{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:44:35Z","timestamp":1773193475446,"version":"3.50.1"},"publisher-location":"Cham","reference-count":90,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030479558","type":"print"},{"value":"9783030479565","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,7,31]],"date-time":"2020-07-31T00:00:00Z","timestamp":1596153600000},"content-version":"vor","delay-in-days":212,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-47956-5_14","type":"book-chapter","created":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T17:26:56Z","timestamp":1596130016000},"page":"405-452","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["ExaStencils: Advanced Multigrid Solver Generation"],"prefix":"10.1007","author":[{"given":"Christian","family":"Lengauer","sequence":"first","affiliation":[]},{"given":"Sven","family":"Apel","sequence":"additional","affiliation":[]},{"given":"Matthias","family":"Bolten","sequence":"additional","affiliation":[]},{"given":"Shigeru","family":"Chiba","sequence":"additional","affiliation":[]},{"given":"Ulrich","family":"R\u00fcde","sequence":"additional","affiliation":[]},{"given":"J\u00fcrgen","family":"Teich","sequence":"additional","affiliation":[]},{"given":"Armin","family":"Gr\u00f6\u00dflinger","sequence":"additional","affiliation":[]},{"given":"Frank","family":"Hannig","sequence":"additional","affiliation":[]},{"given":"Harald","family":"K\u00f6stler","sequence":"additional","affiliation":[]},{"given":"Lisa","family":"Claus","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Grebhahn","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Groth","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Kronawitter","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"Kuckuk","sequence":"additional","affiliation":[]},{"given":"Hannah","family":"Rittich","sequence":"additional","affiliation":[]},{"given":"Christian","family":"Schmitt","sequence":"additional","affiliation":[]},{"given":"Jonas","family":"Schmitt","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,7,31]]},"reference":[{"key":"14_CR1","volume-title":"Structure and Interpretation of Computer Programs","author":"H Abelson","year":"1996","unstructured":"Abelson, H., Sussman, G.J., Sussman, J.: Structure and Interpretation of Computer Programs, 2nd edn. The MIT Press, Cambridge (1996)","edition":"2"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Adams, M.F., Brown, J., Shalf, J., Straalen, B.V., Strohmaier, E., Williams, S.: HPGMG 1.0: a benchmark for ranking high performance computing systems. Tech. Rep. LBNL-6630E, Lawrence Berkeley National Laboratory (2014)","DOI":"10.2172\/1131029"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Afzal, A., Schmitt, C., Alhaddad, S., Grynko, Y., Teich, J., F\u00f6rstner, J., Hannig, F.: Solving Maxwell\u2019s equations with modern C++ and SYCL: a case study. In: Proceedings of the Annual IEEE International Conference on Application-Specific Systems, Architectures and Processors (ASAP), pp. 49\u201356. IEEE, New York (2018)","DOI":"10.1109\/ASAP.2018.8445127"},{"key":"14_CR4","volume-title":"Online-editor und visualisierung f\u00fcr ExaStencils","author":"T Ammenh\u00e4user","year":"2019","unstructured":"Ammenh\u00e4user, T.: Online-editor und visualisierung f\u00fcr ExaStencils. Bachelor\u2019s thesis, University of Wuppertal (2019)"},{"key":"14_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37521-7","volume-title":"Feature-Oriented Software Product Lines: Concepts and Implementation","author":"S Apel","year":"2013","unstructured":"Apel, S., Batory, D., K\u00e4stner, C., Saake, G.: Feature-Oriented Software Product Lines: Concepts and Implementation. Springer, Berlin (2013)"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Bandishti, V., Pananilath, I., Bondhugula, U.: Tiling stencil computations to maximize parallelism. In: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis (SC), pp. 