[{"file_date_updated":"2024-04-26T08:35:17Z","citation":{"mla":"Bauer, Carsten, et al. “Noctua 2 Supercomputer.” Journal of Large-Scale Research Facilities, vol. 9, 2024, doi:10.17815/jlsrf-8-187 .","bibtex":"@article{Bauer_Kenter_Lass_Mazur_Meyer_Nitsche_Riebler_Schade_Schwarz_Winnwa_et al._2024, title={Noctua 2 Supercomputer}, volume={9}, DOI={10.17815/jlsrf-8-187 }, journal={Journal of large-scale research facilities}, author={Bauer, Carsten and Kenter, Tobias and Lass, Michael and Mazur, Lukas and Meyer, Marius and Nitsche, Holger and Riebler, Heinrich and Schade, Robert and Schwarz, Michael and Winnwa, Nils and et al.}, year={2024} }","ama":"Bauer C, Kenter T, Lass M, et al. Noctua 2 Supercomputer. Journal of large-scale research facilities. 2024;9. doi:10.17815/jlsrf-8-187 ","ieee":"C. Bauer et al., “Noctua 2 Supercomputer,” Journal of large-scale research facilities, vol. 9, 2024, doi: 10.17815/jlsrf-8-187 .","apa":"Bauer, C., Kenter, T., Lass, M., Mazur, L., Meyer, M., Nitsche, H., Riebler, H., Schade, R., Schwarz, M., Winnwa, N., Wiens, A., Wu, X., Plessl, C., & Simon, J. (2024). Noctua 2 Supercomputer. Journal of Large-Scale Research Facilities, 9. https://doi.org/10.17815/jlsrf-8-187 ","chicago":"Bauer, Carsten, Tobias Kenter, Michael Lass, Lukas Mazur, Marius Meyer, Holger Nitsche, Heinrich Riebler, et al. “Noctua 2 Supercomputer.” Journal of Large-Scale Research Facilities 9 (2024). https://doi.org/10.17815/jlsrf-8-187 .","short":"C. Bauer, T. Kenter, M. Lass, L. Mazur, M. Meyer, H. Nitsche, H. Riebler, R. Schade, M. Schwarz, N. Winnwa, A. Wiens, X. Wu, C. Plessl, J. Simon, Journal of Large-Scale Research Facilities 9 (2024)."},"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"oa":"1","status":"public","has_accepted_license":"1","_id":"53663","user_id":"8961","ddc":["004"],"volume":9,"publication":"Journal of large-scale research facilities","abstract":[{"lang":"eng","text":"Noctua 2 is a supercomputer operated at the Paderborn Center for Parallel Computing (PC2) at Paderborn University in Germany. Noctua 2 was inaugurated in 2022 and is an Atos BullSequana XH2000 system. It consists mainly of three node types: 1) CPU Compute nodes with AMD EPYC processors in different main memory configurations, 2) GPU nodes with NVIDIA A100 GPUs, and 3) FPGA nodes with Xilinx Alveo U280 and Intel Stratix 10 FPGA cards. While CPUs and GPUs are known off-the-shelf components in HPC systems, the operation of a large number of FPGA cards from different vendors and a dedicated FPGA-to-FPGA network are unique characteristics of Noctua 2. This paper describes in detail the overall setup of Noctua 2 and gives insights into the operation of the cluster from a hardware, software and facility perspective."}],"file":[{"date_created":"2024-04-26T07:30:20Z","creator":"deffel","file_id":"53664","content_type":"application/pdf","file_name":"Noctua2_Supercomputer.pdf","access_level":"open_access","file_size":3825480,"relation":"main_file","date_updated":"2024-04-26T08:35:17Z"}],"date_created":"2024-04-26T07:39:41Z","type":"journal_article","keyword":["Noctua 2","Supercomputer","FPGA","PC2","Paderborn Center for Parallel Computing"],"department":[{"_id":"27"},{"_id":"518"}],"year":"2024","title":"Noctua 2 Supercomputer","author":[{"last_name":"Bauer","first_name":"Carsten","full_name":"Bauer, Carsten","id":"90082"},{"full_name":"Kenter, Tobias","first_name":"Tobias","last_name":"Kenter","id":"3145"},{"full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","last_name":"Lass","first_name":"Michael","id":"24135"},{"id":"90492","full_name":"Mazur, Lukas","orcid":" 