[{"_id":"33493","date_updated":"2023-07-28T08:03:41Z","type":"preprint","year":"2022","citation":{"short":"V. Gavini, S. Baroni, V. Blum, D.R. Bowler, A. Buccheri, J.R. Chelikowsky, S. Das, W. Dawson, P. Delugas, M. Dogan, C. Draxl, G. Galli, L. Genovese, P. Giannozzi, M. Giantomassi, X. Gonze, M. Govoni, A. Gulans, F. Gygi, J.M. Herbert, S. Kokott, T. Kühne, K.-H. Liou, T. Miyazaki, P. Motamarri, A. Nakata, J.E. Pask, C. Plessl, L.E. Ratcliff, R.M. Richard, M. Rossi, R. Schade, M. Scheffler, O. Schütt, P. Suryanarayana, M. Torrent, L. Truflandier, T.L. Windus, Q. Xu, V.W.-Z. Yu, D. Perez, ArXiv:2209.12747 (2022).","ieee":"V. Gavini et al., “Roadmap on Electronic Structure Codes in the Exascale Era,” arXiv:2209.12747. 2022.","apa":"Gavini, V., Baroni, S., Blum, V., Bowler, D. R., Buccheri, A., Chelikowsky, J. R., Das, S., Dawson, W., Delugas, P., Dogan, M., Draxl, C., Galli, G., Genovese, L., Giannozzi, P., Giantomassi, M., Gonze, X., Govoni, M., Gulans, A., Gygi, F., … Perez, D. (2022). Roadmap on Electronic Structure Codes in the Exascale Era. In arXiv:2209.12747.","ama":"Gavini V, Baroni S, Blum V, et al. Roadmap on Electronic Structure Codes in the Exascale Era. arXiv:220912747. Published online 2022.","chicago":"Gavini, Vikram, Stefano Baroni, Volker Blum, David R. Bowler, Alexander Buccheri, James R. Chelikowsky, Sambit Das, et al. “Roadmap on Electronic Structure Codes in the Exascale Era.” ArXiv:2209.12747, 2022.","mla":"Gavini, Vikram, et al. “Roadmap on Electronic Structure Codes in the Exascale Era.” ArXiv:2209.12747, 2022.","bibtex":"@article{Gavini_Baroni_Blum_Bowler_Buccheri_Chelikowsky_Das_Dawson_Delugas_Dogan_et al._2022, title={Roadmap on Electronic Structure Codes in the Exascale Era}, journal={arXiv:2209.12747}, author={Gavini, Vikram and Baroni, Stefano and Blum, Volker and Bowler, David R. and Buccheri, Alexander and Chelikowsky, James R. and Das, Sambit and Dawson, William and Delugas, Pietro and Dogan, Mehmet and et al.}, year={2022} }"},"language":[{"iso":"eng"}],"title":"Roadmap on Electronic Structure Codes in the Exascale Era","user_id":"24135","abstract":[{"lang":"eng","text":"Electronic structure calculations have been instrumental in providing many\r\nimportant insights into a range of physical and chemical properties of various\r\nmolecular and solid-state systems. Their importance to various fields,\r\nincluding materials science, chemical sciences, computational chemistry and\r\ndevice physics, is underscored by the large fraction of available public\r\nsupercomputing resources devoted to these calculations. As we enter the\r\nexascale era, exciting new opportunities to increase simulation numbers, sizes,\r\nand accuracies present themselves. In order to realize these promises, the\r\ncommunity of electronic structure software developers will however first have\r\nto tackle a number of challenges pertaining to the efficient use of new\r\narchitectures that will rely heavily on massive parallelism and hardware\r\naccelerators. This roadmap provides a broad overview of the state-of-the-art in\r\nelectronic structure calculations and of the various new directions being\r\npursued by the community. It covers 14 electronic structure codes, presenting\r\ntheir current status, their development priorities over the next five years,\r\nand their plans towards tackling the challenges and leveraging the\r\nopportunities presented by the advent of exascale computing."}],"external_id":{"arxiv":["2209.12747"]},"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_created":"2022-09-28T05:25:10Z","status":"public","publication":"arXiv:2209.12747","department":[{"_id":"27"},{"_id":"518"}],"author":[{"first_name":"Vikram","full_name":"Gavini, Vikram","last_name":"Gavini"},{"last_name":"Baroni","full_name":"Baroni, Stefano","first_name":"Stefano"},{"last_name":"Blum","first_name":"Volker","full_name":"Blum, Volker"},{"last_name":"Bowler","full_name":"Bowler, David R.","first_name":"David R."},{"first_name":"Alexander","full_name":"Buccheri, Alexander","last_name":"Buccheri"},{"first_name":"James R.","full_name":"Chelikowsky, James R.","last_name":"Chelikowsky"},{"full_name":"Das, Sambit","first_name":"Sambit","last_name":"Das"},{"full_name":"Dawson, William","first_name":"William","last_name":"Dawson"},{"last_name":"Delugas","full_name":"Delugas, Pietro","first_name":"Pietro"},{"last_name":"Dogan","first_name":"Mehmet","full_name":"Dogan, Mehmet"},{"first_name":"Claudia","full_name":"Draxl, Claudia","last_name":"Draxl"},{"full_name":"Galli, Giulia","first_name":"Giulia","last_name":"Galli"},{"full_name":"Genovese, Luigi","first_name":"Luigi","last_name":"Genovese"},{"last_name":"Giannozzi","full_name":"Giannozzi, Paolo","first_name":"Paolo"},{"first_name":"Matteo","full_name":"Giantomassi, Matteo","last_name":"Giantomassi"},{"full_name":"Gonze, Xavier","first_name":"Xavier","last_name":"Gonze"},{"first_name":"Marco","full_name":"Govoni, Marco","last_name":"Govoni"},{"last_name":"Gulans","full_name":"Gulans, Andris","first_name":"Andris"},{"full_name":"Gygi, François","first_name":"François","last_name":"Gygi"},{"last_name":"Herbert","full_name":"Herbert, John M.","first_name":"John M."},{"last_name":"Kokott","full_name":"Kokott, Sebastian","first_name":"Sebastian"},{"first_name":"Thomas","full_name":"Kühne, Thomas","last_name":"Kühne","id":"49079"},{"first_name":"Kai-Hsin","full_name":"Liou, Kai-Hsin","last_name":"Liou"},{"full_name":"Miyazaki, Tsuyoshi","first_name":"Tsuyoshi","last_name":"Miyazaki"},{"last_name":"Motamarri","full_name":"Motamarri, Phani","first_name":"Phani"},{"last_name":"Nakata","full_name":"Nakata, Ayako","first_name":"Ayako"},{"last_name":"Pask","first_name":"John E.","full_name":"Pask, John E."},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"},{"first_name":"Laura E.","full_name":"Ratcliff, Laura E.","last_name":"Ratcliff"},{"full_name":"Richard, Ryan M.","first_name":"Ryan M.","last_name":"Richard"},{"last_name":"Rossi","full_name":"Rossi, Mariana","first_name":"Mariana"},{"first_name":"Robert","full_name":"Schade, Robert","orcid":"0000-0002-6268-539","last_name":"Schade","id":"75963"},{"last_name":"Scheffler","first_name":"Matthias","full_name":"Scheffler, Matthias"},{"full_name":"Schütt, Ole","first_name":"Ole","last_name":"Schütt"},{"last_name":"Suryanarayana","full_name":"Suryanarayana, Phanish","first_name":"Phanish"},{"last_name":"Torrent","full_name":"Torrent, Marc","first_name":"Marc"},{"last_name":"Truflandier","full_name":"Truflandier, Lionel","first_name":"Lionel"},{"full_name":"Windus, Theresa L.","first_name":"Theresa L.","last_name":"Windus"},{"first_name":"Qimen","full_name":"Xu, Qimen","last_name":"Xu"},{"full_name":"Yu, Victor W. -Z.","first_name":"Victor W. -Z.","last_name":"Yu"},{"first_name":"Danny","full_name":"Perez, Danny","last_name":"Perez"}]},{"publication":"International Conference on High Performance Computing in Asia-Pacific