[{"language":[{"iso":"eng"}],"citation":{"ieee":"L. Van Hirtum et al., “A computation of D(9) using FPGA Supercomputing,” arXiv:2304.03039. 2023.","short":"L. Van Hirtum, P. De Causmaecker, J. Goemaere, T. Kenter, H. Riebler, M. Lass, C. Plessl, ArXiv:2304.03039 (2023).","bibtex":"@article{Van Hirtum_De Causmaecker_Goemaere_Kenter_Riebler_Lass_Plessl_2023, title={A computation of D(9) using FPGA Supercomputing}, journal={arXiv:2304.03039}, author={Van Hirtum, Lennart and De Causmaecker, Patrick and Goemaere, Jens and Kenter, Tobias and Riebler, Heinrich and Lass, Michael and Plessl, Christian}, year={2023} }","mla":"Van Hirtum, Lennart, et al. “A Computation of D(9) Using FPGA Supercomputing.” ArXiv:2304.03039, 2023.","chicago":"Van Hirtum, Lennart, Patrick De Causmaecker, Jens Goemaere, Tobias Kenter, Heinrich Riebler, Michael Lass, and Christian Plessl. “A Computation of D(9) Using FPGA Supercomputing.” ArXiv:2304.03039, 2023.","ama":"Van Hirtum L, De Causmaecker P, Goemaere J, et al. A computation of D(9) using FPGA Supercomputing. arXiv:230403039. Published online 2023.","apa":"Van Hirtum, L., De Causmaecker, P., Goemaere, J., Kenter, T., Riebler, H., Lass, M., & Plessl, C. (2023). A computation of D(9) using FPGA Supercomputing. In arXiv:2304.03039."},"year":"2023","type":"preprint","date_updated":"2024-01-22T09:56:42Z","_id":"43439","department":[{"_id":"27"},{"_id":"518"}],"publication":"arXiv:2304.03039","author":[{"last_name":"Van Hirtum","full_name":"Van Hirtum, Lennart","first_name":"Lennart"},{"full_name":"De Causmaecker, Patrick","first_name":"Patrick","last_name":"De Causmaecker"},{"full_name":"Goemaere, Jens","first_name":"Jens","last_name":"Goemaere"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"first_name":"Heinrich","full_name":"Riebler, Heinrich","last_name":"Riebler","id":"8961"},{"id":"24135","last_name":"Lass","orcid":"0000-0002-5708-7632","full_name":"Lass, Michael","first_name":"Michael"},{"full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian","id":"16153","last_name":"Plessl"}],"date_created":"2023-04-08T11:05:29Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"status":"public","external_id":{"arxiv":["2304.03039"]},"abstract":[{"lang":"eng","text":"This preprint makes the claim of having computed the $9^{th}$ Dedekind\r\nNumber. This was done by building an efficient FPGA Accelerator for the core\r\noperation of the process, and parallelizing it on the Noctua 2 Supercluster at\r\nPaderborn University. The resulting value is\r\n286386577668298411128469151667598498812366. This value can be verified in two\r\nsteps. We have made the data file containing the 490M results available, each\r\nof which can be verified separately on CPU, and the whole file sums to our\r\nproposed value."}],"user_id":"3145","title":"A computation of D(9) using FPGA Supercomputing"},{"main_file_link":[{"url":"https://ieeexplore.ieee.org/document/10171537"}],"page":"162-173","citation":{"ama":"Wu X, Kenter T, Schade R, Kühne T, Plessl C. Computing and Compressing Electron Repulsion Integrals on FPGAs. In: 2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). ; 2023:162-173. doi:10.1109/FCCM57271.2023.00026","apa":"Wu, X., Kenter, T., Schade, R., Kühne, T., & Plessl, C. (2023). Computing and Compressing Electron Repulsion Integrals on FPGAs. 