{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T15:36:48Z","timestamp":1759073808127,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031725661"},{"type":"electronic","value":"9783031725678"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72567-8_9","type":"book-chapter","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:19:25Z","timestamp":1726762765000},"page":"126-140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Evaluation of\u00a0Directive-Based Programming Models for Stencil Computation on Current GPGPU Architectures"],"prefix":"10.1007","author":[{"given":"Baodi","family":"Shan","sequence":"first","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":[[2024,9,16]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","unstructured":"Bak, S., et al.: OpenMP application experiences: porting to accelerated nodes. Parallel Comput. 109, 102856 (2022). https:\/\/doi.org\/10.1016\/j.parco.2021.102856","DOI":"10.1016\/j.parco.2021.102856"},{"key":"9_CR2","doi-asserted-by":"publisher","first-page":"22136","DOI":"10.1109\/ACCESS.2023.3252002","volume":"11","author":"A Denzler","year":"2023","unstructured":"Denzler, A., et al.: Casper: accelerating stencil computations using near-cache processing. IEEE Access 11, 22136\u201322154 (2023)","journal-title":"IEEE Access"},{"key":"9_CR3","doi-asserted-by":"publisher","unstructured":"Dubey, A.: Stencils in scientific computations. In: Proceedings of the Second Workshop on Optimizing Stencil Computations, p.\u00a057. WOSC \u201914, Association for Computing Machinery, New York, NY, USA (2014). https:\/\/doi.org\/10.1145\/2686745.2686756","DOI":"10.1145\/2686745.2686756"},{"key":"9_CR4","doi-asserted-by":"publisher","unstructured":"Fuhrer, O., et al.: Towards a performance portable, architecture agnostic implementation strategy for weather and climate models. Supercomput. Front. Innov. Int. J. 1(1), 45\u201362 (2014). https:\/\/doi.org\/10.14529\/jsfi140103","DOI":"10.14529\/jsfi140103"},{"key":"9_CR5","doi-asserted-by":"publisher","unstructured":"Grosser, T., Cohen, A., Kelly, P.H.J., Ramanujam, J., Sadayappan, P., Verdoolaege, S.: Split tiling for GPUs: automatic parallelization using trapezoidal tiles. In: Proceedings of the 6th Workshop on General Purpose Processor Using Graphics Processing Units, pp. 24\u201331. GPGPU-6, Association for Computing Machinery, New York, NY, USA (2013). https:\/\/doi.org\/10.1145\/2458523.2458526","DOI":"10.1145\/2458523.2458526"},{"key":"9_CR6","doi-asserted-by":"publisher","unstructured":"Holewinski, J., Pouchet, L.N., Sadayappan, P.: High-performance code generation for stencil computations on GPU architectures. In: Proceedings of the 26th ACM International Conference on Supercomputing, pp. 311\u2013320. ICS \u201912, Association for Computing Machinery, New York, NY, USA (2012).https:\/\/doi.org\/10.1145\/2304576.2304619","DOI":"10.1145\/2304576.2304619"},{"key":"9_CR7","doi-asserted-by":"publisher","unstructured":"Jacquelin, M., Araya-Polo, M., Meng, J.: Scalable distributed high-order stencil computations. In: SC22: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201313. IEEE (2022). https:\/\/doi.org\/10.1109\/SC41404.2022.00035","DOI":"10.1109\/SC41404.2022.00035"},{"key":"9_CR8","doi-asserted-by":"publisher","unstructured":"Krishnamoorthy, S., Baskaran, M., Bondhugula, U., Ramanujam, J., Rountev, A., Sadayappan, P.: Effective automatic parallelization of stencil computations. In: Proceedings of the 28th ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 235\u2013244. PLDI \u201907, Association for Computing Machinery, New York, NY, USA (2007). https:\/\/doi.org\/10.1145\/1250734.1250761","DOI":"10.1145\/1250734.1250761"},{"key":"9_CR9","doi-asserted-by":"publisher","unstructured":"Lu, W., et al.: Towards efficient remote OpenMP offloading. In: Klemm, M., de Supinski, B.R., Klinkenberg, J., Neth, B. (eds.) OpenMP in a Modern World: From Multi-device Support to Meta Programming. IWOMP 2022. LNCS, vol. 13527, pp. 17\u201331. