{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:14:34Z","timestamp":1743023674574,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030581435"},{"type":"electronic","value":"9783030581442"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58144-2_5","type":"book-chapter","created":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T12:03:48Z","timestamp":1598961828000},"page":"67-81","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Evaluating Performance of OpenMP Tasks in a Seismic Stencil Application"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8091-2066","authenticated-orcid":false,"given":"Eric","family":"Raut","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mauricio","family":"Araya-Polo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barbara","family":"Chapman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,1]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Acun, B., et al.: Parallel programming with migratable objects: Charm++ in practice. In: SC 2014: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 647\u2013658 (2014). https:\/\/doi.org\/10.1109\/SC.2014.58","DOI":"10.1109\/SC.2014.58"},{"key":"5_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/978-3-319-65578-9_7","volume-title":"Scaling OpenMP for Exascale Performance and Portability","author":"P Atkinson","year":"2017","unstructured":"Atkinson, P., McIntosh-Smith, S.: On the performance of parallel tasking runtimes for an irregular fast multipole method application. In: de Supinski, B.R., Olivier, S.L., Terboven, C., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2017. LNCS, vol. 10468, pp. 92\u2013106. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-65578-9_7"},{"issue":"2","key":"5_CR3","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1002\/cpe.1631","volume":"23","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. 23(2), 187\u2013198 (2011). https:\/\/doi.org\/10.1002\/cpe.1631","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"5_CR4","doi-asserted-by":"publisher","unstructured":"Bauer, M., Treichler, S., Slaughter, E., Aiken, A.: Legion: expressing locality and independence with logical regions. In: SC 2012: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, pp. 1\u201311, November 2012. https:\/\/doi.org\/10.1109\/SC.2012.71","DOI":"10.1109\/SC.2012.71"},{"issue":"2","key":"5_CR5","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1006\/jcph.1994.1159","volume":"114","author":"JP Berenger","year":"1994","unstructured":"Berenger, J.P.: A perfectly matched layer for the absorption of electromagnetic waves. J. Comput. Phys. 114(2), 185\u2013200 (1994). https:\/\/doi.org\/10.1006\/jcph.1994.1159","journal-title":"J. Comput. Phys."},{"issue":"8","key":"5_CR6","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1145\/209937.209958","volume":"30","author":"RD Blumofe","year":"1995","unstructured":"Blumofe, R.D., Joerg, C.F., Kuszmaul, B.C., Leiserson, C.E., Randall, K.H., Zhou, Y.: Cilk: an efficient multithreaded runtime system. SIGPLAN Not. 30(8), 207\u2013216 (1995). https:\/\/doi.org\/10.1145\/209937.209958","journal-title":"SIGPLAN Not."},{"issue":"6","key":"5_CR7","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MCSE.2013.98","volume":"15","author":"G Bosilca","year":"2013","unstructured":"Bosilca, G., Bouteiller, A., Danalis, A., Faverge, M., Herault, T., Dongarra, J.J.: PaRSEC: exploiting heterogeneity to enhance scalability. Comput. Sci. Eng. 15(6), 36\u201345 (2013). https:\/\/doi.org\/10.1109\/MCSE.2013.98","journal-title":"Comput. Sci. Eng."},{"key":"5_CR8","doi-asserted-by":"publisher","unstructured":"de la Cruz, R., Araya-Polo, M.: Algorithm 942: semi-stencil. ACM Trans. Math. Softw. 40(3) (2014). https:\/\/doi.org\/10.1145\/2591006","DOI":"10.1145\/2591006"},{"key":"5_CR9","doi-asserted-by":"publisher","unstructured":"de la Cruz, R., Araya-Polo, M.: Towards a multi-level cache performance model for 3D stencil computation. Proc. Comput. Sci. 4, 2146 \u20132155 (2011). https:\/\/doi.org\/10.1016\/j.procs.2011.04.235. Proceedings of the International Conference on Computational Science, ICCS 2011","DOI":"10.1016\/j.procs.2011.04.235"},{"key":"5_CR10","doi-asserted-by":"publisher","unstructured":"Delannoy, O., Petiton, S.: A peer to peer computing framework: design and performance evaluation of YML. In: Third International Symposium on Parallel and Distributed Computing\/Third International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Networks, pp. 362\u2013369 (2004). https:\/\/doi.org\/10.1109\/ISPDC.2004.7","DOI":"10.1109\/ISPDC.2004.7"},{"issue":"02","key":"5_CR11","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1142\/S0129626411000151","volume":"21","author":"A Duran","year":"2011","unstructured":"Duran, A., et al.: OmpSs: a proposal for programming heterogeneous multi-core architectures. Parallel Process. Lett. 21(02), 173\u2013193 (2011). https:\/\/doi.org\/10.1142\/S0129626411000151","journal-title":"Parallel Process. Lett."