[{"language":[{"iso":"eng"}],"type":"book_chapter","citation":{"short":"A. Ramaswami, T. Kenter, T. Kühne, C. Plessl, in: Applied Reconfigurable Computing. Architectures, Tools, and Applications, Springer International Publishing, Cham, 2021.","ieee":"A. Ramaswami, T. Kenter, T. Kühne, and C. Plessl, “Evaluating the Design Space for Offloading 3D FFT Calculations to an FPGA for High-Performance Computing,” in Applied Reconfigurable Computing. Architectures, Tools, and Applications, Cham: Springer International Publishing, 2021.","ama":"Ramaswami A, Kenter T, Kühne T, Plessl C. Evaluating the Design Space for Offloading 3D FFT Calculations to an FPGA for High-Performance Computing. In: Applied Reconfigurable Computing. Architectures, Tools, and Applications. Springer International Publishing; 2021. doi:10.1007/978-3-030-79025-7_21","apa":"Ramaswami, A., Kenter, T., Kühne, T., & Plessl, C. (2021). Evaluating the Design Space for Offloading 3D FFT Calculations to an FPGA for High-Performance Computing. In Applied Reconfigurable Computing. Architectures, Tools, and Applications. Int. Conf. on Applied Reconfigurable Computing. Architectures, Tools, and Applications. Springer International Publishing. https://doi.org/10.1007/978-3-030-79025-7_21","chicago":"Ramaswami, Arjun, Tobias Kenter, Thomas Kühne, and Christian Plessl. “Evaluating the Design Space for Offloading 3D FFT Calculations to an FPGA for High-Performance Computing.” In Applied Reconfigurable Computing. Architectures, Tools, and Applications. Cham: Springer International Publishing, 2021. https://doi.org/10.1007/978-3-030-79025-7_21.","mla":"Ramaswami, Arjun, et al. “Evaluating the Design Space for Offloading 3D FFT Calculations to an FPGA for High-Performance Computing.” Applied Reconfigurable Computing. Architectures, Tools, and Applications, Springer International Publishing, 2021, doi:10.1007/978-3-030-79025-7_21.","bibtex":"@inbook{Ramaswami_Kenter_Kühne_Plessl_2021, place={Cham}, title={Evaluating the Design Space for Offloading 3D FFT Calculations to an FPGA for High-Performance Computing}, DOI={10.1007/978-3-030-79025-7_21}, booktitle={Applied Reconfigurable Computing. Architectures, Tools, and Applications}, publisher={Springer International Publishing}, author={Ramaswami, Arjun and Kenter, Tobias and Kühne, Thomas and Plessl, Christian}, year={2021} }"},"year":"2021","_id":"29936","date_updated":"2023-09-26T11:40:45Z","conference":{"name":"Int. Conf. on Applied Reconfigurable Computing. Architectures, Tools, and Applications"},"doi":"10.1007/978-3-030-79025-7_21","author":[{"orcid":"https://orcid.org/0000-0002-0909-1178","full_name":"Ramaswami, Arjun","first_name":"Arjun","id":"49171","last_name":"Ramaswami"},{"first_name":"Tobias","full_name":"Kenter, Tobias","last_name":"Kenter","id":"3145"},{"last_name":"Kühne","id":"49079","first_name":"Thomas","full_name":"Kühne, Thomas"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"quality_controlled":"1","publisher":"Springer International Publishing","publication":"Applied Reconfigurable Computing. Architectures, Tools, and Applications","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"status":"public","date_created":"2022-02-21T14:22:01Z","publication_status":"published","publication_identifier":{"issn":["0302-9743","1611-3349"],"isbn":["9783030790240","9783030790257"]},"place":"Cham","user_id":"15278","title":"Evaluating the Design Space for Offloading 3D FFT Calculations to an FPGA for High-Performance Computing"},{"_id":"24788","year":"2021","type":"journal_article","citation":{"bibtex":"@article{Alhaddad_Förstner_Groth_Grünewald_Grynko_Hannig_Kenter_Pfreundt_Plessl_Schotte_et al._2021, title={The HighPerMeshes framework for numerical algorithms on unstructured grids}, DOI={10.1002/cpe.6616}, journal={Concurrency and Computation: Practice and Experience}, author={Alhaddad, Samer and Förstner, Jens and Groth, Stefan and Grünewald, Daniel and Grynko, Yevgen and Hannig, Frank and Kenter, Tobias and Pfreundt, Franz‐Josef and Plessl, Christian and Schotte, Merlind and et al.}, year={2021}, pages={e6616} }","mla":"Alhaddad, Samer, et al. “The HighPerMeshes Framework for Numerical Algorithms on Unstructured Grids.” Concurrency and Computation: Practice and Experience, 2021, p. e6616, doi:10.1002/cpe.6616.","apa":"Alhaddad, S., Förstner, J., Groth, S., Grünewald, D., Grynko, Y., Hannig, F., Kenter, T., Pfreundt, F., Plessl, C., Schotte, M., Steinke, T., Teich, J., Weiser, M., & Wende, F. (2021). The HighPerMeshes framework for numerical algorithms on unstructured grids. Concurrency and Computation: Practice and Experience, e6616. https://doi.org/10.1002/cpe.6616","ama":"Alhaddad S, Förstner J, Groth S, et al. The HighPerMeshes framework for numerical algorithms on unstructured grids. Concurrency and Computation: Practice and Experience. Published online 2021:e6616. doi:10.1002/cpe.6616","chicago":"Alhaddad, Samer, Jens Förstner, Stefan Groth, Daniel Grünewald, Yevgen Grynko, Frank Hannig, Tobias Kenter, et al. “The HighPerMeshes Framework for Numerical Algorithms on Unstructured Grids.” Concurrency and Computation: Practice and Experience, 2021, e6616. https://doi.org/10.1002/cpe.6616.","ieee":"S. Alhaddad et al., “The HighPerMeshes framework for numerical algorithms on unstructured grids,” Concurrency and Computation: Practice and Experience, p. e6616, 2021, doi: 10.1002/cpe.6616.","short":"S. Alhaddad, J. Förstner, S. Groth, D. Grünewald, Y. Grynko, F. Hannig, T. Kenter, F. Pfreundt, C. Plessl, M. Schotte, T. Steinke, J. Teich, M. Weiser, F. Wende, Concurrency and Computation: Practice and Experience (2021) e6616."},"page":"e6616","user_id":"15278","ddc":["004"],"file":[{"date_created":"2021-09-22T06:19:29Z","file_name":"2021-09 Alhaddad - Concurrency... - The HighPerMeshes framework for numerical algorithms on unstructured grids.pdf","access_level":"open_access","file_size":2300152,"file_id":"24789","creator":"fossie","content_type":"application/pdf","date_updated":"2021-09-22T06:19:29Z","relation":"main_file"}],"author":[{"id":"42456","last_name":"Alhaddad","full_name":"Alhaddad, Samer","first_name":"Samer"},{"last_name":"Förstner","id":"158","first_name":"Jens","orcid":"0000-0001-7059-9862","full_name":"Förstner, Jens"},{"first_name":"Stefan","full_name":"Groth, Stefan","last_name":"Groth"},{"last_name":"Grünewald","first_name":"Daniel","full_name":"Grünewald, Daniel"},{"id":"26059","last_name":"Grynko","full_name":"Grynko, Yevgen","first_name":"Yevgen"},{"full_name":"Hannig, Frank","first_name":"Frank","last_name":"Hannig"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"full_name":"Pfreundt, Franz‐Josef","first_name":"Franz‐Josef","last_name":"Pfreundt"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"},{"first_name":"Merlind","full_name":"Schotte, Merlind","last_name":"Schotte"},{"last_name":"Steinke","full_name":"Steinke, Thomas","first_name":"Thomas"},{"last_name":"Teich","first_name":"Jürgen","full_name":"Teich, Jürgen"},{"first_name":"Martin","full_name":"Weiser, Martin","last_name":"Weiser"},{"last_name":"Wende","first_name":"Florian","full_name":"Wende, Florian"}],"quality_controlled":"1","publication":"Concurrency and Computation: Practice and Experience","file_date_updated":"2021-09-22T06:19:29Z","keyword":["tet_topic_hpc"],"has_accepted_license":"1","status":"public","date_created":"2021-09-22T06:15:50Z","date_updated":"2023-09-26T11:42:19Z","oa":"1","doi":"10.1002/cpe.6616","language":[{"iso":"eng"}],"title":"The HighPerMeshes framework for numerical algorithms on unstructured grids","department":[{"_id":"61"},{"_id":"230"},{"_id":"27"},{"_id":"518"}],"project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"_id":"33","name":"HighPerMeshes","grant_number":"01|H16005A"}],"publication_identifier":{"issn":["1532-0626","1532-0634"]},"publication_status":"published"},{"publication_status":"published","status":"public","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"date_created":"2022-02-21T14:26:37Z","publisher":"IEEE","quality_controlled":"1","author":[{"full_name":"Karp, Martin","first_name":"Martin","last_name":"Karp"},{"last_name":"Podobas","first_name":"Artur","full_name":"Podobas, Artur"},{"full_name":"Jansson, Niclas","first_name":"Niclas","last_name":"Jansson"},{"first_name":"Tobias","full_name":"Kenter, Tobias","last_name":"Kenter","id":"3145"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"},{"full_name":"Schlatter, Philipp","first_name":"Philipp","last_name":"Schlatter"},{"first_name":"Stefano","full_name":"Markidis, Stefano","last_name":"Markidis"}],"publication":"2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","department":[{"_id":"27"},{"_id":"518"}],"title":"High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection","user_id":"3145","year":"2021","type":"conference","citation":{"bibtex":"@inproceedings{Karp_Podobas_Jansson_Kenter_Plessl_Schlatter_Markidis_2021, title={High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection}, DOI={10.1109/ipdps49936.2021.00116}, booktitle={2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)}, publisher={IEEE}, author={Karp, Martin and Podobas, Artur and Jansson, Niclas and Kenter, Tobias and Plessl, Christian and Schlatter, Philipp and Markidis, Stefano}, year={2021} }","mla":"Karp, Martin, et al. “High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection.” 