Region","department":[{"_id":"27"},{"_id":"518"}],"quality_controlled":"1","author":[{"last_name":"Karp","full_name":"Karp, Martin","first_name":"Martin"},{"full_name":"Podobas, Artur","first_name":"Artur","last_name":"Podobas"},{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"last_name":"Jansson","full_name":"Jansson, Niclas","first_name":"Niclas"},{"orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian","id":"16153","last_name":"Plessl"},{"full_name":"Schlatter, Philipp","first_name":"Philipp","last_name":"Schlatter"},{"full_name":"Markidis, Stefano","first_name":"Stefano","last_name":"Markidis"}],"publisher":"ACM","publication_status":"published","date_created":"2023-07-28T11:51:55Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"status":"public","title":"A High-Fidelity Flow Solver for Unstructured Meshes on Field-Programmable Gate Arrays: Design, Evaluation, and Future Challenges","user_id":"3145","main_file_link":[{"open_access":"1","url":"https://dl.acm.org/doi/pdf/10.1145/3492805.3492808"}],"type":"conference","citation":{"apa":"Karp, M., Podobas, A., Kenter, T., Jansson, N., Plessl, C., Schlatter, P., & Markidis, S. (2022). A High-Fidelity Flow Solver for Unstructured Meshes on Field-Programmable Gate Arrays: Design, Evaluation, and Future Challenges. International Conference on High Performance Computing in Asia-Pacific Region. https://doi.org/10.1145/3492805.3492808","ama":"Karp M, Podobas A, Kenter T, et al. A High-Fidelity Flow Solver for Unstructured Meshes on Field-Programmable Gate Arrays: Design, Evaluation, and Future Challenges. In: International Conference on High Performance Computing in Asia-Pacific Region. ACM; 2022. doi:10.1145/3492805.3492808","chicago":"Karp, Martin, Artur Podobas, Tobias Kenter, Niclas Jansson, Christian Plessl, Philipp Schlatter, and Stefano Markidis. “A High-Fidelity Flow Solver for Unstructured Meshes on Field-Programmable Gate Arrays: Design, Evaluation, and Future Challenges.” In International Conference on High Performance Computing in Asia-Pacific Region. ACM, 2022. https://doi.org/10.1145/3492805.3492808.","mla":"Karp, Martin, et al. “A High-Fidelity Flow Solver for Unstructured Meshes on Field-Programmable Gate Arrays: Design, Evaluation, and Future Challenges.” International Conference on High Performance Computing in Asia-Pacific Region, ACM, 2022, doi:10.1145/3492805.3492808.","bibtex":"@inproceedings{Karp_Podobas_Kenter_Jansson_Plessl_Schlatter_Markidis_2022, title={A High-Fidelity Flow Solver for Unstructured Meshes on Field-Programmable Gate Arrays: Design, Evaluation, and Future Challenges}, DOI={10.1145/3492805.3492808}, booktitle={International Conference on High Performance Computing in Asia-Pacific Region}, publisher={ACM}, author={Karp, Martin and Podobas, Artur and Kenter, Tobias and Jansson, Niclas and Plessl, Christian and Schlatter, Philipp and Markidis, Stefano}, year={2022} }","short":"M. Karp, A. Podobas, T. Kenter, N. Jansson, C. Plessl, P. Schlatter, S. Markidis, in: International Conference on High Performance Computing in Asia-Pacific Region, ACM, 2022.","ieee":"M. Karp et al., “A High-Fidelity Flow Solver for Unstructured Meshes on Field-Programmable Gate Arrays: Design, Evaluation, and Future Challenges,” 2022, doi: 10.1145/3492805.3492808."},"year":"2022","language":[{"iso":"eng"}],"date_updated":"2023-07-28T11:53:15Z","_id":"46193","doi":"10.1145/3492805.3492808","oa":"1"},{"title":"CP2K on the road to exascale","user_id":"75963","external_id":{"arxiv":["2205.14741"]},"abstract":[{"text":"The CP2K program package, which can be considered as the swiss army knife of\r\natomistic simulations, is presented with a special emphasis on ab-initio\r\nmolecular dynamics using the second-generation Car-Parrinello method. After\r\noutlining current and near-term development efforts with regards to massively\r\nparallel low-scaling post-Hartree-Fock and eigenvalue solvers, novel approaches\r\non how we plan to take full advantage of future low-precision hardware\r\narchitectures are introduced. Our focus here is on combining our submatrix\r\nmethod with the approximate computing paradigm to address the immanent exascale\r\nera.","lang":"eng"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"date_created":"2022-07-22T08:14:08Z","status":"public","publication":"arXiv:2205.14741","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"author":[{"id":"49079","last_name":"Kühne","full_name":"Kühne, Thomas","first_name":"Thomas"},{"full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian","id":"16153","last_name":"Plessl"},{"last_name":"Schade","id":"75963","first_name":"Robert","orcid":"0000-0002-6268-539","full_name":"Schade, Robert"},{"full_name":"Schütt, Ole","first_name":"Ole","last_name":"Schütt"}],"_id":"32404","date_updated":"2023-08-02T14:55:35Z","type":"preprint","citation":{"mla":"Kühne, Thomas, et al. “CP2K on the Road to Exascale.” ArXiv:2205.14741, 2022.","bibtex":"@article{Kühne_Plessl_Schade_Schütt_2022, title={CP2K on the road to exascale}, journal={arXiv:2205.14741}, author={Kühne, Thomas and Plessl, Christian and Schade, Robert and Schütt, Ole}, year={2022} }","chicago":"Kühne, Thomas, Christian Plessl, Robert Schade, and Ole Schütt. “CP2K on the Road to Exascale.” ArXiv:2205.14741, 2022.","apa":"Kühne, T., Plessl, C., Schade, R., & Schütt, O. (2022). CP2K on the road to exascale. In arXiv:2205.14741.","ama":"Kühne T, Plessl C, Schade R, Schütt O. CP2K on the road to exascale. arXiv:220514741. Published online 2022.","ieee":"T. Kühne, C. Plessl, R. Schade, and O. Schütt, “CP2K on the road to exascale,” arXiv:2205.14741. 2022.","short":"T. Kühne, C. Plessl, R. Schade, O. Schütt, ArXiv:2205.14741 (2022)."},"year":"2022","language":[{"iso":"eng"}],"main_file_link":[{"url":"https://arxiv.org/abs/2205.14741"}]},{"language":[{"iso":"eng"}],"doi":"10.1103/PhysRevResearch.4.033160","oa":"1","date_updated":"2023-08-02T15:04:22Z","publication_status":"published","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"27"},{"_id":"518"}],"title":"Parallel quantum chemistry on noisy intermediate-scale quantum computers","page":"033160","year":"2022","citation":{"ieee":"R. Schade, C. Bauer, K. Tamoev, L. Mazur, C. Plessl, and T. Kühne, “Parallel quantum chemistry on noisy intermediate-scale quantum computers,” Phys. Rev. Research, vol. 4, p. 033160, 2022, doi: 10.1103/PhysRevResearch.4.033160.","mla":"Schade, Robert, et al. “Parallel Quantum Chemistry on Noisy Intermediate-Scale Quantum Computers.” Phys. Rev. Research, vol. 4, American Physical Society, 2022, p. 033160, doi:10.1103/PhysRevResearch.4.033160.","bibtex":"@article{Schade_Bauer_Tamoev_Mazur_Plessl_Kühne_2022, title={Parallel quantum chemistry on noisy intermediate-scale quantum computers}, volume={4}, DOI={10.1103/PhysRevResearch.4.033160}, journal={Phys. Rev. Research}, publisher={American Physical Society}, author={Schade, Robert and Bauer, Carsten and Tamoev, Konstantin and Mazur, Lukas and Plessl, Christian and Kühne, Thomas}, year={2022}, pages={033160} }","apa":"Schade, R., Bauer, C., Tamoev, K., Mazur, L., Plessl, C., & Kühne, T. (2022). Parallel quantum chemistry on noisy intermediate-scale quantum computers. Phys. Rev. Research, 4, 033160. https://doi.org/10.1103/PhysRevResearch.4.033160","ama":"Schade R, Bauer C, Tamoev K, Mazur L, Plessl C, Kühne T. Parallel quantum chemistry on noisy intermediate-scale quantum computers. Phys Rev Research. 