[{"status":"public","date_created":"2022-06-27T09:08:04Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"author":[{"first_name":"Nicolas","full_name":"Borghini, Nicolas","last_name":"Borghini"},{"last_name":"Borrell","first_name":"Marc","full_name":"Borrell, Marc"},{"last_name":"Roch","full_name":"Roch, Hendrik","first_name":"Hendrik"}],"publication":"arXiv:2201.13294","department":[{"_id":"27"}],"title":"Early time behavior of spatial and momentum anisotropies in kinetic theory across different Knudsen numbers","user_id":"67287","abstract":[{"lang":"eng","text":"We investigate the early time development of the anisotropic transverse flow\r\nand spatial eccentricities of a fireball with various particle-based transport\r\napproaches using a fixed initial condition. In numerical simulations ranging\r\nfrom the quasi-collisionless case to the hydrodynamic regime, we find that the\r\nonset of $v_n$ and of related measures of anisotropic flow can be described\r\nwith a simple power-law ansatz, with an exponent that depends on the amount of\r\nrescatterings in the system. In the few-rescatterings regime we perform\r\nsemi-analytical calculations, based on a systematic expansion in powers of time\r\nand the cross section, which can reproduce the numerical findings."}],"external_id":{"arxiv":["2201.13294"]},"citation":{"ieee":"N. Borghini, M. Borrell, and H. Roch, “Early time behavior of spatial and momentum anisotropies in kinetic theory across different Knudsen numbers,” arXiv:2201.13294. 2022.","short":"N. Borghini, M. Borrell, H. Roch, ArXiv:2201.13294 (2022).","mla":"Borghini, Nicolas, et al. “Early Time Behavior of Spatial and Momentum Anisotropies in Kinetic Theory across Different Knudsen Numbers.” ArXiv:2201.13294, 2022.","bibtex":"@article{Borghini_Borrell_Roch_2022, title={Early time behavior of spatial and momentum anisotropies in kinetic theory across different Knudsen numbers}, journal={arXiv:2201.13294}, author={Borghini, Nicolas and Borrell, Marc and Roch, Hendrik}, year={2022} }","apa":"Borghini, N., Borrell, M., & Roch, H. (2022). Early time behavior of spatial and momentum anisotropies in kinetic theory across different Knudsen numbers. In arXiv:2201.13294.","ama":"Borghini N, Borrell M, Roch H. Early time behavior of spatial and momentum anisotropies in kinetic theory across different Knudsen numbers. arXiv:220113294. Published online 2022.","chicago":"Borghini, Nicolas, Marc Borrell, and Hendrik Roch. “Early Time Behavior of Spatial and Momentum Anisotropies in Kinetic Theory across Different Knudsen Numbers.” ArXiv:2201.13294, 2022."},"year":"2022","type":"preprint","language":[{"iso":"eng"}],"_id":"32177","date_updated":"2022-06-27T09:35:53Z"},{"title":"Even anisotropic-flow harmonics are from Venus, odd ones are from Mars","user_id":"67287","external_id":{"arxiv":["2203.13306"]},"abstract":[{"lang":"eng","text":"We test the ability of the \"escape mechanism\" to create the anisotropic flow\r\nobserved in high-energy nuclear collisions. We compare the flow harmonics $v_n$\r\nin the few-rescatterings regime from two types of transport simulations, with\r\n$2\\to 2$ and $2\\to 0$ collision kernels respectively, and from analytical\r\ncalculations neglecting the gain term of the Boltzmann equation. We find that\r\nthe even flow harmonics are similar in the three approaches, while the odd\r\nharmonics differ significantly."}],"status":"public","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"date_created":"2022-06-27T09:12:26Z","author":[{"first_name":"Benedikt","full_name":"Bachmann, Benedikt","last_name":"Bachmann"},{"first_name":"Nicolas","full_name":"Borghini, Nicolas","last_name":"Borghini"},{"first_name":"Nina","full_name":"Feld, Nina","last_name":"Feld"},{"first_name":"Hendrik","full_name":"Roch, Hendrik","last_name":"Roch"}],"publication":"arXiv:2203.13306","department":[{"_id":"27"}],"_id":"32178","date_updated":"2022-06-27T09:35:34Z","year":"2022","citation":{"apa":"Bachmann, B., Borghini, N., Feld, N., & Roch, H. (2022). Even anisotropic-flow harmonics are from Venus, odd ones are from Mars. In arXiv:2203.13306.","short":"B. Bachmann, N. Borghini, N. Feld, H. Roch, ArXiv:2203.13306 (2022).","ama":"Bachmann B, Borghini N, Feld N, Roch H. Even anisotropic-flow harmonics are from Venus, odd ones are from Mars. arXiv:220313306. Published online 2022.","chicago":"Bachmann, Benedikt, Nicolas Borghini, Nina Feld, and Hendrik Roch. “Even Anisotropic-Flow Harmonics Are from Venus, Odd Ones Are from Mars.” ArXiv:2203.13306, 2022.","ieee":"B. Bachmann, N. Borghini, N. Feld, and H. Roch, “Even anisotropic-flow harmonics are from Venus, odd ones are from Mars,” arXiv:2203.13306. 2022.","bibtex":"@article{Bachmann_Borghini_Feld_Roch_2022, title={Even anisotropic-flow harmonics are from Venus, odd ones are from Mars}, journal={arXiv:2203.13306}, author={Bachmann, Benedikt and Borghini, Nicolas and Feld, Nina and Roch, Hendrik}, year={2022} }","mla":"Bachmann, Benedikt, et al. “Even Anisotropic-Flow Harmonics Are from Venus, Odd Ones Are from Mars.” ArXiv:2203.13306, 2022."},"type":"preprint","language":[{"iso":"eng"}]},{"language":[{"iso":"eng"}],"year":"2022","type":"preprint","citation":{"ieee":"V. Gavini et al., “Roadmap on Electronic Structure Codes in the Exascale Era,” arXiv:2209.12747. 2022.","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).","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} }","mla":"Gavini, Vikram, 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."},"date_updated":"2023-07-28T08:03:41Z","_id":"33493","author":[{"first_name":"Vikram","full_name":"Gavini, Vikram","last_name":"Gavini"},{"full_name":"Baroni, Stefano","first_name":"Stefano","last_name":"Baroni"},{"last_name":"Blum","first_name":"Volker","full_name":"Blum, Volker"},{"last_name":"Bowler","first_name":"David R.","full_name":"Bowler, David R."},{"last_name":"Buccheri","full_name":"Buccheri, Alexander","first_name":"Alexander"},{"full_name":"Chelikowsky, James R.","first_name":"James R.","last_name":"Chelikowsky"},{"full_name":"Das, Sambit","first_name":"Sambit","last_name":"Das"},{"last_name":"Dawson","full_name":"Dawson, William","first_name":"William"},{"last_name":"Delugas","full_name":"Delugas, Pietro","first_name":"Pietro"},{"last_name":"Dogan","full_name":"Dogan, Mehmet","first_name":"Mehmet"},{"first_name":"Claudia","full_name":"Draxl, Claudia","last_name":"Draxl"},{"last_name":"Galli","full_name":"Galli, Giulia","first_name":"Giulia"},{"full_name":"Genovese, Luigi","first_name":"Luigi","last_name":"Genovese"},{"first_name":"Paolo","full_name":"Giannozzi, Paolo","last_name":"Giannozzi"},{"full_name":"Giantomassi, Matteo","first_name":"Matteo","last_name":"Giantomassi"},{"last_name":"Gonze","first_name":"Xavier","full_name":"Gonze, Xavier"},{"first_name":"Marco","full_name":"Govoni, Marco","last_name":"Govoni"},{"first_name":"Andris","full_name":"Gulans, Andris","last_name":"Gulans"},{"full_name":"Gygi, François","first_name":"François","last_name":"Gygi"},{"first_name":"John M.","full_name":"Herbert, John M.","last_name":"Herbert"},{"full_name":"Kokott, Sebastian","first_name":"Sebastian","last_name":"Kokott"},{"id":"49079","last_name":"Kühne","full_name":"Kühne, Thomas","first_name":"Thomas"},{"last_name":"Liou","first_name":"Kai-Hsin","full_name":"Liou, Kai-Hsin"},{"last_name":"Miyazaki","full_name":"Miyazaki, Tsuyoshi","first_name":"Tsuyoshi"},{"first_name":"Phani","full_name":"Motamarri, Phani","last_name":"Motamarri"},{"full_name":"Nakata, Ayako","first_name":"Ayako","last_name":"Nakata"},{"last_name":"Pask","first_name":"John E.","full_name":"Pask, John E."