{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T01:40:06Z","timestamp":1778550006988,"version":"3.51.4"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030256357","type":"print"},{"value":"9783030256364","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-25636-4_16","type":"book-chapter","created":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:04:09Z","timestamp":1564617849000},"page":"199-213","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["GPU Implementation of ConeTorre Algorithm for Fluid Dynamics Simulation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3623-0556","authenticated-orcid":false,"given":"Vadim","family":"Levchenko","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7346-6635","authenticated-orcid":false,"given":"Andrey","family":"Zakirov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2517-6064","authenticated-orcid":false,"given":"Anastasia","family":"Perepelkina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,17]]},"reference":[{"key":"16_CR1","unstructured":"Computer system K-60 (2018). http:\/\/kiam.ru\/MVS\/resourses\/k60.html"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Bailey, P., Myre, J., Walsh, S.D., Lilja, D.J., Saar, M.O.: Accelerating lattice Boltzmann fluid flow simulations using graphics processors. In: International Conference on Parallel Processing, ICPP 2009, pp. 550\u2013557. IEEE (2009)","DOI":"10.1109\/ICPP.2009.38"},{"key":"16_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.parco.2016.08.005","volume":"58","author":"E Calore","year":"2016","unstructured":"Calore, E., Gabbana, A., Kraus, J., Pellegrini, E., Schifano, S.F., Tripiccione, R.: Massively parallel lattice-boltzmann codes on large GPU clusters. Parallel Comput. 58, 1\u201324 (2016)","journal-title":"Parallel Comput."},{"key":"16_CR4","unstructured":"Degenhardt, R.: Advanced Lattice Boltzmann Models for the Simulation of Additive Manufacturing Processes. doctoralthesis, Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU) (2017)"},{"key":"16_CR5","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-981-13-1924-2_12","volume-title":"Advanced Software Technologies for Post-Peta Scale Computing","author":"T Endo","year":"2019","unstructured":"Endo, T., Midorikawa, H., Sato, Y.: Software technology that deals with deeper memory hierarchy in post-petascale era. In: Sato, M. (ed.) Advanced Software Technologies for Post-Peta Scale Computing, pp. 227\u2013248. Springer, Singapore (2019). https:\/\/doi.org\/10.1007\/978-981-13-1924-2_12"},{"key":"16_CR6","unstructured":"Habich, J., Zeiser, T., Hager, G., Wellein, G.: Enabling temporal blocking for a lattice Boltzmann flow solver through multicore-aware wavefront parallelization. In: 21st International Conference on Parallel Computational Fluid Dynamics, pp. 178\u2013182 (2009)"},{"issue":"3","key":"16_CR7","doi-asserted-by":"publisher","first-page":"29","DOI":"10.3390\/computation4030029","volume":"4","author":"V Levchenko","year":"2016","unstructured":"Levchenko, V., Perepelkina, A., Zakirov, A.: Diamondtorre algorithm for high-performance wave modeling. Computation 4(3), 29 (2016)","journal-title":"Computation"},{"issue":"4","key":"16_CR8","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1134\/S1995080218040108","volume":"39","author":"V Levchenko","year":"2018","unstructured":"Levchenko, V., Perepelkina, A.: Locally recursive non-locally asynchronous algorithms for stencil computation. Lobachevskii J. Math. 39(4), 552\u2013561 (2018)","journal-title":"Lobachevskii J. Math."},{"issue":"4","key":"16_CR9","doi-asserted-by":"publisher","first-page":"C439","DOI":"10.1137\/140991133","volume":"37","author":"T Malas","year":"2015","unstructured":"Malas, T., Hager, G., Ltaief, H., Stengel, H., Wellein, G., Keyes, D.: Multicore-optimized wavefront diamond blocking for optimizing stencil updates. SIAM J. Sci. Comput. 37(4), C439\u2013C464 (2015)","journal-title":"SIAM J. Sci. Comput."},{"key":"16_CR10","unstructured":"Maruyama, N., Aoki, T.: Optimizing stencil computations for NVIDIA kepler GPUs. In: Proceedings of the 1st International Workshop on High-Performance Stencil Computations, Vienna, pp. 89\u201395 (2014)"},{"key":"16_CR11","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/B978-0-12-811718-7.00020-4","volume-title":"Numerical Methods and Advanced Simulation in Biomechanics and Biological Processes","author":"A. Montessori","year":"2018","unstructured":"Montessori, A., et al.: Chapter 20 - multicomponent lattice Boltzmann models for biological applications. In: Cerrolaza, M., Shefelbine, S.J., Garz-Alvarado, D. (eds.) Numerical Methods and Advanced Simulation in Biomechanics and Biological Processes, pp. 357\u2013370. Academic Press (2018). https:\/\/doi.org\/10.1016\/B978-0-12-811718-7.00020-4 , http:\/\/www.sciencedirect.com\/science\/article\/pii\/B9780128117187000204"},{"key":"16_CR12","unstructured":"Morton, G.M.: A computer oriented geodetic data base and a new technique in file sequencing (1966)"},{"key":"16_CR13","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: High Performance Computing, Networking, Storage and Analysis (SC), pp. 1\u201313. IEEE (2010)","DOI":"10.1109\/SC.2010.2"},{"key":"16_CR14","unstructured":"Niedermeier, C.A., Jan\u00dfen, C.F., Indinger, T.: Massively-parallel multi-GPU simulations for fast and accurate automotive aerodynamics. In: 7th European Conference on Computational Fluid Dynamics (2018)"},{"key":"16_CR15","doi-asserted-by":"publisher","first-page":"012042","DOI":"10.1088\/1742-6596\/510\/1\/012042","volume":"510","author":"AY Perepelkina","year":"2014","unstructured":"Perepelkina, A.Y., Levchenko, V.D., Goryachev, I.A.: Implementation of the kinetic plasma code with locally recursive non-locally asynchronous algorithms. J. Phys. Conf. Ser. 510, 012042 (2014)","journal-title":"J. Phys. Conf. Ser."},{"key":"16_CR16","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/978-3-030-05807-4_9","volume-title":"Supercomputing","author":"A Perepelkina","year":"2019","unstructured":"Perepelkina, A., Levchenko, V.: LRnLA algorithm ConeFold with non-local vectorization for LBM implementation. In: Voevodin, V., Sobolev, S. (eds.) RuSCDays 2018. CCIS, vol. 965, pp. 101\u2013113. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-05807-4_9"},{"key":"16_CR17","doi-asserted-by":"publisher","unstructured":"Perepelkina, A., Levchenko, V., Khilkov, S.: The DiamondCandy LRnLA algorithm: raising efficiency of the 3D cross-stencil schemes. J. Supercomputing (2018). https:\/\/doi.org\/10.1007\/s11227-018-2461-z","DOI":"10.1007\/s11227-018-2461-z"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Perepelkina, A., Levchenko, V.: The DiamondCandy algorithm for maximum performance vectorized cross-stencil computation. Keldysh Institute Preprints (225) (2018)","DOI":"10.20948\/prepr-2018-225-e"},{"issue":"4","key":"16_CR19","doi-asserted-by":"publisher","first-page":"48","DOI":"10.3390\/computation5040048","volume":"5","author":"C Riesinger","year":"2017","unstructured":"Riesinger, C., Bakhtiari, A., Schreiber, M., Neumann, P., Bungartz, H.J.: A holistic scalable implementation approach of the lattice Boltzmann method for CPU\/GPU heterogeneous clusters. Computation 5(4), 48 (2017)","journal-title":"Computation"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Shimokawabe, T., Endo, T., Onodera, N., Aoki, T.: A stencil framework to realize large-scale computations beyond device memory capacity on GPU supercomputers. In: 2017 IEEE International Conference on Cluster Computing (CLUSTER), pp. 525\u2013529. IEEE (2017)","DOI":"10.1109\/CLUSTER.2017.97"},{"key":"16_CR21","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198503989.001.0001","volume-title":"The Lattice Boltzmann Equation: For Fluid Dynamics And Beyond","author":"S Succi","year":"2001","unstructured":"Succi, S.: The Lattice Boltzmann Equation: For Fluid Dynamics And Beyond. Oxford University Press, Oxford (2001)"},{"key":"16_CR22","unstructured":"Tomczak, T., Szafran, R.G.: A new GPU implementation for lattice-Boltzmann simulations on sparse geometries. arXiv preprint arXiv:1611.02445 (2016)"},{"key":"16_CR23","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":"16_CR24","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":"16_CR25","unstructured":"Wittmann, M.: Hardware-effiziente, hochparallele implementierungen von lattice-boltzmann-verfahren f\u00fcr komplexe geometrien (2016)"},{"key":"16_CR26","doi-asserted-by":"publisher","first-page":"012100","DOI":"10.1088\/1742-6596\/759\/1\/012100","volume":"759","author":"A Zakirov","year":"2016","unstructured":"Zakirov, A., Levchenko, V., Perepelkina, A., Zempo, Y.: High performance FDTD algorithm for GPGPU supercomputers. J. Phys. Conf. Ser. 759, 012100 (2016)","journal-title":"J. Phys. Conf. Ser."}],"container-title":["Lecture Notes in Computer Science","Parallel Computing Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-25636-4_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T15:35:26Z","timestamp":1721576126000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-25636-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030256357","9783030256364"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-25636-4_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"17 July 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PaCT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Computing Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Almaty","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kazakhstan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pact2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ssd.sscc.ru\/conference\/pact2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}