{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:47:43Z","timestamp":1742932063614,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031407437"},{"type":"electronic","value":"9783031407444"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-40744-4_13","type":"book-chapter","created":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T23:03:28Z","timestamp":1693436608000},"page":"195-209","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Simulations of\u00a0Task-Based Applications on\u00a0Complex NUMA Architectures"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2425-8359","authenticated-orcid":false,"given":"Idriss","family":"Daoudi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thierry","family":"Gautier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6411-809X","authenticated-orcid":false,"given":"Samuel","family":"Thibault","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1029-0684","authenticated-orcid":false,"given":"Swann","family":"Perarnau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,1]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Agullo, E., Beaumont, O., Eyraud-Dubois, L., Kumar, S.: Are static schedules so bad? a case study on Cholesky factorization. In: IPDPS (2016)","key":"13_CR1","DOI":"10.1109\/IPDPS.2016.90"},{"issue":"23","key":"13_CR2","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1002\/cpe.1631","volume":"2009","author":"C Augonnet","year":"2011","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.A.: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. Concurr. Comput. Pract. Exp. 2009(23), 187\u2013198 (2011). Special Issue: Euro-Par","journal-title":"Concurr. Comput. Pract. Exp."},{"doi-asserted-by":"crossref","unstructured":"Ayguad\u00e9, E., Badia, R.M., Igual, F.D., Labarta, J., Mayo, R., Quintana-Ort\u00ed, E.S.: An extension of the StarSs programming model for platforms with multiple GPUs. In: Proceedings of the 15th Euro-Par Conference. Delft, The Netherlands (2009)","key":"13_CR3","DOI":"10.1007\/978-3-642-03869-3_79"},{"issue":"1","key":"13_CR4","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1006\/jpdc.1996.0107","volume":"37","author":"RD Blumofe","year":"1996","unstructured":"Blumofe, R.D., Joerg, C.F., Kuszmaul, B.C., Leiserson, C.E., Randall, K.H., Zhou, Y.: Cilk: an efficient multithreaded runtime system. J. Parallel Distrib. Comput. 37(1), 55\u201369 (1996)","journal-title":"J. Parallel Distrib. Comput."},{"doi-asserted-by":"crossref","unstructured":"Broquedis, F., et al.: hwloc: a generic framework for managing hardware affinities in HPC applications. In: International Conference on Parallel, Distributed and Network-Based Processing (PDP2010), pp. 180\u2013186. Pisa, Italia (2010)","key":"13_CR5","DOI":"10.1109\/PDP.2010.67"},{"doi-asserted-by":"crossref","unstructured":"Bueno, J., Martinell, L., Duran, A., Farreras, M., Martorell, X., Badia, R.M., Ayguad\u00e9, E., Labarta, J.: Productive cluster programming with OmpSs. In: Proceedings of the 17th international conference on Parallel processing - Volume Part I. Euro-Par 2011 (2011)","key":"13_CR6","DOI":"10.1007\/978-3-642-23400-2_52"},{"unstructured":"Buttari, A., Langou, J., Kurzak, J., Dongarra, J.: Lapack working note 191: a class of parallel tiled linear algebra algorithms for multicore architectures (2007)","key":"13_CR7"},{"issue":"1","key":"13_CR8","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1002\/spe.995","volume":"41","author":"RN Calheiros","year":"2011","unstructured":"Calheiros, R.N., Ranjan, R., Beloglazov, A., De Rose, C.A.F., Buyya, R.: CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Softw. Pract. Exp. 41(1), 23\u201350 (2011)","journal-title":"Softw. Pract. Exp."