{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:16:07Z","timestamp":1743084967664,"version":"3.40.3"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030692438"},{"type":"electronic","value":"9783030692445"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-69244-5_4","type":"book-chapter","created":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T16:36:12Z","timestamp":1613838972000},"page":"43-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Memory Access Optimization of High-Order CFD Stencil Computations on GPU"],"prefix":"10.1007","author":[{"given":"Shengxiang","family":"Wang","sequence":"first","affiliation":[]},{"given":"Zhuoqian","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yonggang","family":"Che","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,21]]},"reference":[{"issue":"18","key":"4_CR1","doi-asserted-by":"publisher","first-page":"5557","DOI":"10.1002\/cpe.3591","volume":"27","author":"S Tabik","year":"2015","unstructured":"Tabik, S., Peemen, M., Nicol, G., Corporaal, H.: Demystifying the 16 x 16 thread-block for stencils on the GPU. Concurr. Comput. Pract. Exp. 27(18), 5557\u20135573 (2015)","journal-title":"Concurr. Comput. Pract. Exp."},{"issue":"2","key":"4_CR2","first-page":"181","volume":"13","author":"G Peng","year":"2019","unstructured":"Peng, G., Liang, Y., Zhang, Y., Shan, H.: Parallel stencil algorithm based on tessellating. J. Front. Comput. Sci. Technol. 13(2), 181\u2013194 (2019)","journal-title":"J. Front. Comput. Sci. Technol."},{"issue":"4","key":"4_CR3","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/s11704-010-0383-x","volume":"4","author":"X Yang","year":"2010","unstructured":"Yang, X., Liao, X., et al.: TH-1: China\u2019s first petaflop super-computer. Front. Comput. Sci. China 4(4), 445\u2013455 (2010)","journal-title":"Front. Comput. Sci. China"},{"key":"4_CR4","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1016\/j.jcp.2014.08.024","volume":"278","author":"C Xu","year":"2014","unstructured":"Xu, C., Deng, X., et al.: Collaborating CPU and GPU for large-scale high-order CFD simulations with complex grids on the TianHe-1A supercomputer. J. Comput. Phys. 278, 275\u2013297 (2014)","journal-title":"J. Comput. Phys."},{"key":"4_CR5","unstructured":"NVIDIA Corp.: CUDA C Programming Guide v11.0, July 2020"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Falch, T.L., Elster, A.C.: Register caching for stencil computations on GPUs. In: 16th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, pp. 479\u2013486 (2014)","DOI":"10.1109\/SYNASC.2014.70"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Holewinski, J., Pouchet, L.-N., Sadayappan, P.: High-performance code generation for stencil computations on GPU architectures. In: ICS 2012, pp. 311\u2013320 (2012)","DOI":"10.1145\/2304576.2304619"},{"issue":"1","key":"4_CR8","doi-asserted-by":"publisher","first-page":"1020","DOI":"10.1016\/j.jcp.2007.01.023","volume":"225","author":"M Svard","year":"2007","unstructured":"Svard, M., Carpenter, M.H., Nordstrom, J.: A stable high-order finite difference scheme for the compressible Navier-Stokes equations, far-field boundary conditions. J. Comput. Phys. 225(1), 1020\u20131038 (2007)","journal-title":"J. Comput. Phys."},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, W., Che, Y.: GPU acceleration of a high-order CFD program. In: 4th International Conference on High Performance Compilation, Computing and Communications, Guangzhou, China, pp. 123\u2013128 (2020)","DOI":"10.1145\/3407947.3407963"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Lam, M.D., Rothberg, E.E., Wolf, M.E.: The cache performance and optimizations of blocked algorithms. In: ASPLOS 1991, New York, USA, pp. 63\u201374 (1991)","DOI":"10.1145\/106974.106981"},{"issue":"12","key":"4_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00607-018-0613-x","volume":"100","author":"NK Pikle","year":"2018","unstructured":"Pikle, N.K., Sathe, S.R., Vyavahare, A.Y.: High performance iterative elemental product strategy in assembly-free fem on GPU with improved occupancy. Computing 100(12), 1\u201325 (2018). https:\/\/doi.org\/10.1007\/s00607-018-0613-x","journal-title":"Computing"},{"key":"4_CR12","unstructured":"NVIDIA Corp, Kepler Tuning Guide v11.0, July 2020"}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Computing, Applications and Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69244-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,20]],"date-time":"2021-02-20T16:38:30Z","timestamp":1613839110000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69244-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030692438","9783030692445"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69244-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PDCAT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel and Distributed Computing: Applications and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"28 December 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pdcat2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/hpcc.siat.ac.cn\/meeting\/pdcat-paap2020\/index.html","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":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"109","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":"34","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":"31% - 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":"3","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":"6","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)"}}]}}