{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:25:35Z","timestamp":1759134335138,"version":"3.37.3"},"publisher-location":"Cham","reference-count":38,"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_2","type":"book-chapter","created":{"date-parts":[[2018,8,28]],"date-time":"2018-08-28T01:37:01Z","timestamp":1535420221000},"page":"21-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["OpenMP Loop Scheduling Revisited: Making a Case for More Schedules"],"prefix":"10.1007","author":[{"given":"Florina M.","family":"Ciorba","sequence":"first","affiliation":[]},{"given":"Christian","family":"Iwainsky","sequence":"additional","affiliation":[]},{"given":"Patrick","family":"Buder","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,29]]},"reference":[{"key":"2_CR1","unstructured":"An Enhanced OpenMP Library. https:\/\/github.com\/lapesd\/libgomp . Accessed 27 Apr 2018"},{"key":"2_CR2","unstructured":"SPEC OMP2012. https:\/\/www.spec.org\/omp2012\/ . Accessed 27 Apr 2018"},{"key":"2_CR3","unstructured":"The OpenMP API specification for parallel programming. http:\/\/www.openmp.org . Accessed 27 Apr 2018"},{"key":"2_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/3-540-45009-2_12","volume-title":"OpenMP Shared Memory Parallel Programming","author":"E Ayguad\u00e9","year":"2003","unstructured":"Ayguad\u00e9, E., et al.: Is the schedule clause really necessary in OpenMP? In: Voss, M.J. (ed.) WOMPAT 2003. LNCS, vol. 2716, pp. 147\u2013159. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-45009-2_12"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Bailey, D.H., et al.: The NAS parallel benchmarks: summary and preliminary results. In: Proceedings of the 1991 ACM\/IEEE Conference on Supercomputing, Supercomputing 1991, pp. 158\u2013165. ACM, New York (1991)","DOI":"10.1145\/125826.125925"},{"key":"2_CR6","unstructured":"Banicescu, I.: Load Balancing and data locality in the parallelization of the fast multipole algorithm. Ph.D. thesis, New York Polytechnic University (1996)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Banicescu, I., Flynn Hummel, S.: Balancing processor loads and exploiting data locality in N-body simulations. In: Proceedings of IEEE\/ACM SC 1995 Conference on Supercomputing, p. 43 (1995)","DOI":"10.1145\/224170.224306"},{"key":"2_CR8","unstructured":"Banicescu, I., Liu, Z.: Adaptive factoring: a dynamic scheduling method tuned to the rate of weight changes. In: Proceedings of 8th High Performance Computing Symposium, pp. 122\u2013129. Society for Computer Simulation International (2000)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Bast, H.: Dynamic scheduling with incomplete information. In: Proceedings of the Tenth Annual ACM Symposium on Parallel Algorithms and Architectures, SPAA 1998, pp. 182\u2013191. ACM, New York (1998)","DOI":"10.1145\/277651.277684"},{"key":"2_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1007\/3-540-45841-7_13","volume-title":"STACS 2002","author":"H Bast","year":"2002","unstructured":"Bast, H.: Scheduling at twilight the EasyWay. In: Alt, H., Ferreira, A. (eds.) STACS 2002. LNCS, vol. 2285, pp. 166\u2013178. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-45841-7_13"},{"issue":"5","key":"2_CR11","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1145\/324133.324234","volume":"46","author":"RD Blumofe","year":"1999","unstructured":"Blumofe, R.D., Leiserson, C.E.: Scheduling multithreaded computations by work stealing. J. ACM 46(5), 720\u2013748 (1999)","journal-title":"J. ACM"},{"key":"2_CR12","unstructured":"Buder, P.: Evaluation and analysis of dynamic loop scheduling in OpenMP. Master\u2019s thesis, University of Basel, November 2017"},{"key":"2_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-37658-0_1","volume-title":"Languages and Compilers for Parallel Computing","author":"R Cammarota","year":"2013","unstructured":"Cammarota, R., Nicolau, A., Veidenbaum, A.V.: Just in time load balancing. In: Kasahara, H., Kimura, K. (eds.) LCPC 2012. LNCS, vol. 7760, pp. 1\u201316. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37658-0_1"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Che, S., Sheaffer, J.W., Boyer, M., Szafaryn, L.G., Wang, L., Skadron, K.: A characterization of the Rodinia benchmark suite with comparison to contemporary CMP workloads. In: Proceedings of the IEEE International Symposium on Workload Characterization (IISWC 2010), pp. 1\u201311. IEEE Computer Society, Washington, DC (2010)","DOI":"10.1109\/IISWC.2010.5650274"},{"issue":"1","key":"2_CR15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/1094342010391989","volume":"25","author":"J Dongarra","year":"2011","unstructured":"Dongarra, J., Beckman, P., et al.: The international exascale software roadmap. Int. J. High Perform. Comput. Appl. 25(1), 3\u201360 (2011)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Dorta, A.J., Rodriguez, C., Sande, F.d., Gonzalez-Escribano, A.: The OpenMP source code repository. In: Proceedings of the 13th Euromicro Conference on Parallel, Distributed and Network-Based Processing, PDP 2005, pp. 244\u2013250. IEEE Computer Society, Washington, DC (2005)","DOI":"10.1109\/EMPDP.2005.41"},{"key":"2_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/978-3-642-40698-0_11","volume-title":"OpenMP in the Era of Low Power Devices and Accelerators","author":"M Durand","year":"2013","unstructured":"Durand, M., Broquedis, F., Gautier, T., Raffin, B.: An Efficient OpenMP loop scheduler for irregular applications on large-scale NUMA machines. In: Rendell, A.P., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2013. LNCS, vol. 8122, pp. 141\u2013155. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-40698-0_11"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Durand, M.D., Montaut, T., Kervella, L., Jalby, W.: Impact of memory contention on dynamic scheduling on NUMA Multiprocessors. In: Proceedings of International Conference on Parallel Processing, vol. 1, pp. 258\u2013262, August 1993","DOI":"10.1109\/ICPP.1993.101"},{"key":"2_CR19","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/978-1-4615-2315-4_7","volume-title":"Languages, Compilers and Run-Time Systems for Scalable Computers","author":"S Flynn Hummel","year":"1996","unstructured":"Flynn Hummel, S., Banicescu, I., Wang, C.-T., Wein, J.: Load balancing and data locality via fractiling: an experimental study. In: Szymanski, B.K., Sinharoy, B. (eds.) Languages, Compilers and Run-Time Systems for Scalable Computers, pp. 85\u201398. Springer, Boston (1996). https:\/\/doi.org\/10.1007\/978-1-4615-2315-4_7"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Flynn Hummel, S., Schmidt, J., Uma, R.N., Wein, J.: Load-sharing in heterogeneous systems via weighted factoring. In: Proceedings of the Eighth Annual ACM Symposium on Parallel Algorithms and Architectures, SPAA 1996, pp. 318\u2013328. ACM, New York (1996)","DOI":"10.1145\/237502.237576"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Flynn Hummel, S., Schonberg, E., Flynn, L.E.: Factoring: a practical and robust method for scheduling parallel loops. In: Proceedings of ACM\/IEEE Conference Supercomputing (Supercomputing 1991), pp. 610\u2013632, November 1991","DOI":"10.1145\/125826.126137"},{"key":"2_CR22","volume-title":"Computers and Intractability: A Guide to the Theory of NP-Completeness","author":"MR Garey","year":"1990","unstructured":"Garey, M.R., Johnson, D.S.: Computers and Intractability: A Guide to the Theory of NP-Completeness. W. H. Freeman & Co., New York (1990)"},{"key":"2_CR23","unstructured":"Govindaswamy. K.: An API for adaptive loop scheduling in shared address space architectures. Master\u2019s thesis, Mississippi State University (2003)"},{"key":"2_CR24","unstructured":"Kale, V.: Low-overhead scheduling for improving performance of scientific applications. Ph.D. thesis, University of Illinois at Urbana-Champaign, August 2015"},{"key":"2_CR25","unstructured":"Kale, V., Gropp, W.D.: A user-defined schedule for OpenMP. In: Proceedings of the 2017 Conference on OpenMP, Stonybrook, New York, USA, November 2017 (2017)"},{"key":"2_CR26","unstructured":"Klemm, M.: Twenty years of the OpenMP API. Scientific Computing World, April\/May 2017"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Li, H., Tandri, S., Stumm, M., Sevcik, K.C.: Locality and loop scheduling on NUMA multiprocessors. In: Proceedings of the 1993 International Conference on Parallel Processing, ICPP 1993, vol. 02, pp. 140\u2013147. IEEE Computer Society, Washington, DC (1993)","DOI":"10.1109\/ICPP.1993.112"},{"issue":"4","key":"2_CR28","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1109\/71.273046","volume":"5","author":"EP Markatos","year":"1994","unstructured":"Markatos, E.P., LeBlanc, T.J.: Using processor affinity in loop scheduling on shared-memory multiprocessors. IEEE Trans. Parallel Distrib. Syst. 5(4), 379\u2013400 (1994)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2_CR29","unstructured":"Penna, P.H., Castro, M., Plentz, P., Cota de Freitas, H., Broquedis, F., M\u00e9haut, J.