},{"last_name":"Plessl","id":"16153","first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982"},{"first_name":"Laura E.","full_name":"Ratcliff, Laura E.","last_name":"Ratcliff"},{"first_name":"Ryan M.","full_name":"Richard, Ryan M.","last_name":"Richard"},{"full_name":"Rossi, Mariana","first_name":"Mariana","last_name":"Rossi"},{"full_name":"Schade, Robert","orcid":"0000-0002-6268-539","first_name":"Robert","id":"75963","last_name":"Schade"},{"last_name":"Scheffler","full_name":"Scheffler, Matthias","first_name":"Matthias"},{"last_name":"Schütt","first_name":"Ole","full_name":"Schütt, Ole"},{"first_name":"Phanish","full_name":"Suryanarayana, Phanish","last_name":"Suryanarayana"},{"last_name":"Torrent","full_name":"Torrent, Marc","first_name":"Marc"},{"first_name":"Lionel","full_name":"Truflandier, Lionel","last_name":"Truflandier"},{"full_name":"Windus, Theresa L.","first_name":"Theresa L.","last_name":"Windus"},{"first_name":"Qimen","full_name":"Xu, Qimen","last_name":"Xu"},{"last_name":"Yu","full_name":"Yu, Victor W. -Z.","first_name":"Victor W. -Z."},{"first_name":"Danny","full_name":"Perez, Danny","last_name":"Perez"}],"department":[{"_id":"27"},{"_id":"518"}],"publication":"arXiv:2209.12747","status":"public","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"date_created":"2022-09-28T05:25:10Z","abstract":[{"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.","lang":"eng"}],"external_id":{"arxiv":["2209.12747"]},"user_id":"24135","title":"Roadmap on Electronic Structure Codes in the Exascale Era"},{"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"]},"title":"Roadmap on Electronic Structure Codes in the Exascale Era","user_id":"75963","department":[{"_id":"27"}],"publication":"arXiv:2209.12747","author":[{"full_name":"Gavini, Vikram","first_name":"Vikram","last_name":"Gavini"},{"full_name":"Baroni, Stefano","first_name":"Stefano","last_name":"Baroni"},{"last_name":"Blum","full_name":"Blum, Volker","first_name":"Volker"},{"full_name":"Bowler, David R.","first_name":"David R.","last_name":"Bowler"},{"first_name":"Alexander","full_name":"Buccheri, Alexander","last_name":"Buccheri"},{"last_name":"Chelikowsky","first_name":"James R.","full_name":"Chelikowsky, James R."},{"full_name":"Das, Sambit","first_name":"Sambit","last_name":"Das"},{"full_name":"Dawson, William","first_name":"William","last_name":"Dawson"},{"first_name":"Pietro","full_name":"Delugas, Pietro","last_name":"Delugas"},{"first_name":"Mehmet","full_name":"Dogan, Mehmet","last_name":"Dogan"},{"last_name":"Draxl","first_name":"Claudia","full_name":"Draxl, Claudia"},{"last_name":"Galli","first_name":"Giulia","full_name":"Galli, Giulia"},{"last_name":"Genovese","first_name":"Luigi","full_name":"Genovese, Luigi"},{"last_name":"Giannozzi","full_name":"Giannozzi, Paolo","first_name":"Paolo"},{"full_name":"Giantomassi, Matteo","first_name":"Matteo","last_name":"Giantomassi"},{"last_name":"Gonze","first_name":"Xavier","full_name":"Gonze, Xavier"},{"last_name":"Govoni","full_name":"Govoni, Marco","first_name":"Marco"},{"last_name":"Gulans","full_name":"Gulans, Andris","first_name":"Andris"},{"full_name":"Gygi, François","first_name":"François","last_name":"Gygi"},{"full_name":"Herbert, John M.","first_name":"John M.","last_name":"Herbert"},{"last_name":"Kokott","first_name":"Sebastian","full_name":"Kokott, Sebastian"},{"first_name":"Thomas","full_name":"Kühne, Thomas","last_name":"Kühne","id":"49079"},{"last_name":"Liou","full_name":"Liou, Kai-Hsin","first_name":"Kai-Hsin"},{"last_name":"Miyazaki","full_name":"Miyazaki, Tsuyoshi","first_name":"Tsuyoshi"},{"last_name":"Motamarri","first_name":"Phani","full_name":"Motamarri, Phani"},{"first_name":"Ayako","full_name":"Nakata, Ayako","last_name":"Nakata"},{"last_name":"Pask","first_name":"John E.","full_name":"Pask, John E."},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","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"},{"last_name":"Schade","id":"75963","first_name":"Robert","full_name":"Schade, Robert","orcid":"0000-0002-6268-539"},{"full_name":"Scheffler, Matthias","first_name":"Matthias","last_name":"Scheffler"},{"first_name":"Ole","full_name":"Schütt, Ole","last_name":"Schütt"},{"last_name":"Suryanarayana","first_name":"Phanish","full_name":"Suryanarayana, Phanish"},{"last_name":"Torrent","first_name":"Marc","full_name":"Torrent, Marc"},{"first_name":"Lionel","full_name":"Truflandier, Lionel","last_name":"Truflandier"},{"first_name":"Theresa L.","full_name":"Windus, Theresa L.","last_name":"Windus"},{"last_name":"Xu","full_name":"Xu, Qimen","first_name":"Qimen"},{"first_name":"Victor W. -Z.","full_name":"Yu, Victor W. -Z.","last_name":"Yu"},{"first_name":"Danny","full_name":"Perez, Danny","last_name":"Perez"}],"date_created":"2023-08-02T14:59:18Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"status":"public","date_updated":"2023-08-02T15:00:47Z","_id":"46275","citation":{"ieee":"V. Gavini et al., “Roadmap on Electronic Structure Codes in the Exascale Era,” arXiv:2209.12747. 2022.","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).","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} }","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.","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."},"year":"2022","type":"preprint","language":[{"iso":"eng"}]},{"_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":{"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","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.","short":"T. Kenter, A. Shambhu, S. Faghih-Naini, V. Aizinger, in: Proceedings of the Platform for Advanced Scientific Computing Conference, ACM, 2021.","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."