[{"issue":"19","quality_controlled":"1","year":"2020","date_created":"2020-03-10T15:12:31Z","title":"CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations","publication":"The Journal of Chemical Physics","file":[{"success":1,"relation":"main_file","content_type":"application/pdf","file_size":4887650,"file_name":"5.0007045.pdf","access_level":"closed","file_id":"17061","date_updated":"2020-05-25T15:21:56Z","creator":"lass","date_created":"2020-05-25T15:21:56Z"}],"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"}],"external_id":{"arxiv":["2003.03868"]},"language":[{"iso":"eng"}],"ddc":["540"],"has_accepted_license":"1","publication_status":"published","intvolume":"       152","citation":{"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).","mla":"Kühne, Thomas, et al. “CP2K: An Electronic Structure and Molecular Dynamics Software Package - Quickstep: Efficient and Accurate Electronic Structure Calculations.” <i>The Journal of Chemical Physics</i>, vol. 152, no. 19, 194103, 2020, doi:<a href=\"https://doi.org/10.1063/5.0007045\">10.1063/5.0007045</a>.","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={<a href=\"https://doi.org/10.1063/5.0007045\">10.1063/5.0007045</a>}, 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} }","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. <i>The Journal of Chemical Physics</i>. 2020;152(19). doi:<a href=\"https://doi.org/10.1063/5.0007045\">10.1063/5.0007045</a>","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. <i>The Journal of Chemical Physics</i>, <i>152</i>(19), Article 194103. <a href=\"https://doi.org/10.1063/5.0007045\">https://doi.org/10.1063/5.0007045</a>","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.” <i>The Journal of Chemical Physics</i> 152, no. 19 (2020). <a href=\"https://doi.org/10.1063/5.0007045\">https://doi.org/10.1063/5.0007045</a>.","ieee":"T. Kühne <i>et al.</i>, “CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations,” <i>The Journal of Chemical Physics</i>, vol. 152, no. 19, Art. no. 194103, 2020, doi: <a href=\"https://doi.org/10.1063/5.0007045\">10.1063/5.0007045</a>."},"volume":152,"author":[{"first_name":"Thomas","last_name":"Kühne","id":"49079","full_name":"Kühne, Thomas"},{"last_name":"Iannuzzi","full_name":"Iannuzzi, Marcella","first_name":"Marcella"},{"first_name":"Mauro Del","full_name":"Ben, Mauro Del","last_name":"Ben"},{"full_name":"Rybkin, Vladimir V.","last_name":"Rybkin","first_name":"Vladimir V."},{"first_name":"Patrick","last_name":"Seewald","full_name":"Seewald, Patrick"},{"full_name":"Stein, Frederick","last_name":"Stein","first_name":"Frederick"},{"last_name":"Laino","full_name":"Laino, Teodoro","first_name":"Teodoro"},{"first_name":"Rustam Z.","full_name":"Khaliullin, Rustam Z.","last_name":"Khaliullin"},{"last_name":"Schütt","full_name":"Schütt, Ole","first_name":"Ole"},{"last_name":"Schiffmann","full_name":"Schiffmann, Florian","first_name":"Florian"},{"first_name":"Dorothea","full_name":"Golze, Dorothea","last_name":"Golze"},{"last_name":"Wilhelm","full_name":"Wilhelm, Jan","first_name":"Jan"},{"first_name":"Sergey","last_name":"Chulkov","full_name":"Chulkov, Sergey"},{"first_name":"Mohammad Hossein Bani-Hashemian","full_name":"Mohammad Hossein Bani-Hashemian, Mohammad Hossein Bani-Hashemian","last_name":"Mohammad Hossein Bani-Hashemian"},{"last_name":"Weber","full_name":"Weber, Valéry","first_name":"Valéry"},{"first_name":"Urban","full_name":"Borstnik, Urban","last_name":"Borstnik"},{"full_name":"Taillefumier, Mathieu","last_name":"Taillefumier","first_name":"Mathieu"},{"first_name":"Alice Shoshana","last_name":"Jakobovits","full_name":"Jakobovits, Alice Shoshana"},{"last_name":"Lazzaro","full_name":"Lazzaro, Alfio","first_name":"Alfio"},{"first_name":"Hans","last_name":"Pabst","full_name":"Pabst, Hans"},{"full_name":"Müller, Tiziano","last_name":"Müller","first_name":"Tiziano"},{"orcid":"0000-0002-6268-539","last_name":"Schade","id":"75963","full_name":"Schade, Robert","first_name":"Robert"},{"last_name":"Guidon","full_name":"Guidon, Manuel","first_name":"Manuel"},{"first_name":"Samuel","full_name":"Andermatt, Samuel","last_name":"Andermatt"},{"first_name":"Nico","last_name":"Holmberg","full_name":"Holmberg, Nico"},{"full_name":"Schenter, Gregory K.","last_name":"Schenter","first_name":"Gregory K."