{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T13:52:14Z","timestamp":1764251534997,"version":"3.37.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319985206"},{"type":"electronic","value":"9783319985213"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-98521-3_14","type":"book-chapter","created":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T01:37:01Z","timestamp":1535420221000},"page":"205-221","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["On the Impact of OpenMP Task Granularity"],"prefix":"10.1007","author":[{"given":"Thierry","family":"Gautier","sequence":"first","affiliation":[]},{"given":"Christian","family":"Perez","sequence":"additional","affiliation":[]},{"given":"J\u00e9r\u00f4me","family":"Richard","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,29]]},"reference":[{"key":"14_CR1","unstructured":"GNU libgomp. \nhttps:\/\/gcc.gnu.org\/onlinedocs\/libgomp"},{"key":"14_CR2","unstructured":"Intel\u00aeOpenMP* Runtime Library (2016). \nhttps:\/\/www.openmprtl.org"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Acar, U.A., Blelloch, G.E., Blumofe, R.D.: The data locality of work stealing. In: Proceedings of the Twelfth Annual ACM Symposium on Parallel Algorithms and Architectures, SPAA 2000, pp. 1\u201312. ACM, New York (2000)","DOI":"10.1145\/341800.341801"},{"key":"14_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1007\/978-3-642-32820-6_64","volume-title":"Euro-Par 2012 Parallel Processing","author":"SN Agathos","year":"2012","unstructured":"Agathos, S.N., Kallimanis, N.D., Dimakopoulos, V.V.: Speeding up OpenMP tasking. In: Kaklamanis, C., Papatheodorou, T., Spirakis, P.G. (eds.) Euro-Par 2012. LNCS, vol. 7484, pp. 650\u2013661. Springer, Heidelberg (2012). \nhttps:\/\/doi.org\/10.1007\/978-3-642-32820-6_64"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Aumage, O., Bigot, J., Coullon, H., P\u00e9rez, C., Richard, J.: Combining both a component model and a task-based model for HPC applications: a feasibility study on gysela. In: Proceedings of GCCGrid 2017. IEEE (2017)","DOI":"10.1109\/CCGRID.2017.88"},{"key":"14_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/978-3-540-85261-2_5","volume-title":"Languages and Compilers for Parallel Computing","author":"E Ayguad\u00e9","year":"2008","unstructured":"Ayguad\u00e9, E., Duran, A., Hoeflinger, J., Massaioli, F., Teruel, X.: An experimental evaluation of the new OpenMP tasking model. In: Adve, V., Garzar\u00e1n, M.J., Petersen, P. (eds.) LCPC 2007. LNCS, vol. 5234, pp. 63\u201377. Springer, Heidelberg (2008). \nhttps:\/\/doi.org\/10.1007\/978-3-540-85261-2_5"},{"issue":"2","key":"14_CR7","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1145\/301970.301974","volume":"46","author":"GE Blelloch","year":"1999","unstructured":"Blelloch, G.E., Gibbons, P.B., Matias, Y.: Provably efficient scheduling for languages with fine-grained parallelism. J. ACM 46(2), 281\u2013321 (1999)","journal-title":"J. ACM"},{"key":"14_CR8","unstructured":"OpenMP Application Review Board: OpenMP application programming interface - version 4.5, November 2015. \nhttps:\/\/www.openmp.org"},{"key":"14_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-642-30961-8_8","volume-title":"OpenMP in a Heterogeneous World","author":"F Broquedis","year":"2012","unstructured":"Broquedis, F., Gautier, T., Danjean, V.: libKOMP, an efficient OpenMP runtime system for both fork-join and data flow paradigms. In: Chapman, B.M., Massaioli, F., M\u00fcller, M.S., Rorro, M. (eds.) IWOMP 2012. LNCS, vol. 7312, pp. 102\u2013115. Springer, Heidelberg (2012). \nhttps:\/\/doi.org\/10.1007\/978-3-642-30961-8_8"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Scheduling threads for constructive cache sharing on CMPs. In: Proceedings of SPAA 2007, pp. 105\u2013115. ACM, New York (2007)","DOI":"10.1145\/1248377.1248396"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Duran, A., Teruel, X., Ferrer, R., Martorell, X., Ayguade, E.: Barcelona OpenMP tasks suite: a set of benchmarks targeting the exploitation of task parallelism in OpenMP. In: Proceedings of ICPP 2009, pp. 124\u2013131. IEEE (2009)","DOI":"10.1109\/ICPP.2009.64"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Duran, A., Corbal\u00e1n, J., Ayguad\u00e9, E.: An adaptive cut-off for task parallelism. In: Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing, SC 2008, pp. 36:1\u201336:11. IEEE Press, Piscataway (2008)","DOI":"10.1109\/SC.2008.5213927"},{"issue":"5","key":"14_CR13","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1145\/277652.277725","volume":"33","author":"M Frigo","year":"1998","unstructured":"Frigo, M., Leiserson, C.E., Randall, K.H.: The implementation of the Cilk-5 multithreaded language. SIGPLAN Not. 33(5), 212\u2013223 (1998)","journal-title":"SIGPLAN Not."},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Galil\u00e9e, F., Roch, J.L., Cavalheiro, G.G.H., Doreille, M.: Athapascan-1: on-line building data flow graph in a parallel language. In: Proceedings of the 1998 International Conference on Parallel Architectures and Compilation Techniques, PACT 1998, pp. 88\u201395. IEEE Computer Society, Washington, DC (1998)","DOI":"10.1109\/PACT.1998.727176"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Gautier, T., Besseron, X., Pigeon, L.: KAAPI: a thread scheduling runtime system for data flow computations on cluster of multi-processors. In: PASCO 2007 (2007)","DOI":"10.1145\/1278177.1278182"},{"issue":"1","key":"14_CR16","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1006\/jpdc.1996.0104","volume":"37","author":"SC Goldstein","year":"1996","unstructured":"Goldstein, S.C., Schauser, K.E., Culler, D.E.: Lazy threads: implementing a fast parallel call. J. Parallel Distrib. Comput. 