2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 162–173. https://doi.org/10.1109/FCCM57271.2023.00026","short":"X. Wu, T. Kenter, R. Schade, T. Kühne, C. Plessl, in: 2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 2023, pp. 162–173.","chicago":"Wu, Xin, Tobias Kenter, Robert Schade, Thomas Kühne, and Christian Plessl. “Computing and Compressing Electron Repulsion Integrals on FPGAs.” In 2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 162–73, 2023. https://doi.org/10.1109/FCCM57271.2023.00026.","ieee":"X. Wu, T. Kenter, R. Schade, T. Kühne, and C. Plessl, “Computing and Compressing Electron Repulsion Integrals on FPGAs,” in 2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 2023, pp. 162–173, doi: 10.1109/FCCM57271.2023.00026.","bibtex":"@inproceedings{Wu_Kenter_Schade_Kühne_Plessl_2023, title={Computing and Compressing Electron Repulsion Integrals on FPGAs}, DOI={10.1109/FCCM57271.2023.00026}, booktitle={2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)}, author={Wu, Xin and Kenter, Tobias and Schade, Robert and Kühne, Thomas and Plessl, Christian}, year={2023}, pages={162–173} }","mla":"Wu, Xin, et al. “Computing and Compressing Electron Repulsion Integrals on FPGAs.” 2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 2023, pp. 162–73, doi:10.1109/FCCM57271.2023.00026."},"type":"conference","year":"2023","language":[{"iso":"eng"}],"date_updated":"2023-08-02T15:05:42Z","_id":"43228","doi":"10.1109/FCCM57271.2023.00026","department":[{"_id":"27"},{"_id":"518"}],"publication":"2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","author":[{"id":"77439","last_name":"Wu","full_name":"Wu, Xin","first_name":"Xin"},{"first_name":"Tobias","full_name":"Kenter, Tobias","last_name":"Kenter","id":"3145"},{"first_name":"Robert","orcid":"0000-0002-6268-539","full_name":"Schade, Robert","last_name":"Schade","id":"75963"},{"id":"49079","last_name":"Kühne","full_name":"Kühne, Thomas","first_name":"Thomas"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"quality_controlled":"1","date_created":"2023-03-30T11:15:40Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"status":"public","abstract":[{"text":"The computation of electron repulsion integrals (ERIs) over Gaussian-type orbitals (GTOs) is a challenging problem in quantum-mechanics-based atomistic simulations. In practical simulations, several trillions of ERIs may have to be\r\ncomputed for every time step.\r\nIn this work, we investigate FPGAs as accelerators for the ERI computation. We use template parameters, here within the Intel oneAPI tool flow, to create customized designs for 256 different ERI quartet classes, based on their orbitals. To maximize data reuse, all intermediates are buffered in FPGA on-chip memory with customized layout. The pre-calculation of intermediates also helps to overcome data dependencies caused by multi-dimensional recurrence\r\nrelations. The involved loop structures are partially or even fully unrolled for high throughput of FPGA kernels. Furthermore, a lossy compression algorithm utilizing arbitrary bitwidth integers is integrated in the FPGA kernels. To our\r\nbest knowledge, this is the first work on ERI computation on FPGAs that supports more than just the single most basic quartet class. Also, the integration of ERI computation and compression it a novelty that is not even covered by CPU or GPU libraries so far.\r\nOur evaluation shows that using 16-bit integer for the ERI compression, the fastest FPGA kernels exceed the performance of 10 GERIS ($10 \\times 10^9$ ERIs per second) on one Intel Stratix 10 GX 2800 FPGA, with maximum absolute errors around $10^{-7}$ - $10^{-5}$ Hartree. The measured throughput can be accurately explained by a performance model. The FPGA kernels deployed on 2 FPGAs outperform similar computations using the widely used libint reference on a two-socket server with 40 Xeon Gold 6148 CPU cores of the same process technology by factors up to 6.0x and on a new two-socket server with 128 EPYC 7713 CPU cores by up to 