40:1\u201340:11. IEEE Computer Society, Washington (2012)","DOI":"10.1109\/SC.2012.107"},{"key":"14_CR7","unstructured":"Bastian, P., Altenbernd, M., Dreier, N.A., Engwer, C., Fahlke, J., Fritze, R., Geveler, M., G\u00f6ddeke, D., Iliev, O., Ippisch, O., Mohring, J., M\u00fcthing, S., Ohlberger, M., Ribbrock, D., Turek, S.: EXA-DUNE: flexible PDE solvers, numerical methods and applications (in this volume)"},{"key":"14_CR8","unstructured":"Bauer, S., Bunge, H.P., Drzisga, D., Ghelichkhan, S., Huber, M., Kohl, N., Mohr, M., R\u00fcde, U., Th\u00f6nnes, D., Wohlmuth, B.: TerraNeo: mantle convection beyond a trillion degrees of freedom (in this volume)"},{"key":"14_CR9","unstructured":"Blatt, M., Burchardt, A., Dedner, A., Engwer, C., Fahlke, J., Flemisch, B., Gersbacher, C., Gr\u00e4ser, C., Gruber, F., Gr\u00fcninger, C., Kempf, D., Kl\u00f6fkorn, R., Malkmus, T., M\u00fcthing, S., Nolte, M., Piatkowski, M., Sander, O.: The distributed and unified numerics environment, version 2.4. Arch. Numer. Softw. 4(100), 13\u201329 (2016)"},{"issue":"3","key":"14_CR10","doi-asserted-by":"publisher","first-page":"A1642","DOI":"10.1137\/16M1073959","volume":"40","author":"M Bolten","year":"2018","unstructured":"Bolten, M., Rittich, H.: Fourier analysis of periodic stencils in multigrid methods. SIAM J. Sci. Comput. 40(3), A1642\u2013A1668 (2018)","journal-title":"SIAM J. Sci. Comput."},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Bolten, M., Franchetti, F., Kelly, P.H.J., Lengauer, C., Mohr, M.: Algebraic description and automatic generation of multigrid methods in SPIRAL. Concurr. Comput. Pract. Exp. 29(17), 4105:1\u20134105:11 (2017). Special issue: Advanced Stencil-Code Engineering","DOI":"10.1002\/cpe.4105"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Bondhugula, U., Hartono, A., Ramanujam, J., Sadayappan, P.: A practical automatic polyhedral parallelizer and locality optimizer. In: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI), pp. 101\u2013113. ACM, New York (2008)","DOI":"10.1145\/1379022.1375595"},{"issue":"5","key":"14_CR13","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TPDS.2016.2615094","volume":"28","author":"U Bondhugula","year":"2017","unstructured":"Bondhugula, U., Bandishti, V., Pananilath, I.: Diamond tiling: tiling techniques to maximize parallelism for stencil computations. IEEE Trans. Parallel Distrib. Syst. 28(5), 1285\u20131298 (2017)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"14_CR14","unstructured":"Calotoiu, A., Copik, M., Hoefler, T., Ritter, M., Wolf, F.: ExtraPeak: advanced automatic performance modeling for HPC applications (in this volume)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Chiba, S.: Foreign language interfaces by code migration. In: 18th ACM SIGPLAN International Conference on Generative Programming: Concepts & Experiences (GPCE), pp. 1\u201313. ACM, New York (2019)","DOI":"10.1145\/3357765.3359521"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Chiba, S., Zhuang, Y., Scherr, M.: Deeply reifying running code for constructing a domain-specific language. In: Proceedings of the 13th International Conference on Principles and Practices of Programming on the Java Platform: Virtual Machines, Languages, and Tools (PPPJ), pp. 1:1\u20131:12. ACM, New York (2016)","DOI":"10.1145\/2972206.2972219"},{"key":"14_CR17","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-981-13-1924-2_8","volume-title":"Advanced Software Technologies for Post-Peta Scale Computing, chap. 8","author":"S Chiba","year":"2019","unstructured":"Chiba, S., Zhuang, Y., Dao, T.C.: A development platform for embedded domain-specific languages. In: Sato, M. (ed.) Advanced Software Technologies for Post-Peta Scale Computing, chap. 8, pp. 139\u2013161. Springer, Singapore (2019)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Christen, M., Schenk, O., Burkhart, H.: PATUS: a code generation and autotuning framework for parallel iterative stencil computations on modern microarchitectures. In: Proceedings of the 25th IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 676\u2013687 (2011)","DOI":"10.1109\/IPDPS.2011.70"},{"key":"14_CR19","unstructured":"Claus, L.: Multigrid smoothers for saddle point systems. Ph.D. thesis, University of Wuppertal (2019). 