{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:50:51Z","timestamp":1740099051876,"version":"3.37.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319920399"},{"type":"electronic","value":"9783319920405"}],"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\/978-3-319-92040-5_11","type":"book-chapter","created":{"date-parts":[[2018,5,28]],"date-time":"2018-05-28T07:55:05Z","timestamp":1527494105000},"page":"205-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Performance Optimization and Evaluation of Scalable Optoelectronics Application on Large Scale KNL Cluster"],"prefix":"10.1007","author":[{"given":"Yuta","family":"Hirokawa","sequence":"first","affiliation":[]},{"given":"Taisuke","family":"Boku","sequence":"additional","affiliation":[]},{"given":"Mitsuharu","family":"Uemoto","sequence":"additional","affiliation":[]},{"given":"Shunsuke A.","family":"Sato","sequence":"additional","affiliation":[]},{"given":"Kazuhiro","family":"Yabana","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,5,29]]},"reference":[{"issue":"1","key":"11_CR1","doi-asserted-by":"publisher","first-page":"98","DOI":"10.15748\/jasse.1.98","volume":"1","author":"SA Sato","year":"2014","unstructured":"Sato, S.A., Yabana, K.: Maxwell + TDDFT multi-scale simulation for laser-matter interactions. J. Adv. Simulat. Sci. Eng. 1(1), 98\u2013110 (2014)","journal-title":"J. Adv. Simulat. Sci. Eng."},{"issue":"4","key":"11_CR2","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1103\/PhysRevB.85.045134","volume":"85","author":"K Yabana","year":"2012","unstructured":"Yabana, K., Sugiyama, T., Shinohara, Y., et al.: Time-dependent density functional theory for strong electromagnetic fields in crystalline solids. Phys. Rev. B 85(4), 11 (2012). \nhttps:\/\/doi.org\/10.1103\/PhysRevB.85.045134","journal-title":"Phys. Rev. B"},{"key":"11_CR3","doi-asserted-by":"publisher","first-page":"233202","DOI":"10.1088\/0953-8984\/24\/23\/233202","volume":"24","author":"X Andrade","year":"2012","unstructured":"Andrade, X., et al.: Time-dependent density-functional theory in massively parallel computer architectures: the OCTOPUS project. J. Phy. Condens. Matt. 24, 233202 (2012)","journal-title":"J. Phy. Condens. Matt."},{"issue":"14","key":"11_CR4","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.jcp.2014.02.006","volume":"265","author":"M Noda","year":"2014","unstructured":"Noda, M., Ishimura, K., Nobusada, K., et al.: Massively-parallel electron dynamics calculations in real-time and real-space: toward applications to nanostructures of more than ten-nanometers in size. J. Comput. Phys. 265(14), 145\u2013155 (2014)","journal-title":"J. Comput. Phys."},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Draeger, E.W., Andrade, X., Gunnels, J.A., et al.: Massively parallel first-principles simulation of electron dynamics in materials. In: 2016 IEEE International Parallel and Distributed Processing Symposium, p. 832 (2016)","DOI":"10.1109\/IPDPS.2016.46"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Barnes, T., Cook, B., Deslippe, J., et al.: Evaluating and optimizing the NERSC workload on Knights Landing. In: Proceedings of the 7th International Workshop on PMBS 2016, pp. 43\u201353 (2016)","DOI":"10.1109\/PMBS.2016.010"},{"key":"11_CR7","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). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46079-6_22"},{"key":"11_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/978-3-319-46079-6_30","volume-title":"High Performance Computing","author":"B Jo\u00f3","year":"2016","unstructured":"Jo\u00f3, B., Kalamkar, D.D., Kurth, T., Vaidyanathan, K., Walden, A.: Optimizing Wilson-Dirac operator and linear solvers for Intel\u00ae KNL. In: Taufer, M., Mohr, B., Kunkel, J.M. (eds.) ISC High Performance 2016. LNCS, vol. 9945, pp. 415\u2013427. