{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:03:09Z","timestamp":1743105789254,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030602444"},{"type":"electronic","value":"9783030602451"}],"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\/978-3-030-60245-1_27","type":"book-chapter","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T08:06:00Z","timestamp":1601453160000},"page":"386-400","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Performance Modeling of Stencil Computation on SW26010 Processors"],"prefix":"10.1007","author":[{"given":"Yao","family":"Liu","sequence":"first","affiliation":[]},{"given":"Li","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Mengtao","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Xue","sequence":"additional","affiliation":[]},{"given":"Qingting","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Ao, Y., et al.: 26 PFLOPS stencil computations for atmospheric modeling on Sunway TaihuLight. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 535\u2013544. IEEE (2017)","DOI":"10.1109\/IPDPS.2017.9"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Barnes, B.J., Rountree, B., Lowenthal, D.K., Reeves, J., De Supinski, B., Schulz, M.: A regression-based approach to scalability prediction. In: Proceedings of the 22nd Annual International Conference on Supercomputing, pp. 368\u2013377 (2008)","DOI":"10.1145\/1375527.1375580"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Burtscher, M., Kim, B.D., Diamond, J., McCalpin, J., Koesterke, L., Browne, J.: Perfexpert: an easy-to-use performance diagnosis tool for HPC applications. In: SC 2010: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201311. IEEE (2010)","DOI":"10.1109\/SC.2010.41"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Simulating the Wenchuan earthquake with accurate surface topography on Sunway TaihuLight. In: SC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 517\u2013528. IEEE (2018)","DOI":"10.1109\/SC.2018.00043"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Chen, G., Wu, B., Li, D., Shen, X.: Porple: an extensible optimizer for portable data placement on GPU. In: 2014 47th Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 88\u2013100. IEEE (2014)","DOI":"10.1109\/MICRO.2014.20"},{"issue":"1","key":"27_CR6","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1137\/070693199","volume":"51","author":"K Datta","year":"2009","unstructured":"Datta, K., Kamil, S., Williams, S., Oliker, L., Shalf, J., Yelick, K.: Optimization and performance modeling of stencil computations on modern microprocessors. SIAM Rev. 51(1), 129\u2013159 (2009)","journal-title":"SIAM Rev."},{"issue":"1","key":"27_CR7","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1177\/1094342011428142","volume":"26","author":"JM Dennis","year":"2012","unstructured":"Dennis, J.M., et al.: Cam-se: a scalable spectral element dynamical core for the community atmosphere model. Int. J. High Perform. Comput. Appl. 26(1), 74\u201389 (2012)","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"5","key":"27_CR8","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1007\/s00521-018-3496-z","volume":"31","author":"N Ding","year":"2019","unstructured":"Ding, N., Xu, S., Song, Z., Zhang, B., Li, J., Zheng, Z.: Using hardware counter-based performance model to diagnose scaling issues of HPC applications. Neural Comput. Appl. 31(5), 1563\u20131575 (2019). \nhttps:\/\/doi.org\/10.1007\/s00521-018-3496-z","journal-title":"Neural Comput. Appl."},{"issue":"16","key":"27_CR9","doi-asserted-by":"publisher","first-page":"e4468","DOI":"10.1002\/cpe.4468","volume":"30","author":"W Dong","year":"2018","unstructured":"Dong, W., Li, K., Kang, L., Quan, Z., Li, K.: Implementing molecular dynamics simulation on the Sunway TaihuLight system with heterogeneous many-core processors. Concurr. Comput.: Pract. Exp. 30(16), e4468 (2018)","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: Refactoring and optimizing the community atmosphere model (CAM) on the Sunway TaihuLight supercomputer. In: SC 2016: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 969\u2013980. IEEE (2016)","DOI":"10.1109\/SC.2016.82"},{"issue":"7","key":"27_CR11","doi-asserted-by":"publisher","first-page":"072001","DOI":"10.1007\/s11432-016-5588-7","volume":"59","author":"H Fu","year":"2016","unstructured":"Fu, H., et al.: The Sunway TaihuLight supercomputer: system and applications. Sci. China Inf. Sci. 59(7), 072001 (2016). \nhttps:\/\/doi.org\/10.1007\/s11432-016-5588-7","journal-title":"Sci. China Inf. Sci."