},{"doi-asserted-by":"crossref","unstructured":"Casanova, H.: Simgrid: a toolkit for the simulation of application scheduling. In: CC Grid, pp. 430\u2013437 (2001)","key":"13_CR9","DOI":"10.1109\/CCGRID.2001.923223"},{"doi-asserted-by":"crossref","unstructured":"Casanova, H.: Modeling large-scale platforms for the analysis and the simulation of scheduling strategies. In: 18th International Parallel and Distributed Processing Symposium, 2004. Proceedings. p. 170 (2004)","key":"13_CR10","DOI":"10.1109\/IPDPS.2004.1303169"},{"issue":"10","key":"13_CR11","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1145\/1103845.1094852","volume":"40","author":"P Charles","year":"2005","unstructured":"Charles, P., et al.: X10: an object-oriented approach to non-uniform cluster computing. SIGPLAN Notices 40(10), 519\u2013538 (2005)","journal-title":"SIGPLAN Notices"},{"key":"13_CR12","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.simpat.2017.05.009","volume":"77","author":"P Czarnul","year":"2017","unstructured":"Czarnul, P., et al.: MERPSYS: an environment for simulation of parallel application execution on large scale HPC systems. Simul. Model. Pract. Theory 77, 124\u2013140 (2017)","journal-title":"Simul. Model. Pract. Theory"},{"doi-asserted-by":"crossref","unstructured":"Daoudi, I., Virouleau, P., Gautier, T., Thibault, S., Aumage, O.: sOMP: simulating OpenMP task-based applications with NUMA effects. In: IWOMP 2020, pp. 197\u2013211 (2020)","key":"13_CR13","DOI":"10.1007\/978-3-030-58144-2_13"},{"issue":"6","key":"13_CR14","doi-asserted-by":"publisher","first-page":"1374","DOI":"10.1109\/TPDS.2018.2883056","volume":"30","author":"N Denoyelle","year":"2019","unstructured":"Denoyelle, N., Goglin, B., Ilic, A., Jeannot, E., Sousa, L.: Modeling non-uniform memory access on large compute nodes with the cache-aware roofline model. IEEE Trans. Parallel Distrib. Syst. 30(6), 1374\u20131389 (2019)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"13_CR15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.future.2013.04.014","volume":"30","author":"C Engelmann","year":"2014","unstructured":"Engelmann, C.: Scaling to a million cores and beyond: using light-weight simulation to understand the challenges ahead on the road to exascale. Futur. Gener. Comput. Syst. 30, 59\u201365 (2014)","journal-title":"Futur. Gener. Comput. Syst."},{"unstructured":"Galilee, F., Cavalheiro, G., Roch, J.L., Doreille, M.: Athapascan-1: on-line building data flow graph in a parallel language. In: PACT (1998)","key":"13_CR16"},{"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: Proceedings of the 2007 International Workshop on Parallel Symbolic Computation. PASCO 2007 (2007)","key":"13_CR17","DOI":"10.1145\/1278177.1278182"},{"doi-asserted-by":"crossref","unstructured":"Gautier, T., Lima, J.V., Maillard, N., Raffin, B.: Xkaapi: A runtime system for data-flow task programming on heterogeneous architectures. In: IPDPS. IEEE (2013)","key":"13_CR18","DOI":"10.1109\/IPDPS.2013.66"},{"key":"13_CR19","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1023\/A:1026567408307","volume":"17","author":"S Girona","year":"2000","unstructured":"Girona, S., Labarta, J.: Sensitivity of performance prediction of message passing programs. J. Supercomputing 17, 291\u2013298 (2000)","journal-title":"J. Supercomputing"},{"unstructured":"Haugen, B.: Performance analysis and modeling of task-based runtimes, Ph.D. thesis (2016)","key":"13_CR20"},{"doi-asserted-by":"crossref","unstructured":"Haugen, B., Kurzak, J., YarKhan, A., Luszczek, P., Dongarra, J.: Parallel simulation of superscalar scheduling. In: ICPP, pp. 121\u2013130 (2014)","key":"13_CR21","DOI":"10.1109\/ICPP.2014.21"},{"unstructured":"Heinrich, F.: Modeling, prediction and optimization of energy consumption of MPI applications using SimGrid, Theses, Universit\u00e9 Grenoble Alpes (2019)","key":"13_CR22"},{"key":"13_CR23","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1007\/s11227-010-0504-1","volume":"62","author":"D Kliazovich","year":"2012","unstructured":"Kliazovich, D., Bouvry, P., Khan, S.U.: Greencloud: a packet-level simulator of energy-aware cloud computing data centers. J. Supercomput. 62, 1263\u20131283 (2012)","journal-title":"J. Supercomput."