{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:04:07Z","timestamp":1743134647624,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319436586"},{"type":"electronic","value":"9783319436593"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-43659-3_6","type":"book-chapter","created":{"date-parts":[[2016,8,8]],"date-time":"2016-08-08T02:54:01Z","timestamp":1470624841000},"page":"77-89","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Addressing Materials Science Challenges Using GPU-accelerated POWER8 Nodes"],"prefix":"10.1007","author":[{"given":"Paul F.","family":"Baumeister","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcel","family":"Bornemann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"B\u00fchler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thorsten","family":"Hater","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Krill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dirk","family":"Pleiter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rudolf","family":"Zeller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,8,9]]},"reference":[{"key":"6_CR1","unstructured":"OSU Micro-Benchmarks. \n                      http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/"},{"key":"6_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1007\/978-3-319-17248-4_2","volume-title":"High Performance Computing Systems. Performance Modeling, Benchmarking and Simulation","author":"AV Adinetz","year":"2015","unstructured":"Adinetz, A.V., Baumeister, P.F., B\u00f6ttiger, H., Hater, T., Maurer, T., Pleiter, D., Schenck, W., Schifano, S.F.: Performance evaluation of scientific applications on POWER8. In: Jarvis, S.A., Wright, S.A., Hammond, S.D. (eds.) PMBS 2014. LNCS, vol. 8966, pp. 24\u201345. Springer, Heidelberg (2015)"},{"key":"6_CR3","unstructured":"Baumeister, P.F.: Real-Space Finite-Difference PAW Method for Large-Scale Applications on Massively Parallel Computers. Ph.D. thesis, RWTH Aachen (2012)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Baumeister, P.F., Hater, T., Kraus, J., Pleiter, D., Wahl, P.: A performance model for GPU-accelerated FDTD applications. In: 2015 IEEE 22nd International Conference on High Performance Computing (HiPC), pp. 185\u2013193 (2015)","DOI":"10.1109\/HiPC.2015.24"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Beeby, J.: The density of electrons in a perfect or imperfect lattice. In: Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences, vol. 302. The Royal Society (1967)","DOI":"10.1098\/rspa.1967.0230"},{"issue":"11","key":"6_CR6","doi-asserted-by":"publisher","first-page":"4177","DOI":"10.1021\/ct300531w","volume":"8","author":"MD Ben","year":"2012","unstructured":"Ben, M.D., Hutter, J., VandeVondele, J.: Second-order M\u00f8ller-Plesset perturbation theory in the condensed phase. J. Chem. Theory. Comput. 8(11), 4177\u20134188 (2012)","journal-title":"J. Chem. Theory. Comput."},{"key":"6_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1007\/11602569_41","volume-title":"High Performance Computing \u2013 HiPC 2005","author":"G Bilardi","year":"2005","unstructured":"Bilardi, G., Pietracaprina, A., Pucci, G., Schifano, F., Tripiccione, R.: The potential of on-chip multiprocessing for QCD machines. In: Bader, D.A., Parashar, M., Sridhar, V., Prasanna, V.K. (eds.) HiPC 2005. LNCS, vol. 3769, pp. 386\u2013397. Springer, Heidelberg (2005)"},{"key":"6_CR8","unstructured":"Caldeira, A.B., et al.: IBM Power System S824L technical overview and introduction (2014). \n                      redbooks.ibm.com\/Redbooks.nsf\/RedbookAbstracts\/redp5139.html"},{"issue":"2","key":"6_CR9","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1109\/MM.2011.29","volume":"31","author":"M Floyd","year":"2011","unstructured":"Floyd, M., et al.: Introducing the adaptive energy management features of the POWER7 chip. IEEE Micro 31(2), 60\u201375 (2011)","journal-title":"IEEE Micro"},{"issue":"1","key":"6_CR10","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/BF01385726","volume":"60","author":"RW Freund","year":"1991","unstructured":"Freund, R.W., Nachtigal, N.: QMR: a quasi-minimal residual method for non-Hermitian linear systems. Numer. Math. 60(1), 315\u2013339 (1991)","journal-title":"Numer. Math."},{"key":"6_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/978-3-642-36803-5_4","volume-title":"Applied Parallel and Scientific Computing","author":"S Hakala","year":"2013","unstructured":"Hakala, S., Havu, V., Enkovaara, J., Nieminen, R.: Parallel electronic structure calculations using multiple graphics processing units (GPUs). In: Manninen, P., \u00d6ster, P. (eds.) PARA. LNCS, vol. 7782, pp. 63\u201376. Springer, Heidelberg (2013)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Hoefler, T., Gropp, W., Kramer, W., Snir, M.: Performance modeling for systematic performance tuning. In: State of the Practice Reports. SC 2011. ACM (2011)","DOI":"10.1145\/2063348.2063356"},{"issue":"1","key":"6_CR13","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1002\/wcms.1159","volume":"4","author":"J Hutter","year":"2014","unstructured":"Hutter, J., Iannuzzi, M., Schiffmann, F., VandeVondele, J.: CP2K: atomistic simulations of condensed matter systems. Comp. Mol. Sci. 4(1), 15\u201325 (2014)","journal-title":"Comp. Mol. Sci."