},{"first_name":"Anna","last_name":"Hehn","full_name":"Hehn, Anna"},{"first_name":"Augustin","last_name":"Bussy","full_name":"Bussy, Augustin"},{"first_name":"Fabian","full_name":"Belleflamme, Fabian","last_name":"Belleflamme"},{"first_name":"Gloria","last_name":"Tabacchi","full_name":"Tabacchi, Gloria"},{"last_name":"Glöß","full_name":"Glöß, Andreas","first_name":"Andreas"},{"first_name":"Michael","last_name":"Lass","orcid":"0000-0002-5708-7632","id":"24135","full_name":"Lass, Michael"},{"first_name":"Iain","full_name":"Bethune, Iain","last_name":"Bethune"},{"first_name":"Christopher J.","full_name":"Mundy, Christopher J.","last_name":"Mundy"},{"orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153","full_name":"Plessl, Christian","first_name":"Christian"},{"full_name":"Watkins, Matt","last_name":"Watkins","first_name":"Matt"},{"first_name":"Joost","full_name":"VandeVondele, Joost","last_name":"VandeVondele"},{"first_name":"Matthias","last_name":"Krack","full_name":"Krack, Matthias"},{"full_name":"Hutter, Jürg","last_name":"Hutter","first_name":"Jürg"}],"oa":"1","date_updated":"2023-08-02T14:56:21Z","doi":"10.1063/5.0007045","main_file_link":[{"open_access":"1","url":"https://aip.scitation.org/doi/pdf/10.1063/5.0007045?download=true"}],"type":"journal_article","status":"public","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"user_id":"75963","_id":"16277","project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"grant_number":"PL 595/2-1 / 320898746","_id":"32","name":"Performance and Efficiency in HPC with Custom Computing"},{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"file_date_updated":"2020-05-25T15:21:56Z","article_number":"194103"},{"doi":"10.1109/SC41405.2020.00084","conference":{"location":"Atlanta, GA, US","name":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis (SC)"},"main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9355245"}],"author":[{"last_name":"Lass","orcid":"0000-0002-5708-7632","id":"24135","full_name":"Lass, Michael","first_name":"Michael"},{"last_name":"Schade","orcid":"0000-0002-6268-539","id":"75963","full_name":"Schade, Robert","first_name":"Robert"},{"id":"49079","full_name":"Kühne, Thomas","last_name":"Kühne","first_name":"Thomas"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153","full_name":"Plessl, Christian"}],"date_updated":"2023-08-02T14:55:59Z","page":"1127-1140","citation":{"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: <i>Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)</i>. IEEE Computer Society; 2020:1127-1140. doi:<a href=\"https://doi.org/10.1109/SC41405.2020.00084\">10.1109/SC41405.2020.00084</a>","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 <i>Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)</i>, Atlanta, GA, US, 2020, pp. 1127–1140, doi: <a href=\"https://doi.org/10.1109/SC41405.2020.00084\">10.1109/SC41405.2020.00084</a>.","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 <i>Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)</i>, 1127–40. Los Alamitos, CA, USA: IEEE Computer Society, 2020. <a href=\"https://doi.org/10.1109/SC41405.2020.00084\">https://doi.org/10.1109/SC41405.2020.00084</a>.","apa":"Lass, M., Schade, R., Kühne, T., &#38; Plessl, C. (2020). A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K. <i>Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)</i>, 1127–1140. <a href=\"https://doi.org/10.1109/SC41405.2020.00084\">https://doi.org/10.1109/SC41405.2020.00084</a>","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.","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={<a href=\"https://doi.org/10.1109/SC41405.2020.00084\">10.1109/SC41405.2020.00084</a>}, 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.” <i>Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)</i>, IEEE Computer Society, 2020, pp. 1127–40, doi:<a href=\"https://doi.org/10.1109/SC41405.2020.00084\">10.1109/SC41405.2020.00084</a>."