{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T13:37:13Z","timestamp":1762177033947,"version":"3.41.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319676296"},{"type":"electronic","value":"9783319676302"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-67630-2_30","type":"book-chapter","created":{"date-parts":[[2017,10,19]],"date-time":"2017-10-19T04:33:17Z","timestamp":1508387597000},"page":"404-418","source":"Crossref","is-referenced-by-count":4,"title":["Performance Evaluation of NWChem Ab-Initio Molecular Dynamics (AIMD) Simulations on the Intel\u00ae Xeon Phi\u2122 Processor"],"prefix":"10.1007","author":[{"given":"Eric J.","family":"Bylaska","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathias","family":"Jacquelin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wibe A.","family":"de Jong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeff R.","family":"Hammond","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Klemm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,20]]},"reference":[{"key":"30_CR1","unstructured":"Measuring arithmetic intensity, http:\/\/www.nersc.gov\/users\/application-performance\/measuring-arithmetic-intensity\/ . Accessed 22 Oct 2016"},{"issue":"2","key":"30_CR2","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/S0927-0256(03)00108-3","volume":"28","author":"E Apr\u00e0","year":"2003","unstructured":"Apr\u00e0, E., Bylaska, E.J., Dean, D.J., Fortunelli, A., Gao, F., Krsti\u0107, P.S., Wells, J.C., Windus, T.L.: NWChem for materials science. Comput. Mater. Sci. 28(2), 209\u2013221 (2003)","journal-title":"Comput. Mater. Sci."},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Ayala, O., Wang, L.P.: Parallel implementation and scalability analysis of 3D fast fourier transform using 2D domain decomposition. Parallel Comput. 39(1), 58\u201377 (2013). http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167819112000932","DOI":"10.1016\/j.parco.2012.12.002"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Bylaska, E., Tsemekhman, K., Govind, N., Valiev, M.: Large-scale plane-wave-based density functional theory: formalism, parallelization, and applications. In: Computational Methods for Large Systems: Electronic Structure Approaches for Biotechnology and Nanotechnology, pp. 77\u2013116 (2011)","DOI":"10.1002\/9780470930779.ch3"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Bylaska, E.J., Glass, K., Baxter, D., Baden, S.B., Weare, J.H.: Hard scaling challenges for ab initio molecular dynamics capabilities in nwchem: using 100,000 CPUs per second. In: Journal of Physics: Conference Series, vol. 180, p. 012028. IOP Publishing (2009)","DOI":"10.1088\/1742-6596\/180\/1\/012028"},{"issue":"1","key":"30_CR6","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/S0010-4655(01)00413-1","volume":"143","author":"EJ Bylaska","year":"2002","unstructured":"Bylaska, E.J., Valiev, M., Kawai, R., Weare, J.H.: Parallel implementation of the projector augmented plane wave method for charged systems. Comput. Phys. Commun. 143(1), 11\u201328 (2002)","journal-title":"Comput. Phys. Commun."},{"issue":"1","key":"30_CR7","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1016\/j.cpc.2005.03.099","volume":"169","author":"A Canning","year":"2005","unstructured":"Canning, A., Raczkowski, D.: Scaling first-principles plane-wave codes to thousands of processors. Comput. Phys. Commun. 169(1), 449\u2013453 (2005)","journal-title":"Comput. Phys. Commun."