{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T04:13:04Z","timestamp":1781151184902,"version":"3.54.1"},"reference-count":52,"publisher":"American Chemical Society (ACS)","issue":"10","license":[{"start":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T00:00:00Z","timestamp":1650585600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T00:00:00Z","timestamp":1650585600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T00:00:00Z","timestamp":1650585600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/100007000","name":"Laboratory Directed Research and Development","doi-asserted-by":"publisher","award":["20210087DR"],"award-info":[{"award-number":["20210087DR"]}],"id":[{"id":"10.13039\/100007000","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Chem. Inf. Model."],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1021\/acs.jcim.1c01538","type":"journal-article","created":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T12:50:35Z","timestamp":1650631835000},"page":"2378-2386","source":"Crossref","is-referenced-by-count":16,"title":["Performance Analysis of CP2K Code for Ab Initio Molecular Dynamics on CPUs and GPUs"],"prefix":"10.1021","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1453-5906","authenticated-orcid":true,"given":"Dewi","family":"Yokelson","sequence":"first","affiliation":[{"name":"Applied Computer Science Division (CCS-7), Los Alamos National Laboratory, Los Alamos, New Mexico 87545, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7296-4293","authenticated-orcid":true,"given":"Nikolay V.","family":"Tkachenko","sequence":"additional","affiliation":[{"name":"Chemistry Division (C-IIAC), Los Alamos National Laboratory, Los Alamos, New Mexico 87545, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Robey","sequence":"additional","affiliation":[{"name":"Computational Physics Division (XCP-2), Los Alamos National Laboratory, Los Alamos, New Mexico 87545, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying Wai","family":"Li","sequence":"additional","affiliation":[{"name":"Applied Computer Science Division (CCS-7), Los Alamos National Laboratory, Los Alamos, New Mexico 87545, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9750-6603","authenticated-orcid":true,"given":"Pavel A.","family":"Dub","sequence":"additional","affiliation":[{"name":"Chemistry Division (C-IIAC), Los Alamos National Laboratory, Los Alamos, New Mexico 87545, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2022,4,22]]},"reference":[{"key":"ref1\/cit1","doi-asserted-by":"crossref","unstructured":"Kirchner, B.; di Dio, P. J.; Hutter, J.Multiscale Molecular Methods in Applied Chemistry; Kirchner, B., Vrabec, J., Eds. Springer Berlin Heidelberg: Berlin, Heidelberg, 2012; pp 109\u2013153.","DOI":"10.1007\/128_2011_195"},{"key":"ref2\/cit2","unstructured":"Frisch, M. J.; Trucks, G. W.; Schlegel, H. B.; Scuseria, G. E.; Robb, M. A.; Cheese- man, J. R.; Scalmani, G.; Barone, V.; Petersson, G. A.; Nakatsuji, H.Gaussian 16, Revision C.01; Gaussian Inc.: Wallingford CT, 2016."},{"key":"ref3\/cit3","doi-asserted-by":"publisher","DOI":"10.1103\/physrevb.47.558"},{"key":"ref4\/cit4","doi-asserted-by":"publisher","DOI":"10.1016\/0927-0256(96)00008-0"},{"key":"ref5\/cit5","doi-asserted-by":"publisher","DOI":"10.1080\/00268976.2014.952696"},{"key":"ref6\/cit6","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/21\/39\/395502"},{"key":"ref7\/cit7","doi-asserted-by":"publisher","DOI":"10.1039\/c5cp00437c"},{"key":"ref8\/cit8","doi-asserted-by":"publisher","DOI":"10.1063\/5.0004997"},{"key":"ref9\/cit9","doi-asserted-by":"publisher","DOI":"10.1021\/ct9003004"},{"key":"ref10\/cit10","doi-asserted-by":"publisher","DOI":"10.1063\/5.0007045"},{"key":"ref11\/cit11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2004.12.014"},{"key":"ref12\/cit12","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpca.1c02516"},{"key":"ref13\/cit13","doi-asserted-by":"publisher","DOI":"10.1021\/acs.organomet.9b00542"},{"key":"ref14\/cit14","unstructured":"Reid, F.; Bethune, I.Optimising CP2K for the Intel Xeon Phi, 2013."},{"key":"ref15\/cit15","unstructured":"Bethune, I.; Reid, F.; Lazzaro, A.CP2K Performance from Cray XT3 to XC30, 2014."},{"key":"ref16\/cit16","doi-asserted-by":"publisher","DOI":"10.2307\/2331554"},{"key":"ref17\/cit17","unstructured":"Snedecor, G. W.; Cochran, W. G.Statistical Methods, 8th ed. Iowa State University Press: Ames, Iowa, 1989; p 1191."},{"key":"ref18\/cit18","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.21224"},{"key":"ref19\/cit19","doi-asserted-by":"publisher","DOI":"10.1103\/physrev.136.b864"},{"key":"ref20\/cit20","doi-asserted-by":"publisher","DOI":"10.1103\/physrev.140.a1133"},{"key":"ref21\/cit21","doi-asserted-by":"publisher","DOI":"10.1103\/physreva.38.3098"},{"key":"ref22\/cit22","doi-asserted-by":"publisher","DOI":"10.1103\/physrevb.37.785"},{"key":"ref23\/cit23","doi-asserted-by":"publisher","DOI":"10.1063\/1.3382344"},{"key":"ref24\/cit24","doi-asserted-by":"publisher","DOI":"10.1103\/physrevb.54.1703"},{"key":"ref25\/cit25","doi-asserted-by":"publisher","DOI":"10.1103\/physrevb.58.3641"},{"key":"ref26\/cit26","doi-asserted-by":"publisher","DOI":"10.1063\/1.2770708"},{"key":"ref27\/cit27","doi-asserted-by":"publisher","DOI":"10.1103\/physreva.31.1695"},{"key":"ref28\/cit28","doi-asserted-by":"publisher","DOI":"10.1063\/1.447334"},{"key":"ref29\/cit29","doi-asserted-by":"crossref","unstructured":"Amdahl, G. M. Validity of the Single Processor Approach to Achieving Large Scale Computing Capabilities.Proceedings of the April 18\u201320, 1967, Spring Joint Computer Conference, 1967; pp 483\u2013485.","DOI":"10.1145\/1465482.1465560"},{"key":"ref30\/cit30","unstructured":"Snir, M.; Otto, S. W.; Walker, D. W.; Dongarra, J. J.; Huss-Lederman, S.MPI: The Complete Reference, 1996."