},"place":"Los Alamitos, CA, USA","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"user_id":"75963","_id":"16898","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"_id":"32","name":"Performance and Efficiency in HPC with Custom Computing","grant_number":"PL 595/2-1 / 320898746"},{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"status":"public","type":"conference","title":"A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K","date_created":"2020-04-28T14:44:21Z","publisher":"IEEE Computer Society","year":"2020","quality_controlled":"1","language":[{"iso":"eng"}],"external_id":{"arxiv":["2004.10811"]},"abstract":[{"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.","lang":"eng"}],"publication":"Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)"},{"status":"public","type":"journal_article","article_number":"39","user_id":"15278","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"grant_number":"PL 595/2-1 / 320898746","name":"Performance and Efficiency in HPC with Custom Computing","_id":"32"}],"_id":"12878","citation":{"mla":"Rengaraj, Varadarajan, et al. “Accurate Sampling with Noisy Forces from Approximate Computing.” <i>Computation</i>, vol. 8, no. 2, 39, MDPI, 2020, doi:<a href=\"https://doi.org/10.3390/computation8020039\">10.3390/computation8020039</a>.","bibtex":"@article{Rengaraj_Lass_Plessl_Kühne_2020, title={Accurate Sampling with Noisy Forces from Approximate Computing}, volume={8}, DOI={<a href=\"https://doi.org/10.3390/computation8020039\">10.3390/computation8020039</a>}, 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).","apa":"Rengaraj, V., Lass, M., Plessl, C., &#38; Kühne, T. (2020). Accurate Sampling with Noisy Forces from Approximate Computing. <i>Computation</i>, <i>8</i>(2), Article 39. <a href=\"https://doi.org/10.3390/computation8020039\">https://doi.org/10.3390/computation8020039</a>","ama":"Rengaraj V, Lass M, Plessl C, Kühne T. Accurate Sampling with Noisy Forces from Approximate Computing. <i>Computation</i>. 2020;8(2). doi:<a href=\"https://doi.org/10.3390/computation8020039\">10.3390/computation8020039</a>","chicago":"Rengaraj, Varadarajan, Michael Lass, Christian Plessl, and Thomas Kühne. “Accurate Sampling with Noisy Forces from Approximate Computing.” <i>Computation</i> 8, no. 2 (2020). <a href=\"https://doi.org/10.3390/computation8020039\">https://doi.org/10.3390/computation8020039</a>.","ieee":"V. Rengaraj, M. Lass, C. Plessl, and T. Kühne, “Accurate Sampling with Noisy Forces from Approximate Computing,” <i>Computation</i>, vol. 8, no. 2, Art. no. 39, 2020, doi: <a href=\"https://doi.org/10.3390/computation8020039\">10.3390/computation8020039</a>."},"intvolume":"         8","main_file_link":[{"url":"https://www.mdpi.com/2079-3197/8/2/39/pdf","open_access":"1"}],"doi":"10.3390/computation8020039","author":[{"full_name":"Rengaraj, Varadarajan","last_name":"Rengaraj","first_name":"Varadarajan"},{"id":"24135","full_name":"Lass, Michael","last_name":"Lass","orcid":"0000-0002-5708-7632","first_name":"Michael"},{"orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153","full_name":"Plessl, Christian","first_name":"Christian"},{"last_name":"Kühne","id":"49079","full_name":"Kühne, Thomas","first_name":"Thomas"}],"volume":8,"oa":"1","date_updated":"2023-09-26T11:43:52Z","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."