},"language":[{"iso":"eng"}],"title":"Algorithm-hardware co-design of a discontinuous Galerkin shallow-water model for a dataflow architecture on FPGA","user_id":"3145","department":[{"_id":"27"},{"_id":"518"}],"publication":"Proceedings of the Platform for Advanced Scientific Computing Conference","author":[{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"first_name":"Adesh","full_name":"Shambhu, Adesh","last_name":"Shambhu"},{"last_name":"Faghih-Naini","full_name":"Faghih-Naini, Sara","first_name":"Sara"},{"last_name":"Aizinger","full_name":"Aizinger, Vadym","first_name":"Vadym"}],"publisher":"ACM","quality_controlled":"1","publication_status":"published","date_created":"2023-07-28T11:58:14Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"status":"public"},{"title":"Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts","user_id":"27340","publication_status":"published","status":"public","date_created":"2021-01-07T15:32:45Z","author":[{"last_name":"Nickchen","full_name":"Nickchen, Tobias","first_name":"Tobias"},{"full_name":"Heindorf, Stefan","first_name":"Stefan","last_name":"Heindorf"},{"last_name":"Engels","first_name":"Gregor","full_name":"Engels, Gregor"}],"publication":"Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision","department":[{"_id":"66"},{"_id":"534"},{"_id":"624"},{"_id":"219"},{"_id":"27"}],"_id":"20886","date_updated":"2022-01-06T06:54:41Z","conference":{"name":"IEEE/CVF Winter Conference on Applications of Computer Vision","start_date":"2021-05-01","location":"Hawaii","end_date":"2021-09-01"},"type":"conference","year":"2021","citation":{"bibtex":"@inproceedings{Nickchen_Heindorf_Engels_2021, title={Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts}, booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision}, author={Nickchen, Tobias and Heindorf, Stefan and Engels, Gregor}, year={2021}, pages={1994–2002} }","mla":"Nickchen, Tobias, et al. “Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts.” Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 1994–2002.","chicago":"Nickchen, Tobias, Stefan Heindorf, and Gregor Engels. “Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts.” In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 1994–2002, 2021.","apa":"Nickchen, T., Heindorf, S., & Engels, G. (2021). Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 1994–2002). Hawaii.","ama":"Nickchen T, Heindorf S, Engels G. Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. ; 2021:1994-2002.","ieee":"T. Nickchen, S. Heindorf, and G. Engels, “Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Hawaii, 2021, pp. 1994–2002.","short":"T. Nickchen, S. Heindorf, G. Engels, in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 1994–2002."},"page":"1994-2002","language":[{"iso":"eng"}]},{"title":"High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection","user_id":"3145","publication":"2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","department":[{"_id":"27"},{"_id":"518"}],"publisher":"IEEE","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"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"},{"first_name":"Philipp","full_name":"Schlatter, Philipp","last_name":"Schlatter"},{"full_name":"Markidis, Stefano","first_name":"Stefano","last_name":"Markidis"}],"publication_status":"published","date_created":"2023-07-28T12:04:27Z","status":"public","date_updated":"2023-07-28T12:05:15Z","_id":"46195","doi":"10.1109/ipdps49936.2021.00116","type":"conference","year":"2021","citation":{"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.","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.","chicago":"Karp, Martin, Artur Podobas, Niclas Jansson, Tobias Kenter, Christian Plessl, Philipp Schlatter, and Stefano Markidis. “High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection.” In 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 2021. https://doi.org/10.1109/ipdps49936.2021.00116.","apa":"Karp, M., Podobas, A., Jansson, N., Kenter, T., Plessl, C., Schlatter, P., & Markidis, S. (2021). High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection. 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). https://doi.org/10.1109/ipdps49936.2021.00116","ama":"Karp M, Podobas A, Jansson N, et al. High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE; 2021. doi:10.1109/ipdps49936.2021.00116","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."},"language":[{"iso":"eng"}]},{"status":"public","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_created":"2022-02-21T14:26:37Z","publication_status":"published","author":[{"full_name":"Karp, Martin","first_name":"Martin","last_name":"Karp"},{"last_name":"Podobas","first_name":"Artur","full_name":"Podobas, Artur"},{"last_name":"Jansson","first_name":"Niclas","full_name":"Jansson, Niclas"},{"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"},{"full_name":"Schlatter, Philipp","first_name":"Philipp","last_name":"Schlatter"},{"full_name":"Markidis, Stefano","first_name":"Stefano","last_name":"Markidis"}],"quality_controlled":"1","publisher":"IEEE","publication":"2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","department":[{"_id":"27"},{"_id":"518"}],"user_id":"3145","title":"High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection","language":[{"iso":"eng"}],"type":"conference","citation":{"apa":"Karp, M., Podobas, A., Jansson, N., Kenter, T., Plessl, C., Schlatter, P., & Markidis, S. (2021). High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection. 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). https://doi.org/10.1109/ipdps49936.2021.00116","ama":"Karp M, Podobas A, Jansson N, et al. High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE; 2021. doi:10.1109/ipdps49936.2021.00116","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.","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} }","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.","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."},"year":"2021","doi":"10.1109/ipdps49936.2021.00116","_id":"29937","date_updated":"2024-01-22T09:59:13Z"},{"citation":{"apa":"Farheen, H., Leuteritz, T., Linden, S., Myroshnychenko, V., & Förstner, J. (2021). Optimization of optical waveguide antennas for directive emission of light. In arXiv:2106.02468.","ama":"Farheen H, Leuteritz T, Linden S, Myroshnychenko V, Förstner J. Optimization of optical waveguide antennas for directive emission of light. arXiv:210602468. Published online 2021.","chicago":"Farheen, Henna, Till Leuteritz, Stefan Linden, Viktor Myroshnychenko, and Jens Förstner. “Optimization of Optical Waveguide Antennas for Directive Emission of Light.” ArXiv:2106.02468, 2021.","mla":"Farheen, Henna, et al. “Optimization of Optical Waveguide Antennas for Directive Emission of Light.” ArXiv:2106.02468, 2021.","bibtex":"@article{Farheen_Leuteritz_Linden_Myroshnychenko_Förstner_2021, title={Optimization of optical waveguide antennas for directive emission of light}, journal={arXiv:2106.02468}, author={Farheen, Henna and Leuteritz, Till and Linden, Stefan and Myroshnychenko, Viktor and Förstner, Jens}, year={2021} }","short":"H. Farheen, T. Leuteritz, S. Linden, V. Myroshnychenko, J. Förstner, ArXiv:2106.02468 (2021).","ieee":"H. Farheen, T. Leuteritz, S. Linden, V. Myroshnychenko, and J. Förstner, “Optimization of optical waveguide antennas for directive emission of light,” arXiv:2106.02468. 2021."