{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T06:53:06Z","timestamp":1725864786150},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319405261"},{"type":"electronic","value":"9783319405285"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-40528-5_21","type":"book-chapter","created":{"date-parts":[[2016,9,14]],"date-time":"2016-09-14T02:50:15Z","timestamp":1473821415000},"page":"467-481","source":"Crossref","is-referenced-by-count":5,"title":["Automated Performance Modeling of the UG4 Simulation Framework"],"prefix":"10.1007","author":[{"given":"Andreas","family":"Vogel","sequence":"first","affiliation":[]},{"given":"Alexandru","family":"Calotoiu","sequence":"additional","affiliation":[]},{"given":"Arne","family":"N\u00e4gel","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"Reiter","sequence":"additional","affiliation":[]},{"given":"Alexandre","family":"Strube","sequence":"additional","affiliation":[]},{"given":"Gabriel","family":"Wittum","sequence":"additional","affiliation":[]},{"given":"Felix","family":"Wolf","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,9,15]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","first-page":"2864","DOI":"10.1137\/100798806","volume":"33","author":"A. Baker","year":"2011","unstructured":"Baker, A., Falgout, R., Kolev, T., Yang, U.: Multigrid smoothers for ultra-parallel computing. SIAM J. Sci. Comput. 33, 2864\u20132887 (2011)","journal-title":"SIAM J. Sci. Comput."},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Baker, A.H., Falgout, R.D., Gamblin, T., Kolev, T.V., Schulz, M., Yang, U.M.: Scaling algebraic multigrid solvers: on the road to exascale. In: Competence in High Performance Computing 2010, pp. 215\u2013226. Springer, Berlin\/New York (2012)","DOI":"10.1007\/978-3-642-24025-6_18"},{"issue":"2","key":"21_CR3","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1002\/nla.1816","volume":"19","author":"P. Bastian","year":"2012","unstructured":"Bastian, P., Blatt, M., Scheichl, R.: Algebraic multigrid for discontinuous Galerkin discretizations of heterogeneous elliptic problems. Numer. Linear Algebra 19 (2), 367\u2013388 (2012)","journal-title":"Numer. Linear Algebra"},{"issue":"6","key":"21_CR4","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/MCSE.2006.102","volume":"8","author":"B. Bergen","year":"2006","unstructured":"Bergen, B., Gradl, T., Rude, U., Hulsemann, F.: A massively parallel multigrid method for finite elements. Comput. Sci. Eng. 8 (6), 56\u201362 (2006)","journal-title":"Comput. Sci. Eng."},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Boyd, E.L., Azeem, W., Lee, H.H., Shih, T.P., Hung, S.H., Davidson, E.S.: A hierarchical approach to modeling and improving the performance of scientific applications on the KSR1. In: Proceedings of the 1994 International Conference on Parallel Processing, St. Charles, vol. III, pp. 188\u2013192. IEEE (1994)","DOI":"10.1109\/ICPP.1994.30"},{"key":"21_CR6","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-07232-5","volume-title":"Finite Elemente","author":"D. Braess","year":"2003","unstructured":"Braess, D.: Finite Elemente. Springer, Berlin (2003)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Calotoiu, A., Hoefler, T., Poke, M., Wolf, F.: Using automated performance modeling to find scalability bugs in complex codes. In: Proceedings of the ACM\/IEEE Conference on Supercomputing (SC13), Denver. ACM (2013)","DOI":"10.1145\/2503210.2503277"},{"key":"21_CR8","volume-title":"Mass-producing insightful performance models","author":"A. Calotoiu","year":"2014","unstructured":"Calotoiu, A., Hoefler, T., Wolf, F.: Mass-producing insightful performance models. In: Workshop on Modeling & Simulation of Systems and Applications, Seattle, Aug 2014"},{"issue":"4","key":"21_CR9","doi-asserted-by":"crossref","first-page":"1340008","DOI":"10.1142\/S0129626413400082","volume":"23","author":"L. Carrington","year":"2013","unstructured":"Carrington, L., Laurenzano, M., Tiwari, A.: Characterizing large-scale HPC applications through trace extrapolation. Parallel Process. Lett. 23 (4), 1340008 (2013)","journal-title":"Parallel Process. Lett."