}],"publication":"Computation","language":[{"iso":"eng"}],"external_id":{"arxiv":["1907.08497"]},"year":"2020","issue":"2","quality_controlled":"1","title":"Accurate Sampling with Noisy Forces from Approximate Computing","date_created":"2019-07-23T12:03:07Z","publisher":"MDPI"},{"ddc":["004"],"language":[{"iso":"eng"}],"file_date_updated":"2020-01-09T12:53:57Z","_id":"15478","project":[{"grant_number":"01|H16005","name":"HighPerMeshes","_id":"33"},{"grant_number":"PL 595/2-1","name":"Performance and Efficiency in HPC with Custom Computing","_id":"32"}],"department":[{"_id":"27"},{"_id":"518"}],"user_id":"3145","abstract":[{"lang":"eng","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."}],"status":"public","file":[{"relation":"main_file","success":1,"content_type":"application/pdf","access_level":"closed","file_id":"15479","file_name":"gorlani19_fpt.pdf","file_size":250559,"date_created":"2020-01-09T12:53:57Z","creator":"plessl","date_updated":"2020-01-09T12:53:57Z"}],"publication":"Proceedings of the International Conference on Field-Programmable Technology (FPT)","type":"conference","title":"OpenCL Implementation of Cannon's Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs","conference":{"name":"International Conference on Field-Programmable Technology (FPT)"},"doi":"10.1109/ICFPT47387.2019.00020","publisher":"IEEE","date_updated":"2022-01-06T06:52:26Z","date_created":"2020-01-09T12:54:48Z","author":[{"first_name":"Paolo","full_name":"Gorlani, Paolo","id":"72045","last_name":"Gorlani"},{"first_name":"Tobias","id":"3145","full_name":"Kenter, Tobias","last_name":"Kenter"},{"orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153","full_name":"Plessl, Christian","first_name":"Christian"}],"year":"2019","citation":{"mla":"Gorlani, Paolo, et al. “OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs.” <i>Proceedings of the International Conference on Field-Programmable Technology (FPT)</i>, IEEE, 2019, doi:<a href=\"https://doi.org/10.1109/ICFPT47387.2019.00020\">10.1109/ICFPT47387.2019.00020</a>.","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={<a href=\"https://doi.org/10.1109/ICFPT47387.2019.00020\">10.1109/ICFPT47387.2019.00020</a>}, booktitle={Proceedings of the International Conference on Field-Programmable Technology (FPT)}, publisher={IEEE}, author={Gorlani, Paolo and Kenter, Tobias and Plessl, Christian}, year={2019} }","apa":"Gorlani, P., Kenter, T., &#38; Plessl, C. (2019). OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs. In <i>Proceedings of the International Conference on Field-Programmable Technology (FPT)</i>. IEEE. <a href=\"https://doi.org/10.1109/ICFPT47387.2019.00020\">https://doi.org/10.1109/ICFPT47387.2019.00020</a>","ama":"Gorlani P, Kenter T, Plessl C. OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs. In: <i>Proceedings of the International Conference on Field-Programmable Technology (FPT)</i>. IEEE; 2019. doi:<a href=\"https://doi.org/10.1109/ICFPT47387.2019.00020\">10.1109/ICFPT47387.2019.00020</a>","chicago":"Gorlani, Paolo, Tobias Kenter, and Christian Plessl. “OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs.” In <i>Proceedings of the International Conference on Field-Programmable Technology (FPT)</i>. IEEE, 2019. <a href=\"https://doi.org/10.1109/ICFPT47387.2019.00020\">https://doi.org/10.1109/ICFPT47387.2019.00020</a>.","ieee":"P. Gorlani, T. Kenter, and C. Plessl, “OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs,” in <i>Proceedings of the International Conference on Field-Programmable Technology (FPT)</i>, 2019."},"quality_controlled":"1","has_accepted_license":"1"},{"citation":{"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. <i>Communications in Computational Physics</i>. 