0000-0001-6304-7082","last_name":"Mazur","first_name":"Lukas"},{"id":"40778","full_name":"Meyer, Marius","first_name":"Marius","last_name":"Meyer"},{"full_name":"Nitsche, Holger","first_name":"Holger","last_name":"Nitsche","id":"15272"},{"first_name":"Heinrich","last_name":"Riebler","full_name":"Riebler, Heinrich","id":"8961"},{"id":"75963","full_name":"Schade, Robert","orcid":"0000-0002-6268-5397","last_name":"Schade","first_name":"Robert"},{"id":"5312","full_name":"Schwarz, Michael","first_name":"Michael","last_name":"Schwarz"},{"id":"61189","full_name":"Winnwa, Nils","first_name":"Nils","last_name":"Winnwa"},{"id":"23522","first_name":"Alex","last_name":"Wiens","orcid":"0000-0003-1764-9773","full_name":"Wiens, Alex"},{"first_name":"Xin","last_name":"Wu","full_name":"Wu, Xin","id":"77439"},{"orcid":"0000-0001-5728-9982","last_name":"Plessl","first_name":"Christian","full_name":"Plessl, Christian","id":"16153"},{"full_name":"Simon, Jens","last_name":"Simon","first_name":"Jens","id":"15273"}],"publication_status":"published","date_updated":"2024-04-26T08:44:30Z","article_type":"original","intvolume":" 9","language":[{"iso":"eng"}],"doi":"10.17815/jlsrf-8-187 "},{"quality_controlled":"1","citation":{"ama":"Meyer M, Kenter T, Petrica L, O’Brien K, Blott M, Plessl C. Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL. In: Lecture Notes in Computer Science. Springer Nature Switzerland; 2024. doi:10.1007/978-3-031-69766-1_9","short":"M. Meyer, T. Kenter, L. Petrica, K. O’Brien, M. Blott, C. Plessl, in: Lecture Notes in Computer Science, Springer Nature Switzerland, Cham, 2024.","chicago":"Meyer, Marius, Tobias Kenter, Lucian Petrica, Kenneth O’Brien, Michaela Blott, and Christian Plessl. “Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL.” In Lecture Notes in Computer Science. Cham: Springer Nature Switzerland, 2024. https://doi.org/10.1007/978-3-031-69766-1_9.","bibtex":"@inbook{Meyer_Kenter_Petrica_O’Brien_Blott_Plessl_2024, place={Cham}, title={Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL}, DOI={10.1007/978-3-031-69766-1_9}, booktitle={Lecture Notes in Computer Science}, publisher={Springer Nature Switzerland}, author={Meyer, Marius and Kenter, Tobias and Petrica, Lucian and O’Brien, Kenneth and Blott, Michaela and Plessl, Christian}, year={2024} }","mla":"Meyer, Marius, et al. “Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL.” Lecture Notes in Computer Science, Springer Nature Switzerland, 2024, doi:10.1007/978-3-031-69766-1_9.","apa":"Meyer, M., Kenter, T., Petrica, L., O’Brien, K., Blott, M., & Plessl, C. (2024). Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL. In Lecture Notes in Computer Science. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-69766-1_9","ieee":"M. Meyer, T. Kenter, L. Petrica, K. O’Brien, M. Blott, and C. Plessl, “Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL,” in Lecture Notes in Computer Science, Cham: Springer Nature Switzerland, 2024."},"oa":"1","place":"Cham","status":"public","user_id":"3145","_id":"56606","publisher":"Springer Nature Switzerland","abstract":[{"text":"AbstractMost FPGA boards in the HPC domain are well-suited for parallel scaling because of the direct integration of versatile and high-throughput network ports. However, the utilization of their network capabilities is often challenging and error-prone because the whole network stack and communication patterns have to be implemented and managed on the FPGAs. Also, this approach conceptually involves a trade-off between the performance potential of improved communication and the impact of resource consumption for communication infrastructure, since the utilized resources on the FPGAs could otherwise be used for computations. In this work, we investigate this trade-off, firstly, by using synthetic benchmarks to evaluate the different configuration options of the communication framework ACCL and their impact on communication latency and throughput. Finally, we use our findings to implement a shallow water simulation whose scalability heavily depends on low-latency communication. With a suitable configuration of ACCL, good scaling behavior can be shown to all 48 