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), IEEE, 2021, doi:10.1109/ipdps49936.2021.00116.","chicago":"Karp, Martin, Artur Podobas, Niclas Jansson, Tobias Kenter, Christian Plessl, Philipp Schlatter, and Stefano Markidis. “High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection.” In 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 2021. https://doi.org/10.1109/ipdps49936.2021.00116.","apa":"Karp, M., Podobas, A., Jansson, N., Kenter, T., Plessl, C., Schlatter, P., & Markidis, S. (2021). High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection. 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). https://doi.org/10.1109/ipdps49936.2021.00116","ama":"Karp M, Podobas A, Jansson N, et al. High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE; 2021. doi:10.1109/ipdps49936.2021.00116","ieee":"M. Karp et al., “High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection,” 2021, doi: 10.1109/ipdps49936.2021.00116.","short":"M. Karp, A. Podobas, N. Jansson, T. Kenter, C. Plessl, P. Schlatter, S. Markidis, in: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), IEEE, 2021."},"language":[{"iso":"eng"}],"doi":"10.1109/ipdps49936.2021.00116","_id":"29937","date_updated":"2024-01-22T09:59:13Z"},{"external_id":{"arxiv":["2003.03868"]},"title":"CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"name":"Performance and Efficiency in HPC with Custom Computing","grant_number":"PL 595/2-1 / 320898746","_id":"32"},{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"publication_status":"published","date_updated":"2023-08-02T14:56:21Z","oa":"1","doi":"10.1063/5.0007045","language":[{"iso":"eng"}],"abstract":[{"text":"CP2K is an open source electronic structure and molecular dynamics software package to perform atomistic simulations of solid-state, liquid, molecular, and biological systems. It is especially aimed at massively parallel and linear-scaling electronic structure methods and state-of-theart ab initio molecular dynamics simulations. Excellent performance for electronic structure calculations is achieved using novel algorithms implemented for modern high-performance computing systems. This review revisits the main capabilities of CP2K to perform efficient and accurate electronic structure simulations. The emphasis is put on density functional theory and multiple post–Hartree–Fock methods using the Gaussian and plane wave approach and its augmented all-electron extension.","lang":"eng"}],"user_id":"75963","ddc":["540"],"file":[{"date_created":"2020-05-25T15:21:56Z","file_name":"5.0007045.pdf","access_level":"closed","file_size":4887650,"file_id":"17061","creator":"lass","content_type":"application/pdf","date_updated":"2020-05-25T15:21:56Z","success":1,"relation":"main_file"}],"file_date_updated":"2020-05-25T15:21:56Z","publication":"The Journal of Chemical Physics","author":[{"first_name":"Thomas","full_name":"Kühne, Thomas","last_name":"Kühne","id":"49079"},{"first_name":"Marcella","full_name":"Iannuzzi, Marcella","last_name":"Iannuzzi"},{"last_name":"Ben","full_name":"Ben, Mauro Del","first_name":"Mauro Del"},{"last_name":"Rybkin","full_name":"Rybkin, Vladimir V.","first_name":"Vladimir V."},{"full_name":"Seewald, Patrick","first_name":"Patrick","last_name":"Seewald"},{"last_name":"Stein","first_name":"Frederick","full_name":"Stein, Frederick"},{"last_name":"Laino","full_name":"Laino, Teodoro","first_name":"Teodoro"},{"first_name":"Rustam Z.","full_name":"Khaliullin, Rustam Z.","last_name":"Khaliullin"},{"full_name":"Schütt, Ole","first_name":"Ole","last_name":"Schütt"},{"first_name":"Florian","full_name":"Schiffmann, Florian","last_name":"Schiffmann"},{"full_name":"Golze, Dorothea","first_name":"Dorothea","last_name":"Golze"},{"last_name":"Wilhelm","full_name":"Wilhelm, Jan","first_name":"Jan"},{"first_name":"Sergey","full_name":"Chulkov, Sergey","last_name":"Chulkov"},{"last_name":"Mohammad Hossein Bani-Hashemian","first_name":"Mohammad Hossein Bani-Hashemian","full_name":"Mohammad Hossein Bani-Hashemian, Mohammad Hossein Bani-Hashemian"},{"last_name":"Weber","first_name":"Valéry","full_name":"Weber, Valéry"},{"last_name":"Borstnik","first_name":"Urban","full_name":"Borstnik, Urban"},{"last_name":"Taillefumier","full_name":"Taillefumier, Mathieu","first_name":"Mathieu"},{"last_name":"Jakobovits","full_name":"Jakobovits, Alice Shoshana","first_name":"Alice Shoshana"},{"last_name":"Lazzaro","first_name":"Alfio","full_name":"Lazzaro, Alfio"},{"full_name":"Pabst, Hans","first_name":"Hans","last_name":"Pabst"},{"last_name":"Müller","first_name":"Tiziano","full_name":"Müller, Tiziano"},{"last_name":"Schade","id":"75963","first_name":"Robert","orcid":"0000-0002-6268-539","full_name":"Schade, Robert"},{"first_name":"Manuel","full_name":"Guidon, Manuel","last_name":"Guidon"},{"last_name":"Andermatt","first_name":"Samuel","full_name":"Andermatt, Samuel"},{"last_name":"Holmberg","full_name":"Holmberg, Nico","first_name":"Nico"},{"last_name":"Schenter","first_name":"Gregory K.","full_name":"Schenter, Gregory K."},{"last_name":"Hehn","full_name":"Hehn, Anna","first_name":"Anna"},{"last_name":"Bussy","first_name":"Augustin","full_name":"Bussy, Augustin"},{"full_name":"Belleflamme, Fabian","first_name":"Fabian","last_name":"Belleflamme"},{"last_name":"Tabacchi","full_name":"Tabacchi, Gloria","first_name":"Gloria"},{"last_name":"Glöß","full_name":"Glöß, Andreas","first_name":"Andreas"},{"id":"24135","last_name":"Lass","orcid":"0000-0002-5708-7632","full_name":"Lass, Michael","first_name":"Michael"},{"full_name":"Bethune, Iain","first_name":"Iain","last_name":"Bethune"},{"first_name":"Christopher J.","full_name":"Mundy, Christopher J.","last_name":"Mundy"},{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"},{"last_name":"Watkins","first_name":"Matt","full_name":"Watkins, Matt"},{"last_name":"VandeVondele","full_name":"VandeVondele, Joost","first_name":"Joost"},{"full_name":"Krack, Matthias","first_name":"Matthias","last_name":"Krack"},{"full_name":"Hutter, Jürg","first_name":"Jürg","last_name":"Hutter"}],"quality_controlled":"1","date_created":"2020-03-10T15:12:31Z","status":"public","has_accepted_license":"1","volume":152,"intvolume":" 152","_id":"16277","issue":"19","article_number":"194103","main_file_link":[{"open_access":"1","url":"https://aip.scitation.org/doi/pdf/10.1063/5.0007045?download=true"}],"citation":{"apa":"Kühne, T., Iannuzzi, M., Ben, M. D., Rybkin, V. V., Seewald, P., Stein, F., Laino, T., Khaliullin, R. Z., Schütt, O., Schiffmann, F., Golze, D., Wilhelm, J., Chulkov, S., Mohammad Hossein Bani-Hashemian, M. H. B.-H., Weber, V., Borstnik, U., Taillefumier, M., Jakobovits, A. S., Lazzaro, A., … Hutter, J. (2020). CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations. The Journal of Chemical Physics, 152(19), Article 194103. https://doi.org/10.1063/5.0007045","ama":"Kühne T, Iannuzzi M, Ben MD, et al. CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations. The Journal of Chemical Physics. 2020;152(19). doi:10.1063/5.0007045","short":"T. Kühne, M. Iannuzzi, M.D. Ben, V.V. Rybkin, P. Seewald, F. Stein, T. Laino, R.Z. Khaliullin, O. Schütt, F. Schiffmann, D. Golze, J. Wilhelm, S. Chulkov, M.H.B.-H. Mohammad Hossein Bani-Hashemian, V. Weber, U. Borstnik, M. Taillefumier, A.S. Jakobovits, A. Lazzaro, H. Pabst, T. Müller, R. Schade, M. Guidon, S. Andermatt, N. Holmberg, G.K. Schenter, A. Hehn, A. Bussy, F. Belleflamme, G. Tabacchi, A. Glöß, M. Lass, I. Bethune, C.J. Mundy, C. Plessl, M. Watkins, J. VandeVondele, M. Krack, J. Hutter, The Journal of Chemical Physics 152 (2020).","chicago":"Kühne, Thomas, Marcella Iannuzzi, Mauro Del Ben, Vladimir V. Rybkin, Patrick Seewald, Frederick Stein, Teodoro Laino, et al. “CP2K: An Electronic Structure and Molecular Dynamics Software Package - Quickstep: Efficient and Accurate Electronic Structure Calculations.” The Journal of Chemical Physics 152, no. 19 (2020). https://doi.org/10.1063/5.0007045.","ieee":"T. Kühne et al., “CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations,” The Journal of Chemical Physics, vol. 152, no. 19, Art. no. 194103, 2020, doi: 10.1063/5.0007045.","mla":"Kühne, Thomas, et al. “CP2K: An Electronic Structure and Molecular Dynamics Software Package - Quickstep: Efficient and Accurate Electronic Structure Calculations.” The Journal of Chemical Physics, vol. 152, no. 19, 194103, 2020, doi:10.1063/5.0007045.","bibtex":"@article{Kühne_Iannuzzi_Ben_Rybkin_Seewald_Stein_Laino_Khaliullin_Schütt_Schiffmann_et al._2020, title={CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations}, volume={152}, DOI={10.1063/5.0007045}, number={19194103}, journal={The Journal of Chemical Physics}, author={Kühne, Thomas and Iannuzzi, Marcella and Ben, Mauro Del and Rybkin, Vladimir V. and Seewald, Patrick and Stein, Frederick and Laino, Teodoro and Khaliullin, Rustam Z. and Schütt, Ole and Schiffmann, Florian and et al.