133 pp."},{"issue":"2","key":"14_CR20","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1137\/16M1106304","volume":"39","author":"D Drzisga","year":"2018","unstructured":"Drzisga, D., John, L., R\u00fcde, U., Wohlmuth, B., Zulehner, W.: On the analysis of block smoothers for saddle point problems. SIAM J. Matrix Anal. Appl. 39(2), 932\u2013960 (2018)","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Elman, H.C., Silvester, D.J., Wathen, A.J.: Finite Elements and Fast Iterative Solvers. Numerical Mathematics and Scientific Computation, 2nd edn. Oxford University Press, Oxford (2014)","DOI":"10.1093\/acprof:oso\/9780199678792.001.0001"},{"key":"14_CR22","first-page":"1581","volume-title":"Encyclopedia of Parallel Computing","author":"P Feautrier","year":"2011","unstructured":"Feautrier, P., Lengauer, C.: Polyhedron model. In: Padua, D.A., et al. (eds.) Encyclopedia of Parallel Computing, pp. 1581\u20131592. Springer, New York (2011)"},{"key":"14_CR23","first-page":"2171","volume":"13","author":"FA Fortin","year":"2012","unstructured":"Fortin, F.A., De Rainville, F.M., Gardner, M.A., Parizeau, M., Gagn\u00e9, C.: DEAP: evolutionary algorithms made easy. J. Mach. Learn. Res. 13, 2171\u20132175 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Franchetti, F., Low, T.M., Popovici, D.T., Veras, R.M., Spampinato, D.G., Johnson, J.R., P\u00fcschel, M., Hoe, J.C., Moura, J.M.F.: SPIRAL: extreme performance portability. Proc. IEEE 106(11), 1935\u20131968 (2018). Special issue: From High-Level Specification to High-Performance Code","DOI":"10.1109\/JPROC.2018.2873289"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Frigo, M., Johnson, S.G.: The design and implementation of FFTW3. Proc. IEEE 93(2), 216\u2013231 (2005). Special issue: Program Generation, Optimization, and Platform Adaptation","DOI":"10.1109\/JPROC.2004.840301"},{"key":"14_CR26","volume-title":"Implementierung des TGV Algorithmus mithilfe von ExaSlang","author":"M Gerecke","year":"2017","unstructured":"Gerecke, M.: Implementierung des TGV Algorithmus mithilfe von ExaSlang. Bachelor\u2019s thesis, Friedrich-Alexander University Erlangen-N\u00fcrnberg (2017)"},{"key":"14_CR27","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1016\/j.jocs.2016.06.006","volume":"17","author":"B Gmeiner","year":"2016","unstructured":"Gmeiner, B., Huber, M., John, L., R\u00fcde, U., Wohlmuth, B.: A quantitative performance study for Stokes solvers at the extreme scale. J. Computat. Sci. 17, 509\u2013521 (2016)","journal-title":"J. Computat. Sci."},{"key":"14_CR28","unstructured":"Grebhahn, A.: Performance prediction of highly configurable software systems: multigrid systems and beyond. Ph.D. thesis, Faculty of Computer Science and Mathematics, University of Passau (2020, to be submitted)"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Grebhahn, A., Kuckuk, S., Schmitt, C., K\u00f6stler, H., Siegmund, N., Apel, S., Hannig, F., Teich, J.: Experiments on optimizing the performance of stencil codes with SPL Conqueror. Par. Proc. Lett. 24(3), 19 pp. (2014). Article 1441001","DOI":"10.1142\/S0129626414410011"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Grebhahn, A., Siegmund, N., K\u00f6stler, H., Apel, S.: Performance prediction of multigrid-solver configurations. In: Software for Exascale Computing \u2013 SPPEXA 2013\u20132015. Lecture Notes in Computational Science and Engineering, vol. 113, pp. 69\u201388. Springer, New York (2016)","DOI":"10.1007\/978-3-319-40528-5_4"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Grebhahn, A., Engwer, C., Bolten, M., Apel, S.: Variability of stencil computations for porous