},{"key":"21_CR10","volume-title":"Finite Element Methods (Part 1)","author":"P.G. Ciarlet","year":"1991","unstructured":"Ciarlet, P.G., Lions, J.: Finite Element Methods (Part 1). North-Holland, Amsterdam (1991)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Gahvari, H., Gropp, W.: An introductory exascale feasibility study for FFTs and multigrid. In: International Symposium on Parallel & Distributed Processing (IPDPS), pp. 1\u20139. IEEE, Piscataway (2010)","DOI":"10.1109\/IPDPS.2010.5470417"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Gahvari, H., Baker, A.H., Schulz, M., Yang, U.M., Jordan, K.E., Gropp, W.: Modeling the performance of an algebraic multigrid cycle on HPC platforms. In: Proceedings of the International Conference on Supercomputing, pp. 172\u2013181. ACM, New York (2011)","DOI":"10.1145\/1995896.1995924"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Girona, S., Labarta, J., Badia, R.M.: Validation of dimemas communication model for MPI collective operations. In: Proceedings of the 7th European PVM\/MPI Users\u2019 Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface, pp. 39\u201346. Springer, London (2000). http:\/\/dl.acm.org\/citation.cfm?id=648137.746640","DOI":"10.1007\/3-540-45255-9_9"},{"issue":"1","key":"21_CR14","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1002\/cpe.2968","volume":"26","author":"B. Gmeiner","year":"2014","unstructured":"Gmeiner, B., K\u00f6stler, H., St\u00fcrmer, M., R\u00fcde, U.: Parallel multigrid on hierarchical hybrid grids: a performance study on current high performance computing clusters. Concurr. Comput.: Pract. Exp. 26 (1), 217\u2013240 (2014)","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"21_CR15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-02427-0","volume-title":"Multi-grid Methods and Applications","author":"W. Hackbusch","year":"1985","unstructured":"Hackbusch, W.: Multi-grid Methods and Applications, vol. 4. Springer, Berlin\/New York (1985)"},{"key":"21_CR16","unstructured":"Hackbusch, W.: Theorie und Numerik elliptischer Differentialgleichungen: mit Beispielen und \u00dcbungsaufgaben. Teubner (1996)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Heppner, I., Lampe, M., N\u00e4gel, A., Reiter, S., Rupp, M., Vogel, A., Wittum, G.: Software framework ug4: parallel multigrid on the hermit supercomputer. In: High Performance Computing in Science and Engineering \u201912, pp. 435\u2013449. Springer, Cham (2013)","DOI":"10.1007\/978-3-642-33374-3_32"},{"issue":"6","key":"21_CR18","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1002\/(SICI)1097-024X(199606)26:6<635::AID-SPE26>3.0.CO;2-P","volume":"26","author":"R. Ierusalimschy","year":"1996","unstructured":"Ierusalimschy, R., De Figueiredo, L.H., Celes Filho, W.: Lua-an extensible extension language. Softw. Pract. Exp. 26 (6), 635\u2013652 (1996)","journal-title":"Softw. Pract. Exp."},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Lee, B.C., Brooks, D.M., de Supinski, B.R., Schulz, M., Singh, K., McKee, S.A.: Methods of inference and learning for performance modeling of parallel applications. In: Proceedings of the 12th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP \u201907), pp. 249\u2013258. ACM, New York (2007)","DOI":"10.1145\/1229428.1229479"},{"issue":"2","key":"21_CR20","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.ejpb.2008.11.009","volume":"72","author":"A. N\u00e4gel","year":"2009","unstructured":"N\u00e4gel, A., Heisig, M., Wittum, G.: A comparison of two- and three-dimensional models for the simulation of the permeability of human stratum corneum. Eur. J. Pharm. Biopharm. 