}, year={2020} }"},"year":"2020","type":"journal_article"},{"department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"grant_number":"PL 595/2-1 / 320898746","name":"Performance and Efficiency in HPC with Custom Computing","_id":"32"},{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"external_id":{"arxiv":["2004.10811"]},"place":"Los Alamitos, CA, USA","title":"A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K","language":[{"iso":"eng"}],"date_updated":"2023-08-02T14:55:59Z","doi":"10.1109/SC41405.2020.00084","publication":"Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","author":[{"id":"24135","last_name":"Lass","orcid":"0000-0002-5708-7632","full_name":"Lass, Michael","first_name":"Michael"},{"id":"75963","last_name":"Schade","orcid":"0000-0002-6268-539","full_name":"Schade, Robert","first_name":"Robert"},{"id":"49079","last_name":"Kühne","full_name":"Kühne, Thomas","first_name":"Thomas"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"quality_controlled":"1","publisher":"IEEE Computer Society","date_created":"2020-04-28T14:44:21Z","status":"public","abstract":[{"lang":"eng","text":"Electronic structure calculations based on density-functional theory (DFT)\r\nrepresent a significant part of today's HPC workloads and pose high demands on\r\nhigh-performance computing resources. To perform these quantum-mechanical DFT\r\ncalculations on complex large-scale systems, so-called linear scaling methods\r\ninstead of conventional cubic scaling methods are required. In this work, we\r\ntake up the idea of the submatrix method and apply it to the DFT computations\r\nin the software package CP2K. For that purpose, we transform the underlying\r\nnumeric operations on distributed, large, sparse matrices into computations on\r\nlocal, much smaller and nearly dense matrices. This allows us to exploit the\r\nfull floating-point performance of modern CPUs and to make use of dedicated\r\naccelerator hardware, where performance has been limited by memory bandwidth\r\nbefore. We demonstrate both functionality and performance of our implementation\r\nand show how it can be accelerated with GPUs and FPGAs."}],"user_id":"75963","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9355245"}],"page":"1127-1140","type":"conference","citation":{"short":"M. Lass, R. Schade, T. Kühne, C. Plessl, in: Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), IEEE Computer Society, Los Alamitos, CA, USA, 2020, pp. 1127–1140.","ieee":"M. Lass, R. Schade, T. Kühne, and C. Plessl, “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K,” in Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), Atlanta, GA, US, 2020, pp. 1127–1140, doi: 10.1109/SC41405.2020.00084.","apa":"Lass, M., Schade, R., Kühne, T., & Plessl, C. (2020). A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K. Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 1127–1140. https://doi.org/10.1109/SC41405.2020.00084","ama":"Lass M, Schade R, Kühne T, Plessl C. A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K. In: Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC). IEEE Computer Society; 2020:1127-1140. doi:10.1109/SC41405.2020.00084","chicago":"Lass, Michael, Robert Schade, Thomas Kühne, and Christian Plessl. “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K.” In Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 1127–40. Los Alamitos, CA, USA: IEEE Computer Society, 2020. https://doi.org/10.1109/SC41405.2020.00084.","bibtex":"@inproceedings{Lass_Schade_Kühne_Plessl_2020, place={Los Alamitos, CA, USA}, title={A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K}, DOI={10.1109/SC41405.2020.00084}, booktitle={Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)}, publisher={IEEE Computer Society}, author={Lass, Michael and Schade, Robert and Kühne, Thomas and Plessl, Christian}, year={2020}, pages={1127–1140} }","mla":"Lass, Michael, et al. “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K.” Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), IEEE Computer Society, 2020, pp. 1127–40, doi:10.1109/SC41405.2020.00084."},"year":"2020","conference":{"name":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","location":"Atlanta, GA, US"},"_id":"16898"},{"abstract":[{"text":"FPGAs have found increasing adoption in data center applications since a new generation of high-level tools have become available which noticeably reduce development time for FPGA accelerators and still provide high-quality results. There is, however, no high-level benchmark suite available, which specifically enables a comparison of FPGA architectures, programming tools, and libraries for HPC applications. To fill this gap, we have developed an OpenCL-based open-source implementation of the HPCC benchmark suite for Xilinx and Intel FPGAs. This benchmark can serve to analyze the current capabilities of FPGA devices, cards, and development tool flows, track progress over time, and point out specific difficulties for FPGA acceleration in the HPC domain. Additionally, the benchmark documents proven performance optimization patterns. We will continue optimizing and porting the benchmark for new generations of FPGAs and design tools and encourage active participation to create a valuable tool for the community. To fill this gap, we have developed an OpenCL-based open-source implementation of the HPCC benchmark suite for Xilinx and Intel FPGAs. This benchmark can serve to analyze the current capabilities of FPGA devices, cards, and development tool flows, track progress over time, and point out specific difficulties for FPGA acceleration in the HPC domain. Additionally, the benchmark documents proven performance optimization patterns. We will continue optimizing and porting the benchmark for new generations of FPGAs and design tools and encourage active participation to create a valuable tool for the community.","lang":"eng"}],"user_id":"15278","keyword":["FPGA","OpenCL","High Level Synthesis","HPC benchmarking"],"publication":"2020 IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC)","quality_controlled":"1","author":[{"last_name":"Meyer","id":"40778","first_name":"Marius","full_name":"Meyer, Marius"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"}],"date_created":"2021-04-16T10:17:22Z","status":"public","_id":"21632","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9306963"}],"type":"conference","citation":{"short":"M. Meyer, T. Kenter, C. Plessl, in: 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2020.","ieee":"M. Meyer, T. Kenter, and C. Plessl, “Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite,” 2020, doi: 10.1109/h2rc51942.2020.00007.","chicago":"Meyer, Marius, Tobias Kenter, and Christian Plessl. “Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite.” In 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2020. https://doi.org/10.1109/h2rc51942.2020.00007.","apa":"Meyer, M., Kenter, T., & Plessl, C. (2020). Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite. 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC). https://doi.org/10.1109/h2rc51942.2020.00007","ama":"Meyer M, Kenter T, Plessl C. Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite. In: 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC). ; 2020. doi:10.1109/h2rc51942.2020.00007","mla":"Meyer, Marius, et al. “Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite.” 