-F.: BinLPT: a novel workload-aware loop scheduler for irregular parallel loops. In: Simp\u00f3sio em Sistemas Computacionais de Alto Desempenho, Campinas, Brazil, October 2017"},{"key":"2_CR30","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.procs.2017.05.222","volume":"108","author":"PH Penna","year":"2017","unstructured":"Penna, P.H., et al.: Assessing the performance of the SRR loop scheduler with irregular workloads. Procedia Comput. Sci. 108, 255\u2013264 (2017). International Conference on Computational Science, ICCS 2017, 12\u201314 June 2017, Zurich, Switzerland","journal-title":"Procedia Comput. Sci."},{"issue":"12","key":"2_CR31","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1109\/TC.1987.5009495","volume":"C\u201336","author":"CD Polychronopoulos","year":"1987","unstructured":"Polychronopoulos, C.D., Kuck, D.J.: Guided self-scheduling: a practical scheduling scheme for parallel supercomputers. IEEE Trans. Comput. C\u201336(12), 1425\u20131439 (1987)","journal-title":"IEEE Trans. Comput."},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Subramaniam, S., Eager, D.L.: Affinity scheduling of unbalanced workloads. In: Proceedings of Supercomputing 1994, pp. 214\u2013226, November 1994","DOI":"10.1145\/602770.602810"},{"key":"2_CR33","unstructured":"Tang, P., Yew, P.-C.: Processor self-scheduling for multiple-nested parallel loops. In: Proceedings of International Conference on Parallel Processing, vol. 12, pp. 528\u2013535. IEEE (1986)"},{"key":"2_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/978-3-642-30961-8_7","volume-title":"OpenMP in a Heterogeneous World","author":"P Thoman","year":"2012","unstructured":"Thoman, P., Jordan, H., Pellegrini, S., Fahringer, T.: Automatic OpenMP loop scheduling: a combined compiler and runtime approach. In: Chapman, B.M., Massaioli, F., M\u00fcller, M.S., Rorro, M. (eds.) IWOMP 2012. LNCS, vol. 7312, pp. 88\u2013101. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-30961-8_7"},{"issue":"1","key":"2_CR35","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/71.205655","volume":"4","author":"TH Tzen","year":"1993","unstructured":"Tzen, T.H., Ni, L.M.: Trapezoid self-scheduling: a practical scheduling scheme for parallel compilers. IEEE Trans. Parallel Distrib. Syst. 4(1), 87\u201398 (1993)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/978-3-642-35606-3_3","volume-title":"Network and Parallel Computing","author":"Y Wang","year":"2012","unstructured":"Wang, Y., Ji, W., Shi, F., Zuo, Q., Deng, N.: Knowledge-based adaptive self-scheduling. In: Park, J.J., Zomaya, A., Yeo, S.-S., Sahni, S. (eds.) NPC 2012. LNCS, vol. 7513, pp. 22\u201332. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35606-3_3"},{"key":"2_CR37","unstructured":"Zhang, Y., Burcea, M., Cheng, V., Ho, R., Voss M.: An adaptive OpenMP loop scheduler for hyperthreaded SMPs. In. Proceedings of International Conference on Parallel and Distributed Computing Systems (PDCS) (2004)"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Voss, M., Rogers, E.S.: Runtime empirical selection of loop schedulers on hyperthreaded SMPs. In: 19th IEEE International Parallel and Distributed Processing Symposium, p. 44b, April 2005","DOI":"10.1109\/IPDPS.2005.386"}],"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_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,22]],"date-time":"2019-10-22T21:37:58Z","timestamp":1571780278000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-98521-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319985206","9783319985213"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-98521-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}