{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:14:19Z","timestamp":1743081259337,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319780238"},{"type":"electronic","value":"9783319780245"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-78024-5_45","type":"book-chapter","created":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T08:28:25Z","timestamp":1521707305000},"page":"519-530","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Early Experience on Using Knights Landing Processors for Lattice Boltzmann Applications"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2301-3838","authenticated-orcid":false,"given":"Enrico","family":"Calore","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8367-6596","authenticated-orcid":false,"given":"Alessandro","family":"Gabbana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0132-9196","authenticated-orcid":false,"given":"Sebastiano Fabio","family":"Schifano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8516-2492","authenticated-orcid":false,"given":"Raffaele","family":"Tripiccione","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,3,23]]},"reference":[{"key":"45_CR1","doi-asserted-by":"publisher","unstructured":"Tang, P., et al.: An implementation and optimization of lattice Boltzmann method based on the multi-node CPU+MIC heterogeneous architecture. In: International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), pp. 315\u2013320 (2016). \n                      https:\/\/doi.org\/10.1109\/CyberC.2016.67","DOI":"10.1109\/CyberC.2016.67"},{"key":"45_CR2","doi-asserted-by":"publisher","unstructured":"Calore, E., et al.: Optimization of Lattice Boltzmann simulations on heterogeneous computers. Int. J. High Perform. Comput. Appl. 1\u201316 (2017). \n                      https:\/\/doi.org\/10.1177\/1094342017703771","DOI":"10.1177\/1094342017703771"},{"key":"45_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/978-3-319-46079-6_22","volume-title":"High Performance Computing","author":"C Rosales","year":"2016","unstructured":"Rosales, C., Cazes, J., Milfeld, K., G\u00f3mez-Iglesias, A., Koesterke, L., Huang, L., Vienne, J.: A comparative study of application performance and scalability on the intel knights landing processor. In: Taufer, M., Mohr, B., Kunkel, J.M. (eds.) ISC High Performance 2016. LNCS, vol. 9945, pp. 307\u2013318. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46079-6_22"},{"key":"45_CR4","doi-asserted-by":"publisher","unstructured":"Li, S., et al.: Enhancing application performance using heterogeneous memory architectures on a many-core platform. In: International Conference on High Performance Computing Simulation (HPCS), pp. 1035\u20131042 (2016). \n                      https:\/\/doi.org\/10.1109\/HPCSim.2016.7568455","DOI":"10.1109\/HPCSim.2016.7568455"},{"key":"45_CR5","doi-asserted-by":"crossref","unstructured":"Rucci, E., et al.: First Experiences Optimizing Smith-Waterman on Intel\u2019s Knights Landing Processor. ArXiv e-prints, February 2017","DOI":"10.1007\/978-3-319-65482-9_42"},{"key":"45_CR6","unstructured":"Wittmann, M., et al.: Comparison of different propagation steps for the lattice Boltzmann method. CoRR abs\/1111.0922 (2011)"},{"key":"45_CR7","doi-asserted-by":"publisher","first-page":"013314","DOI":"10.1103\/PhysRevE.88.013314","volume":"88","author":"AG Shet","year":"2013","unstructured":"Shet, A.G., et al.: Data structure and movement for lattice-based simulations. Phys. Rev. E 88, 013314 (2013). \n                      https:\/\/doi.org\/10.1103\/PhysRevE.88.013314","journal-title":"Phys. Rev. E"},{"key":"45_CR8","doi-asserted-by":"publisher","first-page":"1340011","DOI":"10.1142\/S0129183113400111","volume":"24","author":"AG Shet","year":"2013","unstructured":"Shet, A.G., et al.: On vectorization for lattice based simulations. Int. J. Mod. Phys. C 24, 1340011 (2013). \n                      https:\/\/doi.org\/10.1142\/S0129183113400111","journal-title":"Int. J. Mod. Phys. C"},{"key":"45_CR9","unstructured":"McCalpin, J.D.: Stream: sustainable memory bandwidth in high performance computers (2017). \n                      https:\/\/www.cs.virginia.edu\/stream\/"},{"key":"45_CR10","unstructured":"Colfax: Clustering modes in knights landing processors (2017). \n                      https:\/\/colfaxresearch.com\/knl-numa\/"},{"key":"45_CR11","unstructured":"Colfax: MCDRAM as high-bandwidth memory (HBM) in knights landing processors: developers guide (2017). \n                      https:\/\/colfaxresearch.com\/knl-mcdram\/"},{"issue":"2","key":"45_CR12","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/MM.2016.25","volume":"36","author":"A Sodani","year":"2016","unstructured":"Sodani, A., et al.: Knights landing: second-generation Intel Xeon Phi product. IEEE Micro 36(2), 34\u201346 (2016). \n                      https:\/\/doi.org\/10.1109\/MM.2016.25","journal-title":"IEEE Micro"},{"key":"45_CR13","volume-title":"The Lattice-Boltzmann Equation","author":"S Succi","year":"2001","unstructured":"Succi, S.: The Lattice-Boltzmann Equation. Oxford University Press, Oxford (2001)"},{"key":"45_CR14","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1017\/S002211200900665X","volume":"628","author":"M Sbragaglia","year":"2009","unstructured":"Sbragaglia, M., et al.: Lattice Boltzmann method with self-consistent thermo-hydrodynamic equilibria. J. Fluid Mech. 628, 299\u2013309 (2009). \n                      https:\/\/doi.org\/10.1017\/S002211200900665X","journal-title":"J. Fluid Mech."