},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: SimNUMA: simulating NUMA-architecture multiprocessor systems efficiently. In: ICPDS (2013)","key":"13_CR24","DOI":"10.1109\/ICPADS.2013.55"},{"doi-asserted-by":"crossref","unstructured":"Mohammed, A., Eleliemy, A., Ciorba, F.M., Kasielke, F., Banicescu, I.: Experimental verification and analysis of dynamic loop scheduling in scientific applications. In: ISPDC. IEEE (2018)","key":"13_CR25","DOI":"10.1109\/ISPDC2018.2018.00028"},{"issue":"2","key":"13_CR26","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1177\/1094342011434065","volume":"26","author":"SL Olivier","year":"2012","unstructured":"Olivier, S.L., Porterfield, A.K., Wheeler, K.B., Spiegel, M., Prins, J.F.: OpenMP task scheduling strategies for multicore NUMA systems. Int. J. High Perform. Comput. Appl. 26(2), 110\u2013124 (2012)","journal-title":"Int. J. High Perform. Comput. Appl."},{"doi-asserted-by":"crossref","unstructured":"Rico, A., Duran, A., Cabarcas, F., Etsion, Y., Ramirez, A., Valero, M.: Trace-driven simulation of multithreaded applications. In: International Symposium on Performance Analysis of Systems and Software (2011)","key":"13_CR27","DOI":"10.1109\/ISPASS.2011.5762718"},{"issue":"8","key":"13_CR28","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1145\/3155284.3018770","volume":"52","author":"S Shudler","year":"2017","unstructured":"Shudler, S., Calotoiu, A., Hoefler, T., Wolf, F.: Isoefficiency in practice: configuring and understanding the performance of task-based applications. SIGPLAN Notices 52(8), 131\u2013143 (2017)","journal-title":"SIGPLAN Notices"},{"doi-asserted-by":"crossref","unstructured":"Stanisic, L., et al.: Fast and accurate simulation of multithreaded sparse linear algebra solvers. In: ICPDS. Melbourne, Australia (2015)","key":"13_CR29","DOI":"10.1109\/ICPADS.2015.67"},{"issue":"16","key":"13_CR30","doi-asserted-by":"publisher","first-page":"4075","DOI":"10.1002\/cpe.3555","volume":"27","author":"L Stanisic","year":"2015","unstructured":"Stanisic, L., Thibault, S., Legrand, A., Videau, B., M\u00e9haut, J.F.: Faithful performance prediction of a dynamic task-based runtime system for heterogeneous multi-core architectures. Concurr. Comput. Pract. Exp. 27(16), 4075\u20134090 (2015)","journal-title":"Concurr. Comput. Pract. Exp."},{"issue":"1","key":"13_CR31","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.peva.2004.10.003","volume":"60","author":"J Tao","year":"2005","unstructured":"Tao, J., Schulz, M., Karl, W.: Simulation as a tool for optimizing memory accesses on NUMA machines. Perform. Eval. 60(1), 31\u201350 (2005)","journal-title":"Perform. Eval."},{"doi-asserted-by":"crossref","unstructured":"Virouleau, P., Broquedis, F., Gautier, T., Rastello, F.: Using data dependencies to improve task-based scheduling strategies on NUMA architectures. In: ECPP (2016)","key":"13_CR32","DOI":"10.1007\/978-3-319-43659-3_39"},{"key":"13_CR33","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). https:\/\/doi.org\/10.1007\/978-3-319-11454-5_2"},{"unstructured":"Zheng, G., Kakulapati, G., Kal\u00e9, L.V.: Bigsim: A parallel simulator for performance prediction of extremely large parallel machines. In: IPDPS, p. 78. IEEE (2004)","key":"13_CR34"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Advanced Task-Based, Device and Compiler Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40744-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T06:14:24Z","timestamp":1730009664000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40744-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031407437","9783031407444"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40744-4_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWOMP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on OpenMP","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bristol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iwomp.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"75% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}