OpenMP in an Age of Extreme Parallelism. 5th International Workshop on OpenMP, IWOMP 2009, Dresden, Germany. LNCS. Springer, Heidelberg (2009)"},{"key":"79_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1007\/978-3-540-85451-7_79","volume-title":"Euro-Par 2008 Parallel Processing","author":"S. Barrachina","year":"2008","unstructured":"Barrachina, S., Castillo, M., Igual, F.D., Mayo, R., Quintana-Ort\u00ed, E.S.: Solving dense linear systems on graphics processors. In: Luque, E., Margalef, T., Ben\u00edtez, D. (eds.) Euro-Par 2008. LNCS, vol.\u00a05168, pp. 739\u2013748. Springer, Heidelberg (2008)"},{"key":"79_CR4","first-page":"86","volume-title":"SC 2006: Proceedings of the 2006 ACM\/IEEE conference on Supercomputing","author":"P. Bellens","year":"2006","unstructured":"Bellens, P., P\u00e9rez, J.M., Badia, R.M., Labarta, J.: CellSs: a programming model for the Cell BE architecture. In: SC 2006: Proceedings of the 2006 ACM\/IEEE conference on Supercomputing, p. 86. ACM Press, New York (2006)"},{"issue":"11","key":"79_CR5","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1109\/TPDS.2002.1058095","volume":"13","author":"S. Chatterjee","year":"2002","unstructured":"Chatterjee, S., Lebeck, A.R., Patnala, P.K., Thottethodi, M.: Recursive array layouts and fast matrix multiplication. IEEE Trans. on Parallel and Distributed Systems\u00a013(11), 1105\u20131123 (2002)","journal-title":"IEEE Trans. on Parallel and Distributed Systems"},{"issue":"1","key":"79_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/77626.79170","volume":"16","author":"J. Dongarra","year":"1990","unstructured":"Dongarra, J., Croz, J.D., Hammarling, S., Duff, I.: A set of level 3 basic linear algebra subprograms. ACM Trans. Math. Soft.\u00a016(1), 1\u201317 (1990)","journal-title":"ACM Trans. Math. Soft."},{"key":"79_CR7","first-page":"101","volume-title":"PPoPP 2009: Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming","author":"S. Lee","year":"2009","unstructured":"Lee, S., Min, S.-J., Eigenmann, R.: Openmp to gpgpu: a compiler framework for automatic translation and optimization. In: PPoPP 2009: Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming, pp. 101\u2013110. ACM Press, New York (2009)"},{"key":"79_CR8","unstructured":"NVIDIA. NVIDIA CUDA Programming Guide 2.2 (2008)"},{"issue":"7","key":"79_CR9","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPDS.2003.1214317","volume":"14","author":"N. Park","year":"2003","unstructured":"Park, N., Hong, B., Prasanna, V.K.: Tiling, block data layout, and memory hierarchy performance. IEEE Trans. on Parallel and Distributed Systems\u00a014(7), 640\u2013654 (2003)","journal-title":"IEEE Trans. on Parallel and Distributed Systems"},{"key":"79_CR10","doi-asserted-by":"crossref","unstructured":"Perez, J.M., Bellens, P., Badia, R.M., Labarta, J.: CellSs: Making it easier to program the cell broadband engine processor. IBM Journal of Research and Development\u00a051(5) (August 2007)","DOI":"10.1147\/rd.515.0593"},{"key":"79_CR11","unstructured":"Perez, J.M., Badia, R.M., Labarta, J.: Scalar-aware grid superscalar. DAC TR UPC-DAC-RR-CAP-2006-12. Technical report, Universitat Polit\u00e9cnica de Catalunya, Computer Architecture Department (2006)"},{"key":"79_CR12","unstructured":"P\u00e9rez, J.M., Badia, R.M., Labarta, J.: A flexible and portable programming model for SMP and multi-cores. Technical Report 03\/2007, Barcelona Supercomputing Center - CNS, Barcelona, Spain (2007)"},{"key":"79_CR13","first-page":"121","volume-title":"PPoPP 2009: Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming","author":"G. Quintana-Ort\u00ed","year":"2009","unstructured":"Quintana-Ort\u00ed, G., Igual, F.D., Quintana-Ort\u00ed, E.S., van de Geijn, R.A.: Solving dense linear systems on platforms with multiple hardware accelerators. In: PPoPP 2009: Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming, pp. 121\u2013130. ACM, New York (2009)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2009 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-03869-3_79","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,19]],"date-time":"2020-05-19T13:52:42Z","timestamp":1589896362000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-03869-3_79"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642038686","9783642038693"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-03869-3_79","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}