},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Hoefler, T., Gropp, W., Kramer, W., Snir, M.: Performance modeling for systematic performance tuning. In: SC 2011: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201312. IEEE (2011)","DOI":"10.1145\/2063348.2063356"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Hong, S., Kim, H.: An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness. In: Proceedings of the 36th Annual International Symposium on Computer Architecture, pp. 152\u2013163 (2009)","DOI":"10.1145\/1555815.1555775"},{"key":"27_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-01170-6","volume-title":"Computational Partial Differential Equations: Numerical Methods and Diffpack Programming","author":"HP Langtangen","year":"1999","unstructured":"Langtangen, H.P.: Computational Partial Differential Equations: Numerical Methods and Diffpack Programming, vol. 2. Springer, Berlin (1999). \nhttps:\/\/doi.org\/10.1007\/978-3-662-01170-6"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: swCaffe: a parallel framework for accelerating deep learning applications on Sunway TaihuLight. In: 2018 IEEE International Conference on Cluster Computing (CLUSTER), pp. 413\u2013422. IEEE (2018)","DOI":"10.1109\/CLUSTER.2018.00087"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liao, Q., Sun, J., Hu, M., Liu, L., Zheng, L.: A heterogeneous parallel genetic algorithm based on sw26010 processors. In: 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp. 54\u201361. IEEE (2019)","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2019.00023"},{"key":"27_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/978-3-642-28652-0_6","volume-title":"Compiler Construction","author":"J Shirako","year":"2012","unstructured":"Shirako, J., et al.: Analytical bounds for optimal tile size selection. In: O\u2019Boyle, Michael (ed.) CC 2012. LNCS, vol. 7210, pp. 101\u2013121. Springer, Heidelberg (2012). \nhttps:\/\/doi.org\/10.1007\/978-3-642-28652-0_6"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Vizitiu, A., Itu, L., Ni\u0163\u0103, C., Suciu, C.: Optimized three-dimensional stencil computation on Fermi and Kepler GPUs. In: 2014 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20136. IEEE (2014)","DOI":"10.1109\/HPEC.2014.7040968"},{"issue":"4","key":"27_CR19","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009)","journal-title":"Commun. ACM"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Xu, Z., Lin, J., Matsuoka, S.: Benchmarking sw26010 many-core processor. In: 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 743\u2013752. IEEE (2017)","DOI":"10.1109\/IPDPSW.2017.9"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: 10m-core scalable fully-implicit solver for nonhydrostatic atmospheric dynamics. In: SC 2016: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 57\u201368. IEEE (2016)","DOI":"10.1109\/SC.2016.5"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"You, Y., et al.: Accelerating the 3D elastic wave forward modeling on GPU and MIC. In: 2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum, pp. 1088\u20131096. IEEE (2013)","DOI":"10.1109\/IPDPSW.2013.216"},{"key":"27_CR23","unstructured":"Zhang, G., Zhao, Y.: Modeling the performance of 2.5 d blocking of 3D stencil code on GPUs. In: IEEE High Performance Extreme Computing Conference, HPEC (2016)"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Extreme-scale phase field simulations of coarsening dynamics on the Sunway TaihuLight supercomputer. In: SC 2016: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 34\u201345. IEEE (2016)","DOI":"10.1109\/SC.2016.3"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60245-1_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T08:27:05Z","timestamp":1601454425000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60245-1_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602444","9783030602451"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60245-1_27","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":"29 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New York, NY","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":"2 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2020","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":"ica3pp2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cloud-conf.net\/ica3pp2020\/","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":"495","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":"142","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":"5","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":"29% - 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":"305","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":"10","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)"}}]}}