2022;4:033160. doi:10.1103/PhysRevResearch.4.033160","short":"R. Schade, C. Bauer, K. Tamoev, L. Mazur, C. Plessl, T. Kühne, Phys. Rev. Research 4 (2022) 033160.","chicago":"Schade, Robert, Carsten Bauer, Konstantin Tamoev, Lukas Mazur, Christian Plessl, and Thomas Kühne. “Parallel Quantum Chemistry on Noisy Intermediate-Scale Quantum Computers.” Phys. Rev. Research 4 (2022): 033160. https://doi.org/10.1103/PhysRevResearch.4.033160."},"type":"journal_article","main_file_link":[{"open_access":"1","url":"https://journals.aps.org/prresearch/abstract/10.1103/PhysRevResearch.4.033160"}],"_id":"33226","intvolume":" 4","volume":4,"date_created":"2022-08-29T14:07:01Z","status":"public","publication":"Phys. Rev. Research","author":[{"first_name":"Robert","full_name":"Schade, Robert","orcid":"0000-0002-6268-539","last_name":"Schade","id":"75963"},{"first_name":"Carsten","full_name":"Bauer, Carsten","last_name":"Bauer","id":"90082"},{"first_name":"Konstantin","full_name":"Tamoev, Konstantin","last_name":"Tamoev","id":"50177"},{"id":"90492","last_name":"Mazur","full_name":"Mazur, Lukas","orcid":" 0000-0001-6304-7082","first_name":"Lukas"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"},{"first_name":"Thomas","full_name":"Kühne, Thomas","last_name":"Kühne","id":"49079"}],"quality_controlled":"1","publisher":"American Physical Society","user_id":"75963","abstract":[{"lang":"eng","text":"A parallel hybrid quantum-classical algorithm for the solution of the quantum-chemical ground-state energy problem on gate-based quantum computers is presented. This approach is based on the reduced density-matrix functional theory (RDMFT) formulation of the electronic structure problem. For that purpose, the density-matrix functional of the full system is decomposed into an indirectly coupled sum of density-matrix functionals for all its subsystems using the adaptive cluster approximation to RDMFT. The approximations involved in the decomposition and the adaptive cluster approximation itself can be systematically converged to the exact result. The solutions for the density-matrix functionals of the effective subsystems involves a constrained minimization over many-particle states that are approximated by parametrized trial states on the quantum computer similarly to the variational quantum eigensolver. The independence of the density-matrix functionals of the effective subsystems introduces a new level of parallelization and allows for the computational treatment of much larger molecules on a quantum computer with a given qubit count. In addition, for the proposed algorithm techniques are presented to reduce the qubit count, the number of quantum programs, as well as its depth. The evaluation of a density-matrix functional as the essential part of our approach is demonstrated for Hubbard-like systems on IBM quantum computers based on superconducting transmon qubits."}],"article_type":"original"},{"language":[{"iso":"eng"}],"doi":"10.1016/j.parco.2022.102920","oa":"1","date_updated":"2023-08-02T15:03:55Z","publication_status":"published","publication_identifier":{"issn":["0167-8191"]},"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"department":[{"_id":"613"},{"_id":"27"},{"_id":"518"}],"title":"Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms","year":"2022","citation":{"short":"R. Schade, T. Kenter, H. Elgabarty, M. Lass, O. Schütt, A. Lazzaro, H. Pabst, S. Mohr, J. Hutter, T. Kühne, C. Plessl, Parallel Computing 111 (2022).","ieee":"R. Schade et al., “Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms,” Parallel Computing, vol. 111, Art. no. 102920, 2022, doi: 10.1016/j.parco.2022.102920.","chicago":"Schade, Robert, Tobias Kenter, Hossam Elgabarty, Michael Lass, Ole Schütt, Alfio Lazzaro, Hans Pabst, et al. “Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms.” Parallel Computing 111 (2022). https://doi.org/10.1016/j.parco.2022.102920.","apa":"Schade, R., Kenter, T., Elgabarty, H., Lass, M., Schütt, O., Lazzaro, A., Pabst, H., Mohr, S., Hutter, J., Kühne, T., & Plessl, C. (2022). Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms. Parallel Computing, 111, Article 102920. https://doi.org/10.1016/j.parco.2022.102920","ama":"Schade R, Kenter T, Elgabarty H, et al. Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms. Parallel Computing. 2022;111. doi:10.1016/j.parco.2022.102920","bibtex":"@article{Schade_Kenter_Elgabarty_Lass_Schütt_Lazzaro_Pabst_Mohr_Hutter_Kühne_et al._2022, title={Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms}, volume={111}, DOI={10.1016/j.parco.2022.102920}, number={102920}, journal={Parallel Computing}, publisher={Elsevier BV}, author={Schade, Robert and Kenter, Tobias and Elgabarty, Hossam and Lass, Michael and Schütt, Ole and Lazzaro, Alfio and Pabst, Hans and Mohr, Stephan and Hutter, Jürg and Kühne, Thomas and et al.}, year={2022} }","mla":"Schade, Robert, et al. “Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms.” Parallel Computing, vol. 111, 102920, Elsevier BV, 2022, doi:10.1016/j.parco.2022.102920."},"type":"journal_article","main_file_link":[{"url":"https://www.sciencedirect.com/science/article/pii/S0167819122000242","open_access":"1"}],"article_number":"102920","intvolume":" 111","_id":"33684","volume":111,"date_created":"2022-10-11T08:17:02Z","status":"public","publication":"Parallel Computing","keyword":["Artificial Intelligence","Computer Graphics and Computer-Aided Design","Computer Networks and Communications","Hardware and Architecture","Theoretical Computer Science","Software"],"publisher":"Elsevier BV","quality_controlled":"1","author":[{"last_name":"Schade","id":"75963","first_name":"Robert","full_name":"Schade, Robert","orcid":"0000-0002-6268-539"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"last_name":"Elgabarty","id":"60250","first_name":"Hossam","full_name":"Elgabarty, Hossam","orcid":"0000-0002-4945-1481"},{"id":"24135","last_name":"Lass","full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","first_name":"Michael"},{"full_name":"Schütt, Ole","first_name":"Ole","last_name":"Schütt"},{"last_name":"Lazzaro","first_name":"Alfio","full_name":"Lazzaro, Alfio"},{"last_name":"Pabst","first_name":"Hans","full_name":"Pabst, Hans"},{"last_name":"Mohr","full_name":"Mohr, Stephan","first_name":"Stephan"},{"last_name":"Hutter","full_name":"Hutter, Jürg","first_name":"Jürg"},{"last_name":"Kühne","id":"49079","first_name":"Thomas","full_name":"Kühne, Thomas"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian"}],"user_id":"75963"},{"date_updated":"2023-09-26T10:26:56Z","_id":"27364","doi":"10.1016/j.jpdc.2021.10.007","language":[{"iso":"eng"}],"citation":{"chicago":"Meyer, Marius, Tobias Kenter, and Christian Plessl. “In-Depth FPGA Accelerator Performance Evaluation with Single Node Benchmarks from the HPC Challenge Benchmark Suite for Intel and Xilinx FPGAs Using OpenCL.” Journal of Parallel and Distributed Computing, 2022. https://doi.org/10.1016/j.jpdc.2021.10.007.","ama":"Meyer