2019;25(2):564-585. doi:<a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">10.4208/cicp.OA-2018-0053</a>","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,” <i>Communications in Computational Physics</i>, vol. 25, no. 2, pp. 564–585, 2019, doi: <a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">10.4208/cicp.OA-2018-0053</a>.","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.” <i>Communications in Computational Physics</i> 25, no. 2 (2019): 564–85. <a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">https://doi.org/10.4208/cicp.OA-2018-0053</a>.","mla":"Richters, Dorothee, et al. “A General Algorithm to Calculate the Inverse Principal P-Th Root of Symmetric Positive Definite Matrices.” <i>Communications in Computational Physics</i>, vol. 25, no. 2, Global Science Press, 2019, pp. 564–85, doi:<a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">10.4208/cicp.OA-2018-0053</a>.","short":"D. Richters, M. Lass, A. Walther, C. Plessl, T. Kühne, Communications in Computational Physics 25 (2019) 564–585.","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={<a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">10.4208/cicp.OA-2018-0053</a>}, 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} }","apa":"Richters, D., Lass, M., Walther, A., Plessl, C., &#38; Kühne, T. (2019). A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices. <i>Communications in Computational Physics</i>, <i>25</i>(2), 564–585. <a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">https://doi.org/10.4208/cicp.OA-2018-0053</a>"},"intvolume":"        25","page":"564-585","date_updated":"2023-09-26T11:45:02Z","author":[{"first_name":"Dorothee","last_name":"Richters","full_name":"Richters, Dorothee"},{"first_name":"Michael","full_name":"Lass, Michael","id":"24135","orcid":"0000-0002-5708-7632","last_name":"Lass"},{"first_name":"Andrea","full_name":"Walther, Andrea","last_name":"Walther"},{"orcid":"0000-0001-5728-9982","last_name":"Plessl","full_name":"Plessl, Christian","id":"16153","first_name":"Christian"},{"first_name":"Thomas","full_name":"Kühne, Thomas","id":"49079","last_name":"Kühne"}],"volume":25,"doi":"10.4208/cicp.OA-2018-0053","type":"journal_article","status":"public","project":[{"grant_number":"PL 595/2-1 / 320898746","name":"Performance and Efficiency in HPC with Custom Computing","_id":"32"},{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"21","user_id":"15278","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"},{"_id":"104"}],"quality_controlled":"1","issue":"2","year":"2019","publisher":"Global Science Press","date_created":"2017-07-25T14:48:26Z","title":"A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices","publication":"Communications in Computational Physics","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."}],"external_id":{"arxiv":["1703.02456"]},"language":[{"iso":"eng"}]},{"publisher":"IEEE","date_created":"2017-07-25T14:41:08Z","title":"Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots","issue":"2","year":"2018","external_id":{"arxiv":["1703.02283"]},"language":[{"iso":"eng"}],"publication":"Embedded Systems Letters","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"}],"date_updated":"2022-01-06T06:54:18Z","volume":10,"author":[{"full_name":"Lass, Michael","id":"24135","orcid":"0000-0002-5708-7632","last_name":"Lass","first_name":"Michael"},{"first_name":"Thomas","full_name":"Kühne, Thomas","id":"49079","last_name":"Kühne"},{"last_name":"Plessl","orcid":"0000-0001-5728-9982","id":"16153","full_name":"Plessl, Christian","first_name":"Christian"}],"doi":"10.1109/LES.2017.2760923","publication_identifier":{"issn":["1943-0663"],"eissn":["1943-0671"]},"publication_status":"published","intvolume":"        10","page":" 33-36","citation":{"mla":"Lass, Michael, et al. “Using Approximate Computing for the Calculation of Inverse Matrix P-Th Roots.” <i>Embedded Systems Letters</i>, vol. 10, no. 2, IEEE, 2018, pp. 33–36, doi:<a href=\"https://doi.org/10.1109/LES.2017.2760923\">10.1109/LES.2017.2760923</a>.","bibtex":"@article{Lass_Kühne_Plessl_2018, title={Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots}, volume={10}, DOI={<a href=\"https://doi.org/10.1109/LES.2017.2760923\">10.1109/LES.2017.2760923</a>}, number={2}, journal={Embedded Systems Letters}, publisher={IEEE}, author={Lass, Michael and Kühne, Thomas and Plessl, Christian}, year={2018}, pages={33–36} }","short":"M. Lass, T. Kühne, C. Plessl, Embedded Systems Letters 10 (2018) 33–36.","apa":"Lass, M., Kühne, T., &#38; Plessl, C. (2018). Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots. <i>Embedded Systems Letters</i>, <i>10</i>(2), 33–36. <a href=\"https://doi.org/10.1109/LES.2017.2760923\">https://doi.org/10.1109/LES.2017.2760923</a>","ama":"Lass M, Kühne T, Plessl C. Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots. <i>Embedded Systems Letters</i>. 2018;10(2):33-36. doi:<a href=\"https://doi.org/10.1109/LES.2017.2760923\">10.1109/LES.2017.2760923</a>","ieee":"M. Lass, T. Kühne, and C. Plessl, “Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots,” <i>Embedded Systems Letters</i>, vol. 10, no. 2, pp. 33–36, 2018.","chicago":"Lass, Michael, Thomas Kühne, and Christian Plessl. “Using Approximate Computing for the Calculation of Inverse Matrix P-Th Roots.” <i>Embedded Systems Letters</i> 10, no. 2 (2018): 33–36. <a href=\"https://doi.org/10.1109/LES.2017.2760923\">https://doi.org/10.1109/LES.2017.2760923</a>."},"_id":"20","project":[{"grant_number":"PL 595/2-1","_id":"32","name":"Performance and Efficiency in HPC with Custom Computing"},{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"user_id":"16153","type":"journal_article","status":"public"},{"place":"New York, NY, USA","citation":{"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: <i>Proc. Platform for Advanced Scientific Computing (PASC) Conference</i>. ACM; 2018. doi:<a href=\"https://doi.org/10.1145/3218176.3218231\">10.1145/3218176.3218231</a>","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 <i>Proc. Platform for Advanced Scientific Computing (PASC) Conference</i>. New York, NY, USA: ACM, 2018. <a href=\"https://doi.org/10.1145/3218176.3218231\">https://doi.org/10.1145/3218176.3218231</a>.","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: <a href=\"https://doi.org/10.1145/3218176.3218231\">10.1145/3218176.3218231</a>.","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.","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={<a href=\"https://doi.org/10.1145/3218176.3218231\">10.1145/3218176.3218231</a>}, 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.” <i>Proc. Platform for Advanced Scientific Computing (PASC) Conference</i>, ACM, 2018, doi:<a href=\"https://doi.org/10.1145/3218176.3218231\">10.1145/3218176.3218231</a>.","apa":"Lass, M., Mohr, S., Wiebeler, H., Kühne, T., &#38; Plessl, C. (2018). A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices. <i>Proc. Platform for Advanced Scientific Computing (PASC) Conference</i>. Platform for Advanced Scientific Computing Conference (PASC), Basel, Switzerland. <a href=\"https://doi.org/10.1145/3218176.3218231\">https://doi.org/10.1145/3218176.3218231</a>"},"publication_identifier":{"isbn":["978-1-4503-5891-0/18/07"]},"doi":"10.1145/3218176.3218231","conference":{"start_date":"2018-07-02","name":"Platform for Advanced Scientific Computing Conference (PASC)","location":"Basel, Switzerland","end_date":"2018-07-04"},"date_updated":"2023-09-26T11:48:12Z","author":[{"first_name":"Michael","id":"24135","full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","last_name":"Lass"},{"first_name":"Stephan","full_name":"Mohr, Stephan","last_name":"Mohr"},{"first_name":"Hendrik","full_name":"Wiebeler, Hendrik","last_name":"Wiebeler"},{"first_name":"Thomas","last_name":"Kühne","id":"49079","full_name":"Kühne, Thomas"},{"last_name":"Plessl","orcid":"0000-0001-5728-9982","id":"16153","full_name":"Plessl, Christian","first_name":"Christian"}],"status":"public","type":"conference","_id":"1590","project":[{"_id":"32","name":"Performance