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2020, doi:10.1109/h2rc51942.2020.00007.","bibtex":"@inproceedings{Meyer_Kenter_Plessl_2020, title={Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite}, DOI={10.1109/h2rc51942.2020.00007}, booktitle={2020 IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC)}, author={Meyer, Marius and Kenter, Tobias and Plessl, Christian}, year={2020} }"},"year":"2020","related_material":{"link":[{"url":"https://github.com/pc2/HPCC_FPGA","description":"Official repository of the benchmark suite on GitHub","relation":"supplementary_material"}]},"title":"Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite","department":[{"_id":"27"},{"_id":"518"}],"project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"publication_identifier":{"isbn":["9781665415927"]},"publication_status":"published","date_updated":"2023-09-26T11:42:53Z","doi":"10.1109/h2rc51942.2020.00007","language":[{"iso":"eng"}]},{"external_id":{"arxiv":["1907.08497"]},"title":"Accurate Sampling with Noisy Forces from Approximate Computing","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"_id":"32","name":"Performance and Efficiency in HPC with Custom Computing","grant_number":"PL 595/2-1 / 320898746"}],"date_updated":"2023-09-26T11:43:52Z","oa":"1","doi":"10.3390/computation8020039","language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"In scientific computing, the acceleration of atomistic computer simulations by means of custom hardware is finding ever-growing application. A major limitation, however, is that the high efficiency in terms of performance and low power consumption entails the massive usage of low precision computing units. Here, based on the approximate computing paradigm, we present an algorithmic method to compensate for numerical inaccuracies due to low accuracy arithmetic operations rigorously, yet still obtaining exact expectation values using a properly modified Langevin-type equation."}],"user_id":"15278","publisher":"MDPI","author":[{"full_name":"Rengaraj, Varadarajan","first_name":"Varadarajan","last_name":"Rengaraj"},{"first_name":"Michael","full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","last_name":"Lass","id":"24135"},{"last_name":"Plessl","id":"16153","first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982"},{"last_name":"Kühne","id":"49079","first_name":"Thomas","full_name":"Kühne, Thomas"}],"quality_controlled":"1","publication":"Computation","status":"public","date_created":"2019-07-23T12:03:07Z","volume":8,"intvolume":" 8","_id":"12878","issue":"2","article_number":"39","main_file_link":[{"open_access":"1","url":"https://www.mdpi.com/2079-3197/8/2/39/pdf"}],"type":"journal_article","year":"2020","citation":{"apa":"Rengaraj, V., Lass, M., Plessl, C., & Kühne, T. (2020). Accurate Sampling with Noisy Forces from Approximate Computing. Computation, 8(2), Article 39. https://doi.org/10.3390/computation8020039","ama":"Rengaraj V, Lass M, Plessl C, Kühne T. Accurate Sampling with Noisy Forces from Approximate Computing. Computation. 2020;8(2). doi:10.3390/computation8020039","chicago":"Rengaraj, Varadarajan, Michael Lass, Christian Plessl, and Thomas Kühne. “Accurate Sampling with Noisy Forces from Approximate Computing.” Computation 8, no. 2 (2020). https://doi.org/10.3390/computation8020039.","mla":"Rengaraj, Varadarajan, et al. “Accurate Sampling with Noisy Forces from Approximate Computing.” Computation, vol. 8, no. 2, 39, MDPI, 2020, doi:10.3390/computation8020039.","bibtex":"@article{Rengaraj_Lass_Plessl_Kühne_2020, title={Accurate Sampling with Noisy Forces from Approximate Computing}, volume={8}, DOI={10.3390/computation8020039}, number={239}, journal={Computation}, publisher={MDPI}, author={Rengaraj, Varadarajan and Lass, Michael and Plessl, Christian and Kühne, Thomas}, year={2020} }","short":"V. Rengaraj, M. Lass, C. Plessl, T. Kühne, Computation 8 (2020).","ieee":"V. Rengaraj, M. Lass, C. Plessl, and T. Kühne, “Accurate Sampling with Noisy Forces from Approximate Computing,” Computation, vol. 8, no. 2, Art. no. 39, 2020, doi: 10.3390/computation8020039."}},{"language":[{"iso":"eng"}],"doi":"10.1145/3319423","date_updated":"2022-01-06T07:03:44Z","publication_status":"published","project":[{"_id":"1","name":"SFB 901"},{"_id":"4","name":"SFB 901 - Project Area C"},{"name":"SFB 901 - Subproject C2","_id":"14"}],"department":[{"_id":"27"},{"_id":"518"}],"title":"Transparent Acceleration for Heterogeneous Platforms with Compilation to OpenCL","page":"14:1–14:26","citation":{"short":"H. Riebler, G.F. Vaz, T. Kenter, C. Plessl, ACM Trans. Archit. Code Optim. (TACO) 16 (2019) 14:1–14:26.","ieee":"H. Riebler, G. F. Vaz, T. Kenter, and C. Plessl, “Transparent Acceleration for Heterogeneous Platforms with Compilation to OpenCL,” ACM Trans. Archit. Code Optim. (TACO), vol. 16, no. 2, pp. 14:1–14:26, 2019.","apa":"Riebler, H., Vaz, G. F., Kenter, T., & Plessl, C. (2019). Transparent Acceleration for Heterogeneous Platforms with Compilation to OpenCL. ACM Trans. Archit. Code Optim. (TACO), 16(2), 14:1–14:26. https://doi.org/10.1145/3319423","ama":"Riebler H, Vaz GF, Kenter T, Plessl C. Transparent Acceleration for Heterogeneous Platforms with Compilation to OpenCL. ACM Trans Archit Code Optim (TACO). 2019;16(2):14:1–14:26. doi:10.1145/3319423","chicago":"Riebler, Heinrich, Gavin Francis Vaz, Tobias Kenter, and Christian Plessl. “Transparent Acceleration for Heterogeneous Platforms with Compilation to OpenCL.” ACM Trans. Archit. Code Optim. (TACO) 16, no. 2 (2019): 14:1–14:26. https://doi.org/10.1145/3319423.","mla":"Riebler, Heinrich, et al. “Transparent Acceleration for Heterogeneous Platforms with Compilation to OpenCL.” ACM Trans. Archit. Code Optim. (TACO), vol. 16, no. 2, ACM, 2019, pp. 14:1–14:26, doi:10.1145/3319423.","bibtex":"@article{Riebler_Vaz_Kenter_Plessl_2019, title={Transparent Acceleration for Heterogeneous Platforms with Compilation to OpenCL}, volume={16}, DOI={10.1145/3319423}, number={2}, journal={ACM Trans. Archit. Code Optim. (TACO)}, publisher={ACM}, author={Riebler, Heinrich and Vaz, Gavin Francis and Kenter, Tobias and Plessl, Christian}, year={2019}, pages={14:1–14:26} }"},"type":"journal_article","year":"2019","issue":"2","intvolume":" 16","_id":"7689","volume":16,"date_created":"2019-02-13T15:01:43Z","status":"public","has_accepted_license":"1","publication":"ACM Trans. Archit. Code Optim. (TACO)","file_date_updated":"2019-02-13T14:59:07Z","keyword":["htrop"],"author":[{"first_name":"Heinrich","full_name":"Riebler, Heinrich","last_name":"Riebler","id":"8961"},{"id":"30332","last_name":"Vaz","full_name":"Vaz, Gavin Francis","first_name":"Gavin Francis"},{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian","id":"16153","last_name":"Plessl"}],"publisher":"ACM","quality_controlled":"1","file":[{"date_updated":"2019-02-13T14:59:07Z","content_type":"application/pdf","relation":"main_file","file_size":872822,"file_id":"7695","creator":"deffel","access_level":"closed","date_created":"2019-02-13T14:59:07Z","file_name":"htrop19_taco.pdf"}],"ddc":["000"],"user_id":"16153","article_type":"original"},{"title":"OpenCL Implementation of Cannon's Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs","department":[{"_id":"27"},{"_id":"518"}],"project":[{"_id":"33","grant_number":"01|H16005","name":"HighPerMeshes"},{"_id":"32","name":"Performance and Efficiency in HPC with Custom Computing","grant_number":"PL 595/2-1"}],"date_updated":"2022-01-06T06:52:26Z","doi":"10.1109/ICFPT47387.2019.00020","language":[{"iso":"eng"}],"abstract":[{"text":"Stratix 10 FPGA cards have a good potential for the acceleration of HPC workloads since the Stratix 10 product line introduces devices with a large number of DSP and memory blocks. The high level synthesis of OpenCL codes can play a fundamental role for FPGAs in HPC, because it allows to implement different designs with lower development effort compared to hand optimized HDL. However, Stratix 10 cards are still hard to fully exploit using the Intel FPGA SDK for OpenCL. The implementation of designs with thousands of concurrent arithmetic operations often suffers from place and route problems that limit the maximum frequency or entirely prevent a successful synthesis. In order to overcome these issues for the implementation of the matrix multiplication, we formulate Cannon's matrix multiplication algorithm with regard to its efficient synthesis within the FPGA logic. We obtain a two-level block algorithm, where the lower level sub-matrices are multiplied using our Cannon's algorithm implementation. Following this design approach with multiple compute units, we are able to get maximum frequencies close to and above 300 MHz with high utilization of DSP and memory blocks. This allows for performance results above 1 TeraFLOPS.","lang":"eng"}],"user_id":"3145","ddc":["004"],"file":[{"file_size":250559,"file_id":"15479","creator":"plessl","content_type":"application/pdf","date_updated":"2020-01-09T12:53:57Z","success":1,"relation":"main_file","date_created":"2020-01-09T12:53:57Z","file_name":"gorlani19_fpt.pdf","access_level":"closed"}],"publication":"Proceedings of the International Conference on Field-Programmable Technology (FPT)","file_date_updated":"2020-01-09T12:53:57Z","quality_controlled":"1","publisher":"IEEE","author":[{"last_name":"Gorlani","id":"72045","first_name":"Paolo","full_name":"Gorlani, Paolo"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"}],"date_created":"2020-01-09T12:54:48Z","status":"public","has_accepted_license":"1","conference":{"name":"International