M, Kenter T, Plessl C. In-depth FPGA Accelerator Performance Evaluation with Single Node Benchmarks from the HPC Challenge Benchmark Suite for Intel and Xilinx FPGAs using OpenCL. Journal of Parallel and Distributed Computing. Published online 2022. doi:10.1016/j.jpdc.2021.10.007","apa":"Meyer, M., Kenter, T., & Plessl, C. (2022). In-depth FPGA Accelerator Performance Evaluation with Single Node Benchmarks from the HPC Challenge Benchmark Suite for Intel and Xilinx FPGAs using OpenCL. Journal of Parallel and Distributed Computing. https://doi.org/10.1016/j.jpdc.2021.10.007","bibtex":"@article{Meyer_Kenter_Plessl_2022, title={In-depth FPGA Accelerator Performance Evaluation with Single Node Benchmarks from the HPC Challenge Benchmark Suite for Intel and Xilinx FPGAs using OpenCL}, DOI={10.1016/j.jpdc.2021.10.007}, journal={Journal of Parallel and Distributed Computing}, author={Meyer, Marius and Kenter, Tobias and Plessl, Christian}, year={2022} }","mla":"Meyer, Marius, et al. “In-Depth FPGA Accelerator Performance Evaluation with Single Node Benchmarks from the HPC Challenge Benchmark Suite for Intel and Xilinx FPGAs Using OpenCL.” Journal of Parallel and Distributed Computing, 2022, doi:10.1016/j.jpdc.2021.10.007.","short":"M. Meyer, T. Kenter, C. Plessl, Journal of Parallel and Distributed Computing (2022).","ieee":"M. Meyer, T. Kenter, and C. Plessl, “In-depth FPGA Accelerator Performance Evaluation with Single Node Benchmarks from the HPC Challenge Benchmark Suite for Intel and Xilinx FPGAs using OpenCL,” Journal of Parallel and Distributed Computing, 2022, doi: 10.1016/j.jpdc.2021.10.007."},"type":"journal_article","year":"2022","user_id":"15278","title":"In-depth FPGA Accelerator Performance Evaluation with Single Node Benchmarks from the HPC Challenge Benchmark Suite for Intel and Xilinx FPGAs using OpenCL","department":[{"_id":"27"},{"_id":"518"}],"publication":"Journal of Parallel and Distributed Computing","quality_controlled":"1","author":[{"last_name":"Meyer","id":"40778","first_name":"Marius","full_name":"Meyer, Marius"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"}],"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_created":"2021-11-10T14:36:27Z","status":"public","publication_status":"published","publication_identifier":{"issn":["0743-7315"]}},{"title":"The Strong Scaling Advantage of FPGAs in HPC for N-body Simulations","department":[{"_id":"27"},{"_id":"518"}],"publication_status":"published","publication_identifier":{"issn":["1936-7406","1936-7414"]},"date_updated":"2022-01-06T06:57:51Z","doi":"10.1145/3491235","oa":"1","language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"N-body methods are one of the essential algorithmic building blocks of high-performance and parallel computing. Previous research has shown promising performance for implementing n-body simulations with pairwise force calculations on FPGAs. However, to avoid challenges with accumulation and memory access patterns, the presented designs calculate each pair of forces twice, along with both force sums of the involved particles. Also, they require large problem instances with hundreds of thousands of particles to reach their respective peak performance, limiting the applicability for strong scaling scenarios. This work addresses both issues by presenting a novel FPGA design that uses each calculated force twice and overlaps data transfers and computations in a way that allows to reach peak performance even for small problem instances, outperforming previous single precision results even in double precision, and scaling linearly over multiple interconnected FPGAs. For a comparison across architectures, we provide an equally optimized CPU reference, which for large problems actually achieves higher peak performance per device, however, given the strong scaling advantages of the FPGA design, in parallel setups with few thousand particles per device, the FPGA platform achieves highest performance and power efficiency."}],"article_type":"original","user_id":"3145","publication":"ACM Transactions on Reconfigurable Technology and Systems","author":[{"first_name":"Johannes","full_name":"Menzel, Johannes","last_name":"Menzel"},{"orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian","id":"16153","last_name":"Plessl"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"}],"quality_controlled":"1","volume":15,"date_created":"2021-11-30T10:00:31Z","status":"public","intvolume":" 15","_id":"28099","issue":"1","main_file_link":[{"url":"https://dl.acm.org/doi/10.1145/3491235","open_access":"1"}],"page":"1-30","citation":{"bibtex":"@article{Menzel_Plessl_Kenter_2021, title={The Strong Scaling Advantage of FPGAs in HPC for N-body Simulations}, volume={15}, DOI={10.1145/3491235}, number={1}, journal={ACM Transactions on Reconfigurable Technology and Systems}, author={Menzel, Johannes and Plessl, Christian and Kenter, Tobias}, year={2021}, pages={1–30} }","mla":"Menzel, Johannes, et al. “The Strong Scaling Advantage of FPGAs in HPC for N-Body Simulations.” ACM Transactions on Reconfigurable Technology and Systems, vol. 15, no. 1, 2021, pp. 1–30, doi:10.1145/3491235.","ama":"Menzel J, Plessl C, Kenter T. The Strong Scaling Advantage of FPGAs in HPC for N-body Simulations. ACM Transactions on Reconfigurable Technology and Systems. 2021;15(1):1-30. doi:10.1145/3491235","apa":"Menzel, J., Plessl, C., & Kenter, T. (2021). The Strong Scaling Advantage of FPGAs in HPC for N-body Simulations. ACM Transactions on Reconfigurable Technology and Systems, 15(1), 1–30. https://doi.org/10.1145/3491235","chicago":"Menzel, Johannes, Christian Plessl, and Tobias Kenter. “The Strong Scaling Advantage of FPGAs in HPC for N-Body Simulations.” ACM Transactions on Reconfigurable Technology and Systems 15, no. 1 (2021): 1–30. https://doi.org/10.1145/3491235.","ieee":"J. Menzel, C. Plessl, and T. Kenter, “The Strong Scaling Advantage of FPGAs in HPC for N-body Simulations,” ACM Transactions on Reconfigurable Technology and Systems, vol. 15, no. 1, pp. 1–30, 2021, doi: 10.1145/3491235.","short":"J. Menzel, C. Plessl, T. Kenter, ACM Transactions on Reconfigurable Technology and Systems 15 (2021) 1–30."