media. Concurr. Computat. Pract. Exp. 29(17), 4119:1\u20134119:14 (2017). Special issue: Advanced Stencil-Code Engineering","DOI":"10.1002\/cpe.4119"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Grebhahn, A., Rodrigo, C., Siegmund, N., Gaspar, F.J., Apel, S.: Performance-influence models of multigrid methods: a case study on triangular meshes. Concurr. Comput. Pract. Exp. 29(17), 4057:1\u20134057:13 (2017). Special issue: Advanced Stencil-Code Engineering","DOI":"10.1002\/cpe.4057"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Groth, S., Schmitt, C., Teich, J., Hannig, F.: SYCL code generation for multigrid methods. In: Proceedings of the 22nd International Workshop on Software and Compilers for Embedded Systems (SCOPES), pp. 41\u201344. ACM, New York (2019)","DOI":"10.1145\/3323439.3323984"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Gysi, T., Osuna, C., Fuhrer, O., Bianco, M., Schulthess, T.C.: Stella: a domain-specific tool for structured grid methods in weather and climate models. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC), pp. 41:1\u201341:12. ACM, New York (2015)","DOI":"10.1145\/2807591.2807627"},{"key":"14_CR35","unstructured":"Hannig, F.: Domain-specific and resource-aware computing (2017). Habilitation thesis, Friedrich-Alexander University Erlangen-N\u00fcrnberg, 444 pp."},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Kaltenecker, C., Grebhahn, A., Siegmund, N., Guo, J., Apel, S.: Distance-based sampling of software configuration spaces. In: Proceedings of the IEEE\/ACM International Conference on Software Engineering (ICSE), pp. 1084\u20131094. IEEE Computer Society, Washington (2019)","DOI":"10.1109\/ICSE.2019.00112"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Kenter, T., Mahale, G., Alhaddad, S., Grynko, Y., Schmitt, C., Afzal, A., Hannig, F., F\u00f6rstner, J., Plessl, C.: OpenCL-based FPGA design to accelerate the nodal discontinuous Galerkin method for unstructured meshes. In: Proceedings of the 26th IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 189\u2013196. IEEE, New York (2018)","DOI":"10.1109\/FCCM.2018.00037"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Kohl, N., Th\u00f6nnes, D., Drzisga, D., Bartuschat, D., R\u00fcde, U.: The HyTeG finite-element software framework for scalable multigrid solvers. Int. J. Parallel Emergent Distrib. Syst. 1\u201320 (2018).","DOI":"10.1080\/17445760.2018.1506453"},{"issue":"3","key":"14_CR39","doi-asserted-by":"publisher","first-page":"2265","DOI":"10.1007\/s10270-018-0662-9","volume":"18","author":"S Kolesnikov","year":"2019","unstructured":"Kolesnikov, S., Siegmund, N., K\u00e4stner, C., Grebhahn, A., Apel, S.: Tradeoffs in modeling performance of highly-configurable software systems. Softw. Syst. Model. 18(3), 2265\u20132283 (2019)","journal-title":"Softw. Syst. Model."},{"key":"14_CR40","unstructured":"K\u00f6stler, H.: Effiziente numerische Algorithmen und Softwareentwicklung f\u00fcr hochparallele Rechensysteme (2014). Habilitation thesis, Friedrich-Alexander University Erlangen-N\u00fcrnberg, 94 pp."},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"K\u00f6stler, H., Heisig, M., Kohl, N., Kuckuk, S., Bauer, M., R\u00fcde, U.: Code generation approaches for parallel geometric multigrid solvers. Analele Stiintifice ale Universitatii Ovidius, Seria Matematica (2019, accepted for publication)","DOI":"10.2478\/auom-2020-0038"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Krause, D., Th\u00f6rnig, P.: JURECA: modular supercomputer at J\u00fclich Supercomputing Centre. J. Large-Scale Res. Fac. 4, A132, 9 pp. (2018)","DOI":"10.17815\/jlsrf-4-121-1"},{"key":"14_CR43","unstructured":"Kronawitter, S.: Automatic optimization of stencil codes. Ph.D. thesis, University of Passau (2019), 130 pp."