37(1), 5\u201320 (1996)","journal-title":"J. Parallel Distrib. Comput."},{"key":"14_CR17","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.cpc.2016.05.007","volume":"207","author":"V Grandgirard","year":"2016","unstructured":"Grandgirard, V., et al.: A 5D gyrokinetic full-$$f$$ global semi-Lagrangian code for flux-driven ion turbulence simulations. Comput. Phys. Commun. 207, 35\u201368 (2016)","journal-title":"Comput. Phys. Commun."},{"key":"14_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-540-72521-3_18","volume-title":"Languages and Compilers for Parallel Computing","author":"S Olivier","year":"2007","unstructured":"Olivier, S., et al.: UTS: an unbalanced tree search benchmark. In: Alm\u00e1si, G., Ca\u015fcaval, C., Wu, P. (eds.) LCPC 2006. LNCS, vol. 4382, pp. 235\u2013250. Springer, Heidelberg (2007). \nhttps:\/\/doi.org\/10.1007\/978-3-540-72521-3_18"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Olivier, S.L., Porterfield, A.K., Wheeler, K.B., Prins, J.F.: Scheduling task parallelism on multi-socket multicore systems. In: Proceedings of the 1st International Workshop on Runtime and Operating Systems for Supercomputers, ROSS 2011, pp. 49\u201356. ACM, New York (2011)","DOI":"10.1145\/1988796.1988804"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"P\u00e9rez, J.M., Beltran, V., Labarta, J., Ayguad\u00e9, E.: Improving the integration of task nesting and dependencies in OpenMP. In: IPDPS, pp. 809\u2013818. IEEE Computer Society (2017)","DOI":"10.1109\/IPDPS.2017.69"},{"key":"14_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-3-319-11454-5_4","volume-title":"Using and Improving OpenMP for Devices, Tasks, and More","author":"A Podobas","year":"2014","unstructured":"Podobas, A., Brorsson, M., Vlassov, V.: TurboB\u0141YSK: scheduling for improved data-driven task performance with fast dependency resolution. In: DeRose, L., de Supinski, B.R., Olivier, S.L., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2014. LNCS, vol. 8766, pp. 45\u201357. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-11454-5_4"},{"key":"14_CR22","unstructured":"Revire, R.: Scheduling dynamic task graph on large scale architecture. Ph.D. thesis, Institut National Polytechnique de Grenoble - INPG, France, September 2004. \nhttps:\/\/tel.archives-ouvertes.fr\/tel-00010909"},{"key":"14_CR23","volume-title":"Component Software: Beyond Object-Oriented Programming","author":"C Szyperski","year":"2002","unstructured":"Szyperski, C.: Component Software: Beyond Object-Oriented Programming. Addison-Wesley Longman Publishing Co., Inc., Boston (2002)"},{"key":"14_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1007\/978-3-540-85451-7_95","volume-title":"Euro-Par 2008 \u2013 Parallel Processing","author":"D Traor\u00e9","year":"2008","unstructured":"Traor\u00e9, D., Roch, J.-L., Maillard, N., Gautier, T., Bernard, J.: Deque-free work-optimal parallel STL algorithms. In: Luque, E., Margalef, T., Ben\u00edtez, D. (eds.) Euro-Par 2008. LNCS, vol. 5168, pp. 887\u2013897. Springer, Heidelberg (2008). \nhttps:\/\/doi.org\/10.1007\/978-3-540-85451-7_95"},{"issue":"4","key":"14_CR25","first-page":"61:1","volume":"10","author":"H Vandierendonck","year":"2013","unstructured":"Vandierendonck, H., Tzenakis, G., Nikolopoulos, D.S.: Analysis of dependence tracking algorithms for task dataflow execution. ACM TACO 10(4), 61:1\u201361:24 (2013)","journal-title":"ACM TACO"},{"key":"14_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/978-3-319-43659-3_39","volume-title":"Euro-Par 2016: Parallel Processing","author":"P Virouleau","year":"2016","unstructured":"Virouleau, P., Broquedis, F., Gautier, T., Rastello, F.: Using data dependencies to improve task-based scheduling strategies on NUMA architectures. In: Dutot, P.-F., Trystram, D. (eds.) Euro-Par 2016. LNCS, vol. 9833, pp. 531\u2013544. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-43659-3_39"},{"key":"14_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/978-3-319-11454-5_2","volume-title":"Using and Improving OpenMP for Devices, Tasks, and More","author":"P Virouleau","year":"2014","unstructured":"Virouleau, P., et al.: Evaluation of OpenMP dependent tasks with the KASTORS benchmark suite. In: DeRose, L., de Supinski, B.R., Olivier, S.L., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2014. LNCS, vol. 8766, pp. 16\u201329. Springer, Cham (2014). \nhttps:\/\/doi.org\/10.1007\/978-3-319-11454-5_2"}],"container-title":["Lecture Notes in Computer Science","Evolving OpenMP for Evolving Architectures"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-98521-3_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T01:46:43Z","timestamp":1535420803000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-98521-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319985206","9783319985213"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-98521-3_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}