},"year":"2021","type":"journal_article"},{"title":"Algorithm-hardware co-design of a discontinuous Galerkin shallow-water model for a dataflow architecture on FPGA","user_id":"3145","publisher":"ACM","quality_controlled":"1","author":[{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"last_name":"Shambhu","full_name":"Shambhu, Adesh","first_name":"Adesh"},{"last_name":"Faghih-Naini","first_name":"Sara","full_name":"Faghih-Naini, Sara"},{"first_name":"Vadym","full_name":"Aizinger, Vadym","last_name":"Aizinger"}],"publication":"Proceedings of the Platform for Advanced Scientific Computing Conference","department":[{"_id":"27"},{"_id":"518"}],"publication_status":"published","status":"public","date_created":"2023-07-28T11:58:14Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"46194","date_updated":"2023-07-28T12:03:19Z","doi":"10.1145/3468267.3470617","oa":"1","main_file_link":[{"url":"https://dl.acm.org/doi/pdf/10.1145/3468267.3470617","open_access":"1"}],"year":"2021","type":"conference","citation":{"ieee":"T. Kenter, A. Shambhu, S. Faghih-Naini, and V. Aizinger, “Algorithm-hardware co-design of a discontinuous Galerkin shallow-water model for a dataflow architecture on FPGA,” 2021, doi: 10.1145/3468267.3470617.","short":"T. Kenter, A. Shambhu, S. Faghih-Naini, V. Aizinger, in: Proceedings of the Platform for Advanced Scientific Computing Conference, ACM, 2021.","bibtex":"@inproceedings{Kenter_Shambhu_Faghih-Naini_Aizinger_2021, title={Algorithm-hardware co-design of a discontinuous Galerkin shallow-water model for a dataflow architecture on FPGA}, DOI={10.1145/3468267.3470617}, booktitle={Proceedings of the Platform for Advanced Scientific Computing Conference}, publisher={ACM}, author={Kenter, Tobias and Shambhu, Adesh and Faghih-Naini, Sara and Aizinger, Vadym}, year={2021} }","mla":"Kenter, Tobias, et al. “Algorithm-Hardware Co-Design of a Discontinuous Galerkin Shallow-Water Model for a Dataflow Architecture on FPGA.” Proceedings of the Platform for Advanced Scientific Computing Conference, ACM, 2021, doi:10.1145/3468267.3470617.","chicago":"Kenter, Tobias, Adesh Shambhu, Sara Faghih-Naini, and Vadym Aizinger. “Algorithm-Hardware Co-Design of a Discontinuous Galerkin Shallow-Water Model for a Dataflow Architecture on FPGA.” In Proceedings of the Platform for Advanced Scientific Computing Conference. ACM, 2021. https://doi.org/10.1145/3468267.3470617.","apa":"Kenter, T., Shambhu, A., Faghih-Naini, S., & Aizinger, V. (2021). Algorithm-hardware co-design of a discontinuous Galerkin shallow-water model for a dataflow architecture on FPGA. Proceedings of the Platform for Advanced Scientific Computing Conference. https://doi.org/10.1145/3468267.3470617","ama":"Kenter T, Shambhu A, Faghih-Naini S, Aizinger V. Algorithm-hardware co-design of a discontinuous Galerkin shallow-water model for a dataflow architecture on FPGA. In: Proceedings of the Platform for Advanced Scientific Computing Conference. ACM; 2021. doi:10.1145/3468267.3470617"},"language":[{"iso":"eng"}]},{"publication_status":"published","date_created":"2023-07-28T12:04:27Z","status":"public","department":[{"_id":"27"},{"_id":"518"}],"publication":"2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","quality_controlled":"1","author":[{"first_name":"Martin","full_name":"Karp, Martin","last_name":"Karp"},{"last_name":"Podobas","full_name":"Podobas, Artur","first_name":"Artur"},{"first_name":"Niclas","full_name":"Jansson, Niclas","last_name":"Jansson"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian","id":"16153","last_name":"Plessl"},{"last_name":"Schlatter","full_name":"Schlatter, Philipp","first_name":"Philipp"},{"first_name":"Stefano","full_name":"Markidis, Stefano","last_name":"Markidis"}],"publisher":"IEEE","title":"High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection","user_id":"3145","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.","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","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","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."},"year":"2021","type":"conference","language":[{"iso":"eng"}],"doi":"10.1109/ipdps49936.2021.00116","date_updated":"2023-07-28T12:05:15Z","_id":"46195"},{"language":[{"iso":"eng"}],"doi":"10.1007/978-3-030-71593-9_15","date_updated":"2023-09-26T11:40:25Z","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"publication_identifier":{"issn":["0302-9743","1611-3349"],"isbn":["9783030715922","9783030715939"]},"publication_status":"published","department":[{"_id":"61"},{"_id":"230"},{"_id":"429"},{"_id":"27"},{"_id":"518"}],"title":"HighPerMeshes – A Domain-Specific Language for Numerical Algorithms on Unstructured Grids","place":"Cham","type":"book_chapter","citation":{"mla":"Alhaddad, Samer, et al. “HighPerMeshes – A Domain-Specific Language for Numerical Algorithms on Unstructured Grids.” Euro-Par 2020: Parallel Processing Workshops, 2021, doi:10.1007/978-3-030-71593-9_15.","bibtex":"@inbook{Alhaddad_Förstner_Groth_Grünewald_Grynko_Hannig_Kenter_Pfreundt_Plessl_Schotte_et al._2021, place={Cham}, title={HighPerMeshes – A Domain-Specific Language for Numerical Algorithms on Unstructured Grids}, DOI={10.1007/978-3-030-71593-9_15}, booktitle={Euro-Par 2020: Parallel Processing Workshops}, 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} }","chicago":"Alhaddad, Samer, Jens Förstner, Stefan Groth, Daniel Grünewald, Yevgen Grynko, Frank Hannig, Tobias Kenter, et al. “HighPerMeshes – A Domain-Specific Language for Numerical Algorithms on Unstructured Grids.” In Euro-Par 2020: Parallel Processing Workshops. Cham, 2021. https://doi.org/10.1007/978-3-030-71593-9_15.","ama":"Alhaddad S, Förstner J, Groth S, et al. HighPerMeshes – A Domain-Specific Language for Numerical Algorithms on Unstructured Grids. In: Euro-Par 2020: Parallel Processing Workshops. ; 2021. doi:10.1007/978-3-030-71593-9_15","apa":"Alhaddad, S., Förstner, J., Groth, S., Grünewald, D., Grynko, Y., Hannig, F., Kenter, T., Pfreundt, F.-J., Plessl, C., Schotte, M., Steinke, T., Teich, J., Weiser, M., & Wende, F. (2021). HighPerMeshes – A Domain-Specific Language for Numerical Algorithms on Unstructured Grids. In Euro-Par 2020: Parallel Processing Workshops. https://doi.org/10.1007/978-3-030-71593-9_15","ieee":"S. Alhaddad et al., “HighPerMeshes – A Domain-Specific Language for Numerical Algorithms on Unstructured Grids,” in Euro-Par 2020: Parallel Processing Workshops, Cham, 2021.","short":"S. Alhaddad, J. Förstner, S. Groth, D. Grünewald, Y. Grynko, F. Hannig, T. Kenter, F.-J. Pfreundt, C. Plessl, M. Schotte, T. Steinke, J. Teich, M. Weiser, F. Wende, in: Euro-Par 2020: Parallel Processing Workshops, Cham, 2021."},"year":"2021","_id":"21587","date_created":"2021-03-31T19:39:42Z","has_accepted_license":"1","status":"public","file":[{"access_level":"closed","date_created":"2021-03-31T19:42:52Z","file_name":"2021-03 Alhaddad2021_Chapter_HighPerMeshesADomain-SpecificL.pdf","success":1,"relation":"main_file","date_updated":"2021-03-31T19:42:52Z","content_type":"application/pdf","file_id":"21588","creator":"fossie","file_size":564398}],"keyword":["tet_topic_hpc"],"file_date_updated":"2021-03-31T19:42:52Z","publication":"Euro-Par 2020: Parallel Processing Workshops","quality_controlled":"1","author":[{"id":"42456","last_name":"Alhaddad","full_name":"Alhaddad, Samer","first_name":"Samer"},{"id":"158","last_name":"Förstner","orcid":"0000-0001-7059-9862","full_name":"Förstner, Jens","first_name":"Jens"},{"last_name":"Groth","full_name":"Groth, Stefan","first_name":"Stefan"},{"first_name":"Daniel","full_name":"Grünewald, Daniel","last_name":"Grünewald"},{"first_name":"Yevgen","full_name":"Grynko, Yevgen","last_name":"Grynko","id":"26059"},{"last_name":"Hannig","first_name":"Frank","full_name":"Hannig, Frank"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"full_name":"Pfreundt, Franz-Josef","first_name":"Franz-Josef","last_name":"Pfreundt"},{"last_name":"Plessl","id":"16153","first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982"},{"first_name":"Merlind","full_name":"Schotte, Merlind","last_name":"Schotte"},{"last_name":"Steinke","full_name":"Steinke, Thomas","first_name":"Thomas"},{"first_name":"Jürgen","full_name":"Teich, Jürgen","last_name":"Teich"},{"last_name":"Weiser","full_name":"Weiser, Martin","first_name":"Martin"},{"last_name":"Wende","first_name":"Florian","full_name":"Wende, Florian"}],"user_id":"15278","ddc":["004"],"abstract":[{"lang":"eng","text":"Solving