1.9x.","lang":"eng"}],"external_id":{"arxiv":["2303.13632"]},"title":"Computing and Compressing Electron Repulsion Integrals on FPGAs","user_id":"75963"},{"user_id":"3145","title":"FPGA Acceleration for HPC Supercapacitor Simulations","status":"public","date_created":"2023-07-28T09:46:25Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"publication_status":"published","publisher":"ACM","author":[{"full_name":"Prouveur, Charles","first_name":"Charles","last_name":"Prouveur"},{"first_name":"Matthieu","full_name":"Haefele, Matthieu","last_name":"Haefele"},{"first_name":"Tobias","full_name":"Kenter, Tobias","last_name":"Kenter","id":"3145"},{"last_name":"Voss","full_name":"Voss, Nils","first_name":"Nils"}],"quality_controlled":"1","publication":"Proceedings of the Platform for Advanced Scientific Computing Conference","department":[{"_id":"27"},{"_id":"518"}],"oa":"1","doi":"10.1145/3592979.3593419","_id":"46189","date_updated":"2023-07-28T09:58:16Z","language":[{"iso":"eng"}],"type":"conference","year":"2023","citation":{"mla":"Prouveur, Charles, et al. “FPGA Acceleration for HPC Supercapacitor Simulations.” Proceedings of the Platform for Advanced Scientific Computing Conference, ACM, 2023, doi:10.1145/3592979.3593419.","bibtex":"@inproceedings{Prouveur_Haefele_Kenter_Voss_2023, title={FPGA Acceleration for HPC Supercapacitor Simulations}, DOI={10.1145/3592979.3593419}, booktitle={Proceedings of the Platform for Advanced Scientific Computing Conference}, publisher={ACM}, author={Prouveur, Charles and Haefele, Matthieu and Kenter, Tobias and Voss, Nils}, year={2023} }","chicago":"Prouveur, Charles, Matthieu Haefele, Tobias Kenter, and Nils Voss. “FPGA Acceleration for HPC Supercapacitor Simulations.” In Proceedings of the Platform for Advanced Scientific Computing Conference. ACM, 2023. https://doi.org/10.1145/3592979.3593419.","apa":"Prouveur, C., Haefele, M., Kenter, T., & Voss, N. (2023). FPGA Acceleration for HPC Supercapacitor Simulations. Proceedings of the Platform for Advanced Scientific Computing Conference. https://doi.org/10.1145/3592979.3593419","ama":"Prouveur C, Haefele M, Kenter T, Voss N. FPGA Acceleration for HPC Supercapacitor Simulations. In: Proceedings of the Platform for Advanced Scientific Computing Conference. ACM; 2023. doi:10.1145/3592979.3593419","ieee":"C. Prouveur, M. Haefele, T. Kenter, and N. Voss, “FPGA Acceleration for HPC Supercapacitor Simulations,” 2023, doi: 10.1145/3592979.3593419.","short":"C. Prouveur, M. Haefele, T. Kenter, N. Voss, in: Proceedings of the Platform for Advanced Scientific Computing Conference, ACM, 2023."},"main_file_link":[{"url":"https://dl.acm.org/doi/pdf/10.1145/3592979.3593419","open_access":"1"}]},{"_id":"50172","date_updated":"2024-01-04T08:47:47Z","language":[{"iso":"eng"}],"citation":{"ama":"Ochsenfeld S, Schlichting S. Hydrodynamic and Non-hydrodynamic Excitations in Kinetic Theory -- A Numerical Analysis in Scalar Field Theory. arXiv:230804491. Published online 2023.","apa":"Ochsenfeld, S., & Schlichting, S. (2023). Hydrodynamic and Non-hydrodynamic Excitations in Kinetic Theory -- A Numerical Analysis in Scalar Field Theory. In arXiv:2308.04491.","chicago":"Ochsenfeld, Stephan, and Sören Schlichting. “Hydrodynamic and Non-Hydrodynamic Excitations in Kinetic Theory -- A Numerical Analysis in Scalar Field Theory.” ArXiv:2308.04491, 2023.","bibtex":"@article{Ochsenfeld_Schlichting_2023, title={Hydrodynamic and Non-hydrodynamic Excitations in Kinetic Theory -- A Numerical Analysis in Scalar Field Theory}, journal={arXiv:2308.04491}, author={Ochsenfeld, Stephan and Schlichting, Sören}, year={2023} }","mla":"Ochsenfeld, Stephan, and Sören Schlichting. “Hydrodynamic and Non-Hydrodynamic Excitations in Kinetic Theory -- A Numerical Analysis in Scalar Field Theory.” ArXiv:2308.04491, 2023.","short":"S. Ochsenfeld, S. Schlichting, ArXiv:2308.04491 (2023).","ieee":"S. Ochsenfeld and S. Schlichting, “Hydrodynamic and Non-hydrodynamic Excitations in Kinetic Theory -- A Numerical Analysis in Scalar Field Theory,” arXiv:2308.04491. 