{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T14:16:06Z","timestamp":1774534566981,"version":"3.50.1"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319729701","type":"print"},{"value":"9783319729718","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,12,23]],"date-time":"2017-12-23T00:00:00Z","timestamp":1513987200000},"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\/978-3-319-72971-8_4","type":"book-chapter","created":{"date-parts":[[2017,12,22]],"date-time":"2017-12-22T08:44:54Z","timestamp":1513932294000},"page":"67-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["A Performance Study of Quantum ESPRESSO\u2019s PWscf Code on Multi-core and GPU Systems"],"prefix":"10.1007","author":[{"given":"Joshua","family":"Romero","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Everett","family":"Phillips","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory","family":"Ruetsch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Massimiliano","family":"Fatica","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Filippo","family":"Spiga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Giannozzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,12,23]]},"reference":[{"issue":"12","key":"4_CR1","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1016\/j.parco.2011.05.002","volume":"37","author":"T Auckenthaler","year":"2011","unstructured":"Auckenthaler, T., Blum, V., Bungartz, H.J., Huckle, T., Johanni, R., Kr\u00e4mer, L., Lang, B., Lederer, H., Willems, P.R.: Parallel solution of partial symmetric eigenvalue problems from electronic structure calculations. Parallel Comput. 37(12), 783\u2013794 (2011)","journal-title":"Parallel Comput."},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Blackford, L.S., Choi, J., Cleary, A., D\u2019Azeuedo, E., Demmel, J., Dhillon, I., Hammarling, S., Henry, G., Petitet, A., Stanley, K., Walker, D., Whaley, R.C.: ScaLAPACK User\u2019s Guide. Society for Industrial and Applied Mathematics (1997)","DOI":"10.1137\/1.9780898719642"},{"key":"4_CR3","unstructured":"Fatica, M.: Customize CUDA Fortran Profiling with NVTX (2015). https:\/\/devblogs.nvidia.com\/parallelforall\/customize-cuda-fortran-profiling-nvtx"},{"key":"4_CR4","volume-title":"CUDA Fortran for Scientists and Engineers","author":"M Fatica","year":"2014","unstructured":"Fatica, M., Ruetsch, G.: CUDA Fortran for Scientists and Engineers. Morgan Kaufmann, Burlington (2014)"},{"key":"4_CR5","doi-asserted-by":"crossref","first-page":"3168","DOI":"10.1103\/PhysRevB.39.3168","volume":"39","author":"S Froyen","year":"1989","unstructured":"Froyen, S.: Brillouin-zone integration by Fourier quadrature: special points for superlattice and supercell calculations. Phys. Rev. B 39, 3168\u20133172 (1989)","journal-title":"Phys. Rev. B"},{"issue":"39","key":"4_CR6","doi-asserted-by":"crossref","first-page":"395502","DOI":"10.1088\/0953-8984\/21\/39\/395502","volume":"21","author":"P Giannozzi","year":"2009","unstructured":"Giannozzi, P., Baroni, S., Bonini, N., Calandra, M., Car, R., Cavazzoni, C., Ceresoli, D., Chiarotti, G.L., Cococcioni, M., Dabo, I., et al.: QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials. J. Phys. Condensed Matter 21(39), 395502 (2009)","journal-title":"J. Phys. Condensed Matter"},{"key":"4_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-06548-9_1","volume-title":"Numerical Computations with GPUs","author":"J Dongarra","year":"2014","unstructured":"Dongarra, J., Gates, M., Haidar, A., Kurzak, J., Luszczek, P., Tomov, S., Yamazaki, I.: Accelerating numerical dense linear algebra calculations with GPUs. In: Kindratenko, V. (ed.) Numerical Computations with GPUs, pp. 3\u201328. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-06548-9_1"},{"key":"4_CR8","doi-asserted-by":"crossref","first-page":"12807","DOI":"10.1103\/PhysRevB.38.12807","volume":"38","author":"DD Johnson","year":"1988","unstructured":"Johnson, D.D.: Modified Broyden\u2019s method for accelerating convergence in self-consistent calculations. Phys. Rev. B 38, 12807\u201312813 (1988)","journal-title":"Phys. Rev. B"},{"key":"4_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/BFb0106731","volume-title":"Density Functionals: Theory and Applications","author":"W Kohn","year":"1998","unstructured":"Kohn, W.: Fundamentals of density functional theory. In: Joubert, D. (ed.) Density Functionals: Theory and Applications, pp. 1\u20137. Springer, Heidelberg (1998). https:\/\/doi.org\/10.1007\/BFb0106731"},{"key":"4_CR10","unstructured":"Kraus, J.: CUDA Pro Tip: generate custom application profile timelines with NVTX (2013). https:\/\/devblogs.nvidia.com\/parallelforall\/cuda-pro-tip-generate-custom-application-profile-timelines-nvtx"},{"issue":"21","key":"4_CR11","doi-asserted-by":"crossref","first-page":"213201","DOI":"10.1088\/0953-8984\/26\/21\/213201","volume":"26","author":"A Marek","year":"2014","unstructured":"Marek, A., Blum, V., Johanni, R., Havu, V., Lang, B., Auckenthaler, T., Heinecke, A., Bungartz, H.J., Lederer, H.: The ELPA library: scalable parallel eigenvalue solutions for electronic structure theory and computational science. J. Phys. Condensed Matter 26(21), 213201 (2014)","journal-title":"J. Phys. Condensed Matter"},{"key":"4_CR12","unstructured":"Message Passing Interface Forum: MPI: A Message-Passing Interface Standard, Version 2.2. Technical report (2009). http:\/\/www.mpi-forum.org\/docs\/mpi-2.2\/mpi22-report.pdf"},{"key":"4_CR13","volume-title":"Density-Functional Theory of Atoms and Molecules (International Series of Monographs on Chemistry)","author":"RG Parr","year":"1994","unstructured":"Parr, R.G., Yang, W.: Density-Functional Theory of Atoms and Molecules (International Series of Monographs on Chemistry). Oxford University Press, New York (1994)"},{"issue":"3","key":"4_CR14","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/0167-7977(89)90002-6","volume":"9","author":"WE Pickett","year":"1989","unstructured":"Pickett, W.E.: Pseudopotential methods in condensed matter applications. Comput. Phys. Rep. 9(3), 115\u2013197 (1989)","journal-title":"Comput. Phys. Rep."},{"key":"4_CR15","unstructured":"Romero, J.: Developing an Improved Generalized Eigensolver with Limited CPU Offloading. In: GPU Technology Conference, San Jose, CA (2017). http:\/\/on-demand.gputechconf.com\/gtc\/2017\/presentation\/s7388-joshua-romero-developing-an-improved-generalized-eigensolver.pdf"},{"key":"4_CR16","unstructured":"Spiga, F.: Plug-in code to accelerate Quantum ESPRESSO v5 using NVIDIA GPU. https:\/\/github.com\/fspiga\/qe-gpu-plugin"},{"key":"4_CR17","unstructured":"Spiga, F.: Implementing and testing mixed parallel programming model into Quantum ESPRESSO. In: Science and Supercomputing in Europe - Research Highlights 2009, CINECA Consorzio Interuniversitario, Bologna, Italy (2010)"},{"key":"4_CR18","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, pp. 368\u2013375 (2012)","DOI":"10.1109\/PDP.2012.72"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-72971-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,8]],"date-time":"2019-10-08T13:29:38Z","timestamp":1570541378000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-72971-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,23]]},"ISBN":["9783319729701","9783319729718"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-72971-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12,23]]}}}