},{"key":"5_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-540-79561-2_9","volume-title":"OpenMP in a New Era of Parallelism","author":"A Duran","year":"2008","unstructured":"Duran, A., Corbal\u00e1n, J., Ayguad\u00e9, E.: Evaluation of OpenMP task scheduling strategies. In: Eigenmann, R., de Supinski, B.R. (eds.) IWOMP 2008. LNCS, vol. 5004, pp. 100\u2013110. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-79561-2_9"},{"key":"5_CR13","doi-asserted-by":"publisher","unstructured":"Ghosh, S., Liao, T., Calandra, H., Chapman, B.M.: Experiences with OpenMP, PGI, HMPP and OpenACC directives on ISO\/TTI kernels. In: 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, pp. 691\u2013700, November 2012. https:\/\/doi.org\/10.1109\/SC.Companion.2012.95","DOI":"10.1109\/SC.Companion.2012.95"},{"key":"5_CR14","doi-asserted-by":"publisher","unstructured":"Gurhem, J., Tsuji, M., Petiton, S.G., Sato, M.: Distributed and parallel programming paradigms on the K computer and a cluster. In: Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2019, pp. 9\u201317. Association for Computing Machinery, New York (2019). https:\/\/doi.org\/10.1145\/3293320.3293330","DOI":"10.1145\/3293320.3293330"},{"key":"5_CR15","doi-asserted-by":"publisher","unstructured":"Kaiser, H., Heller, T., Adelstein-Lelbach, B., Serio, A., Fey, D.: HPX: a task based programming model in a global address space. In: Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models, PGAS 2014. Association for Computing Machinery, New York (2014). https:\/\/doi.org\/10.1145\/2676870.2676883","DOI":"10.1145\/2676870.2676883"},{"key":"5_CR16","doi-asserted-by":"publisher","unstructured":"Klinkenberg, J., Samfass, P., Bader, M., Terboven, C., M\u00fcller, M.S.: Chameleon: reactive load balancing for hybrid MPI + OpenMP task-parallel applications. J. Parallel Distrib. Comput. 138, 55\u201364 (2020). https:\/\/doi.org\/10.1016\/j.jpdc.2019.12.005","DOI":"10.1016\/j.jpdc.2019.12.005"},{"key":"5_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1007\/978-3-319-98521-3_16","volume-title":"Evolving OpenMP for Evolving Architectures","author":"J Klinkenberg","year":"2018","unstructured":"Klinkenberg, J., et al.: Assessing task-to-data affinity in the LLVM OpenMP runtime. In: de Supinski, B.R., Valero-Lara, P., Martorell, X., Mateo Bellido, S., Labarta, J. (eds.) IWOMP 2018. LNCS, vol. 11128, pp. 236\u2013251. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-98521-3_16"},{"key":"5_CR18","doi-asserted-by":"publisher","unstructured":"Lee, J., Sato, M.: Implementation and performance evaluation of XcalableMP: a parallel programming language for distributed memory systems. In: 2010 39th International Conference on Parallel Processing Workshops, pp. 413\u2013420 (2010). https:\/\/doi.org\/10.1109\/ICPPW.2010.62","DOI":"10.1109\/ICPPW.2010.62"},{"key":"5_CR19","doi-asserted-by":"publisher","unstructured":"Louboutin, M., et al.: Devito (v3.1.0): an embedded domain-specific language for finite differences and geophysical exploration. Geosci. Model Dev. 12(3), 1165\u20131187 (2019). https:\/\/doi.org\/10.5194\/gmd-12-1165-2019","DOI":"10.5194\/gmd-12-1165-2019"},{"key":"5_CR20","doi-asserted-by":"publisher","unstructured":"Mellor-Crummey, J., Fowler, R., Whalley, D.: Tools for application-oriented performance tuning. In: Proceedings of the 15th International Conference on Supercomputing, ICS 2001, pp. 154\u2013165. Association for Computing Machinery, New York (2001). https:\/\/doi.org\/10.1145\/377792.377826","DOI":"10.1145\/377792.377826"},{"key":"5_CR21","unstructured":"Meng, J., Atle, A., Calandra, H., Araya-Polo, M.: Minimod: a finite difference solver for seismic modeling. arXiv (2020). https:\/\/arxiv.org\/abs\/2007.06048"},{"key":"5_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1007\/978-3-319-96983-1_54","volume-title":"Euro-Par 2018: Parallel Processing","author":"S Moustafa","year":"2018","unstructured":"Moustafa, S., Kirschenmann, W., Dupros, F., Aochi, H.: Task-based programming on emerging parallel architectures for finite-differences seismic numerical kernel. In: Aldinucci, M., Padovani, L., Torquati, M. (eds.) Euro-Par 2018. LNCS, vol. 11014, pp. 764\u2013777. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-96983-1_54"},{"key":"5_CR23","unstructured":"NERSC: Cori. https:\/\/docs.nersc.gov\/systems\/cori\/"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Satish, N., Chhugani, J., Kim, C., Dubey, P.: 3.5-D blocking optimization for stencil computations on modern CPUs and GPUs. In: SC 2010: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201313 (2010)","DOI":"10.1109\/SC.2010.2"},{"key":"5_CR25","unstructured":"Oak Ridge Leadership Computing Facility: Summit. https:\/\/www.olcf.ornl.gov\/olcf-resources\/compute-systems\/summit\/"},{"key":"5_CR26","unstructured":"OpenMP Architecture Review Board: OpenMP Application Programming Interface, November 2018. https:\/\/www.openmp.org\/wp-content\/uploads\/OpenMP-API-Specification-5.0.pdf. version 5.0"},{"key":"5_CR27","doi-asserted-by":"publisher","unstructured":"Planas, J., Badia, R.M., Ayguad\u00e9, E., Labarta, J.: Hierarchical task-based programming with StarSs. Int. J. High Perform. Comput. Appl. 23(3), 284\u2013299 (2009). https:\/\/doi.org\/10.1177\/1094342009106195","DOI":"10.1177\/1094342009106195"},{"issue":"5","key":"5_CR28","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1177\/1094342016675678","volume":"31","author":"A Qawasmeh","year":"2017","unstructured":"Qawasmeh, A., Hugues, M.R., Calandra, H., Chapman, B.M.: Performance portability in reverse time migration and seismic modelling via OpenACC. Int. J. High Perform. Comput. Appl. 31(5), 422\u2013440 (2017). https:\/\/doi.org\/10.1177\/1094342016675678","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"5_CR29","volume-title":"Intel Threading Building Blocks: Outfitting C++ for Multi-core Processor Parallelism","author":"J Reinders","year":"2007","unstructured":"Reinders, J.: Intel Threading Building Blocks: Outfitting C++ for Multi-core Processor Parallelism. O\u2019Reilly Media, Beijing (2007)"},{"key":"5_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/978-3-030-28596-8_15","volume-title":"OpenMP: Conquering the Full Hardware Spectrum","author":"A Rico","year":"2019","unstructured":"Rico, A., S\u00e1nchez Barrera, I., Joao, J.A., Randall, J., Casas, M., Moret\u00f3, M.: On the benefits of tasking with OpenMP. In: Fan, X., de Supinski, B.R., Sinnen, O., Giacaman, N. (eds.) IWOMP 2019. LNCS, vol. 11718, pp. 217\u2013230. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-28596-8_15"},{"key":"5_CR31","doi-asserted-by":"publisher","unstructured":"Slaughter, E., Lee, W., Treichler, S., Bauer, M., Aiken, A.: Regent: a high-productivity programming language for HPC with logical regions. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2015. Association for Computing Machinery, New York (2015). https:\/\/doi.org\/10.1145\/2807591.2807629","DOI":"10.1145\/2807591.2807629"},{"key":"5_CR32","doi-asserted-by":"publisher","unstructured":"Thaler, F., et al.: Porting the COSMO weather model to manycore CPUs. In: Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2019. Association for Computing Machinery, New York (2019). https:\/\/doi.org\/10.1145\/3324989.3325723","DOI":"10.1145\/3324989.3325723"},{"key":"5_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/978-3-319-24595-9_5","volume-title":"OpenMP: Heterogenous Execution and Data Movements","author":"R Vidal","year":"2015","unstructured":"Vidal, R., et al.: Evaluating the impact of OpenMP 4.0 extensions on relevant parallel workloads. In: Terboven, C., de Supinski, B.R., Reble, P., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2015. LNCS, vol. 9342, pp. 60\u201372. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24595-9_5"},{"key":"5_CR34","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"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Portable Multi-Level Parallelism on Modern Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58144-2_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,23]],"date-time":"2021-04-23T19:29:43Z","timestamp":1619206183000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58144-2_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030581435","9783030581442"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58144-2_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"1 September 2020","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":"Austin, TX","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/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":"25","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":"21","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":"84% - 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":"5","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}