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46079-6_30"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Yount, C., Duran, A.:: Effective use of large high-bandwidth memory caches in HPC stencil computation via temporal wave-front tiling. In: Proceedings of the 7th International Workshop on PMBS 2016, pp. 65\u201375 (2016)","DOI":"10.1109\/PMBS.2016.012"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Hofmann, J., Treibig, J., Hager, G., Wellein, G.: Comparing the performance of different x86 SIMD instruction sets for a medical imaging application on modern multi- and manycore chips. In: Proceedings of WPMVP 2014, pp. 55\u201364 (2014)","DOI":"10.1145\/2568058.2568068"},{"key":"11_CR11","unstructured":"Andreolli, C.: Eight Optimizations for 3-Dimensional Finite Difference (3DFD) Code with an Isotropic (ISO). \nhttps:\/\/software.intel.com\/en-us\/articles\/eight-optimizations-for-3-dimensional-finite-difference-3dfd-code-with-an-isotropic-iso"},{"key":"11_CR12","unstructured":"Blelloch, G.E.: Prefix Sums and Their Applications, School of Computer Science, Carnegie Mellon University, CMU-CS-90-190, November 1990"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Martin, P.J., Ayuso, L.F., Torres, R., Gavilanes, A.: Algorithmic strategies for optimizing the parallel reduction primitive in CUDA. In: 2012 International Conference on High Performance Computing and Simulation, pp. 511\u2013519, July 2012","DOI":"10.1109\/HPCSim.2012.6266966"},{"key":"11_CR14","first-page":"1","volume":"27","author":"A Sodani","year":"2015","unstructured":"Sodani, A.: Knights Landing (KNL): 2nd generation intel Xeon Phi processor. IEEE Hot Chips 27, 1\u201324 (2015)","journal-title":"IEEE Hot Chips"},{"issue":"4","key":"11_CR15","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":"11_CR16","doi-asserted-by":"crossref","unstructured":"Hirokawa, Y., Boku, T., Sato, S.A., Yabana, K.: Electron dynamics simulation with time-dependent density functional theory on large scale symmetric mode Xeon Phi cluster. In: The 17th IEEE International Workshop on PDSEC 2016 (2016)","DOI":"10.1109\/IPDPSW.2016.200"},{"issue":"6215","key":"11_CR17","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1126\/science.1260311","volume":"346","author":"M Schultze","year":"2014","unstructured":"Schultze, M., Ramasesha, K., Pemmaraju, C., et al.: Attosecond band-gap dynamics in Silicon. Science 346(6215), 1348\u20131352 (2014)","journal-title":"Science"},{"issue":"6302","key":"11_CR18","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1126\/science.aag1268","volume":"353","author":"M Lucchini","year":"2016","unstructured":"Lucchini, M., Sato, S.A., Ludwig, A., et al.: Attosecond dynamical Franz-Keldysh effect in polycrystalline diamond. Science 353(6302), 916\u2013919 (2016)","journal-title":"Science"},{"key":"11_CR19","doi-asserted-by":"publisher","first-page":"e16133","DOI":"10.1038\/lsa.2016.133","volume":"5","author":"M Malinauskas","year":"2016","unstructured":"Malinauskas, M., Zukauskas, A., Hasegawa, S., et al.: Ultrafast laser processing of materials: from science to industry. Light Sci. Appl. 5, e16133 (2016)","journal-title":"Light Sci. Appl."},{"key":"11_CR20","unstructured":"RIKEN AICS. \nhttp:\/\/www.aics.riken.jp\/en\/"},{"key":"11_CR21","unstructured":"CCS, University of Tsukuba. \nhttp:\/\/www.ccs.tsukuba.ac.jp\/eng\/"},{"key":"11_CR22","unstructured":"Joint Center for Advanced HPC. \nhttp:\/\/jcahpc.jp\/eng\/"},{"key":"11_CR23","unstructured":"TOP500. \nhttp:\/\/www.top500.org\/"},{"key":"11_CR24","unstructured":"OCTOPUS. \nhttp:\/\/octopus-code.org"},{"key":"11_CR25","unstructured":"Github: ARTED. \nhttps:\/\/github.com\/ARTED\/ARTED"},{"key":"11_CR26","unstructured":"SALMON. \nhttp:\/\/salmon-tddft.jp\/"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-92040-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,5,28]],"date-time":"2018-05-28T07:59:27Z","timestamp":1527494367000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-92040-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319920399","9783319920405"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-92040-5_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}