FPGAs installed in the system. Overall, the results show that the availability of inter-FPGA communication frameworks as well as the configurability of framework and network stack are crucial to achieve the best application performance with low latency communication.","lang":"eng"}],"publication":"Lecture Notes in Computer Science","department":[{"_id":"27"},{"_id":"518"}],"type":"book_chapter","date_created":"2024-10-14T07:51:51Z","publication_status":"published","date_updated":"2024-10-14T07:55:50Z","author":[{"full_name":"Meyer, Marius","first_name":"Marius","last_name":"Meyer"},{"last_name":"Kenter","first_name":"Tobias","full_name":"Kenter, Tobias"},{"full_name":"Petrica, Lucian","first_name":"Lucian","last_name":"Petrica"},{"full_name":"O’Brien, Kenneth","last_name":"O’Brien","first_name":"Kenneth"},{"full_name":"Blott, Michaela","last_name":"Blott","first_name":"Michaela"},{"first_name":"Christian","last_name":"Plessl","full_name":"Plessl, Christian"}],"publication_identifier":{"issn":["0302-9743","1611-3349"],"isbn":["9783031697654","9783031697661"]},"title":"Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL","year":"2024","doi":"10.1007/978-3-031-69766-1_9","language":[{"iso":"eng"}],"main_file_link":[{"open_access":"1"}]},{"publisher":"IEEE","_id":"56605","language":[{"iso":"eng"}],"doi":"10.1109/fpl64840.2024.00023","user_id":"3145","author":[{"orcid":"0000-0003-2314-2784","first_name":"Jan-Oliver","last_name":"Opdenhövel","full_name":"Opdenhövel, Jan-Oliver","id":"73960"},{"id":"100625","first_name":"Christoph","last_name":"Alt","full_name":"Alt, Christoph"},{"id":"16153","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","first_name":"Christian"},{"id":"3145","first_name":"Tobias","last_name":"Kenter","full_name":"Kenter, Tobias"}],"year":"2024","title":"StencilStream: A SYCL-based Stencil Simulation Framework Targeting FPGAs","status":"public","date_updated":"2024-10-14T07:56:26Z","publication_status":"published","date_created":"2024-10-14T07:49:24Z","department":[{"_id":"27"},{"_id":"518"}],"type":"conference","citation":{"chicago":"Opdenhövel, Jan-Oliver, Christoph Alt, Christian Plessl, and Tobias Kenter. “StencilStream: A SYCL-Based Stencil Simulation Framework Targeting FPGAs.” In 2024 34th International Conference on Field-Programmable Logic and Applications (FPL). IEEE, 2024. https://doi.org/10.1109/fpl64840.2024.00023.","short":"J.-O. Opdenhövel, C. Alt, C. Plessl, T. Kenter, in: 2024 34th International Conference on Field-Programmable Logic and Applications (FPL), IEEE, 2024.","ama":"Opdenhövel J-O, Alt C, Plessl C, Kenter T. StencilStream: A SYCL-based Stencil Simulation Framework Targeting FPGAs. In: 2024 34th International Conference on Field-Programmable Logic and Applications (FPL). IEEE; 2024. doi:10.1109/fpl64840.2024.00023","bibtex":"@inproceedings{Opdenhövel_Alt_Plessl_Kenter_2024, title={StencilStream: A SYCL-based Stencil Simulation Framework Targeting FPGAs}, DOI={10.1109/fpl64840.2024.00023}, booktitle={2024 34th International Conference on Field-Programmable Logic and Applications (FPL)}, publisher={IEEE}, author={Opdenhövel, Jan-Oliver and Alt, Christoph and Plessl, Christian and Kenter, Tobias}, year={2024} }","apa":"Opdenhövel, J.-O., Alt, C., Plessl, C., & Kenter, T. (2024). StencilStream: A SYCL-based Stencil Simulation Framework Targeting FPGAs. 2024 34th International Conference on Field-Programmable Logic and Applications (FPL). https://doi.org/10.1109/fpl64840.2024.00023","mla":"Opdenhövel, Jan-Oliver, et al. “StencilStream: A SYCL-Based Stencil Simulation Framework Targeting FPGAs.” 2024 34th International Conference on Field-Programmable Logic and Applications (FPL), IEEE, 2024, doi:10.1109/fpl64840.2024.00023.","ieee":"J.-O. Opdenhövel, C. Alt, C. Plessl, and T. Kenter, “StencilStream: A SYCL-based Stencil Simulation Framework Targeting FPGAs,” 2024, doi: 10.1109/fpl64840.2024.00023."