Conference on Field-Programmable Technology (FPT)"},"_id":"15478","type":"conference","citation":{"ieee":"P. Gorlani, T. Kenter, and C. Plessl, “OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs,” in Proceedings of the International Conference on Field-Programmable Technology (FPT), 2019.","short":"P. Gorlani, T. Kenter, C. Plessl, in: Proceedings of the International Conference on Field-Programmable Technology (FPT), IEEE, 2019.","bibtex":"@inproceedings{Gorlani_Kenter_Plessl_2019, title={OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs}, DOI={10.1109/ICFPT47387.2019.00020}, booktitle={Proceedings of the International Conference on Field-Programmable Technology (FPT)}, publisher={IEEE}, author={Gorlani, Paolo and Kenter, Tobias and Plessl, Christian}, year={2019} }","mla":"Gorlani, Paolo, et al. “OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs.” Proceedings of the International Conference on Field-Programmable Technology (FPT), IEEE, 2019, doi:10.1109/ICFPT47387.2019.00020.","apa":"Gorlani, P., Kenter, T., & Plessl, C. (2019). OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs. In Proceedings of the International Conference on Field-Programmable Technology (FPT). IEEE. https://doi.org/10.1109/ICFPT47387.2019.00020","ama":"Gorlani P, Kenter T, Plessl C. OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs. In: Proceedings of the International Conference on Field-Programmable Technology (FPT). IEEE; 2019. doi:10.1109/ICFPT47387.2019.00020","chicago":"Gorlani, Paolo, Tobias Kenter, and Christian Plessl. “OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs.” In Proceedings of the International Conference on Field-Programmable Technology (FPT). IEEE, 2019. https://doi.org/10.1109/ICFPT47387.2019.00020."},"year":"2019"},{"author":[{"last_name":"Vaz","id":"30332","first_name":"Gavin Francis","full_name":"Vaz, Gavin Francis"}],"publisher":"Universität Paderborn","file_date_updated":"2019-11-07T14:13:14Z","department":[{"_id":"518"}],"file":[{"date_created":"2019-11-07T14:13:14Z","file_name":"PhDThesis_GavinVaz_2019-07-11.pdf","access_level":"closed","creator":"florida","file_id":"14850","file_size":1462659,"success":1,"relation":"main_file","date_updated":"2019-11-07T14:13:14Z","content_type":"application/pdf"}],"has_accepted_license":"1","status":"public","date_created":"2019-11-07T14:13:54Z","project":[{"name":"SFB 901","_id":"1"},{"name":"SFB 901 - Project Area C","_id":"4"},{"_id":"14","name":"SFB 901 - Subproject C2"}],"title":"Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems","ddc":["040"],"user_id":"477","type":"dissertation","year":"2019","citation":{"ieee":"G. F. Vaz, Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems. Universität Paderborn, 2019.","short":"G.F. Vaz, Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems, Universität Paderborn, 2019.","bibtex":"@book{Vaz_2019, title={Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems}, publisher={Universität Paderborn}, author={Vaz, Gavin Francis}, year={2019} }","mla":"Vaz, Gavin Francis. Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems. Universität Paderborn, 2019.","chicago":"Vaz, Gavin Francis. Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems. Universität Paderborn, 2019.","ama":"Vaz GF. Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems. Universität Paderborn; 2019.","apa":"Vaz, G. F. (2019). Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems. Universität Paderborn."},"language":[{"iso":"eng"}],"supervisor":[{"full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian","id":"16153","last_name":"Plessl"}],"_id":"14849","date_updated":"2022-01-06T06:52:08Z"},{"external_id":{"arxiv":["1703.02456"]},"title":"A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"},{"_id":"104"}],"project":[{"name":"Performance and Efficiency in HPC with Custom Computing","grant_number":"PL 595/2-1 / 320898746","_id":"32"},{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_updated":"2023-09-26T11:45:02Z","doi":"10.4208/cicp.OA-2018-0053","language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"We address the general mathematical problem of computing the inverse p-th\r\nroot of a given matrix in an efficient way. A new method to construct iteration\r\nfunctions that allow calculating arbitrary p-th roots and their inverses of\r\nsymmetric positive definite matrices is presented. We show that the order of\r\nconvergence is at least quadratic and that adaptively adjusting a parameter q\r\nalways leads to an even faster convergence. In this way, a better performance\r\nthan with previously known iteration schemes is achieved. The efficiency of the\r\niterative functions is demonstrated for various matrices with different\r\ndensities, condition numbers and spectral radii."}],"user_id":"15278","publication":"Communications in Computational Physics","publisher":"Global Science Press","quality_controlled":"1","author":[{"last_name":"Richters","full_name":"Richters, Dorothee","first_name":"Dorothee"},{"last_name":"Lass","id":"24135","first_name":"Michael","full_name":"Lass, Michael","orcid":"0000-0002-5708-7632"},{"last_name":"Walther","full_name":"Walther, Andrea","first_name":"Andrea"},{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"},{"last_name":"Kühne","id":"49079","first_name":"Thomas","full_name":"Kühne, Thomas"}],"volume":25,"date_created":"2017-07-25T14:48:26Z","status":"public","intvolume":" 25","_id":"21","issue":"2","page":"564-585","year":"2019","type":"journal_article","citation":{"short":"D. Richters, M. Lass, A. Walther, C. Plessl, T. Kühne, Communications in Computational Physics 25 (2019) 564–585.","ieee":"D. Richters, M. Lass, A. Walther, C. Plessl, and T. Kühne, “A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices,” Communications in Computational Physics, vol. 25, no. 2, pp. 564–585, 2019, doi: 10.4208/cicp.OA-2018-0053.","ama":"Richters D, Lass M, Walther A, Plessl C, Kühne T. A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices. Communications in Computational Physics. 2019;25(2):564-585. doi:10.4208/cicp.OA-2018-0053","apa":"Richters, D., Lass, M., Walther, A., Plessl, C., & Kühne, T. (2019). A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices. Communications in Computational Physics, 25(2), 564–585. https://doi.org/10.4208/cicp.OA-2018-0053","chicago":"Richters, Dorothee, Michael Lass, Andrea Walther, Christian Plessl, and Thomas Kühne. “A General Algorithm to Calculate the Inverse Principal P-Th Root of Symmetric Positive Definite Matrices.” Communications in Computational Physics 25, no. 2 (2019): 564–85. https://doi.org/10.4208/cicp.OA-2018-0053.","mla":"Richters, Dorothee, et al. “A General Algorithm to Calculate the Inverse Principal P-Th Root of Symmetric Positive Definite Matrices.” Communications in Computational Physics, vol. 25, no. 2, Global Science Press, 2019, pp. 564–85, doi:10.4208/cicp.OA-2018-0053.","bibtex":"@article{Richters_Lass_Walther_Plessl_Kühne_2019, title={A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices}, volume={25}, DOI={10.4208/cicp.OA-2018-0053}, number={2}, journal={Communications in Computational Physics}, publisher={Global Science Press}, author={Richters, Dorothee and Lass, Michael and Walther, Andrea and Plessl, Christian and Kühne, Thomas}, year={2019}, pages={564–585} }"}},{"user_id":"15278","ddc":["004"],"date_created":"2019-07-22T12:42:44Z","has_accepted_license":"1","status":"public","file":[{"date_created":"2019-07-22T12:45:02Z","file_name":"plessl19_informatik_spektrum.pdf","access_level":"open_access","file_size":248360,"creator":"plessl","file_id":"12872","content_type":"application/pdf","date_updated":"2019-07-22T12:45:02Z","relation":"main_file"}],"file_date_updated":"2019-07-22T12:45:02Z","publication":"Informatik Spektrum","author":[{"id":"398","last_name":"Platzner","full_name":"Platzner, Marco","first_name":"Marco"},{"last_name":"Plessl","id":"16153","first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982"}],"quality_controlled":"1","_id":"12871","year":"2019","type":"journal_article","citation":{"ieee":"M. Platzner and C. Plessl, “FPGAs im Rechenzentrum,” Informatik Spektrum, 2019, doi: 10.1007/s00287-019-01187-w.","short":"M. Platzner, C. Plessl, Informatik Spektrum (2019).","mla":"Platzner, Marco, and Christian Plessl. “FPGAs im Rechenzentrum.” Informatik Spektrum, 2019, doi:10.1007/s00287-019-01187-w.","bibtex":"@article{Platzner_Plessl_2019, title={FPGAs im Rechenzentrum}, DOI={10.1007/s00287-019-01187-w}, journal={Informatik Spektrum}, author={Platzner, Marco and Plessl, Christian}, year={2019} }","ama":"Platzner M, Plessl C. FPGAs im Rechenzentrum. Informatik Spektrum. Published online 2019. doi:10.1007/s00287-019-01187-w","apa":"Platzner, M., & Plessl, C. (2019). FPGAs im Rechenzentrum. Informatik Spektrum. https://doi.org/10.1007/s00287-019-01187-w","chicago":"Platzner, Marco, and Christian Plessl. “FPGAs im Rechenzentrum.” Informatik Spektrum, 2019. https://doi.org/10.1007/s00287-019-01187-w."