72 (2), 332\u2013338 (2009)","journal-title":"Eur. J. Pharm. Biopharm."},{"issue":"2","key":"21_CR21","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.addr.2012.10.009","volume":"65","author":"A. N\u00e4gel","year":"2013","unstructured":"N\u00e4gel, A., Heisig, M., Wittum, G.: Detailed modeling of skin penetration\u2014an overview. Adv. Drug Deliv. Rev. 65 (2), 191\u2013207 (2013)","journal-title":"Adv. Drug Deliv. Rev."},{"key":"21_CR22","unstructured":"ParMetis (Nov 2015), http:\/\/glaros.dtc.umn.edu\/gkhome\/metis\/parmetis\/overview"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Petrini, F., Kerbyson, D.J., Pakin, S.: The case of the missing supercomputer performance: achieving optimal performance on the 8,192 processors of ASCI Q. In: Proceedings of the ACM\/IEEE Conference on Supercomputing (SC\u201903), pp. 55ff. ACM, New York (2003)","DOI":"10.1145\/1048935.1050204"},{"issue":"387","key":"21_CR24","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1080\/01621459.1984.10478083","volume":"79","author":"R.R. Picard","year":"1984","unstructured":"Picard, R.R., Cook, R.D.: Cross-validation of regression models. J. Am. Stat. Assoc. 79 (387), 575\u2013583 (1984)","journal-title":"J. Am. Stat. Assoc."},{"key":"21_CR25","unstructured":"Reiter, S.: Efficient algorithms and data structures for the realization of adaptive, hierarchical grids on massively parallel systems. Ph.D. thesis, University of Frankfurt, Germany (2014)"},{"key":"21_CR26","unstructured":"Reiter, S.: Promesh (Nov 2015), http:\/\/www.promesh3d.com"},{"issue":"4","key":"21_CR27","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1007\/s00791-014-0231-x","volume":"16","author":"S. Reiter","year":"2013","unstructured":"Reiter, S., Vogel, A., Heppner, I., Rupp, M., Wittum, G.: A massively parallel geometric multigrid solver on hierarchically distributed grids. Comput. Vis. Sci. 16 (4), 151\u2013164 (2013)","journal-title":"Comput. Vis. Sci."},{"key":"21_CR28","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898718003","volume-title":"Iterative Methods for Sparse Linear Systems","author":"Y. Saad","year":"2003","unstructured":"Saad, Y.: Iterative Methods for Sparse Linear Systems. SIAM, Philadelphia (2003)"},{"key":"21_CR29","doi-asserted-by":"crossref","first-page":"1361","DOI":"10.1137\/090747774","volume":"32","author":"R. Sampath","year":"2010","unstructured":"Sampath, R., Biros, G.: A parallel geometric multigrid method for finite elements on octree meshes. SIAM J. Sci. Comput. 32, 1361\u20131392 (2010)","journal-title":"SIAM J. Sci. Comput."},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Shudler, S., Calotoiu, A., Hoefler, T., Strube, A., Wolf, F.: Exascaling your library: will your implementation meet your expectations? In: Proceedings of the International Conference on Supercomputing (ICS), Newport Beach, pp. 1\u201311. ACM (2015)","DOI":"10.1145\/2751205.2751216"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Siebert, C., Wolf, F.: Parallel sorting with minimal data. In: Recent Advances in the Message Passing Interface, pp. 170\u2013177. Springer, Berlin\/New York (2011)","DOI":"10.1007\/978-3-642-24449-0_20"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Spafford, K.L., Vetter, J.S.: Aspen: a domain specific language for performance modeling. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC \u201912, pp. 84:1\u201384:11. IEEE Computer Society Press, Los Alamitos (2012)","DOI":"10.1109\/SC.2012.20"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Sundar, H., Biros, G., Burstedde, C., Rudi, J., Ghattas, O., Stadler, G.: Parallel geometric-algebraic multigrid on unstructured forests of octrees. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, p. 43. IEEE Computer Society Press, Los Alamitos (2012)","DOI":"10.1109\/SC.2012.91"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Tallent, N.R., Hoisie, A.: Palm: easing the burden of analytical performance modeling. In: Proceedings of the International Conference on Supercomputing (ICS), pp. 221\u2013230. ACM, New York (2014)","DOI":"10.1145\/2597652.2597683"},{"key":"21_CR35","unstructured":"UG4 (Nov 2015), https:\/\/github.com\/UG4"},{"key":"21_CR36","unstructured":"Vogel, A.: Flexible und kombinierbare Implementierung von Finite-Volumen-Verfahren h\u00f6herer Ordnung mit Anwendungen f\u00fcr die Konvektions-Diffusions-, Navier-Stokes- und Nernst-Planck-Gleichungen sowie dichtegetriebene Grundwasserstr\u00f6mung in por\u00f6sen Medien. Ph.D. thesis, Universit\u00e4t Frankfurt am Main (2014)"},{"issue":"4","key":"21_CR37","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s00791-014-0232-9","volume":"16","author":"A. Vogel","year":"2013","unstructured":"Vogel, A., Reiter, S., Rupp, M., N\u00e4gel, A., Wittum, G.: UG 4: a novel flexible software system for simulating PDE based models on high performance computers. Comput. Vis. Sci. 16 (4), 165\u2013179 (2013)","journal-title":"Comput. Vis. Sci."},{"key":"21_CR38","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1007\/978-3-662-48096-0_40","volume-title":"Euro-Par 2015: Parallel Processing, Theoretical Computer Science and General Issues","author":"A. Vogel","year":"2015","unstructured":"Vogel, A., Calotoiu, A., Strube, A., Reiter, S., N\u00e4gel, A., Wolf, F., Wittum, G.: 10,000 performance models per minute\u2014scalability of the UG4 simulation framework. In: Tr\u00e4ff, J.L., Hunold, S., Versaci, F. (eds.) Euro-Par 2015: Parallel Processing, Theoretical Computer Science and General Issues, vol. 9233, pp. 519\u2013531. Springer, Heidelberg (2015)"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Williams, S., Lijewski, M., Almgren, A., Straalen, B.V., Carson, E., Knight, N., Demmel, J.: s-step Krylov subspace methods as bottom solvers for geometric multigrid. In: 28th International Parallel and Distributed Processing Symposium, pp. 1149\u20131158. IEEE, Piscataway (2014)","DOI":"10.1109\/IPDPS.2014.119"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Wolf, F., Bischof, C., Hoefler, T., Mohr, B., Wittum, G., Calotoiu, A., Iwainsky, C., Strube, A., Vogel, A.: Catwalk: a quick development path for performance models. In: Euro-Par 2014: Parallel Processing Workshops. Lecture Notes in Computer Science, pp. 589\u2013600. Springer, Cham (2014)","DOI":"10.1007\/978-3-319-14313-2_50"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Wu, X., Mueller, F.: ScalaExtrap: trace-based communication extrapolation for SPMD programs. In: Proceedings of the 16th ACM Symposium on Principles and Practice of Parallel Programming (PPoPP \u201911), pp. 113\u2013122. ACM, New York (2011)","DOI":"10.1145\/1941553.1941569"},{"issue":"5","key":"21_CR42","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1145\/1837853.1693493","volume":"45","author":"J. Zhai","year":"2010","unstructured":"Zhai, J., Chen, W., Zheng, W.: Phantom: predicting performance of parallel applications on large-scale parallel machines using a single node. Sigplan Not. 45 (5), 305\u2013314 (2010)","journal-title":"Sigplan Not."}],"container-title":["Lecture Notes in Computational Science and Engineering","Software for Exascale Computing - SPPEXA 2013-2015"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-40528-5_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,13]],"date-time":"2019-09-13T09:13:00Z","timestamp":1568365980000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-40528-5_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319405261","9783319405285"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-40528-5_21","relation":{},"ISSN":["1439-7358","2197-7100"],"issn-type":[{"type":"print","value":"1439-7358"},{"type":"electronic","value":"2197-7100"}],"subject":[],"published":{"date-parts":[[2016]]}}}