partial differential equations on unstructured grids is a cornerstone of engineering and scientific computing. Nowadays, heterogeneous parallel platforms with CPUs, GPUs, and FPGAs enable energy-efficient and computationally demanding simulations. We developed the HighPerMeshes C++-embedded Domain-Specific Language (DSL) for bridging the abstraction gap between the mathematical and algorithmic formulation of mesh-based algorithms for PDE problems on the one hand and an increasing number of heterogeneous platforms with their different parallel programming and runtime models on the other hand. Thus, the HighPerMeshes DSL aims at higher productivity in the code development process for multiple target platforms. We introduce the concepts as well as the basic structure of the HighPerMeshes DSL, and demonstrate its usage with three examples, a Poisson and monodomain problem, respectively, solved by the continuous finite element method, and the discontinuous Galerkin method for Maxwell’s equation. The mapping of the abstract algorithmic description onto parallel hardware, including distributed memory compute clusters, is presented. Finally, the achievable performance and scalability are demonstrated for a typical example problem on a multi-core CPU cluster."}]},{"user_id":"15278","title":"Evaluating the Design Space for Offloading 3D FFT Calculations to an FPGA for High-Performance Computing","place":"Cham","date_created":"2022-02-21T14:22:01Z","status":"public","publication_identifier":{"issn":["0302-9743","1611-3349"],"isbn":["9783030790240","9783030790257"]},"publication_status":"published","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"publication":"Applied Reconfigurable Computing. Architectures, Tools, and Applications","quality_controlled":"1","author":[{"first_name":"Arjun","orcid":"https://orcid.org/0000-0002-0909-1178","full_name":"Ramaswami, Arjun","last_name":"Ramaswami","id":"49171"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"last_name":"Kühne","id":"49079","first_name":"Thomas","full_name":"Kühne, Thomas"},{"full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian","id":"16153","last_name":"Plessl"}],"publisher":"Springer International Publishing","doi":"10.1007/978-3-030-79025-7_21","conference":{"name":"Int. Conf. on Applied Reconfigurable Computing. Architectures, Tools, and Applications"},"date_updated":"2023-09-26T11:40:45Z","_id":"29936","language":[{"iso":"eng"}],"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.","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.","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","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","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} }"},"type":"book_chapter","year":"2021"},{"status":"public","has_accepted_license":"1","date_created":"2021-09-22T06:15:50Z","file":[{"file_id":"24789","creator":"fossie","file_size":2300152,"relation":"main_file","date_updated":"2021-09-22T06:19:29Z","content_type":"application/pdf","file_name":"2021-09 Alhaddad - Concurrency... - The HighPerMeshes framework for numerical algorithms on unstructured grids.pdf","date_created":"2021-09-22T06:19:29Z","access_level":"open_access"}],"author":[{"full_name":"Alhaddad, Samer","first_name":"Samer","id":"42456","last_name":"Alhaddad"},{"id":"158","last_name":"Förstner","full_name":"Förstner, Jens","orcid":"0000-0001-7059-9862","first_name":"Jens"},{"first_name":"Stefan","full_name":"Groth, Stefan","last_name":"Groth"},{"last_name":"Grünewald","full_name":"Grünewald, Daniel","first_name":"Daniel"},{"full_name":"Grynko, Yevgen","first_name":"Yevgen","id":"26059","last_name":"Grynko"},{"last_name":"Hannig","first_name":"Frank","full_name":"Hannig, Frank"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"last_name":"Pfreundt","first_name":"Franz‐Josef","full_name":"Pfreundt, Franz‐Josef"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian"},{"first_name":"Merlind","full_name":"Schotte, Merlind","last_name":"Schotte"},{"last_name":"Steinke","full_name":"Steinke, Thomas","first_name":"Thomas"},{"last_name":"Teich","full_name":"Teich, Jürgen","first_name":"Jürgen"},{"last_name":"Weiser","full_name":"Weiser, Martin","first_name":"Martin"},{"last_name":"Wende","first_name":"Florian","full_name":"Wende, Florian"}],"quality_controlled":"1","keyword":["tet_topic_hpc"],"publication":"Concurrency and Computation: Practice and Experience","file_date_updated":"2021-09-22T06:19:29Z","user_id":"15278","ddc":["004"],"type":"journal_article","year":"2021","citation":{"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.","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.","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.","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","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.","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} }"},"page":"e6616","_id":"24788","project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"_id":"33","grant_number":"01|H16005A","name":"HighPerMeshes"}],"publication_status":"published","publication_identifier":{"issn":["1532-0626","1532-0634"]},"department":[{"_id":"61"},{"_id":"230"},{"_id":"27"},{"_id":"518"}],"title":"The HighPerMeshes framework for numerical algorithms on unstructured grids","language":[{"iso":"eng"}],"oa":"1","doi":"10.1002/cpe.6616","date_updated":"2023-09-26T11:42:19Z"},{"title":"High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection","user_id":"3145","publication_status":"published","status":"public","date_created":"2022-02-21T14:26:37Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"publisher":"IEEE","quality_controlled":"1","author":[{"full_name":"Karp, Martin","first_name":"Martin","last_name":"Karp"},{"first_name":"Artur","full_name":"Podobas, Artur","last_name":"Podobas"},{"full_name":"Jansson, Niclas","first_name":"Niclas","last_name":"Jansson"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian"},{"last_name":"Schlatter","first_name":"Philipp","full_name":"Schlatter, Philipp"},{"last_name":"Markidis","first_name":"Stefano","full_name":"Markidis, Stefano"}],"department":[{"_id":"27"},{"_id":"518"}],"publication":"2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","doi":"10.1109/ipdps49936.2021.00116","date_updated":"2024-01-22T09:59:13Z","_id":"29937","type":"conference","year":"2021","citation":{"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.","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.","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} }","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.","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","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"},"language":[{"iso":"eng"}]},{"user_id":"75963","ddc":["540"],"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"}],"has_accepted_license":"1","status":"public","date_created":"2020-03-10T15:12:31Z","volume":152,"file":[{"file_name":"5.0007045.pdf","date_created":"2020-05-25T15:21:56Z","access_level":"closed","creator":"lass","file_id":"17061","file_size":4887650,"relation":"main_file","success":1,"date_updated":"2020-05-25T15:21:56Z","content_type":"application/pdf"}],"quality_controlled":"1","author":[{"full_name":"Kühne, Thomas","first_name":"Thomas","id":"49079","last_name":"Kühne"},{"last_name":"Iannuzzi","first_name":"Marcella","full_name":"Iannuzzi, Marcella"},{"last_name":"Ben","first_name":"Mauro