2023."},"type":"preprint","year":"2023","user_id":"67287","title":"Hydrodynamic and Non-hydrodynamic Excitations in Kinetic Theory -- A Numerical Analysis in Scalar Field Theory","abstract":[{"lang":"eng","text":"Viscous hydrodynamics serves as a successful mesoscopic description of the\r\nQuark-Gluon Plasma produced in relativistic heavy-ion collisions. In order to\r\ninvestigate, how such an effective description emerges from the underlying\r\nmicroscopic dynamics we calculate the hydrodynamic and non-hydrodynamic modes\r\nof linear response in the sound channel from a first-principle calculation in\r\nkinetic theory. We do this with a new approach wherein we discretize the\r\ncollision kernel to directly calculate eigenvalues and eigenmodes of the\r\nevolution operator. This allows us to study the Green's functions at any point\r\nin the complex frequency space. Our study focuses on scalar theory with quartic\r\ninteraction and we find that the analytic structure of Green's functions in the\r\ncomplex plane is far more complicated than just poles or cuts which is a first\r\nstep towards an equivalent study in QCD kinetic theory."}],"external_id":{"arxiv":["2308.04491"]},"date_created":"2024-01-04T08:47:38Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"status":"public","publication":"arXiv:2308.04491","department":[{"_id":"27"}],"author":[{"last_name":"Ochsenfeld","first_name":"Stephan","full_name":"Ochsenfeld, Stephan"},{"full_name":"Schlichting, Sören","first_name":"Sören","last_name":"Schlichting"}]},{"_id":"50221","date_updated":"2024-01-05T12:39:50Z","year":"2023","citation":{"short":"M. Pleines, M. Pallasch, F. Zimmer, M. Preuss, ArXiv:2309.17207 (2023).","ieee":"M. Pleines, M. Pallasch, F. Zimmer, and M. Preuss, “Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents,” arXiv:2309.17207. 2023.","chicago":"Pleines, Marco, Matthias Pallasch, Frank Zimmer, and Mike Preuss. “Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents.” ArXiv:2309.17207, 2023.","ama":"Pleines M, Pallasch M, Zimmer F, Preuss M. Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents. arXiv:230917207. Published online 2023.","apa":"Pleines, M., Pallasch, M., Zimmer, F., & Preuss, M. (2023). Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents. In arXiv:2309.17207.","mla":"Pleines, Marco, et al. “Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents.” ArXiv:2309.17207, 2023.","bibtex":"@article{Pleines_Pallasch_Zimmer_Preuss_2023, title={Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents}, journal={arXiv:2309.17207}, author={Pleines, Marco and Pallasch, Matthias and Zimmer, Frank and Preuss, Mike}, year={2023} }"},"type":"preprint","language":[{"iso":"eng"}],"external_id":{"arxiv":["2309.17207"]},"abstract":[{"text":"Memory Gym presents a suite of 2D partially observable environments, namely\r\nMortar Mayhem, Mystery Path, and Searing Spotlights, designed to benchmark\r\nmemory capabilities in decision-making agents. These environments, originally\r\nwith finite tasks, are expanded into innovative, endless formats, mirroring the\r\nescalating challenges of cumulative memory games such as ``I packed my bag''.