},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Canning, A., Shalf, J., Wang, L.W., Wasserman, H., Gajbe, M.: A comparison of different communication structures for scalable parallel three dimensional FFTs in first principle codes. In: Chapman, B., Desprez, F., Joubert, G.R., et al. (eds.), pp. 107\u2013116 (2010)","DOI":"10.3233\/978-1-60750-530-3-107"},{"issue":"22","key":"30_CR9","doi-asserted-by":"crossref","first-page":"2471","DOI":"10.1103\/PhysRevLett.55.2471","volume":"55","author":"R Car","year":"1985","unstructured":"Car, R., Parrinello, M.: Unified approach for molecular dynamics and density-functional theory. Phys. Rev. Lett. 55(22), 2471 (1985)","journal-title":"Phys. Rev. Lett."},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bylaska, E., Weare, J.: First principles estimation of geochemically important transition metal oxide properties. In: Molecular Modeling of Geochemical Reactions: An Introduction, p. 107 (2016)","DOI":"10.1002\/9781118845226.ch4"},{"key":"30_CR11","unstructured":"Cramer, T., Schmidl, D., Klemm, M., an Mey, D.: OpenMP programming on Intel Xeon Phi Coprocessors: an early performance comparison. In: Proceedings of Many Core Applications Research Community (MARC) Symposium, pp. 38\u201344 (2012)"},{"issue":"1","key":"30_CR12","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/99.660313","volume":"5","author":"L Dagum","year":"1998","unstructured":"Dagum, L., Menon, R.: OpenMP: an industry standard API for shared-memory programming. IEEE Computat. Sci. Eng. 5(1), 46\u201355 (1998)","journal-title":"IEEE Computat. Sci. Eng."},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Fattebert, J.L., Osei-Kuffuor, D., Draeger, E.W., Ogitsu, T., Krauss, W.D.: Modeling dilute solutions using first-principles molecular dynamics: computing more than a million atoms with over a million cores. In: International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2016, pp. 12\u201322. IEEE (2016)","DOI":"10.1109\/SC.2016.88"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Gygi, F.: Architecture of Qbox: A scalable first-principles molecular dynamics code. IBM J. Res. Develop. 52(1.2), 137\u2013144 (2008)","DOI":"10.1147\/rd.521.0137"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Jacquelin, M., De Jong, W., Bylaska, E.: Towards highly scalable Ab initio molecular dynamics (AIMD) simulations on the Intel knights landing manycore processor. In: 31st IEEE International Parallel & Distributed Processing Symposium. IEEE Computer Society (2017, Accepted)","DOI":"10.1109\/IPDPS.2017.26"},{"issue":"26","key":"30_CR16","doi-asserted-by":"crossref","first-page":"6896","DOI":"10.1039\/c002859b","volume":"12","author":"WA Jong de","year":"2010","unstructured":"de Jong, W.A., Bylaska, E., Govind, N., Janssen, C.L., Kowalski, K., M\u00fcller, T., Nielsen, I.M., van Dam, H.J., Veryazov, V., Lindh, R.: Utilizing high performance computing for chemistry: parallel computational chemistry. Phys. Chem. Chem. Phys. 12(26), 6896\u20136920 (2010)","journal-title":"Phys. Chem. Chem. Phys."},{"key":"30_CR17","unstructured":"Kim, J., Dally, W.J., Scott, S., Abts, D.: Technology-driven, highly-scalable dragonfly topology. SIGARCH Comput. Archit. News 36(3), 77\u201388 (2008). http:\/\/doi.acm.org\/10.1145\/1394608.1382129"},{"issue":"4A","key":"30_CR18","doi-asserted-by":"crossref","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(4A), A1133 (1965)","journal-title":"Phys. Rev."},{"key":"30_CR19","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198537953.001.0001","volume-title":"Algebraic Riccati Equations","author":"P Lancaster","year":"1995","unstructured":"Lancaster, P., Rodman, L.: Algebraic Riccati Equations. Clarendon Press, Oxford (1995)"},{"key":"30_CR20","unstructured":"Marx, D., Hutter, J.: Modern methods and algorithms of quantum chemistry. Grotendorst, J. (ed.), pp. 301\u2013449 (2000)"},{"key":"30_CR21","unstructured":"MPI Forum: MPI: A Message-passing Interface Standard. Tech. rep., June 2015"},{"issue":"4","key":"30_CR22","doi-asserted-by":"crossref","first-page":"1765","DOI":"10.1103\/PhysRevB.47.1765","volume":"47","author":"J