},{"key":"ref31\/cit31","doi-asserted-by":"crossref","unstructured":"Dagum, L.; Menon, R.OpenMP: An Industry Standard API for Shared-Memory Programming, 1998.","DOI":"10.1109\/99.660313"},{"key":"ref32\/cit32","doi-asserted-by":"crossref","unstructured":"Nickolls, J. R.; Buck, I.; Garland, M.; Skadron, K. Scalable Parallel Programming with CUDA.2008 IEEE Hot Chips 20 Symposium (HCS), 2008; pp 1\u20132.","DOI":"10.1109\/HOTCHIPS.2008.7476525"},{"key":"ref33\/cit33","series-title":"Software, Environments and Tools","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898719604","volume-title":"LAPACK Users\u2019 Guide","author":"Anderson E.","year":"1999","edition":"3"},{"key":"ref34\/cit34","volume-title":"ScaLAPACK Users\u2019 Guide","author":"Blackford L. S.","year":"1987"},{"key":"ref35\/cit35","doi-asserted-by":"crossref","unstructured":"Frigo, M.; Johnson, S. G. FFTW: an Adaptive Software Architecture for the FFT.Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP\u201998 (Cat. No. 98CH36181), 1998; Vol. 33, pp 1381\u20131384.","DOI":"10.1109\/ICASSP.1998.681704"},{"key":"ref36\/cit36","unstructured":"Seewald, P.; Muller, T.; Lazarro, A. Libint-cp2k. https:\/\/github.com\/cp2k\/libint-cp2k."},{"key":"ref37\/cit37","unstructured":"Heinecke, A.; Pabst, H.; Henry, G. M.LIBXSMM: A High Performance Library for Small Matrix Multiplications, 2015."},{"key":"ref38\/cit38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2012.05.007"},{"key":"ref39\/cit39","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/26\/21\/213201"},{"key":"ref40\/cit40","unstructured":"Seewald, P. Enabling DFT Simulations of Large Metallic Systems by Integrating the PEXSI Method into CP2K, Master Thesis; ETH Z\u00fcrich, 2015."},{"key":"ref41\/cit41","unstructured":"Cs\u00e1anyi, G.; Winfield, S.; Kermode, J. R.; De Vita, A.; Comisso, A.; Bernstein, N.; Payne, M. C. Expressive Programming for Computational Physics in Fortran 95+.IoP Computational Physics Group Newsletter, Spring, 2007."},{"key":"ref42\/cit42","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2013.09.018"},{"key":"ref43\/cit43","unstructured":"Togo, A.; Tanaka, I. ${Spglib}$: a Software Library for Crystal Symmetry Search, 2018. arXiv:1808.01590."},{"key":"ref44\/cit44","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0344-8"},{"key":"ref45\/cit45","doi-asserted-by":"crossref","unstructured":"Ramaswami, A.; Kenter, T.; K\u00fchne, T. D.; Plessl, C. Efficient Ab-Initio Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGAs.2020 30th International Conference on Field-Programmable Logic and Applications (FPL), 2020; pp 353\u2013354.","DOI":"10.1109\/FPL50879.2020.00065"},{"key":"ref46\/cit46","doi-asserted-by":"crossref","unstructured":"Kwasniewski, G.; Kabic, M.; Besta, M.; VandeVondele, J.; Solca, R.; Hoefler, T. Red-blue Pebbling Revisited: Near Optimal Parallel Matrix-Matrix Multiplication.Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2019; pp 1\u201322.","DOI":"10.1145\/3295500.3356181"},{"key":"ref47\/cit47","unstructured":"Brehm, M. Libvori. https:\/\/brehm-research.de\/libvori.php."},{"key":"ref48\/cit48","unstructured":"VandeVondele, J.; Schuett, O.; Lazzaro, A.; Krack, M.; Mathieu, T.; Hutter, J. How to Compile the CP2K Code, 2021. https:\/\/github.com\/cp2k\/cp2k\/blob\/master\/INSTALL.md."},{"key":"ref49\/cit49","volume-title":"Parallel and High Performance Computing","author":"Robey R.","year":"2021"},{"key":"ref50\/cit50","volume-title":"Probability and Statistical Inference","author":"Hogg R. V.","year":"2006","edition":"9"},{"key":"ref51\/cit51","volume-title":"LIKWID: Lightweight Performance Tools","author":"Treibig J.","year":"2010"},{"key":"ref53\/cit53","unstructured":"NVIDIA A100 Tensor Core Gpu. https:\/\/www.nvidia.com\/en-us\/data-center\/a100\/, Note: NVIDIA also offers the A100 Tensor Core GPU accelerators, which are expected to perform up to 2\u00d7 faster than the V100. We note here that CP2K does not yet appear to support the A100s."}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.1c01538","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.1c01538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T19:40:57Z","timestamp":1727034057000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/doi\/10.1021\/acs.jcim.1c01538"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,22]]},"references-count":52,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,5,23]]}},"alternative-id":["10.1021\/acs.jcim.1c01538"],"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.1c01538","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,22]]}}}