Del","full_name":"Ben, Mauro Del"},{"full_name":"Rybkin, Vladimir V.","first_name":"Vladimir V.","last_name":"Rybkin"},{"first_name":"Patrick","full_name":"Seewald, Patrick","last_name":"Seewald"},{"last_name":"Stein","full_name":"Stein, Frederick","first_name":"Frederick"},{"first_name":"Teodoro","full_name":"Laino, Teodoro","last_name":"Laino"},{"last_name":"Khaliullin","first_name":"Rustam Z.","full_name":"Khaliullin, Rustam Z."},{"first_name":"Ole","full_name":"Schütt, Ole","last_name":"Schütt"},{"last_name":"Schiffmann","full_name":"Schiffmann, Florian","first_name":"Florian"},{"last_name":"Golze","first_name":"Dorothea","full_name":"Golze, Dorothea"},{"last_name":"Wilhelm","full_name":"Wilhelm, Jan","first_name":"Jan"},{"last_name":"Chulkov","full_name":"Chulkov, Sergey","first_name":"Sergey"},{"full_name":"Mohammad Hossein Bani-Hashemian, Mohammad Hossein Bani-Hashemian","first_name":"Mohammad Hossein Bani-Hashemian","last_name":"Mohammad Hossein Bani-Hashemian"},{"full_name":"Weber, Valéry","first_name":"Valéry","last_name":"Weber"},{"last_name":"Borstnik","full_name":"Borstnik, Urban","first_name":"Urban"},{"first_name":"Mathieu","full_name":"Taillefumier, Mathieu","last_name":"Taillefumier"},{"full_name":"Jakobovits, Alice Shoshana","first_name":"Alice Shoshana","last_name":"Jakobovits"},{"last_name":"Lazzaro","first_name":"Alfio","full_name":"Lazzaro, Alfio"},{"first_name":"Hans","full_name":"Pabst, Hans","last_name":"Pabst"},{"last_name":"Müller","full_name":"Müller, Tiziano","first_name":"Tiziano"},{"id":"75963","last_name":"Schade","full_name":"Schade, Robert","orcid":"0000-0002-6268-539","first_name":"Robert"},{"last_name":"Guidon","full_name":"Guidon, Manuel","first_name":"Manuel"},{"last_name":"Andermatt","first_name":"Samuel","full_name":"Andermatt, Samuel"},{"full_name":"Holmberg, Nico","first_name":"Nico","last_name":"Holmberg"},{"last_name":"Schenter","first_name":"Gregory K.","full_name":"Schenter, Gregory K."},{"last_name":"Hehn","full_name":"Hehn, Anna","first_name":"Anna"},{"first_name":"Augustin","full_name":"Bussy, Augustin","last_name":"Bussy"},{"last_name":"Belleflamme","full_name":"Belleflamme, Fabian","first_name":"Fabian"},{"last_name":"Tabacchi","full_name":"Tabacchi, Gloria","first_name":"Gloria"},{"first_name":"Andreas","full_name":"Glöß, Andreas","last_name":"Glöß"},{"id":"24135","last_name":"Lass","full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","first_name":"Michael"},{"last_name":"Bethune","full_name":"Bethune, Iain","first_name":"Iain"},{"first_name":"Christopher J.","full_name":"Mundy, Christopher J.","last_name":"Mundy"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"},{"first_name":"Matt","full_name":"Watkins, Matt","last_name":"Watkins"},{"full_name":"VandeVondele, Joost","first_name":"Joost","last_name":"VandeVondele"},{"first_name":"Matthias","full_name":"Krack, Matthias","last_name":"Krack"},{"full_name":"Hutter, Jürg","first_name":"Jürg","last_name":"Hutter"}],"publication":"The Journal of Chemical Physics","file_date_updated":"2020-05-25T15:21:56Z","issue":"19","article_number":"194103","_id":"16277","intvolume":" 152","year":"2020","citation":{"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} }","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.","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.","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.","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).","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","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"},"type":"journal_article","main_file_link":[{"url":"https://aip.scitation.org/doi/pdf/10.1063/5.0007045?download=true","open_access":"1"}],"title":"CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations","external_id":{"arxiv":["2003.03868"]},"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"},{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"publication_status":"published","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"oa":"1","doi":"10.1063/5.0007045","date_updated":"2023-08-02T14:56:21Z","language":[{"iso":"eng"}]},{"date_updated":"2023-08-02T14:55:59Z","doi":"10.1109/SC41405.2020.00084","language":[{"iso":"eng"}],"place":"Los Alamitos, CA, USA","external_id":{"arxiv":["2004.10811"]},"title":"A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"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"}],"_id":"16898","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"}],"year":"2020","citation":{"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.","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.","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.","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} }","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","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","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."},"type":"conference","page":"1127-1140","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"}],"user_id":"75963","publisher":"IEEE Computer Society","quality_controlled":"1","author":[{"first_name":"Michael","orcid":"0000-0002-5708-7632","full_name":"Lass, Michael","last_name":"Lass","id":"24135"},{"first_name":"Robert","orcid":"0000-0002-6268-539","full_name":"Schade, Robert","last_name":"Schade","id":"75963"},{"last_name":"Kühne","id":"49079","first_name":"Thomas","full_name":"Kühne, Thomas"},{"full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian","id":"16153","last_name":"Plessl"}],"publication":"Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","status":"public","date_created":"2020-04-28T14:44:21Z"},{"language":[{"iso":"eng"}],"date_updated":"2023-09-26T11:42:53Z","doi":"10.1109/h2rc51942.2020.00007","department":[{"_id":"27"},{"_id":"518"}],"publication_status":"published","publication_identifier":{"isbn":["9781665415927"]},"project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"title":"Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite","related_material":{"link":[{"url":"https://github.com/pc2/HPCC_FPGA","description":"Official repository of the benchmark suite on GitHub","relation":"supplementary_material"}]},"main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9306963"}],"citation":{"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} }","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.","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.","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","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","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.","short":"M. Meyer, T. Kenter, C. Plessl, in: 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2020."