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15922-0_2","DOI":"10.1007\/978-3-031-15922-0_2"},{"key":"9_CR10","unstructured":"Meng, J., Atle, A., Calandra, H., Araya-Polo, M.: Minimod: a finite difference solver for seismic modeling (2020)"},{"key":"9_CR11","doi-asserted-by":"publisher","unstructured":"Moczo, P., Kristek, J., G\u00e1lis, M.: The Finite-Difference Modelling of Earthquake Motions: Waves and Ruptures. Cambridge University Press, Cambridge (2014). https:\/\/doi.org\/10.1017\/CBO9781139236911","DOI":"10.1017\/CBO9781139236911"},{"key":"9_CR12","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\u201910: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201313. IEEE (2010)","DOI":"10.1109\/SC.2010.2"},{"key":"9_CR13","unstructured":"OpenACC-Standard.org: Openacc (2023). https:\/\/www.openacc.org\/. Accessed 14 Aug 2023"},{"key":"9_CR14","unstructured":"OpenMP.org: Openmp (2023). https:\/\/www.openmp.org\/. Accessed 14 Aug 2023"},{"key":"9_CR15","doi-asserted-by":"publisher","unstructured":"Sai, R., Mellor-Crummey, J., Meng, X., Araya-Polo, M., Meng, J.: Accelerating high-order stencils on GPUs. In: 2020 IEEE\/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS), pp. 86\u2013108 (2020). https:\/\/doi.org\/10.1109\/PMBS51919.2020.00014","DOI":"10.1109\/PMBS51919.2020.00014"},{"key":"9_CR16","unstructured":"Shan, B., Araya-Polo, M.: Evaluation of programming models and performance for stencil computation on current GPU architectures (2024). https:\/\/arxiv.org\/abs\/2404.04441"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Shan, B., Araya-Polo, M., Malik, A.M., Chapman, B.: MPI-based remote OpenMP offloading: a more efficient and easy-to-use implementation. In: Proceedings of the 14th International Workshop on Programming Models and Applications for Multicores and Manycores, pp. 50\u201359. PMAM\u201923 (2023). https:\/\/doi.org\/10.1145\/3582514.3582519","DOI":"10.1145\/3582514.3582519"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Sun, B., Li, M., Yang, H., Xu, J., Luan, Z., Qian, D.: Adapting combined tiling to stencil optimizations on sunway processor. CCF Trans. High Perform. Comput. 1\u201312 (2023)","DOI":"10.1007\/s42514-023-00147-x"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Sun, Q., Liu, Y., Yang, H., Jiang, Z., Luan, Z., Qian, D.: StencilMART: predicting optimization selection for stencil computations across GPUs. In: 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 875\u2013885. IEEE (2022)","DOI":"10.1109\/IPDPS53621.2022.00090"},{"key":"9_CR20","doi-asserted-by":"publisher","unstructured":"Tylor-Jones, T., Azevedo, L.: A Practical Guide to Seismic Reservoir Characterization. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-030-99854-7","DOI":"10.1007\/978-3-030-99854-7"},{"key":"9_CR21","doi-asserted-by":"publisher","unstructured":"Wonnacott, D.: Using time skewing to eliminate idle time due to memory bandwidth and network limitations. In: Proceedings 14th International Parallel and Distributed Processing Symposium. IPDPS 2000, pp. 171\u2013180 (2000). https:\/\/doi.org\/10.1109\/IPDPS.2000.845979","DOI":"10.1109\/IPDPS.2000.845979"},{"key":"9_CR22","doi-asserted-by":"publisher","unstructured":"Wonnacott, D.: Achieving scalable locality with time skewing. Int. J. Parallel Program. 30 (1999). https:\/\/doi.org\/10.1023\/A:1015460304860","DOI":"10.1023\/A:1015460304860"}],"container-title":["Lecture Notes in Computer Science","Advancing OpenMP for Future Accelerators"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72567-8_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:21:13Z","timestamp":1726762873000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72567-8_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031725661","9783031725678"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72567-8_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"16 September 2024","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":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2024","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"}}]}}