},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Kronawitter, S., Lengauer, C.: Polyhedral search space exploration in the ExaStencils code generator. ACM Trans. Archit. Code Op. 15(4), 40:1\u201340:25 (2019)","DOI":"10.1145\/3274653"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Kronawitter, S., Kuckuk, S., Lengauer, C.: Redundancy elimination in the ExaStencils code generator. In: Carretero, J., et al. (eds.) Algorithms and Architectures for Parallel Processing (ICA3PP), Collocated Workshops. Lecture Notes in Computer Science, vol. 10049, pp. 159\u2013173. Springer, New York (2016). First International Workshop on Data Locality in Modern Computing Systems (DLMCS)","DOI":"10.1007\/978-3-319-49956-7_13"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Kronawitter, S., Kuckuk, S., K\u00f6stler, H., Lengauer, C.: Automatic data layout transformations in the ExaStencils code generator. Parallel Proc. Lett. 28(3), 18 pp. (2018). Article 1850009","DOI":"10.1142\/S0129626418500093"},{"key":"14_CR47","unstructured":"Kuckuk, S.: Automatic code generation for massively parallel applications in computational fluid dynamics. Ph.D. thesis, Friedrich\u2013Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (2019), 243 pp."},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Kuckuk, S., K\u00f6stler, H.: Automatic generation of massively parallel codes from ExaSlang. Computation 4(3), 20 pp. (2016). Article 27. Special issue: High Performance Computing (HPC) Software Design","DOI":"10.3390\/computation4030027"},{"key":"14_CR49","doi-asserted-by":"crossref","unstructured":"Kuckuk, S., K\u00f6stler, H.: Whole program generation of massively parallel shallow water equation solvers. In: 2018 IEEE International Conference on Cluster Computing (CLUSTER), pp. 78\u201387. IEEE, New York (2018)","DOI":"10.1109\/CLUSTER.2018.00020"},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Kuckuk, S., Haase, G., Vasco, D., K\u00f6stler, H.: Towards generating efficient flow solvers with the ExaStencils approach. Concurr. Comput. Pract. Exp. 29(17), 4062:1\u20134062:17 (2017). Special issue: Advanced Stencil-Code Engineering","DOI":"10.1002\/cpe.4062"},{"key":"14_CR51","unstructured":"Kuckuk, S., Leitenmaier, L., Schmitt, C., Sch\u00f6nwetter, D., K\u00f6stler, H., Fey, D.: Towards virtual hardware prototyping for generated geometric multigrid solvers. Tech. Rep. CS 2017-01, Department of Computer Science, Friedrich-Alexander University Erlangen-N\u00fcrnberg (2017). 10 pp."},{"key":"14_CR52","doi-asserted-by":"crossref","unstructured":"Lange, M., Kukreja, N., Louboutin, M., Luporini, F., Vieira, F., Pandolfo, V., Velesko, P., Kazakas, P., Gorman, G.: Devito: towards a generic finite difference DSL using symbolic Python. In: Proceedings of the Workshop on Python for High-Performance and Scientific Computing (PyHPC), pp. 67\u201375. IEEE, New York (2016)","DOI":"10.1109\/PyHPC.2016.013"},{"key":"14_CR53","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1007\/978-3-319-14313-2_47","volume-title":"Euro-Par 2014: Parallel Processing Workshops, Part II. Lecture Notes in Computer Science","author":"C Lengauer","year":"2014","unstructured":"Lengauer, C., Apel, S., Bolten, M., Gr\u00f6\u00dflinger, A., Hannig, F., K\u00f6stler, H., R\u00fcde, U., Teich, J., Grebhahn, A., Kronawitter, S., Kuckuk, S., Rittich, H., Schmitt, C.: ExaStencils: advanced stencil-code engineering. In: Lopes, L., et al. (eds.) Euro-Par 2014: Parallel Processing Workshops, Part II. Lecture Notes in Computer Science, vol. 8806, pp. 553\u2013564. Springer, New York (2014)"},{"key":"14_CR54","doi-asserted-by":"crossref","unstructured":"Luporini, F., Varbanescu, A.L., Rathgeber, F., Bercea, G.T., Ramanujam, J., Ham, D.A., Kelly, P.H.J.: Cross-loop optimization of arithmetic intensity for finite element local assembly. ACM Trans. Archit. Code Op. 11(4), 57:1\u201357:25 (2015)","DOI":"10.1145\/2687415"},{"key":"14_CR55","doi-asserted-by":"crossref","unstructured":"Membarth, R., Hannig, F., Teich, J., K\u00f6rner, M., Eckert, W.: Generating device-specific GPU code for local operators in medical imaging. In: Proceedings of the 26th IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 569\u2013581. IEEE, New York (2012)","DOI":"10.1109\/IPDPS.2012.59"},{"issue":"12","key":"14_CR56","doi-asserted-by":"publisher","first-page":"3191","DOI":"10.1016\/j.jpdc.2014.08.008","volume":"74","author":"R Membarth","year":"2014","unstructured":"Membarth, R., Reiche, O., Schmitt, C., Hannig, F., Teich, J., St\u00fcrmer, M., K\u00f6stler, H.: Towards a performance-portable description of geometric multigrid algorithms using a domain-specific language. J. Parallel Distrib. Comput. 