},{"key":"6_CR14","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1103\/PhysRev.94.1111","volume":"94","author":"W Kohn","year":"1954","unstructured":"Kohn, W., Rostoker, N.: Solution of the Schr\u00f6dinger equation in periodic lattices with an application to metallic Lithium. Phys. Rev. 94, 1111\u20131120 (1954)","journal-title":"Phys. Rev."},{"key":"6_CR15","doi-asserted-by":"publisher","first-page":"A1133","DOI":"10.1103\/PhysRev.140.A1133","volume":"140","author":"W Kohn","year":"1965","unstructured":"Kohn, W., Sham, L.J.: Self-consistent equations including exchange and correlation effects. Phys. Rev. 140, A1133\u2013A1138 (1965)","journal-title":"Phys. Rev."},{"issue":"6","key":"6_CR16","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1016\/0031-8914(47)90013-X","volume":"13","author":"J Korringa","year":"1947","unstructured":"Korringa, J.: On the calculation of the energy of a Bloch wave in a metal. Physica 13(6), 392\u2013400 (1947)","journal-title":"Physica"},{"key":"6_CR17","unstructured":"Lefurgy, C., Wang, X., Ware, M.: Server-level power control. In: Fourth International Conference on Autonomic Computing, 2007. ICAC 2007, pp. 4\u20134, June 2007"},{"issue":"1","key":"6_CR18","doi-asserted-by":"publisher","first-page":"6:1","DOI":"10.1147\/JRD.2014.2380197","volume":"59","author":"AEA Mericas","year":"2015","unstructured":"Mericas, A.E.A.: IBM POWER8 performance features and evaluation. IBM J. Res. Dev. 59(1), 6:1\u20136:10 (2015)","journal-title":"IBM J. Res. Dev."},{"key":"6_CR19","unstructured":"Pleiter, D.: Parallel computer architectures. In: 45th IFF Spring School 2014 \u201cComputing Solids Models, ab-initio Methods and Supercomputing\u201d, Schriften des Forschungszentrums J\u00fclich, Reihe Schl\u00fcsseltechnologien, vol. 74 (2014)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Solc\u00e0, R., Kozhevnikov, A., et al.: Efficient implementation of quantum materials simulations on distributed CPU-GPU systems. In: SC 2015 Conference on Proceed, pp. 10:1 (2015)","DOI":"10.1145\/2807591.2807654"},{"issue":"11","key":"6_CR21","first-page":"2745","volume":"14","author":"JM Soler","year":"2002","unstructured":"Soler, J.M., et al.: The SIESTA method for ab initio order-N materials simulation. J. Phys.: Condens. Matter 14(11), 2745 (2002)","journal-title":"J. Phys.: Condens. Matter"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Spiga, F., Girotto, I.: phiGEMM: a CPU-GPU library for porting Quantum ESPRESSO on hybrid systems. In: 2012 20th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2012, pp. 368\u2013375, February 2012","DOI":"10.1109\/PDP.2012.72"},{"key":"6_CR23","doi-asserted-by":"publisher","first-page":"235103","DOI":"10.1103\/PhysRevB.85.235103","volume":"85","author":"A Thiess","year":"2012","unstructured":"Thiess, A., et al.: Massively parallel density functional calculations for thousands of atoms: KKRnano. Phys. Rev. B 85, 235103 (2012)","journal-title":"Phys. Rev. B"},{"key":"6_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1007\/978-3-642-40047-6_82","volume-title":"Euro-Par 2013 Parallel Processing","author":"B Videau","year":"2013","unstructured":"Videau, B., Marangozova-Martin, V., Genovese, L., Deutsch, T.: Optimizing 3D convolutions for wavelet transforms on CPUs with SSE units and GPUs. In: Wolf, F., Mohr, B., an Mey, D. (eds.) Euro-Par 2013. LNCS, vol. 8097, pp. 826\u2013837. Springer, Heidelberg (2013)"},{"issue":"4","key":"6_CR25","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":"6_CR26","doi-asserted-by":"publisher","first-page":"8807","DOI":"10.1103\/PhysRevB.52.8807","volume":"52","author":"R Zeller","year":"1995","unstructured":"Zeller, R., et al.: Theory and convergence properties of the screened Korringa-Kohn-Rostoker method. Phys. Rev. B 52, 8807\u20138812 (1995)","journal-title":"Phys. Rev. B"},{"issue":"29","key":"6_CR27","first-page":"294215","volume":"20","author":"R Zeller","year":"2008","unstructured":"Zeller, R.: Towards a linear-scaling algorithm for electronic structure calculations with the tight-binding Korringa-Kohn-Rostoker Green function method. J. Phys.: Condens. Matter 20(29), 294215 (2008)","journal-title":"J. Phys.: Condens. Matter"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2016: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-43659-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,9]],"date-time":"2020-08-09T00:03:08Z","timestamp":1596931388000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-43659-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319436586","9783319436593"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-43659-3_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"9 August 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 August 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/europar2016.inria.fr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}