Nelson","year":"1993","unstructured":"Nelson, J., Plimpton, S., Sears, M.: Plane-wave electronic-structure calculations on a parallel supercomputer. Phys. Rev. B 47(4), 1765 (1993)","journal-title":"Phys. Rev. B"},{"key":"30_CR23","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface, Version 4.5, November 2015. http:\/\/www.openmp.org\/"},{"key":"30_CR24","doi-asserted-by":"publisher","unstructured":"Parr, R.G.: Density functional theory of atoms and molecules. In: Fukui, K., Pullman, B. (eds.) Horizons of Quantum Chemistry. Acad\u00e9mie Internationale Des Sciences Mol\u00e9culaires Quantiques\/International Academy of Quantum Molecular Science, vol. 3, pp. 5\u201315. Springer, Dordrecht (1980). doi: 10.1007\/978-94-009-9027-2_2","DOI":"10.1007\/978-94-009-9027-2_2"},{"issue":"4","key":"30_CR25","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1103\/RevModPhys.64.1045","volume":"64","author":"MC Payne","year":"1992","unstructured":"Payne, M.C., Teter, M.P., Allan, D.C., Arias, T., Joannopoulos, J.: Iterative minimization techniques for ab initio total-energy calculations: molecular dynamics and conjugate gradients. Rev. Mod. Phys. 64(4), 1045 (1992)","journal-title":"Rev. Mod. Phys."},{"key":"30_CR26","unstructured":"Polian, A., Loubeyre, P., Boccara, N.: Simple molecular systems at very high density. In: NATO Advanced Science Institutes (ASI) Series B, vol. 186 (1989)"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Rabenseifner, R., Hager, G., Jost, G.: Hybrid MPI\/OpenMP parallel programming on clusters of multi-core SMP nodes. In: 2009 17th Euromicro International Conference on Parallel, Distributed and Network-based Processing, pp. 427\u2013436. IEEE (2009)","DOI":"10.1109\/PDP.2009.43"},{"issue":"6","key":"30_CR28","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1080\/00268979000101451","volume":"70","author":"DK Remler","year":"1990","unstructured":"Remler, D.K., Madden, P.A.: Molecular dynamics without effective potentials via the car-parrinello approach. Mol. Phys. 70(6), 921\u2013966 (1990)","journal-title":"Mol. Phys."},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Sodani, A.: Knights landing (KNL): 2nd Generation Intel $$^{\\textregistered }$$ Xeon Phi Processor. In: Presentation at Hot Chips: A Symposium on High Performance Chips, August 2015","DOI":"10.1109\/HOTCHIPS.2015.7477467"},{"key":"30_CR30","unstructured":"Swarztrauber, P.: Fftpack: a package of fortran subprograms for the fast fourier transform of periodic and other symmetric sequences. Obtainable by e-mail or by ftp from nctlib@ornl.gov (1985)"},{"issue":"4","key":"30_CR31","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2","volume":"9","author":"RA Geijn Van De","year":"1997","unstructured":"Van De Geijn, R.A., Watts, J.: Summa: scalable universal matrix multiplication algorithm. Concurrency-Pract. Exp. 9(4), 255\u2013274 (1997)","journal-title":"Concurrency-Pract. Exp."},{"issue":"3","key":"30_CR32","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/0010-4655(94)00153-S","volume":"87","author":"J Wiggs","year":"1995","unstructured":"Wiggs, J., Jonsson, H.: A hybrid decomposition parallel implementation of the car-parrinello method. Comput. Phys. Commun. 87(3), 319\u2013340 (1995)","journal-title":"Comput. Phys. Commun."},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009). http:\/\/doi.acm.org\/10.1145\/1498765.1498785","DOI":"10.1145\/1498765.1498785"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-67630-2_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T15:25:28Z","timestamp":1750951528000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-67630-2_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319676296","9783319676302"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-67630-2_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}