},"year":"2021","type":"preprint","language":[{"iso":"eng"}],"_id":"32245","date_updated":"2022-06-28T08:01:39Z","status":"public","date_created":"2022-06-28T08:01:09Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"author":[{"last_name":"Farheen","full_name":"Farheen, Henna","first_name":"Henna"},{"last_name":"Leuteritz","first_name":"Till","full_name":"Leuteritz, Till"},{"first_name":"Stefan","full_name":"Linden, Stefan","last_name":"Linden"},{"first_name":"Viktor","full_name":"Myroshnychenko, Viktor","last_name":"Myroshnychenko"},{"first_name":"Jens","full_name":"Förstner, Jens","last_name":"Förstner"}],"publication":"arXiv:2106.02468","department":[{"_id":"27"}],"title":"Optimization of optical waveguide antennas for directive emission of light","user_id":"15278","abstract":[{"text":"Optical travelling wave antennas offer unique opportunities to control and\r\nselectively guide light into a specific direction which renders them as\r\nexcellent candidates for optical communication and sensing. These applications\r\nrequire state of the art engineering to reach optimized functionalities such as\r\nhigh directivity and radiation efficiency, low side lobe level, broadband and\r\ntunable capabilities, and compact design. In this work we report on the\r\nnumerical optimization of the directivity of optical travelling wave antennas\r\nmade from low-loss dielectric materials using full-wave numerical simulations\r\nin conjunction with a particle swarm optimization algorithm. The antennas are\r\ncomposed of a reflector and a director deposited on a glass substrate and an\r\nemitter placed in the feed gap between them serves as an internal source of\r\nexcitation. In particular, we analysed antennas with rectangular- and\r\nhorn-shaped directors made of either Hafnium dioxide or Silicon. The optimized\r\nantennas produce highly directional emission due to the presence of two\r\ndominant guided TE modes in the director in addition to leaky modes. These\r\nguided modes dominate the far-field emission pattern and govern the direction\r\nof the main lobe emission which predominately originates from the end facet of\r\nthe director. Our work also provides a comprehensive analysis of the modes,\r\nradiation patterns, parametric influences, and bandwidths of the antennas that\r\nhighlights their robust nature.","lang":"eng"}],"external_id":{"arxiv":["2106.02468"]}},{"_id":"32236","date_updated":"2023-02-10T16:00:12Z","year":"2021","type":"preprint","citation":{"bibtex":"@article{Rose_Tikhonova_Meier_Sharapova_2021, title={Steady states of $Λ$-type three-level systems excited by quantum light in lossy cavities}, journal={arXiv:2109.00842}, author={Rose, H. and Tikhonova, O. V. and Meier, T. and Sharapova, P. }, year={2021} }","mla":"Rose, H., et al. “Steady States of $Λ$-Type Three-Level Systems Excited by Quantum Light in Lossy Cavities.” ArXiv:2109.00842, 2021.","chicago":"Rose, H., O. V. Tikhonova, T. Meier, and P. Sharapova. “Steady States of $Λ$-Type Three-Level Systems Excited by Quantum Light in Lossy Cavities.” ArXiv:2109.00842, 2021.","ama":"Rose H, Tikhonova OV, Meier T, Sharapova P. Steady states of $Λ$-type three-level systems excited by quantum light in lossy cavities. arXiv:210900842. Published online 2021.","apa":"Rose, H., Tikhonova, O. V., Meier, T., & Sharapova, P. (2021). Steady states of $Λ$-type three-level systems excited by quantum light in lossy cavities. In arXiv:2109.00842.","ieee":"H. Rose, O. V. Tikhonova, T. Meier, and P. Sharapova, “Steady states of $Λ$-type three-level systems excited by quantum light in lossy cavities,” arXiv:2109.00842. 2021.","short":"H. Rose, O.V. Tikhonova, T. Meier, P. Sharapova, ArXiv:2109.00842 (2021)."},"language":[{"iso":"eng"}],"external_id":{"arxiv":["2109.00842"]},"abstract":[{"lang":"eng","text":"The interaction between quantum light and matter is being intensively studied\r\nfor systems that are enclosed in high-$Q$ cavities which strongly enhance the\r\nlight-matter coupling. However, for many applications, cavities with lower\r\n$Q$-factors are preferred due to the increased spectral width of the cavity\r\nmode. Here, we investigate the interaction between quantum light and matter\r\nrepresented by a $\\Lambda$-type three-level system in lossy cavities, assuming\r\nthat cavity losses are the dominant loss mechanism. We demonstrate that cavity\r\nlosses lead to non-trivial steady states of the electronic occupations that can\r\nbe controlled by the loss rate and the initial statistics of the quantum\r\nfields. The mechanism of formation of such steady states can be understood on\r\nthe basis of the equations of motion. Analytical expressions for steady states\r\nand their numerical simulations are presented and discussed."}],"title":"Steady states of $Λ$-type three-level systems excited by quantum light in lossy cavities","user_id":"14931","author":[{"full_name":"Rose, H.","first_name":"H.","last_name":"Rose"},{"first_name":"O. V.","full_name":"Tikhonova, O. V.","last_name":"Tikhonova"},{"full_name":"Meier, T.","first_name":"T.","last_name":"Meier"},{"first_name":"P. ","full_name":"Sharapova, P. ","last_name":"Sharapova"}],"department":[{"_id":"27"}],"publication":"arXiv:2109.00842","status":"public","date_created":"2022-06-28T07:03:29Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}]},{"date_updated":"2022-06-28T07:49:31Z","_id":"32244","type":"preprint","citation":{"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.” ArXiv:2104.08245, 2021.","ama":"Schade R, Kenter T, Elgabarty H, et al. Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms. arXiv:210408245. Published online 2021.","apa":"Schade, R., Kenter, T., Elgabarty, H., Lass, M., Schütt, O., Lazzaro, A., Pabst, H., Mohr, S., Hutter, J., Kühne, T. D., & Plessl, C. (2021). Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms. In arXiv:2104.08245.","bibtex":"@article{Schade_Kenter_Elgabarty_Lass_Schütt_Lazzaro_Pabst_Mohr_Hutter_Kühne_et al._2021, title={Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms}, journal={arXiv:2104.08245}, 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 D. and et al.}, year={2021} }","mla":"Schade, Robert, et al. “Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms.” ArXiv:2104.08245, 2021.","short":"R. Schade, T. Kenter, H. Elgabarty, M. Lass, O. Schütt, A. Lazzaro, H. Pabst, S. Mohr, J. Hutter, T.D. Kühne, C. Plessl, ArXiv:2104.08245 (2021).","ieee":"R. Schade et al., “Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms,” arXiv:2104.08245. 2021."},"year":"2021","language":[{"iso":"eng"}],"title":"Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms","user_id":"15278","external_id":{"arxiv":["2104.08245"]},"abstract":[{"lang":"eng","text":"We push the boundaries of electronic structure-based \\textit{ab-initio}\r\nmolecular dynamics (AIMD) beyond 100 million atoms. This scale is otherwise\r\nbarely reachable with classical force-field methods or novel neural network and\r\nmachine learning potentials. We achieve this breakthrough by combining\r\ninnovations in linear-scaling AIMD, efficient and approximate sparse linear\r\nalgebra, low and mixed-precision floating-point computation on GPUs, and a\r\ncompensation scheme for the errors introduced by numerical approximations. The\r\ncore of our work is the non-orthogonalized local submatrix method (NOLSM),\r\nwhich scales very favorably to massively parallel computing systems and\r\ntranslates large sparse matrix operations into highly parallel, dense matrix\r\noperations that are ideally suited to hardware accelerators. We demonstrate\r\nthat the NOLSM method, which is at the center point of each AIMD step, is able\r\nto achieve a sustained performance of 324 PFLOP/s in mixed FP16/FP32 precision\r\ncorresponding to an efficiency of 67.7% when running on 1536 NVIDIA A100 GPUs."