and Efficiency in HPC with Custom Computing","grant_number":"PL 595/2-1 / 320898746"},{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"user_id":"15278","year":"2018","quality_controlled":"1","title":"A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices","publisher":"ACM","date_created":"2018-03-22T10:53:01Z","abstract":[{"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.","lang":"eng"}],"publication":"Proc. Platform for Advanced Scientific Computing (PASC) Conference","keyword":["approximate computing","linear algebra","matrix inversion","matrix p-th roots","numeric algorithm","parallel computing"],"language":[{"iso":"eng"}],"external_id":{"arxiv":["1710.10899"]}},{"date_updated":"2023-09-26T13:24:38Z","author":[{"last_name":"Kenter","id":"3145","full_name":"Kenter, Tobias","first_name":"Tobias"},{"last_name":"Förstner","orcid":"0000-0001-7059-9862","id":"158","full_name":"Förstner, Jens","first_name":"Jens"},{"last_name":"Plessl","orcid":"0000-0001-5728-9982","id":"16153","full_name":"Plessl, Christian","first_name":"Christian"}],"doi":"10.23919/FPL.2017.8056844","has_accepted_license":"1","citation":{"mla":"Kenter, Tobias, et al. “Flexible FPGA Design for FDTD Using OpenCL.” <i>Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)</i>, IEEE, 2017, doi:<a href=\"https://doi.org/10.23919/FPL.2017.8056844\">10.23919/FPL.2017.8056844</a>.","short":"T. Kenter, J. Förstner, C. Plessl, in: Proc. Int. Conf. on Field Programmable Logic and Applications (FPL), IEEE, 2017.","bibtex":"@inproceedings{Kenter_Förstner_Plessl_2017, title={Flexible FPGA design for FDTD using OpenCL}, DOI={<a href=\"https://doi.org/10.23919/FPL.2017.8056844\">10.23919/FPL.2017.8056844</a>}, booktitle={Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)}, publisher={IEEE}, author={Kenter, Tobias and Förstner, Jens and Plessl, Christian}, year={2017} }","apa":"Kenter, T., Förstner, J., &#38; Plessl, C. (2017). Flexible FPGA design for FDTD using OpenCL. <i>Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)</i>. <a href=\"https://doi.org/10.23919/FPL.2017.8056844\">https://doi.org/10.23919/FPL.2017.8056844</a>","chicago":"Kenter, Tobias, Jens Förstner, and Christian Plessl. “Flexible FPGA Design for FDTD Using OpenCL.” In <i>Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)</i>. IEEE, 2017. <a href=\"https://doi.org/10.23919/FPL.2017.8056844\">https://doi.org/10.23919/FPL.2017.8056844</a>.","ieee":"T. Kenter, J. Förstner, and C. Plessl, “Flexible FPGA design for FDTD using OpenCL,” 2017, doi: <a href=\"https://doi.org/10.23919/FPL.2017.8056844\">10.23919/FPL.2017.8056844</a>.","ama":"Kenter T, Förstner J, Plessl C. Flexible FPGA design for FDTD using OpenCL. In: <i>Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)</i>. IEEE; 2017. doi:<a href=\"https://doi.org/10.23919/FPL.2017.8056844\">10.23919/FPL.2017.8056844</a>"},"project":[{"grant_number":"160364472","name":"SFB 901","_id":"1"},{"name":"SFB 901 - Project Area C","_id":"4"},{"_id":"14","name":"SFB 901 - Subproject C2","grant_number":"160364472"},{"grant_number":"01|H16005A","name":"HighPerMeshes","_id":"33"},{"name":"Performance and Efficiency in HPC with Custom Computing","_id":"32","grant_number":"PL 595/2-1 / 320898746"},{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"_id":"1592","user_id":"15278","department":[{"_id":"27"},{"_id":"518"},{"_id":"61"}],"file_date_updated":"2018-11-02T15:02:28Z","type":"conference","status":"public","publisher":"IEEE","date_created":"2018-03-22T11:10:23Z","title":"Flexible FPGA design for FDTD using OpenCL","quality_controlled":"1","year":"2017","ddc":["000"],"keyword":["tet_topic_hpc"],"language":[{"iso":"eng"}],"publication":"Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)","abstract":[{"lang":"eng","text":"Compared