},{"issue":"5","key":"45_CR15","doi-asserted-by":"publisher","first-page":"055101","DOI":"10.1063\/1.3392774","volume":"22","author":"A Scagliarini","year":"2010","unstructured":"Scagliarini, A., et al.: Lattice Boltzmann methods for thermal flows: continuum limit and applications to compressible Rayleigh-Taylor systems. Phys. Fluids 22(5), 055101 (2010). \n                      https:\/\/doi.org\/10.1063\/1.3392774","journal-title":"Phys. Fluids"},{"issue":"1","key":"45_CR16","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1016\/j.procs.2010.04.119","volume":"1","author":"L Biferale","year":"2010","unstructured":"Biferale, L., Mantovani, F., Pivanti, M., Sbragaglia, M., Scagliarini, A., Schifano, S.F., Toschi, F., Tripiccione, R.: Lattice Boltzmann fluid-dynamics on the QPACE supercomputer. Proc. Comput. Sci. 1(1), 1075\u20131082 (2010). \n                      https:\/\/doi.org\/10.1016\/j.procs.2010.04.119","journal-title":"Proc. Comput. Sci."},{"issue":"1","key":"45_CR17","doi-asserted-by":"publisher","first-page":"016305","DOI":"10.1103\/PhysRevE.84.016305","volume":"84","author":"L Biferale","year":"2011","unstructured":"Biferale, L., et al.: Second-order closure in stratified turbulence: simulations and modeling of bulk and entrainment regions. Phys. Rev. E 84(1), 016305 (2011). \n                      https:\/\/doi.org\/10.1103\/PhysRevE.84.016305","journal-title":"Phys. Rev. E"},{"key":"45_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-319-32149-3_6","volume-title":"Parallel Processing and Applied Mathematics","author":"E Calore","year":"2016","unstructured":"Calore, E., Demo, N., Schifano, S.F., Tripiccione, R.: Experience on vectorizing lattice Boltzmann kernels for multi- and many-core architectures. In: Wyrzykowski, R., Deelman, E., Dongarra, J., Karczewski, K., Kitowski, J., Wiatr, K. (eds.) PPAM 2015. LNCS, vol. 9573, pp. 53\u201362. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-32149-3_6"},{"key":"45_CR19","doi-asserted-by":"publisher","unstructured":"Jeffers, J., et al.: Intel Xeon Phi Processor High Performance Programming, 2nd edn, pp. 213\u2013250. Morgan Kaufmann, Boston (2016). \n                      https:\/\/doi.org\/10.1016\/B978-0-12-809194-4.00010-7","DOI":"10.1016\/B978-0-12-809194-4.00010-7"},{"key":"45_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/cpe.4143","volume":"29","author":"E Calore","year":"2017","unstructured":"Calore, E., et al.: Evaluation of DVFS techniques on modern HPC processors and accelerators for energy-aware applications. Concurr. Comput.: Pract. Exp. 29, 1\u201319 (2017). \n                      https:\/\/doi.org\/10.1002\/cpe.4143","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"45_CR21","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/j.procs.2013.05.219","volume":"18","author":"G Crimi","year":"2013","unstructured":"Crimi, G., et al.: Early experience on porting and running a lattice Boltzmann code on the Xeon-Phi co-processor. Proc. Comput. Sci. 18, 551\u2013560 (2013). \n                      https:\/\/doi.org\/10.1016\/j.procs.2013.05.219","journal-title":"Proc. Comput. Sci."},{"key":"45_CR22","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.compfluid.2012.06.003","volume":"80","author":"L Biferale","year":"2013","unstructured":"Biferale, L., et al.: An optimized D2Q37 lattice Boltzmann code on GP-GPUs. Comput. Fluids 80, 55\u201362 (2013). \n                      https:\/\/doi.org\/10.1016\/j.compfluid.2012.06.003","journal-title":"Comput. Fluids"},{"key":"45_CR23","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., et al.: Massively parallel lattice Boltzmann codes on large GPU clusters. Parallel Comput. 58, 1\u201324 (2016). \n                      https:\/\/doi.org\/10.1016\/j.parco.2016.08.005","journal-title":"Parallel Comput."},{"key":"45_CR24","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1016\/j.compfluid.2013.05.014","volume":"88","author":"F Mantovani","year":"2013","unstructured":"Mantovani, F., et al.: Performance issues on many-core processors: a D2Q37 lattice Boltzmann scheme as a test-case. Comput. Fluids 88, 743\u2013752 (2013). \n                      https:\/\/doi.org\/10.1016\/j.compfluid.2013.05.014","journal-title":"Comput. Fluids"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-78024-5_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T03:33:22Z","timestamp":1558323202000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78024-5_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319780238","9783319780245"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78024-5_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"23 March 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PPAM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Processing and Applied Mathematics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czestochowa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ppam2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ppam.pl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}