}],"status":"public","date_created":"2022-06-28T07:48:31Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"author":[{"last_name":"Schade","full_name":"Schade, Robert","first_name":"Robert"},{"last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"last_name":"Elgabarty","first_name":"Hossam","full_name":"Elgabarty, Hossam"},{"first_name":"Michael","full_name":"Lass, Michael","last_name":"Lass"},{"full_name":"Schütt, Ole","first_name":"Ole","last_name":"Schütt"},{"last_name":"Lazzaro","first_name":"Alfio","full_name":"Lazzaro, Alfio"},{"first_name":"Hans","full_name":"Pabst, Hans","last_name":"Pabst"},{"full_name":"Mohr, Stephan","first_name":"Stephan","last_name":"Mohr"},{"last_name":"Hutter","full_name":"Hutter, Jürg","first_name":"Jürg"},{"full_name":"Kühne, Thomas D.","first_name":"Thomas D.","last_name":"Kühne"},{"full_name":"Plessl, Christian","first_name":"Christian","last_name":"Plessl"}],"publication":"arXiv:2104.08245","department":[{"_id":"27"}]},{"publication_status":"published","status":"public","date_created":"2021-11-10T14:42:17Z","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"author":[{"first_name":"Marius","full_name":"Meyer, Marius","last_name":"Meyer","id":"40778"}],"department":[{"_id":"27"}],"publication":"Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies","title":"Towards Performance Characterization of FPGAs in Context of HPC using OpenCL Benchmarks","user_id":"40778","type":"conference","year":"2021","citation":{"ieee":"M. Meyer, “Towards Performance Characterization of FPGAs in Context of HPC using OpenCL Benchmarks,” 2021, doi: 10.1145/3468044.3468058.","short":"M. Meyer, in: Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies, 2021.","bibtex":"@inproceedings{Meyer_2021, title={Towards Performance Characterization of FPGAs in Context of HPC using OpenCL Benchmarks}, DOI={10.1145/3468044.3468058}, booktitle={Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies}, author={Meyer, Marius}, year={2021} }","mla":"Meyer, Marius. “Towards Performance Characterization of FPGAs in Context of HPC Using OpenCL Benchmarks.” Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies, 2021, doi:10.1145/3468044.3468058.","apa":"Meyer, M. (2021). Towards Performance Characterization of FPGAs in Context of HPC using OpenCL Benchmarks. Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies. https://doi.org/10.1145/3468044.3468058","ama":"Meyer M. Towards Performance Characterization of FPGAs in Context of HPC using OpenCL Benchmarks. In: Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies. ; 2021. doi:10.1145/3468044.3468058","chicago":"Meyer, Marius. “Towards Performance Characterization of FPGAs in Context of HPC Using OpenCL Benchmarks.” In Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies, 2021. https://doi.org/10.1145/3468044.3468058."},"language":[{"iso":"eng"}],"doi":"10.1145/3468044.3468058","_id":"27365","date_updated":"2022-01-06T06:57:38Z"},{"external_id":{"arxiv":["2004.10811"]},"place":"Los Alamitos, CA, USA","title":"A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"name":"Performance and Efficiency in HPC with Custom Computing","grant_number":"PL 595/2-1 / 320898746","_id":"32"},{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"date_updated":"2023-08-02T14:55:59Z","doi":"10.1109/SC41405.2020.00084","language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"Electronic structure calculations based on density-functional theory (DFT)\r\nrepresent a significant part of today's HPC workloads and pose high demands on\r\nhigh-performance computing resources. To perform these quantum-mechanical DFT\r\ncalculations on complex large-scale systems, so-called linear scaling methods\r\ninstead of conventional cubic scaling methods are required. In this work, we\r\ntake up the idea of the submatrix method and apply it to the DFT computations\r\nin the software package CP2K. For that purpose, we transform the underlying\r\nnumeric operations on distributed, large, sparse matrices into computations on\r\nlocal, much smaller and nearly dense matrices. This allows us to exploit the\r\nfull floating-point performance of modern CPUs and to make use of dedicated\r\naccelerator hardware, where performance has been limited by memory bandwidth\r\nbefore. We demonstrate both functionality and performance of our implementation\r\nand show how it can be accelerated with GPUs and FPGAs."}],"user_id":"75963","publication":"Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","publisher":"IEEE Computer Society","author":[{"orcid":"0000-0002-5708-7632","full_name":"Lass, Michael","first_name":"Michael","id":"24135","last_name":"Lass"},{"first_name":"Robert","orcid":"0000-0002-6268-539","full_name":"Schade, Robert","last_name":"Schade","id":"75963"},{"first_name":"Thomas","full_name":"Kühne, Thomas","last_name":"Kühne","id":"49079"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"quality_controlled":"1","date_created":"2020-04-28T14:44:21Z","status":"public","conference":{"name":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","location":"Atlanta, GA, US"},"_id":"16898","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9355245"}],"page":"1127-1140","year":"2020","type":"conference","citation":{"short":"M. Lass, R. Schade, T. Kühne, C. Plessl, in: Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), IEEE Computer Society, Los Alamitos, CA, USA, 2020, pp. 1127–1140.","ieee":"M. Lass, R. Schade, T. Kühne, and C. Plessl, “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K,” in Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), Atlanta, GA, US, 2020, pp. 1127–1140, doi: 10.1109/SC41405.2020.00084.","apa":"Lass, M., Schade, R., Kühne, T., & Plessl, C. (2020). A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K. Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 1127–1140. https://doi.org/10.1109/SC41405.2020.00084","ama":"Lass M, Schade R, Kühne T, Plessl C. A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K. In: Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC). IEEE Computer Society; 2020:1127-1140. doi:10.1109/SC41405.2020.00084","chicago":"Lass, Michael, Robert Schade, Thomas Kühne, and Christian Plessl. “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K.” In Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 1127–40. Los Alamitos, CA, USA: IEEE Computer Society, 2020. https://doi.org/10.1109/SC41405.2020.00084.","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} }"}},{"related_material":{"link":[{"url":"https://github.com/pc2/HPCC_FPGA","description":"Official repository of the benchmark suite on GitHub","relation":"supplementary_material"}]},"title":"Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite","department":[{"_id":"27"},{"_id":"518"}],"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"publication_status":"published","publication_identifier":{"isbn":["9781665415927"]},"date_updated":"2023-09-26T11:42:53Z","doi":"10.1109/h2rc51942.2020.00007","language":[{"iso":"eng"}],"abstract":[{"lang":"eng","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."