to classical HDL designs, generating FPGA with high-level synthesis from an OpenCL specification promises easier exploration of different design alternatives and, through ready-to-use infrastructure and common abstractions for host and memory interfaces, easier portability between different FPGA families. In this work, we evaluate the extent of this promise. To this end, we present a parameterized FDTD implementation for photonic microcavity simulations. Our design can trade-off different forms of parallelism and works for two independent OpenCL-based FPGA design flows. Hence, we can target FPGAs from different vendors and different FPGA families. We describe how we used pre-processor macros to achieve this flexibility and to work around different shortcomings of the current tools. Choosing the right design configurations, we are able to present two extremely competitive solutions for very different FPGA targets, reaching up to 172 GFLOPS sustained performance. With the portability and flexibility demonstrated, code developers not only avoid vendor lock-in, but can even make best use of real trade-offs between different architectures."}],"file":[{"file_id":"5291","access_level":"closed","file_name":"08056844.pdf","file_size":230235,"creator":"ups","date_created":"2018-11-02T15:02:28Z","date_updated":"2018-11-02T15:02:28Z","relation":"main_file","success":1,"content_type":"application/pdf"}]},{"title":"Microdisk Cavity FDTD Simulation on FPGA using OpenCL","date_created":"2017-07-26T15:00:43Z","author":[{"last_name":"Kenter","id":"3145","full_name":"Kenter, Tobias","first_name":"Tobias"},{"first_name":"Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","id":"16153"}],"date_updated":"2023-09-26T13:26:17Z","citation":{"bibtex":"@inproceedings{Kenter_Plessl_2016, title={Microdisk Cavity FDTD Simulation on FPGA using OpenCL}, booktitle={Proc. Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC)}, author={Kenter, Tobias and Plessl, Christian}, year={2016} }","short":"T. Kenter, C. Plessl, in: Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2016.","mla":"Kenter, Tobias, and Christian Plessl. “Microdisk Cavity FDTD Simulation on FPGA Using OpenCL.” <i>Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC)</i>, 2016.","apa":"Kenter, T., &#38; Plessl, C. (2016). Microdisk Cavity FDTD Simulation on FPGA using OpenCL. <i>Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC)</i>.","chicago":"Kenter, Tobias, and Christian Plessl. “Microdisk Cavity FDTD Simulation on FPGA Using OpenCL.” In <i>Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC)</i>, 2016.","ieee":"T. Kenter and C. Plessl, “Microdisk Cavity FDTD Simulation on FPGA using OpenCL,” 2016.","ama":"Kenter T, Plessl C. Microdisk Cavity FDTD Simulation on FPGA using OpenCL. In: <i>Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC)</i>. ; 2016."},"year":"2016","quality_controlled":"1","has_accepted_license":"1","language":[{"iso":"eng"}],"file_date_updated":"2018-11-14T12:38:45Z","ddc":["004"],"department":[{"_id":"27"},{"_id":"518"}],"user_id":"15278","_id":"24","project":[{"grant_number":"PL 595/2-1 / 320898746","name":"Performance and Efficiency in HPC with Custom Computing","_id":"32"},{"grant_number":"160364472","_id":"1","name":"SFB 901"},{"name":"SFB 901 - Project Area C","_id":"4"},{"grant_number":"160364472","name":"SFB 901 - Subproject C2","_id":"14"}],"status":"public","file":[{"content_type":"application/pdf","relation":"main_file","success":1,"date_created":"2018-11-14T12:38:45Z","creator":"kenter","date_updated":"2018-11-14T12:38:45Z","file_name":"paper_26.pdf","file_id":"5602","access_level":"closed","file_size":129552}],"publication":"Proc. Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC)","type":"conference"}]