},"type":"conference","year":"2020","_id":"21632","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":[{"id":"40778","last_name":"Meyer","full_name":"Meyer, Marius","first_name":"Marius"},{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian"}],"date_created":"2021-04-16T10:17:22Z","status":"public","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"},{"volume":8,"status":"public","date_created":"2019-07-23T12:03:07Z","quality_controlled":"1","publisher":"MDPI","author":[{"full_name":"Rengaraj, Varadarajan","first_name":"Varadarajan","last_name":"Rengaraj"},{"full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","first_name":"Michael","id":"24135","last_name":"Lass"},{"orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian","id":"16153","last_name":"Plessl"},{"first_name":"Thomas","full_name":"Kühne, Thomas","last_name":"Kühne","id":"49079"}],"publication":"Computation","user_id":"15278","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."}],"year":"2020","type":"journal_article","citation":{"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} }","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.","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","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","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.","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.","short":"V. Rengaraj, M. Lass, C. Plessl, T. Kühne, Computation 8 (2020)."},"main_file_link":[{"url":"https://www.mdpi.com/2079-3197/8/2/39/pdf","open_access":"1"}],"article_number":"39","issue":"2","intvolume":" 8","_id":"12878","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"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"title":"Accurate Sampling with Noisy Forces from Approximate Computing","external_id":{"arxiv":["1907.08497"]},"language":[{"iso":"eng"}],"doi":"10.3390/computation8020039","oa":"1","date_updated":"2023-09-26T11:43:52Z"},{"article_type":"original","ddc":["000"],"user_id":"16153","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"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"quality_controlled":"1","publisher":"ACM","publication":"ACM Trans. Archit. Code Optim. (TACO)","keyword":["htrop"],"file_date_updated":"2019-02-13T14:59:07Z","file":[{"file_id":"7695","creator":"deffel","file_size":872822,"relation":"main_file","content_type":"application/pdf","date_updated":"2019-02-13T14:59:07Z","file_name":"htrop19_taco.pdf","date_created":"2019-02-13T14:59:07Z","access_level":"closed"}],"volume":16,"status":"public","has_accepted_license":"1","date_created":"2019-02-13T15:01:43Z","intvolume":" 16","_id":"7689","issue":"2","type":"journal_article","citation":{"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} }","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.","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.","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","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","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.","short":"H. Riebler, G.F. Vaz, T. Kenter, C. Plessl, ACM Trans. Archit. Code Optim. (TACO) 16 (2019) 14:1–14:26."},"year":"2019","page":"14:1–14:26","title":"Transparent Acceleration for Heterogeneous Platforms with Compilation to OpenCL","department":[{"_id":"27"},{"_id":"518"}],"publication_status":"published","project":[{"name":"SFB 901","_id":"1"},{"_id":"4","name":"SFB 901 - Project Area C"},{"name":"SFB 901 - Subproject C2","_id":"14"}],"date_updated":"2022-01-06T07:03:44Z","doi":"10.1145/3319423","language":[{"iso":"eng"}]},{"date_updated":"2022-01-06T06:52:26Z","doi":"10.1109/ICFPT47387.2019.00020","language":[{"iso":"eng"}],"title":"OpenCL Implementation of Cannon's Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs","department":[{"_id":"27"},{"_id":"518"}],"project":[{"name":"HighPerMeshes","grant_number":"01|H16005","_id":"33"},{"_id":"32","grant_number":"PL 595/2-1","name":"Performance and Efficiency in HPC with Custom Computing"}],"conference":{"name":"International Conference on Field-Programmable Technology (FPT)"},"_id":"15478","citation":{"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.","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} }","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","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","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.","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."},"year":"2019","type":"conference","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"}],"ddc":["004"],"user_id":"3145","file_date_updated":"2020-01-09T12:53:57Z","publication":"Proceedings of the International Conference on Field-Programmable Technology (FPT)","publisher":"IEEE","quality_controlled":"1","author":[{"full_name":"Gorlani, Paolo","first_name":"Paolo","id":"72045","last_name":"Gorlani"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"}],"file":[{"relation":"main_file","success":1,"content_type":"application/pdf","date_updated":"2020-01-09T12:53:57Z","file_id":"15479","creator":"plessl","file_size":250559,"access_level":"closed","date_created":"2020-01-09T12:53:57Z","file_name":"gorlani19_fpt.pdf"}],"date_created":"2020-01-09T12:54:48Z","has_accepted_license":"1","status":"public"},{"_id":"14849","date_updated":"2022-01-06T06:52:08Z","type":"dissertation","year":"2019","citation":{"short":"G.F. Vaz, Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems, Universität Paderborn, 2019.","ieee":"G. F. Vaz, 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.","chicago":"Vaz, Gavin Francis. Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems. Universität Paderborn, 2019.","mla":"Vaz, Gavin Francis. 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} }"},"language":[{"iso":"eng"}],"supervisor":[{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"}],"ddc":["040"],"title":"Using Just-in-Time Code Generation to Transparently Accelerate Applications in Heterogeneous Systems","user_id":"477","project":[{"name":"SFB 901","_id":"1"},{"name":"SFB 901 - Project Area C","_id":"4"},{"name":"SFB 901 - Subproject C2","_id":"14"}],"date_created":"2019-11-07T14:13:54Z","has_accepted_license":"1","status":"public","department":[{"_id":"518"}],"file_date_updated":"2019-11-07T14:13:14Z","author":[{"last_name":"Vaz","id":"30332","first_name":"Gavin Francis","full_name":"Vaz, Gavin Francis"}],"publisher":"Universität Paderborn","file":[{"relation":"main_file","success":1,"content_type":"application/pdf","date_updated":"2019-11-07T14:13:14Z","file_id":"14850","creator":"florida","file_size":1462659,"access_level":"closed","file_name":"PhDThesis_GavinVaz_2019-07-11.pdf","date_created":"2019-11-07T14:13:14Z"}]}]