74(12), 3191\u20133201 (2014)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"1","key":"14_CR57","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1109\/TPDS.2015.2394802","volume":"27","author":"R Membarth","year":"2016","unstructured":"Membarth, R., Reiche, O., Hannig, F., Teich, J., K\u00f6rner, M., Eckert, W.: HIPAcc: a domain-specific language and compiler for image processing. IEEE Trans. Parallel Distrib. Syst. 27(1), 210\u2013224 (2016)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"1","key":"14_CR58","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1145\/2786763.2694364","volume":"43","author":"RT Mullapudi","year":"2015","unstructured":"Mullapudi, R.T., Vasista, V., Bondhugula, U.: PolyMage: automatic optimization for image processing pipelines. SIGARCH Comput. Archit. News 43(1), 429\u2013443 (2015)","journal-title":"SIGARCH Comput. Archit. News"},{"key":"14_CR59","unstructured":"Nair, V., Yu, Z., Menzies, T., Siegmund, N., Apel, S.: Finding faster configurations using FLASH. IEEE Trans. Softw. Eng. (2018) [Online first]"},{"key":"14_CR60","volume-title":"Encyclopedia of Parallel Computing","year":"2011","unstructured":"Padua, D.A., et al. (eds.): Encyclopedia of Parallel Computing. Springer, New York (2011)"},{"key":"14_CR61","first-page":"1920","volume-title":"Encyclopedia of Parallel Computing","author":"M P\u00fcschel","year":"2011","unstructured":"P\u00fcschel, M., Franchetti, F., Voronenko, Y.: Spiral. In: Padua, D.A., et al. (eds.) Encyclopedia of Parallel Computing, pp. 1920\u20131933. Springer, New York (2011)"},{"key":"14_CR62","doi-asserted-by":"crossref","unstructured":"Ragan-Kelley Jonathan, E.A.: Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines. ACM SIGPLAN Not. 48(6), 519\u2013530 (2013). Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI)","DOI":"10.1145\/2499370.2462176"},{"key":"14_CR63","doi-asserted-by":"crossref","unstructured":"Rathgeber, F., Ham, D.A., Mitchell, L., Lange, M., Luporini, F., Mcrae, A.T.T., Bercea, G.T., Markall, G.R., Kelly, P.H.J.: Firedrake: automating the finite element method by composing abstractions. ACM Trans. Math. Softw. 43(3), 24:1\u201324:27 (2017)","DOI":"10.1145\/2998441"},{"key":"14_CR64","volume-title":"Code generation vs","author":"D Ribica","year":"2018","unstructured":"Ribica, D.: Code generation vs. HPC framework. Bachelor\u2019s thesis, Friedrich-Alexander University Erlangen-N\u00fcrnberg (2018)"},{"key":"14_CR65","unstructured":"Rittich, H.: LFA Lab. https:\/\/hrittich.github.io\/lfa-lab\/"},{"key":"14_CR66","unstructured":"Rittich, H.: Extending and automating Fourier analysis for multigrid methods. Ph.D. thesis, Faculty of Mathematics and Natural Sciences, University of Wuppertal (2017). 202 pp."},{"issue":"6","key":"14_CR67","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1002\/jcc.20008","volume":"25","author":"R Schmid","year":"2004","unstructured":"Schmid, R.: Car-Parrinello simulations with a real space method. J. Comput. Chem. 25(6), 799\u2013812 (2004)","journal-title":"J. Comput. Chem."