\r\nThis progression in task design shifts the focus from merely assessing sample\r\nefficiency to also probing the levels of memory effectiveness in dynamic,\r\nprolonged scenarios. To address the gap in available memory-based Deep\r\nReinforcement Learning baselines, we introduce an implementation that\r\nintegrates Transformer-XL (TrXL) with Proximal Policy Optimization. This\r\napproach utilizes TrXL as a form of episodic memory, employing a sliding window\r\ntechnique. Our comparative study between the Gated Recurrent Unit (GRU) and\r\nTrXL reveals varied performances across different settings. TrXL, on the finite\r\nenvironments, demonstrates superior sample efficiency in Mystery Path and\r\noutperforms in Mortar Mayhem. However, GRU is more efficient on Searing\r\nSpotlights. Most notably, in all endless tasks, GRU makes a remarkable\r\nresurgence, consistently outperforming TrXL by significant margins. Website and\r\nSource Code: https://github.com/MarcoMeter/endless-memory-gym/","lang":"eng"}],"title":"Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents","user_id":"67287","publication":"arXiv:2309.17207","department":[{"_id":"27"}],"author":[{"full_name":"Pleines, Marco","first_name":"Marco","last_name":"Pleines"},{"last_name":"Pallasch","full_name":"Pallasch, Matthias","first_name":"Matthias"},{"first_name":"Frank","full_name":"Zimmer, Frank","last_name":"Zimmer"},{"last_name":"Preuss","first_name":"Mike","full_name":"Preuss, Mike"}],"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_created":"2024-01-05T12:38:42Z","status":"public"},{"author":[{"full_name":"Opdenhövel, Jan-Oliver","first_name":"Jan-Oliver","last_name":"Opdenhövel"},{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"}],"quality_controlled":"1","publisher":"ACM","publication":"Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies","department":[{"_id":"27"},{"_id":"518"}],"status":"public","date_created":"2023-07-28T09:49:23Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"publication_status":"published","user_id":"3145","title":"Mutation Tree Reconstruction of Tumor Cells on FPGAs Using a Bit-Level Matrix Representation","main_file_link":[{"url":"https://dl.acm.org/doi/pdf/10.1145/3597031.3597050","open_access":"1"}],"language":[{"iso":"eng"}],"type":"conference","year":"2023","citation":{"ieee":"J.-O. Opdenhövel, C. Plessl, and T. Kenter, “Mutation Tree Reconstruction of Tumor Cells on FPGAs Using a Bit-Level Matrix Representation,” 2023, doi: 10.1145/3597031.3597050.","short":"J.-O. Opdenhövel, C. Plessl, T. Kenter, in: Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies, ACM, 2023.","bibtex":"@inproceedings{Opdenhövel_Plessl_Kenter_2023, title={Mutation Tree Reconstruction of Tumor Cells on FPGAs Using a Bit-Level Matrix Representation}, DOI={10.1145/3597031.3597050}, booktitle={Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies}, publisher={ACM}, author={Opdenhövel, Jan-Oliver and Plessl, Christian and Kenter, Tobias}, year={2023} }","mla":"Opdenhövel, Jan-Oliver, et al. “Mutation Tree Reconstruction of Tumor Cells on FPGAs Using a Bit-Level Matrix Representation.” Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies, ACM, 2023, doi:10.1145/3597031.3597050.","chicago":"Opdenhövel, Jan-Oliver, Christian Plessl, and Tobias Kenter. “Mutation Tree Reconstruction of Tumor Cells on FPGAs Using a Bit-Level Matrix Representation.” In Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies. ACM, 2023. https://doi.org/10.1145/3597031.3597050.","ama":"Opdenhövel J-O, Plessl C, Kenter T. Mutation Tree Reconstruction of Tumor Cells on FPGAs Using a Bit-Level Matrix Representation. In: Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies. ACM; 2023. doi:10.1145/3597031.3597050","apa":"Opdenhövel, J.-O., Plessl, C., & Kenter, T. (2023). Mutation Tree Reconstruction of Tumor Cells on FPGAs Using a Bit-Level Matrix Representation. Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies. https://doi.org/10.1145/3597031.3597050"},"date_updated":"2023-07-28T09:58:06Z","_id":"46190","oa":"1","doi":"10.1145/3597031.3597050"},{"date_created":"2023-07-28T09:42:14Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"status":"public","publication_status":"published","department":[{"_id":"27"},{"_id":"518"}],"publication":"Proceedings of the Platform for Advanced Scientific Computing Conference","quality_controlled":"1","author":[{"last_name":"Faj","id":"78722","first_name":"Jennifer","full_name":"Faj, Jennifer"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"last_name":"Faghih-Naini","full_name":"Faghih-Naini, Sara","first_name":"Sara"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"},{"last_name":"Aizinger","full_name":"Aizinger, Vadym","first_name":"Vadym"}],"publisher":"ACM","user_id":"3145","title":"Scalable Multi-FPGA Design of a Discontinuous Galerkin Shallow-Water Model on Unstructured Meshes","language":[{"iso":"eng"}],"year":"2023","citation":{"bibtex":"@inproceedings{Faj_Kenter_Faghih-Naini_Plessl_Aizinger_2023, title={Scalable Multi-FPGA Design of a Discontinuous Galerkin Shallow-Water Model on Unstructured Meshes}, DOI={10.1145/3592979.3593407}, booktitle={Proceedings of the Platform for Advanced Scientific Computing Conference}, publisher={ACM}, author={Faj, Jennifer and Kenter, Tobias and Faghih-Naini, Sara and Plessl, Christian and Aizinger, Vadym}, year={2023} }","mla":"Faj, Jennifer, et al. “Scalable Multi-FPGA Design of a Discontinuous Galerkin Shallow-Water Model on Unstructured Meshes.” Proceedings of the Platform for Advanced Scientific Computing Conference, ACM, 2023, doi:10.1145/3592979.3593407.","ama":"Faj J, Kenter T, Faghih-Naini S, Plessl C, Aizinger V. Scalable Multi-FPGA Design of a Discontinuous Galerkin Shallow-Water Model on Unstructured Meshes. In: Proceedings of the Platform for Advanced Scientific Computing Conference. ACM; 2023. doi:10.1145/3592979.3593407","apa":"Faj, J., Kenter, T., Faghih-Naini, S., Plessl, C., & Aizinger, V. (2023). Scalable Multi-FPGA Design of a Discontinuous Galerkin Shallow-Water Model on Unstructured Meshes. Proceedings of the Platform for Advanced Scientific Computing Conference. https://doi.org/10.1145/3592979.3593407","chicago":"Faj, Jennifer, Tobias Kenter, Sara Faghih-Naini, Christian Plessl, and Vadym Aizinger. “Scalable Multi-FPGA Design of a Discontinuous Galerkin Shallow-Water Model on Unstructured Meshes.” In Proceedings of the Platform for Advanced Scientific Computing Conference. ACM, 2023. https://doi.org/10.1145/3592979.3593407.","ieee":"J. Faj, T. Kenter, S. Faghih-Naini, C. Plessl, and V. Aizinger, “Scalable Multi-FPGA Design of a Discontinuous Galerkin Shallow-Water Model on Unstructured Meshes,” 2023, doi: 10.1145/3592979.3593407.","short":"J. Faj, T. Kenter, S. Faghih-Naini, C. Plessl, V. Aizinger, in: Proceedings of the Platform for Advanced Scientific Computing Conference, ACM, 2023."},"type":"conference","main_file_link":[{"url":"https://dl.acm.org/doi/pdf/10.1145/3592979.3593407","open_access":"1"}],"oa":"1","doi":"10.1145/3592979.3593407","_id":"46188","date_updated":"2023-07-28T09:48:19Z"},{"doi":"10.1145/3492805.3492808","oa":"1","date_updated":"2023-07-28T11:53:15Z","_id":"46193","type":"conference","year":"2022","citation":{"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.","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.","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} }","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.","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."