}],"user_id":"15278","publication":"2020 IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC)","keyword":["FPGA","OpenCL","High Level Synthesis","HPC benchmarking"],"quality_controlled":"1","author":[{"full_name":"Meyer, Marius","first_name":"Marius","id":"40778","last_name":"Meyer"},{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"}],"date_created":"2021-04-16T10:17:22Z","status":"public","_id":"21632","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9306963"}],"type":"conference","citation":{"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.","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.","apa":"Meyer, M., Kenter, T., & Plessl, C. (2020). Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite. 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC). https://doi.org/10.1109/h2rc51942.2020.00007","ama":"Meyer M, Kenter T, Plessl C. Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite. In: 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC). ; 2020. doi:10.1109/h2rc51942.2020.00007","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."},"year":"2020"},{"language":[{"iso":"eng"}],"type":"preprint","citation":{"bibtex":"@article{Bengs_Hüllermeier_2020, title={Multi-Armed Bandits with Censored Consumption of Resources}, journal={arXiv:2011.00813}, author={Bengs, Viktor and Hüllermeier, Eyke}, year={2020} }","mla":"Bengs, Viktor, and Eyke Hüllermeier. “Multi-Armed Bandits with Censored Consumption of Resources.” ArXiv:2011.00813, 2020.","ama":"Bengs V, Hüllermeier E. Multi-Armed Bandits with Censored Consumption of Resources. arXiv:201100813. Published online 2020.","apa":"Bengs, V., & Hüllermeier, E. (2020). Multi-Armed Bandits with Censored Consumption of Resources. In arXiv:2011.00813.","chicago":"Bengs, Viktor, and Eyke Hüllermeier. “Multi-Armed Bandits with Censored Consumption of Resources.” ArXiv:2011.00813, 2020.","ieee":"V. Bengs and E. Hüllermeier, “Multi-Armed Bandits with Censored Consumption of Resources,” arXiv:2011.00813. 2020.","short":"V. Bengs, E. Hüllermeier, ArXiv:2011.00813 (2020)."},"year":"2020","_id":"32242","date_updated":"2022-06-28T07:27:19Z","date_created":"2022-06-28T07:26:54Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"status":"public","publication":"arXiv:2011.00813","department":[{"_id":"27"}],"author":[{"last_name":"Bengs","full_name":"Bengs, Viktor","first_name":"Viktor"},{"last_name":"Hüllermeier","full_name":"Hüllermeier, Eyke","first_name":"Eyke"}],"user_id":"15278","title":"Multi-Armed Bandits with Censored Consumption of Resources","abstract":[{"text":"We consider a resource-aware variant of the classical multi-armed bandit\r\nproblem: In each round, the learner selects an arm and determines a resource\r\nlimit. It then observes a corresponding (random) reward, provided the (random)\r\namount of consumed resources remains below the limit. Otherwise, the\r\nobservation is censored, i.e., no reward is obtained. For this problem setting,\r\nwe introduce a measure of regret, which incorporates the actual amount of\r\nallocated resources of each learning round as well as the optimality of\r\nrealizable rewards. Thus, to minimize regret, the learner needs to set a\r\nresource limit and choose an arm in such a way that the chance to realize a\r\nhigh reward within the predefined resource limit is high, while the resource\r\nlimit itself should be kept as low as possible. We derive the theoretical lower\r\nbound on the cumulative regret and propose a learning algorithm having a regret\r\nupper bound that matches the lower bound. In a simulation study, we show that\r\nour learning algorithm outperforms straightforward extensions of standard\r\nmulti-armed bandit algorithms.","lang":"eng"}],"external_id":{"arxiv":["2011.00813"]}},{"language":[{"iso":"eng"}],"doi":"10.1109/ICFPT47387.2019.00020","date_updated":"2022-01-06T06:52:26Z","project":[{"_id":"33","grant_number":"01|H16005","name":"HighPerMeshes"},{"_id":"32","grant_number":"PL 595/2-1","name":"Performance and Efficiency in HPC with Custom Computing"}],"department":[{"_id":"27"},{"_id":"518"}],"title":"OpenCL Implementation of Cannon's Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs","type":"conference","citation":{"ieee":"P. Gorlani, T. Kenter, and C. Plessl, “OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs,” in Proceedings of the International Conference on Field-Programmable Technology (FPT), 2019.","short":"P. Gorlani, T. Kenter, C. Plessl, in: Proceedings of the International Conference on Field-Programmable Technology (FPT), IEEE, 2019.","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} }","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.","apa":"Gorlani, P., Kenter, T., & Plessl, C. (2019). OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs. In Proceedings of the International Conference on Field-Programmable Technology (FPT). IEEE. https://doi.org/10.1109/ICFPT47387.2019.00020","ama":"Gorlani P, Kenter T, Plessl C. OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs. In: Proceedings of the International Conference on Field-Programmable Technology (FPT). IEEE; 2019. doi:10.1109/ICFPT47387.2019.00020"},"year":"2019","_id":"15478","conference":{"name":"International Conference on Field-Programmable Technology (FPT)"},"has_accepted_license":"1","status":"public","date_created":"2020-01-09T12:54:48Z","file":[{"file_name":"gorlani19_fpt.pdf","date_created":"2020-01-09T12:53:57Z","access_level":"closed","file_id":"15479","creator":"plessl","file_size":250559,"success":1,"relation":"main_file","date_updated":"2020-01-09T12:53:57Z","content_type":"application/pdf"}],"quality_controlled":"1","author":[{"last_name":"Gorlani","id":"72045","first_name":"Paolo","full_name":"Gorlani, Paolo"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian","id":"16153","last_name":"Plessl"}],"publisher":"IEEE","file_date_updated":"2020-01-09T12:53:57Z","publication":"Proceedings of the International Conference on Field-Programmable Technology (FPT)","user_id":"3145","ddc":["004"],"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"}]},{"abstract":[{"lang":"eng","text":"This paper describes a data structure and a heuristic to plan and map arbitrary resources in complex combinations while applying time dependent constraints. The approach is used in the planning based workload manager OpenCCS at the Paderborn Center for Parallel Computing (PC\\(^2\\)) to operate heterogeneous clusters with up to 10000 cores. We also show performance results derived from four years of operation."