},"title":"FPGAs im Rechenzentrum","publication_identifier":{"issn":["0170-6012","1432-122X"]},"publication_status":"published","department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"oa":"1","doi":"10.1007/s00287-019-01187-w","date_updated":"2023-09-26T11:45:57Z","language":[{"iso":"ger"}]},{"language":[{"iso":"eng"}],"doi":"10.1109/LES.2017.2760923","date_updated":"2022-01-06T06:54:18Z","publication_identifier":{"eissn":["1943-0671"],"issn":["1943-0663"]},"publication_status":"published","project":[{"_id":"32","name":"Performance and Efficiency in HPC with Custom Computing","grant_number":"PL 595/2-1"},{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"title":"Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots","external_id":{"arxiv":["1703.02283"]},"page":" 33-36","year":"2018","citation":{"bibtex":"@article{Lass_Kühne_Plessl_2018, title={Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots}, volume={10}, DOI={10.1109/LES.2017.2760923}, number={2}, journal={Embedded Systems Letters}, publisher={IEEE}, author={Lass, Michael and Kühne, Thomas and Plessl, Christian}, year={2018}, pages={33–36} }","mla":"Lass, Michael, et al. “Using Approximate Computing for the Calculation of Inverse Matrix P-Th Roots.” Embedded Systems Letters, vol. 10, no. 2, IEEE, 2018, pp. 33–36, doi:10.1109/LES.2017.2760923.","apa":"Lass, M., Kühne, T., & Plessl, C. (2018). Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots. Embedded Systems Letters, 10(2), 33–36. https://doi.org/10.1109/LES.2017.2760923","ama":"Lass M, Kühne T, Plessl C. Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots. Embedded Systems Letters. 2018;10(2):33-36. doi:10.1109/LES.2017.2760923","chicago":"Lass, Michael, Thomas Kühne, and Christian Plessl. “Using Approximate Computing for the Calculation of Inverse Matrix P-Th Roots.” Embedded Systems Letters 10, no. 2 (2018): 33–36. https://doi.org/10.1109/LES.2017.2760923.","ieee":"M. Lass, T. Kühne, and C. Plessl, “Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots,” Embedded Systems Letters, vol. 10, no. 2, pp. 33–36, 2018.","short":"M. Lass, T. Kühne, C. Plessl, Embedded Systems Letters 10 (2018) 33–36."},"type":"journal_article","issue":"2","_id":"20","intvolume":" 10","volume":10,"date_created":"2017-07-25T14:41:08Z","status":"public","publication":"Embedded Systems Letters","publisher":"IEEE","author":[{"full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","first_name":"Michael","id":"24135","last_name":"Lass"},{"first_name":"Thomas","full_name":"Kühne, Thomas","last_name":"Kühne","id":"49079"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"user_id":"16153","abstract":[{"text":"Approximate computing has shown to provide new ways to improve performance\r\nand power consumption of error-resilient applications. While many of these\r\napplications can be found in image processing, data classification or machine\r\nlearning, we demonstrate its suitability to a problem from scientific\r\ncomputing. Utilizing the self-correcting behavior of iterative algorithms, we\r\nshow that approximate computing can be applied to the calculation of inverse\r\nmatrix p-th roots which are required in many applications in scientific\r\ncomputing. Results show great opportunities to reduce the computational effort\r\nand bandwidth required for the execution of the discussed algorithm, especially\r\nwhen targeting special accelerator hardware.","lang":"eng"}]},{"user_id":"477","title":"Study Effects of Approximation on Conjugate Gradient Algorithm and Accelerate it on FPGA Platform","status":"public","date_created":"2018-11-07T15:14:26Z","project":[{"name":"SFB 901","_id":"1"},{"name":"SFB 901 - Project Area C","_id":"4"},{"name":"SFB 901 - Subproject C2","_id":"14"}],"author":[{"first_name":"Tasneem","full_name":"Filmwala, Tasneem","last_name":"Filmwala"}],"publisher":"Universität Paderborn","department":[{"_id":"27"},{"_id":"518"}],"date_updated":"2022-01-06T07:01:52Z","_id":"5414","supervisor":[{"orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian","id":"16153","last_name":"Plessl"}],"language":[{"iso":"eng"}],"citation":{"bibtex":"@book{Filmwala_2018, title={Study Effects of Approximation on Conjugate Gradient Algorithm and Accelerate it on FPGA Platform}, publisher={Universität Paderborn}, author={Filmwala, Tasneem}, year={2018} }","mla":"Filmwala, Tasneem. Study Effects of Approximation on Conjugate Gradient Algorithm and Accelerate It on FPGA Platform. Universität Paderborn, 2018.","ama":"Filmwala T. Study Effects of Approximation on Conjugate Gradient Algorithm and Accelerate It on FPGA Platform. Universität Paderborn; 2018.","apa":"Filmwala, T. (2018). Study Effects of Approximation on Conjugate Gradient Algorithm and Accelerate it on FPGA Platform. Universität Paderborn.","chicago":"Filmwala, Tasneem. Study Effects of Approximation on Conjugate Gradient Algorithm and Accelerate It on FPGA Platform. Universität Paderborn, 2018.","ieee":"T. Filmwala, Study Effects of Approximation on Conjugate Gradient Algorithm and Accelerate it on FPGA Platform. Universität Paderborn, 2018.","short":"T. Filmwala, Study Effects of Approximation on Conjugate Gradient Algorithm and Accelerate It on FPGA Platform, Universität Paderborn, 2018."},"type":"mastersthesis","year":"2018"},{"supervisor":[{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"}],"language":[{"iso":"eng"}],"year":"2018","type":"mastersthesis","citation":{"bibtex":"@book{Gadewar_2018, title={Programmable Programs? - Designing FPGA Overlay Architectures with OpenCL}, publisher={Universität Paderborn}, author={Gadewar, Onkar}, year={2018} }","mla":"Gadewar, Onkar. Programmable Programs? - Designing FPGA Overlay Architectures with OpenCL. Universität Paderborn, 2018.","chicago":"Gadewar, Onkar. Programmable Programs? - Designing FPGA Overlay Architectures with OpenCL. Universität Paderborn, 2018.","ama":"Gadewar O. Programmable Programs? - Designing FPGA Overlay Architectures with OpenCL. Universität Paderborn; 2018.","apa":"Gadewar, O. (2018). Programmable Programs? - Designing FPGA Overlay Architectures with OpenCL. Universität Paderborn.","ieee":"O. Gadewar, Programmable Programs? - Designing FPGA Overlay Architectures with OpenCL. Universität Paderborn, 2018.","short":"O. Gadewar, Programmable Programs? - Designing FPGA Overlay Architectures with OpenCL, Universität Paderborn, 2018."},"date_updated":"2022-01-06T07:01:53Z","_id":"5421","department":[{"_id":"27"},{"_id":"518"}],"publisher":"Universität Paderborn","author":[{"full_name":"Gadewar, Onkar","first_name":"Onkar","last_name":"Gadewar"}],"project":[{"_id":"1","name":"SFB 901"},{"name":"SFB 901 - Project Area C","_id":"4"},{"name":"SFB 901 - Subproject C2","_id":"14"}],"date_created":"2018-11-07T16:16:56Z","status":"public","user_id":"477","title":"Programmable Programs? - Designing FPGA Overlay Architectures with OpenCL"},{"title":"Sprint diagnostic with GPS and inertial sensor fusion","publication_identifier":{"issn":["1369-7072","1460-2687"]},"publication_status":"published","department":[{"_id":"27"},{"_id":"518"}],"doi":"10.1007/s12283-018-0291-0","date_updated":"2022-01-06T07:03:09Z","language":[{"iso":"eng"}],"ddc":["000"],"user_id":"16153","volume":21,"status":"public","has_accepted_license":"1","date_created":"2019-01-08T17:44:43Z","publisher":"Springer Nature","quality_controlled":"1","author":[{"full_name":"Mertens, Jan Cedric","first_name":"Jan Cedric","last_name":"Mertens"},{"first_name":"Alexander","full_name":"Boschmann, Alexander","last_name":"Boschmann"},{"first_name":"M.","full_name":"Schmidt, M.","last_name":"Schmidt"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"}],"file_date_updated":"2019-01-08T17:47:06Z","publication":"Sports Engineering","file":[{"file_size":2141021,"file_id":"6517","creator":"plessl","content_type":"application/pdf","date_updated":"2019-01-08T17:47:06Z","relation":"main_file","date_created":"2019-01-08T17:47:06Z","file_name":"plessl18_sportseng.pdf","access_level":"closed"}],"issue":"4","intvolume":" 21","_id":"6516","citation":{"ieee":"J. C. Mertens, A. Boschmann, M. Schmidt, and C. Plessl, “Sprint diagnostic with GPS and inertial sensor fusion,” Sports Engineering, vol. 21, no. 4, pp. 441–451, 2018.","short":"J.C. Mertens, A. Boschmann, M. Schmidt, C. Plessl, Sports Engineering 21 (2018) 441–451.","bibtex":"@article{Mertens_Boschmann_Schmidt_Plessl_2018, title={Sprint diagnostic with GPS and inertial sensor fusion}, volume={21}, DOI={10.1007/s12283-018-0291-0}, number={4}, journal={Sports Engineering}, publisher={Springer Nature}, author={Mertens, Jan Cedric and Boschmann, Alexander and Schmidt, M. and Plessl, Christian}, year={2018}, pages={441–451} }","mla":"Mertens, Jan Cedric, et al. “Sprint Diagnostic with GPS and Inertial Sensor Fusion.” Sports Engineering, vol. 21, no. 4, Springer Nature, 2018, pp. 441–51, doi:10.1007/s12283-018-0291-0.","chicago":"Mertens, Jan Cedric, Alexander Boschmann, M. Schmidt, and Christian Plessl. “Sprint Diagnostic with GPS and Inertial Sensor Fusion.” Sports Engineering 21, no. 4 (2018): 441–51. https://doi.org/10.1007/s12283-018-0291-0.","ama":"Mertens JC, Boschmann A, Schmidt M, Plessl C. Sprint diagnostic with GPS and inertial sensor fusion. Sports Engineering. 