},"language":[{"iso":"eng"}],"main_file_link":[{"url":"https://dl.acm.org/doi/pdf/10.1145/3492805.3492808","open_access":"1"}],"title":"A High-Fidelity Flow Solver for Unstructured Meshes on Field-Programmable Gate Arrays: Design, Evaluation, and Future Challenges","user_id":"3145","publication_status":"published","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_created":"2023-07-28T11:51:55Z","status":"public","publication":"International Conference on High Performance Computing in Asia-Pacific Region","department":[{"_id":"27"},{"_id":"518"}],"author":[{"last_name":"Karp","first_name":"Martin","full_name":"Karp, Martin"},{"full_name":"Podobas, Artur","first_name":"Artur","last_name":"Podobas"},{"first_name":"Tobias","full_name":"Kenter, Tobias","last_name":"Kenter","id":"3145"},{"last_name":"Jansson","full_name":"Jansson, Niclas","first_name":"Niclas"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"},{"last_name":"Schlatter","full_name":"Schlatter, Philipp","first_name":"Philipp"},{"full_name":"Markidis, Stefano","first_name":"Stefano","last_name":"Markidis"}],"quality_controlled":"1","publisher":"ACM"},{"_id":"36879","date_updated":"2023-01-16T09:16:20Z","oa":"1","main_file_link":[{"url":"https://arxiv.org/abs/2211.02740","open_access":"1"}],"language":[{"iso":"eng"}],"citation":{"short":"V. Churavy, W.F. Godoy, C. Bauer, H. Ranocha, M. Schlottke-Lakemper, L. Räss, J. Blaschke, M. Giordano, E. Schnetter, S. Omlin, J.S. Vetter, A. Edelman, (2022).","ieee":"V. Churavy et al., “Bridging HPC Communities through the Julia Programming Language.” 2022.","chicago":"Churavy, Valentin, William F Godoy, Carsten Bauer, Hendrik Ranocha, Michael Schlottke-Lakemper, Ludovic Räss, Johannes Blaschke, et al. “Bridging HPC Communities through the Julia Programming Language,” 2022.","ama":"Churavy V, Godoy WF, Bauer C, et al. Bridging HPC Communities through the Julia Programming Language. Published online 2022.","apa":"Churavy, V., Godoy, W. F., Bauer, C., Ranocha, H., Schlottke-Lakemper, M., Räss, L., Blaschke, J., Giordano, M., Schnetter, E., Omlin, S., Vetter, J. S., & Edelman, A. (2022). Bridging HPC Communities through the Julia Programming Language.","mla":"Churavy, Valentin, et al. Bridging HPC Communities through the Julia Programming Language. 2022.","bibtex":"@article{Churavy_Godoy_Bauer_Ranocha_Schlottke-Lakemper_Räss_Blaschke_Giordano_Schnetter_Omlin_et al._2022, title={Bridging HPC Communities through the Julia Programming Language}, author={Churavy, Valentin and Godoy, William F and Bauer, Carsten and Ranocha, Hendrik and Schlottke-Lakemper, Michael and Räss, Ludovic and Blaschke, Johannes and Giordano, Mosè and Schnetter, Erik and Omlin, Samuel and et al.}, year={2022} }"},"year":"2022","type":"preprint","abstract":[{"text":"The Julia programming language has evolved into a modern alternative to fill existing gaps in scientific computing and data science applications. Julia leverages a unified and coordinated single-language and ecosystem paradigm and has a proven track record of achieving high performance without sacrificing user productivity. These aspects make Julia a viable alternative to high-performance computing's (HPC's) existing and increasingly costly many-body workflow composition strategy in which traditional HPC languages (e.g., Fortran, C, C++) are used for simulations, and higher-level languages (e.g., Python, R, MATLAB) are used for data analysis and interactive computing. Julia's rapid growth in language capabilities, package ecosystem, and community make it a promising universal language for HPC. This paper presents the views of a multidisciplinary group of researchers from academia, government, and