}],"user_id":"15274","author":[{"first_name":"Axel","full_name":"Keller, Axel","last_name":"Keller","id":"15274"}],"publisher":"Springer","publication":"Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP)","keyword":["Scheduling Planning Mapping Workload management"],"status":"public","date_created":"2017-07-25T14:54:08Z","volume":10773,"_id":"22","intvolume":" 10773","conference":{"end_date":"2017-06-02","start_date":"2017-06-02","name":"21st Workshop on Job Scheduling Strategies for Parallel Processing","location":"Orlando, FL, USA"},"citation":{"chicago":"Keller, Axel. “A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems.” In Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), edited by D. Klusáček, W. Cirne, and N. Desai, 10773:132–51. Lecture Notes in Computer Science. Springer, 2018. https://doi.org/10.1007/978-3-319-77398-8_8.","apa":"Keller, A. (2018). A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems. In D. Klusáček, W. Cirne, & N. Desai (Eds.), Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP) (Vol. 10773, pp. 132–151). Orlando, FL, USA: Springer. https://doi.org/10.1007/978-3-319-77398-8_8","ama":"Keller A. A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems. In: Klusáček D, Cirne W, Desai N, eds. Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP). Vol 10773. Lecture Notes in Computer Science. Springer; 2018:132-151. doi:10.1007/978-3-319-77398-8_8","mla":"Keller, Axel. “A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems.” Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), edited by D. Klusáček et al., vol. 10773, Springer, 2018, pp. 132–51, doi:10.1007/978-3-319-77398-8_8.","bibtex":"@inproceedings{Keller_2018, series={Lecture Notes in Computer Science}, title={A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems}, volume={10773}, DOI={10.1007/978-3-319-77398-8_8}, booktitle={Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP)}, publisher={Springer}, author={Keller, Axel}, editor={Klusáček, D. and Cirne, W. and Desai, N.Editors}, year={2018}, pages={132–151}, collection={Lecture Notes in Computer Science} }","short":"A. Keller, in: D. Klusáček, W. Cirne, N. Desai (Eds.), Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), Springer, 2018, pp. 132–151.","ieee":"A. Keller, “A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems,” in Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), Orlando, FL, USA, 2018, vol. 10773, pp. 132–151."},"type":"conference","year":"2018","page":"132-151","title":"A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems","department":[{"_id":"27"}],"editor":[{"last_name":"Klusáček","first_name":"D.","full_name":"Klusáček, D."},{"first_name":"W.","full_name":"Cirne, W.","last_name":"Cirne"},{"last_name":"Desai","full_name":"Desai, N.","first_name":"N."}],"publication_status":"published","publication_identifier":{"isbn":["978-3-319-77398-8","978-3-319-77397-1"]},"date_updated":"2022-01-06T06:55:22Z","doi":"10.1007/978-3-319-77398-8_8","series_title":"Lecture Notes in Computer Science","language":[{"iso":"eng"}]},{"external_id":{"arxiv":["1710.10899"]},"place":"New York, NY, USA","title":"A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"project":[{"_id":"32","grant_number":"PL 595/2-1 / 320898746","name":"Performance and Efficiency in HPC with Custom Computing"},{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"publication_identifier":{"isbn":["978-1-4503-5891-0/18/07"]},"date_updated":"2023-09-26T11:48:12Z","doi":"10.1145/3218176.3218231","language":[{"iso":"eng"}],"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"}],"user_id":"15278","keyword":["approximate computing","linear algebra","matrix inversion","matrix p-th roots","numeric algorithm","parallel computing"],"publication":"Proc. Platform for Advanced Scientific Computing (PASC) Conference","author":[{"full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","first_name":"Michael","id":"24135","last_name":"Lass"},{"full_name":"Mohr, Stephan","first_name":"Stephan","last_name":"Mohr"},{"last_name":"Wiebeler","first_name":"Hendrik","full_name":"Wiebeler, Hendrik"},{"id":"49079","last_name":"Kühne","full_name":"Kühne, Thomas","first_name":"Thomas"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"}],"publisher":"ACM","quality_controlled":"1","date_created":"2018-03-22T10:53:01Z","status":"public","conference":{"end_date":"2018-07-04","start_date":"2018-07-02","name":"Platform for Advanced Scientific Computing Conference (PASC)","location":"Basel, Switzerland"},"_id":"1590","citation":{"ieee":"M. Lass, S. Mohr, H. Wiebeler, T. Kühne, and C. Plessl, “A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices,” presented at the Platform for Advanced Scientific Computing Conference (PASC), Basel, Switzerland, 2018, doi: 10.1145/3218176.3218231.","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={10.1145/3218176.3218231}, booktitle={Proc. Platform for Advanced Scientific Computing (PASC) Conference}, publisher={ACM}, author={Lass, Michael and Mohr, Stephan and Wiebeler, Hendrik and Kühne, Thomas and Plessl, Christian}, year={2018} }","mla":"Lass, Michael, et al. “A Massively Parallel Algorithm for the Approximate Calculation of Inverse P-Th Roots of Large Sparse Matrices.” Proc. Platform for Advanced Scientific Computing (PASC) Conference, ACM, 2018, doi:10.1145/3218176.3218231.","chicago":"Lass, Michael, Stephan Mohr, Hendrik Wiebeler, Thomas Kühne, and Christian Plessl. “A Massively Parallel Algorithm for the Approximate Calculation of Inverse P-Th Roots of Large Sparse Matrices.” In Proc. Platform for Advanced Scientific Computing (PASC) Conference. New York, NY, USA: ACM, 2018. https://doi.org/10.1145/3218176.3218231.","ama":"Lass M, Mohr S, Wiebeler H, Kühne T, Plessl C. A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices. In: Proc. Platform for Advanced Scientific Computing (PASC) Conference. ACM; 2018. doi:10.1145/3218176.3218231","apa":"Lass, M., Mohr, S., Wiebeler, H., Kühne, T., & Plessl, C. (2018). A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices. Proc. Platform for Advanced Scientific Computing (PASC) Conference. Platform for Advanced Scientific Computing Conference (PASC), Basel, Switzerland. https://doi.org/10.1145/3218176.3218231"},"type":"conference","year":"2018"},{"status":"public","has_accepted_license":"1","date_created":"2018-03-08T14:45:18Z","file":[{"file_name":"p417-riebler.pdf","date_created":"2018-11-02T14:43:37Z","access_level":"closed","file_size":447769,"creator":"ups","file_id":"5281","content_type":"application/pdf","date_updated":"2018-11-02T14:43:37Z","success":1,"relation":"main_file"}],"publisher":"ACM","author":[{"last_name":"Riebler","id":"8961","first_name":"Heinrich","full_name":"Riebler, Heinrich"},{"last_name":"Vaz","id":"30332","first_name":"Gavin Francis","full_name":"Vaz, Gavin Francis"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian","id":"16153","last_name":"Plessl"}],"quality_controlled":"1","file_date_updated":"2018-11-02T14:43:37Z","keyword":["htrop"],"publication":"Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP)","user_id":"15278","ddc":["000"],"citation":{"short":"H. Riebler, G.F. Vaz, T. Kenter, C. Plessl, in: Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP), ACM, 2018.","ieee":"H. Riebler, G. F. Vaz, T. Kenter, and C. Plessl, “Automated Code Acceleration Targeting Heterogeneous OpenCL Devices,” 2018, doi: 10.1145/3178487.3178534.","ama":"Riebler H, Vaz GF, Kenter T, Plessl C. Automated Code Acceleration Targeting Heterogeneous OpenCL Devices. In: Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). ACM; 2018. doi:10.1145/3178487.3178534","apa":"Riebler, H., Vaz, G. F., Kenter, T., & Plessl, C. (2018). Automated Code Acceleration Targeting Heterogeneous OpenCL Devices. Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). https://doi.org/10.1145/3178487.3178534","chicago":"Riebler, Heinrich, Gavin Francis Vaz, Tobias Kenter, and Christian Plessl. “Automated Code Acceleration Targeting Heterogeneous OpenCL Devices.” In Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). ACM, 2018. https://doi.org/10.1145/3178487.3178534.","mla":"Riebler, Heinrich, et al. “Automated Code Acceleration Targeting Heterogeneous OpenCL Devices.” Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP), ACM, 2018, doi:10.1145/3178487.3178534.","bibtex":"@inproceedings{Riebler_Vaz_Kenter_Plessl_2018, title={Automated Code Acceleration Targeting Heterogeneous OpenCL Devices}, DOI={10.1145/3178487.3178534}, booktitle={Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP)}, publisher={ACM}, author={Riebler, Heinrich and Vaz, Gavin Francis and Kenter, Tobias and Plessl, Christian}, year={2018} }"},"type":"conference","year":"2018","_id":"1204","project":[{"_id":"1","grant_number":"160364472","name":"SFB 901"},{"name":"SFB 901 - Project Area C","_id":"4"},{"grant_number":"160364472","name":"SFB 901 - Subproject C2","_id":"14"}],"publication_identifier":{"isbn":["9781450349826"]},"publication_status":"published","department":[{"_id":"27"},{"_id":"518"}],"title":"Automated Code Acceleration Targeting Heterogeneous OpenCL Devices","language":[{"iso":"eng"}],"doi":"10.1145/3178487.3178534","date_updated":"2023-09-26T11:47:23Z"},{"_id":"1588","conference":{"name":"Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)"},"year":"2018","type":"conference","citation":{"short":"T. Kenter, G. Mahale, S. Alhaddad, Y. Grynko, C. Schmitt, A. Afzal, F. Hannig, J. Förstner, C. Plessl, in: Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM), IEEE, 2018.","ieee":"T. Kenter et al., “OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes,” presented at the Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM), 2018, doi: 10.1109/FCCM.2018.00037.","apa":"Kenter, T., Mahale, G., Alhaddad, S., Grynko, Y., Schmitt, C., Afzal, A., Hannig, F., Förstner, J., & Plessl, C. (2018). OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes. Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). https://doi.org/10.1109/FCCM.2018.00037","ama":"Kenter T, Mahale G, Alhaddad S, et al. OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes. In: Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). IEEE; 2018. doi:10.1109/FCCM.2018.00037","chicago":"Kenter, Tobias, Gopinath Mahale, Samer Alhaddad, Yevgen Grynko, Christian Schmitt, Ayesha Afzal, Frank Hannig, Jens Förstner, and Christian Plessl. “OpenCL-Based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes.” In Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). IEEE, 2018. https://doi.org/10.1109/FCCM.2018.00037.","bibtex":"@inproceedings{Kenter_Mahale_Alhaddad_Grynko_Schmitt_Afzal_Hannig_Förstner_Plessl_2018, title={OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes}, DOI={10.1109/FCCM.2018.00037}, booktitle={Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)}, publisher={IEEE}, author={Kenter, Tobias and Mahale, Gopinath and Alhaddad, Samer and Grynko, Yevgen and Schmitt, Christian and Afzal, Ayesha and Hannig, Frank and Förstner, Jens and Plessl, Christian}, year={2018} }","mla":"Kenter, Tobias, et al. “OpenCL-Based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes.” Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM), IEEE, 2018, doi:10.1109/FCCM.2018.00037."},"abstract":[{"text":"The exploration of FPGAs as accelerators for scientific simulations has so far mostly been focused on small kernels of methods working on regular data structures, for example in the form of stencil computations for finite difference methods. In computational sciences, often more advanced methods are employed that promise better stability, convergence, locality and scaling. Unstructured meshes are shown to be more effective and more accurate, compared to regular grids, in representing computation domains of various shapes. Using unstructured meshes, the discontinuous Galerkin method preserves the ability to perform explicit local update operations for simulations in the time domain. In this work, we investigate FPGAs as target platform for an implementation of the nodal discontinuous Galerkin method to find time-domain solutions of Maxwell's equations in an unstructured mesh. When maximizing data reuse and fitting constant coefficients into suitably partitioned on-chip memory, high computational intensity allows us to implement and feed wide data paths with hundreds of floating point operators. By decoupling off-chip memory accesses from the computations, high memory bandwidth can be sustained, even for the irregular access pattern required by parts of the application. Using the Intel/Altera OpenCL SDK for FPGAs, we present different implementation variants for different polynomial orders of the method. In different phases of the algorithm, either computational or bandwidth limits of the Arria 10 platform are almost reached, thus outperforming a highly multithreaded CPU implementation by around 2x.","lang":"eng"}],"user_id":"15278","ddc":["000"],"file":[{"date_created":"2018-11-02T14:45:05Z","file_name":"08457652.pdf","access_level":"closed","file_id":"5282","creator":"ups","file_size":269130,"relation":"main_file","success":1,"date_updated":"2018-11-02T14:45:05Z","content_type":"application/pdf"}],"quality_controlled":"1","author":[{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"last_name":"Mahale","full_name":"Mahale, Gopinath","first_name":"Gopinath"},{"first_name":"Samer","full_name":"Alhaddad, Samer","last_name":"Alhaddad","id":"42456"},{"id":"26059","last_name":"Grynko","full_name":"Grynko, Yevgen","first_name":"Yevgen"},{"first_name":"Christian","full_name":"Schmitt, Christian","last_name":"Schmitt"},{"last_name":"Afzal","first_name":"Ayesha","full_name":"Afzal, Ayesha"},{"first_name":"Frank","full_name":"Hannig, Frank","last_name":"Hannig"},{"id":"158","last_name":"Förstner","full_name":"Förstner, Jens","orcid":"0000-0001-7059-9862","first_name":"Jens"},{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"}],"publisher":"IEEE","keyword":["tet_topic_hpc"],"file_date_updated":"2018-11-02T14:45:05Z","publication":"Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)","status":"public","has_accepted_license":"1","date_created":"2018-03-22T10:48:01Z","date_updated":"2023-09-26T11:47:52Z","doi":"10.1109/FCCM.2018.00037","language":[{"iso":"eng"}],"title":"OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes","department":[{"_id":"27"},{"_id":"518"},{"_id":"61"}],"project":[{"grant_number":"01|H16005A","name":"HighPerMeshes","_id":"33"},{"_id":"1","grant_number":"160364472","name":"SFB 901"},{"name":"SFB 901 - Project Area C","_id":"4"},{"_id":"14","grant_number":"160364472","name":"SFB 901 - Subproject C2"}]}]