2018;21(4):441-451. doi:10.1007/s12283-018-0291-0","apa":"Mertens, J. C., Boschmann, A., Schmidt, M., & Plessl, C. (2018). Sprint diagnostic with GPS and inertial sensor fusion. Sports Engineering, 21(4), 441–451. https://doi.org/10.1007/s12283-018-0291-0"},"type":"journal_article","year":"2018","page":"441-451"},{"title":"Accelerating Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGA","project":[{"_id":"1","name":"SFB 901"},{"name":"SFB 901 - Project Area C","_id":"4"},{"name":"SFB 901 - Subproject C2","_id":"14"}],"department":[{"_id":"27"},{"_id":"518"}],"oa":"1","date_updated":"2022-01-12T16:32:23Z","language":[{"iso":"eng"}],"ddc":["000"],"user_id":"49171","abstract":[{"text":"Molecular Dynamic (MD) simulations are computationally intensive and accelerating them using specialized hardware is a topic of investigation in many studies. One of the routines in the critical path of MD simulations is the three-dimensional Fast Fourier Transformation (FFT3d). The potential in accelerating FFT3d using hardware is usually bound by bandwidth and memory. Therefore, designing a high throughput solution for an FPGA that overcomes this problem is challenging.\r\nIn this thesis, the feasibility of offloading FFT3d computations to FPGA implemented using OpenCL is investigated. In order to mask the latency in memory access, an FFT3d that overlaps computation with communication is designed. The implementa- tion of this design is synthesized for the Arria 10 GX 1150 FPGA and evaluated with the FFTW benchmark. Analysis shows a better performance using FPGA over CPU for larger FFT sizes, with the 643 FFT showing a 70% improvement in runtime using FPGAs.\r\nThis FFT3d design is integrated with CP2K to explore the potential in accelerating molecular dynamic simulations. Evaluation of CP2K simulations using FPGA shows a 41% improvement in runtime in FFT3d computations over CPU for larger FFT3d designs.","lang":"eng"}],"date_created":"2018-11-07T16:08:32Z","has_accepted_license":"1","status":"public","keyword":["FFT: FPGA","CP2K","OpenCL"],"file_date_updated":"2020-06-15T11:29:38Z","publisher":"Universität Paderborn","author":[{"orcid":"https://orcid.org/0000-0002-0909-1178","full_name":"Ramaswami, Arjun","first_name":"Arjun","id":"49171","last_name":"Ramaswami"}],"file":[{"date_created":"2020-06-15T11:29:38Z","file_name":"masterthesis.pdf","access_level":"closed","file_id":"17093","creator":"arjunr","file_size":1297585,"success":1,"relation":"main_file","date_updated":"2020-06-15T11:29:38Z","content_type":"application/pdf"}],"_id":"5417","year":"2018","citation":{"bibtex":"@book{Ramaswami_2018, title={Accelerating Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGA}, publisher={Universität Paderborn}, author={Ramaswami, Arjun}, year={2018} }","mla":"Ramaswami, Arjun. Accelerating Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGA. Universität Paderborn, 2018.","chicago":"Ramaswami, Arjun. Accelerating Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGA. Universität Paderborn, 2018.","apa":"Ramaswami, A. (2018). Accelerating Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGA. Universität Paderborn.","ama":"Ramaswami A. Accelerating Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGA. Universität Paderborn; 2018.","ieee":"A. Ramaswami, Accelerating Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGA. Universität Paderborn, 2018.","short":"A. Ramaswami, Accelerating Molecular Dynamic Simulations by Offloading Fast Fourier Transformations to FPGA, Universität Paderborn, 2018."},"type":"mastersthesis","supervisor":[{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"}],"main_file_link":[{"open_access":"1"}]},{"department":[{"_id":"27"},{"_id":"518"},{"_id":"61"}],"project":[{"grant_number":"01|H16005A","name":"HighPerMeshes","_id":"33"},{"grant_number":"160364472","name":"SFB 901","_id":"1"},{"name":"SFB 901 - Project Area C","_id":"4"},{"grant_number":"160364472","name":"SFB 901 - Subproject C2","_id":"14"}],"title":"OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes","language":[{"iso":"eng"}],"date_updated":"2023-09-26T11:47:52Z","doi":"10.1109/FCCM.2018.00037","publisher":"IEEE","quality_controlled":"1","author":[{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"first_name":"Gopinath","full_name":"Mahale, Gopinath","last_name":"Mahale"},{"full_name":"Alhaddad, Samer","first_name":"Samer","id":"42456","last_name":"Alhaddad"},{"first_name":"Yevgen","full_name":"Grynko, Yevgen","last_name":"Grynko","id":"26059"},{"first_name":"Christian","full_name":"Schmitt, Christian","last_name":"Schmitt"},{"last_name":"Afzal","first_name":"Ayesha","full_name":"Afzal, Ayesha"},{"first_name":"Frank","full_name":"Hannig, Frank","last_name":"Hannig"},{"id":"158","last_name":"Förstner","full_name":"Förstner, Jens","orcid":"0000-0001-7059-9862","first_name":"Jens"},{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"}],"file_date_updated":"2018-11-02T14:45:05Z","publication":"Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)","keyword":["tet_topic_hpc"],"file":[{"date_updated":"2018-11-02T14:45:05Z","content_type":"application/pdf","success":1,"relation":"main_file","file_size":269130,"file_id":"5282","creator":"ups","access_level":"closed","file_name":"08457652.pdf","date_created":"2018-11-02T14:45:05Z"}],"has_accepted_license":"1","status":"public","date_created":"2018-03-22T10:48:01Z","abstract":[{"text":"The exploration of FPGAs as accelerators for scientific simulations has so far mostly been focused on small kernels of methods working on regular data structures, for example in the form of stencil computations for finite difference methods. In computational sciences, often more advanced methods are employed that promise better stability, convergence, locality and scaling. Unstructured meshes are shown to be more effective and more accurate, compared to regular grids, in representing computation domains of various shapes. Using unstructured meshes, the discontinuous Galerkin method preserves the ability to perform explicit local update operations for simulations in the time domain. In this work, we investigate FPGAs as target platform for an implementation of the nodal discontinuous Galerkin method to find time-domain solutions of Maxwell's equations in an unstructured mesh. When maximizing data reuse and fitting constant coefficients into suitably partitioned on-chip memory, high computational intensity allows us to implement and feed wide data paths with hundreds of floating point operators. By decoupling off-chip memory accesses from the computations, high memory bandwidth can be sustained, even for the irregular access pattern required by parts of the application. Using the Intel/Altera OpenCL SDK for FPGAs, we present different implementation variants for different polynomial orders of the method. In different phases of the algorithm, either computational or bandwidth limits of the Arria 10 platform are almost reached, thus outperforming a highly multithreaded CPU implementation by around 2x.","lang":"eng"}],"ddc":["000"],"user_id":"15278","year":"2018","type":"conference","citation":{"ieee":"T. Kenter et al., “OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes,” presented at the Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM), 2018, doi: 10.1109/FCCM.2018.00037.","short":"T. Kenter, G. Mahale, S. Alhaddad, Y. Grynko, C. Schmitt, A. Afzal, F. Hannig, J. Förstner, C. Plessl, in: Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM), IEEE, 2018.","mla":"Kenter, Tobias, et al. “OpenCL-Based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes.” Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM), IEEE, 2018, doi:10.1109/FCCM.2018.00037.","bibtex":"@inproceedings{Kenter_Mahale_Alhaddad_Grynko_Schmitt_Afzal_Hannig_Förstner_Plessl_2018, title={OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes}, DOI={10.1109/FCCM.2018.00037}, booktitle={Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)}, publisher={IEEE}, author={Kenter, Tobias and Mahale, Gopinath and Alhaddad, Samer and Grynko, Yevgen and Schmitt, Christian and Afzal, Ayesha and Hannig, Frank and Förstner, Jens and Plessl, Christian}, year={2018} }","ama":"Kenter T, Mahale G, Alhaddad S, et al. OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes. In: Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). IEEE; 2018. doi:10.1109/FCCM.2018.00037","apa":"Kenter, T., Mahale, G., Alhaddad, S., Grynko, Y., Schmitt, C., Afzal, A., Hannig, F., Förstner, J., & Plessl, C. (2018). OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes. Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). https://doi.org/10.1109/FCCM.2018.00037","chicago":"Kenter, Tobias, Gopinath Mahale, Samer Alhaddad, Yevgen Grynko, Christian Schmitt, Ayesha Afzal, Frank Hannig, Jens Förstner, and Christian Plessl. “OpenCL-Based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes.” In Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). IEEE, 2018. https://doi.org/10.1109/FCCM.2018.00037."},"_id":"1588","conference":{"name":"Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)"}},{"user_id":"15278","abstract":[{"lang":"eng","text":"We present the submatrix method, a highly parallelizable method for the approximate calculation of inverse p-th roots of large sparse symmetric matrices which are required in different scientific applications. Following the idea of Approximate Computing, we allow imprecision in the final result in order to utilize the sparsity of the input matrix and to allow massively parallel execution. For an n x n matrix, the proposed algorithm allows to distribute the calculations over n nodes with only little communication overhead. The result matrix exhibits the same sparsity pattern as the input matrix, allowing for efficient reuse of allocated data structures.\r\n\r\nWe evaluate the algorithm with respect to the error that it introduces into calculated results, as well as its performance and scalability. We demonstrate that the error is relatively limited for well-conditioned matrices and that results are still valuable for error-resilient applications like preconditioning even for ill-conditioned matrices. We discuss the execution time and scaling of the algorithm on a theoretical level and present a distributed implementation of the algorithm using MPI and OpenMP. We demonstrate the scalability of this implementation by running it on a high-performance compute cluster comprised of 1024 CPU cores, showing a speedup of 665x compared to single-threaded execution."}],"status":"public","date_created":"2018-03-22T10:53:01Z","author":[{"first_name":"Michael","full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","last_name":"Lass","id":"24135"},{"last_name":"Mohr","first_name":"Stephan","full_name":"Mohr, Stephan"},{"last_name":"Wiebeler","first_name":"Hendrik","full_name":"Wiebeler, Hendrik"},{"full_name":"Kühne, Thomas","first_name":"Thomas","id":"49079","last_name":"Kühne"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"}],"publisher":"ACM","quality_controlled":"1","publication":"Proc. Platform for Advanced Scientific Computing (PASC) Conference","keyword":["approximate computing","linear algebra","matrix inversion","matrix p-th roots","numeric algorithm","parallel computing"],"_id":"1590","conference":{"start_date":"2018-07-02","name":"Platform for Advanced Scientific Computing Conference (PASC)","location":"Basel, Switzerland","end_date":"2018-07-04"},"citation":{"chicago":"Lass, Michael, Stephan Mohr, Hendrik Wiebeler, Thomas Kühne, and Christian Plessl. “A Massively Parallel Algorithm for the Approximate Calculation of Inverse P-Th Roots of Large Sparse Matrices.” In Proc. Platform for Advanced Scientific Computing (PASC) Conference. New York, NY, USA: ACM, 2018. https://doi.org/10.1145/3218176.3218231.","ama":"Lass M, Mohr S, Wiebeler H, Kühne T, Plessl C. A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices. In: Proc. Platform for Advanced Scientific Computing (PASC) Conference. ACM; 2018. doi:10.1145/3218176.3218231","apa":"Lass, M., Mohr, S., Wiebeler, H., Kühne, T., & Plessl, C. (2018). A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices. Proc. Platform for Advanced Scientific Computing (PASC) Conference. Platform for Advanced Scientific Computing Conference (PASC), Basel, Switzerland. https://doi.org/10.1145/3218176.3218231","bibtex":"@inproceedings{Lass_Mohr_Wiebeler_Kühne_Plessl_2018, place={New York, NY, USA}, title={A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices}, DOI={10.1145/3218176.3218231}, booktitle={Proc. Platform for Advanced Scientific Computing (PASC) Conference}, publisher={ACM}, author={Lass, Michael and Mohr, Stephan and Wiebeler, Hendrik and Kühne, Thomas and Plessl, Christian}, year={2018} }","mla":"Lass, Michael, et al. “A Massively Parallel Algorithm for the Approximate Calculation of Inverse P-Th Roots of Large Sparse Matrices.” Proc. Platform for Advanced Scientific Computing (PASC) Conference, ACM, 2018, doi:10.1145/3218176.3218231.","short":"M. Lass, S. Mohr, H. Wiebeler, T. Kühne, C. Plessl, in: Proc. Platform for Advanced Scientific Computing (PASC) Conference, ACM, New York, NY, USA, 2018.","ieee":"M. Lass, S. Mohr, H. Wiebeler, T. Kühne, and C. Plessl, “A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices,” presented at the Platform for Advanced Scientific Computing Conference (PASC), Basel, Switzerland, 2018, doi: 10.1145/3218176.3218231."},"type":"conference","year":"2018","title":"A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices","place":"New York, NY, USA","external_id":{"arxiv":["1710.10899"]},"publication_identifier":{"isbn":["978-1-4503-5891-0/18/07"]},"project":[{"grant_number":"PL 595/2-1 / 320898746","name":"Performance and Efficiency in HPC with Custom Computing","_id":"32"},{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"doi":"10.1145/3218176.3218231","date_updated":"2023-09-26T11:48:12Z","language":[{"iso":"eng"}]},{"type":"conference","year":"2018","citation":{"ieee":"H. Riebler, G. F. Vaz, T. Kenter, and C. Plessl, “Automated Code Acceleration Targeting Heterogeneous OpenCL Devices,” 2018, doi: 10.1145/3178487.3178534.","short":"H. Riebler, G.F. Vaz, T. Kenter, C. Plessl, in: Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP), ACM, 2018.","mla":"Riebler, Heinrich, et al. “Automated Code Acceleration Targeting Heterogeneous OpenCL Devices.” Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP), ACM, 2018, doi:10.1145/3178487.3178534.","bibtex":"@inproceedings{Riebler_Vaz_Kenter_Plessl_2018, title={Automated Code Acceleration Targeting Heterogeneous OpenCL Devices}, DOI={10.1145/3178487.3178534}, booktitle={Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP)}, publisher={ACM}, author={Riebler, Heinrich and Vaz, Gavin Francis and Kenter, Tobias and Plessl, Christian}, year={2018} }","chicago":"Riebler, Heinrich, Gavin Francis Vaz, Tobias Kenter, and Christian Plessl. “Automated Code Acceleration Targeting Heterogeneous OpenCL Devices.” In Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). ACM, 2018. https://doi.org/10.1145/3178487.3178534.","ama":"Riebler H, Vaz GF, Kenter T, Plessl C. Automated Code Acceleration Targeting Heterogeneous OpenCL Devices. In: Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). ACM; 2018. doi:10.1145/3178487.3178534","apa":"Riebler, H., Vaz, G. F., Kenter, T., & Plessl, C. (2018). Automated Code Acceleration Targeting Heterogeneous OpenCL Devices. Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). https://doi.org/10.1145/3178487.3178534"},"_id":"1204","status":"public","has_accepted_license":"1","date_created":"2018-03-08T14:45:18Z","file":[{"date_created":"2018-11-02T14:43:37Z","file_name":"p417-riebler.pdf","access_level":"closed","creator":"ups","file_id":"5281","file_size":447769,"success":1,"relation":"main_file","content_type":"application/pdf","date_updated":"2018-11-02T14:43:37Z"}],"quality_controlled":"1","publisher":"ACM","author":[{"first_name":"Heinrich","full_name":"Riebler, Heinrich","last_name":"Riebler","id":"8961"},{"first_name":"Gavin Francis","full_name":"Vaz, Gavin Francis","last_name":"Vaz","id":"30332"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"}],"keyword":["htrop"],"publication":"Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP)","file_date_updated":"2018-11-02T14:43:37Z","user_id":"15278","ddc":["000"],"language":[{"iso":"eng"}],"doi":"10.1145/3178487.3178534","date_updated":"2023-09-26T11:47:23Z","project":[{"_id":"1","name":"SFB 901","grant_number":"160364472"},{"name":"SFB 901 - Project Area C","_id":"4"},{"grant_number":"160364472","name":"SFB 901 - Subproject C2","_id":"14"}],"publication_identifier":{"isbn":["9781450349826"]},"publication_status":"published","department":[{"_id":"27"},{"_id":"518"}],"title":"Automated Code Acceleration Targeting Heterogeneous OpenCL Devices"}]