industry that advocate for an HPC software development paradigm that emphasizes developer productivity, workflow portability, and low barriers for entry. We believe that the Julia programming language, its ecosystem, and its community provide modern and powerful capabilities that enable this group's objectives. Crucially, we believe that Julia can provide a feasible and less costly approach to programming scientific applications and workflows that target HPC facilities. In this work, we examine the current practice and role of Julia as a common, end-to-end programming model to address major challenges in scientific reproducibility, data-driven AI/machine learning, co-design and workflows, scalability and performance portability in heterogeneous computing, network communication, data management, and community education. As a result, the diversification of current investments to fulfill the needs of the upcoming decade is crucial as more supercomputing centers prepare for the exascale era.","lang":"eng"}],"user_id":"90082","title":"Bridging HPC Communities through the Julia Programming Language","author":[{"last_name":"Churavy","first_name":"Valentin","full_name":"Churavy, Valentin"},{"last_name":"Godoy","first_name":"William F","full_name":"Godoy, William F"},{"id":"90082","last_name":"Bauer","full_name":"Bauer, Carsten","first_name":"Carsten"},{"last_name":"Ranocha","full_name":"Ranocha, Hendrik","first_name":"Hendrik"},{"first_name":"Michael","full_name":"Schlottke-Lakemper, Michael","last_name":"Schlottke-Lakemper"},{"full_name":"Räss, Ludovic","first_name":"Ludovic","last_name":"Räss"},{"full_name":"Blaschke, Johannes","first_name":"Johannes","last_name":"Blaschke"},{"last_name":"Giordano","first_name":"Mosè","full_name":"Giordano, Mosè"},{"last_name":"Schnetter","first_name":"Erik","full_name":"Schnetter, Erik"},{"full_name":"Omlin, Samuel","first_name":"Samuel","last_name":"Omlin"},{"last_name":"Vetter","full_name":"Vetter, Jeffrey S","first_name":"Jeffrey S"},{"full_name":"Edelman, Alan","first_name":"Alan","last_name":"Edelman"}],"department":[{"_id":"27"}],"status":"public","date_created":"2023-01-16T09:10:48Z"},{"main_file_link":[{"url":"https://arxiv.org/abs/2205.14741"}],"language":[{"iso":"eng"}],"type":"preprint","citation":{"short":"T. Kühne, C. Plessl, R. Schade, O. Schütt, ArXiv:2205.14741 (2022).","ieee":"T. Kühne, C. Plessl, R. Schade, and O. Schütt, “CP2K on the road to exascale,” arXiv:2205.14741. 2022.","ama":"Kühne T, Plessl C, Schade R, Schütt O. CP2K on the road to exascale. arXiv:220514741. Published online 2022.","apa":"Kühne, T., Plessl, C., Schade, R., & Schütt, O. (2022). CP2K on the road to exascale. In arXiv:2205.14741.","chicago":"Kühne, Thomas, Christian Plessl, Robert Schade, and Ole Schütt. “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} }","mla":"Kühne, Thomas, et al. “CP2K on the Road to Exascale.” ArXiv:2205.14741, 2022."},"year":"2022","_id":"32404","date_updated":"2023-08-02T14:55:35Z","author":[{"full_name":"Kühne, Thomas","first_name":"Thomas","id":"49079","last_name":"Kühne"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"},{"last_name":"Schade","id":"75963","first_name":"Robert","full_name":"Schade, Robert","orcid":"0000-0002-6268-539"},{"last_name":"Schütt","full_name":"Schütt, Ole","first_name":"Ole"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"publication":"arXiv:2205.14741","status":"public","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_created":"2022-07-22T08:14:08Z","external_id":{"arxiv":["2205.14741"]},"abstract":[{"lang":"eng","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."}],"user_id":"75963","title":"CP2K on the road to exascale"}]