},{"key":"14_CR68","doi-asserted-by":"crossref","unstructured":"Schmid, R., Tafipolsky, M., K\u00f6nig, P.H., K\u00f6stler, H.: Car-Parrinello molecular dynamics using real space wavefunctions. Phys. Status Solidi (B) 243(5), 1001\u20131015 (2006)","DOI":"10.1002\/pssb.200541391"},{"key":"14_CR69","unstructured":"Schmid, M., Reiche, O., Schmitt, C., Hannig, F., Teich, J.: Code generation for high-level synthesis of multiresolution applications on FPGAs. In: Proceedings of the First International Workshop on FPGAs for Software Programmers (FSP), pp. 21\u201326 (2014). arXiv:1408.4721"},{"key":"14_CR70","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/978-3-319-26408-0_7","volume-title":"FPGAs for Software Programmers, chap. 7","author":"M Schmid","year":"2016","unstructured":"Schmid, M., Schmitt, C., Hannig, F., Malazgirt, G.A., S\u00f6nmez, N., Yurdakul, A., Cristal, A.: Big Data and HPC acceleration with Vivado HLS. In: Koch, D., Hannig, F., Ziener, D. (eds.) FPGAs for Software Programmers, chap. 7, pp. 115\u2013136. Springer, New York (2016)"},{"key":"14_CR71","unstructured":"Schmitt, C.: A domain-specific language and source-to-source compilation framework for geometric multigrid methods. Ph.D. thesis, Friedrich-Alexander University Erlangen-N\u00fcrnberg (2019). Verlag Dr. Hut, 203 pp."},{"key":"14_CR72","doi-asserted-by":"crossref","unstructured":"Schmitt, C., Kuckuk, S., Hannig, F., K\u00f6stler, H., Teich, J.: ExaSlang: a domain-specific language for highly scalable multigrid solvers. In: Proceedings of the 4th International Workshop on Domain-Specific Languages and High-Level Frameworks for High Performance Computing (WOLFHPC), pp. 42\u201351. IEEE Computer Society, Washington (2014)","DOI":"10.1109\/WOLFHPC.2014.11"},{"key":"14_CR73","unstructured":"Schmitt, C., Schmid, M., Hannig, F., Teich, J., Kuckuk, S., K\u00f6stler, H.: Generation of multigrid-based numerical solvers for FPGA accelerators. In: Gr\u00f6\u00dflinger, A., K\u00f6stler, H. (eds.) Proceedings of the 2nd International Workshop on High-Performance Stencil Computations (HiStencils), pp. 9\u201315 (2015). www.viaprinto.de"},{"key":"14_CR74","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/978-3-319-40528-5_3","volume-title":"Software for Exascale Computing \u2013 SPPEXA 2013\u20132015, Lecture Notes in Computational Science and Engineering","author":"C Schmitt","year":"2016","unstructured":"Schmitt, C., Kuckuk, S., Hannig, F., Teich, J., K\u00f6stler, H., R\u00fcde, U., Lengauer, C.: Systems of partial differential equations in ExaSlang. In: Bungartz, H.J., Neumann, P., Nagel, W.E. (eds.) Software for Exascale Computing \u2013 SPPEXA 2013-2015, Lecture Notes in Computational Science and Engineering, vol. 113, pp. 47\u201367. Springer, Heidelberg (2016)"},{"key":"14_CR75","unstructured":"Schmitt, C., Hannig, F., Teich, J.: A target platform description language for code generation in HPC. In: Workshop Proceedings of the 31st GI\/ITG International Conference on Architecture of Computing Systems (ARCS), pp. 59\u201366. VDE, Berlin (2018)"},{"key":"14_CR76","doi-asserted-by":"crossref","unstructured":"Schmitt, C., Kronawitter, S., Hannig, F., Teich, J., Lengauer, C.: Automating the development of high-performance multigrid solvers. Proc. IEEE 106(11), 1969\u20131984 (2018). Special issue: From High-Level Specification to High-Performance Code","DOI":"10.1109\/JPROC.2018.2854229"},{"key":"14_CR77","doi-asserted-by":"crossref","unstructured":"Schmitt, C., Schmid, M., Kuckuk, S., K\u00f6stler, H., Teich, J., Hannig, F.: Reconfigurable hardware generation of multigrid solvers with conjugate gradient coarse-grid solution. Parallel Process. Lett. 28(4), 20 pp. (2018). Article 1850013","DOI":"10.1142\/S0129626418500160"},{"key":"14_CR78","unstructured":"Schmitt, J., Kuckuk, S., K\u00f6stler, H.: Optimizing Geometric Multigrid Methods with Evolutionary Computation (2019). arXiv:1910.02749"},{"key":"14_CR79","volume-title":"Multigrid for the SPIRAL prototype in Scala","author":"S Schweikl","year":"2017","unstructured":"Schweikl, S.: Multigrid for the SPIRAL prototype in Scala. Bachelor\u2019s thesis, University of Passau (2017)"},{"key":"14_CR80","doi-asserted-by":"crossref","unstructured":"Siegmund, N., Grebhahn, A., Apel, S., K\u00e4stner, C.: Performance-influence models for highly configurable systems. In: Proceedings of the European Software Engineering Conference and ACM SIGSOFT International Symposium on the Foundations of Software Engineering (ESEC\/FSE), pp. 284\u2013294. ACM Press, New York (2015)","DOI":"10.1145\/2786805.2786845"},{"key":"14_CR81","doi-asserted-by":"crossref","unstructured":"Spampinato, D., Fabregat-Traver, D., Bientinesi, P., P\u00fcschel, M.: Program generation for small-scale linear algebra applications. In: Proceedings of the International Symposium on Code Generation and Optimization (CGO), pp. 327\u2013339. ACM, New York (2018)","DOI":"10.1145\/3168812"},{"key":"14_CR82","doi-asserted-by":"crossref","unstructured":"Tang, Y., Chowdhury, R.A., Kuszmaul, B.C., Luk, C.K., Leiserson, C.E.: The Pochoir stencil compiler. In: Proceedings of the 23rd Annual ACM Symposium on Parallelism in Algorithms and Architectures (SPAA), pp. 117\u2013128. ACM, New York (2011)","DOI":"10.1145\/1989493.1989508"},{"key":"14_CR83","doi-asserted-by":"crossref","unstructured":"Treibig, J., Hager, G., Wellein, G.: LIKWID: a lightweight performance-oriented tool suite for \u00d786 multicore environments. In: Proceedings of the 39th International Conference on Parallel Processing Workshops (ICPPW), vol. 1, pp. 207\u2013216 (2010). International Workshop on Parallel Software Tools and Tool Infrastructures (PSTI)","DOI":"10.1109\/ICPPW.2010.38"},{"key":"14_CR84","volume-title":"Multigrid","author":"U Trottenberg","year":"2001","unstructured":"Trottenberg, U., Oosterlee, C.W., Schuller, A.: Multigrid. Academic, London (2001)"},{"key":"14_CR85","doi-asserted-by":"crossref","unstructured":"Unat, D., Cai, X., Baden, S.B.: Mint: realizing CUDA performance in 3D stencil methods with annotated C. In: Proceedings of the International Conference on Supercomputing (ICS), pp. 214\u2013224. ACM, New York (2011)","DOI":"10.1145\/1995896.1995932"},{"key":"14_CR86","unstructured":"van Rossum, G.: Python Reference Manual. Tech. Rep. CS-R9525, Centrum voor Wiskunde en Informatica (CWI) (1995)"},{"issue":"1","key":"14_CR87","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1016\/0021-9991(86)90008-2","volume":"65","author":"S Vanka","year":"1986","unstructured":"Vanka, S.: Block-implicit multigrid solution of Navier-Stokes equations in primitive variables. J. Comput. Phys. 65(1), 138\u2013158 (1986)","journal-title":"J. Comput. Phys."},{"key":"14_CR88","volume-title":"Practical Fourier Analysis For Multigrid Methods","author":"R Wienands","year":"2005","unstructured":"Wienands, R., Joppich, W.: Practical Fourier Analysis For Multigrid Methods. Chapman Hall\/CRC Press, Boca Raton (2005)"},{"issue":"4","key":"14_CR89","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Watermann, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009)","journal-title":"Commun. ACM"},{"key":"14_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, N., Driscoll, M., Markley, C., Williams, S., Basu, P., Fox, A.: Snowflake: a lightweight portable stencil DSL. In: Proceedings of the IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 795\u2013804. IEEE, New York (2017)","DOI":"10.1109\/IPDPSW.2017.89"}],"container-title":["Lecture Notes in Computational Science and Engineering","Software for Exascale Computing - SPPEXA 2016-2019"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-47956-5_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,27]],"date-time":"2021-03-27T10:21:09Z","timestamp":1616840469000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-47956-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030479558","9783030479565"],"references-count":90,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-47956-5_14","relation":{},"ISSN":["1439-7358","2197-7100"],"issn-type":[{"value":"1439-7358","type":"print"},{"value":"2197-7100","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"31 July 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}