},"publication":"2024 34th International Conference on Field-Programmable Logic and Applications (FPL)","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"quality_controlled":"1"},{"type":"conference","department":[{"_id":"27"},{"_id":"518"}],"date_created":"2024-10-14T07:59:08Z","quality_controlled":"1","publication":"2024 IEEE 32nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","citation":{"ieee":"A. R. Tareen, M. Meyer, C. Plessl, and T. Kenter, “HiHiSpMV: Sparse Matrix Vector Multiplication with Hierarchical Row Reductions on FPGAs with High Bandwidth Memory,” in 2024 IEEE 32nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 2024, vol. 35, doi: 10.1109/fccm60383.2024.00014.","apa":"Tareen, A. R., Meyer, M., Plessl, C., & Kenter, T. (2024). HiHiSpMV: Sparse Matrix Vector Multiplication with Hierarchical Row Reductions on FPGAs with High Bandwidth Memory. 2024 IEEE 32nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 35. https://doi.org/10.1109/fccm60383.2024.00014","short":"A.R. Tareen, M. Meyer, C. Plessl, T. Kenter, in: 2024 IEEE 32nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), IEEE, 2024.","chicago":"Tareen, Abdul Rehman, Marius Meyer, Christian Plessl, and Tobias Kenter. “HiHiSpMV: Sparse Matrix Vector Multiplication with Hierarchical Row Reductions on FPGAs with High Bandwidth Memory.” In 2024 IEEE 32nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), Vol. 35. IEEE, 2024. https://doi.org/10.1109/fccm60383.2024.00014.","mla":"Tareen, Abdul Rehman, et al. “HiHiSpMV: Sparse Matrix Vector Multiplication with Hierarchical Row Reductions on FPGAs with High Bandwidth Memory.” 2024 IEEE 32nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), vol. 35, IEEE, 2024, doi:10.1109/fccm60383.2024.00014.","bibtex":"@inproceedings{Tareen_Meyer_Plessl_Kenter_2024, title={HiHiSpMV: Sparse Matrix Vector Multiplication with Hierarchical Row Reductions on FPGAs with High Bandwidth Memory}, volume={35}, DOI={10.1109/fccm60383.2024.00014}, booktitle={2024 IEEE 32nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)}, publisher={IEEE}, author={Tareen, Abdul Rehman and Meyer, Marius and Plessl, Christian and Kenter, Tobias}, year={2024} }","ama":"Tareen AR, Meyer M, Plessl C, Kenter T. HiHiSpMV: Sparse Matrix Vector Multiplication with Hierarchical Row Reductions on FPGAs with High Bandwidth Memory. In: 2024 IEEE 32nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). Vol 35. IEEE; 2024. doi:10.1109/fccm60383.2024.00014"},"doi":"10.1109/fccm60383.2024.00014","user_id":"3145","volume":35,"publisher":"IEEE","_id":"56607","language":[{"iso":"eng"}],"date_updated":"2024-10-14T12:27:55Z","publication_status":"published","intvolume":" 35","status":"public","year":"2024","title":"HiHiSpMV: Sparse Matrix Vector Multiplication with Hierarchical Row Reductions on FPGAs with High Bandwidth Memory","author":[{"first_name":"Abdul Rehman","last_name":"Tareen","full_name":"Tareen, Abdul Rehman","id":"76938"},{"full_name":"Meyer, Marius","first_name":"Marius","last_name":"Meyer","id":"40778"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","first_name":"Christian","full_name":"Plessl, Christian"},{"id":"3145","full_name":"Kenter, Tobias","first_name":"Tobias","last_name":"Kenter"}]},{"publication_status":"published","date_updated":"2024-10-15T08:37:27Z","author":[{"full_name":"Stachura, Philip","last_name":"Stachura","first_name":"Philip"},{"full_name":"Li, Guanyu","last_name":"Li","first_name":"Guanyu"},{"id":"77439","full_name":"Wu, Xin","last_name":"Wu","first_name":"Xin"},{"id":"16153","last_name":"Plessl","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"},{"last_name":"Fang","first_name":"Zhenman","full_name":"Fang, Zhenman"}],"year":"2024","title":"SERI: High-Throughput Streaming Acceleration of Electron Repulsion Integral Computation in Quantum Chemistry using HBM-based FPGAs","doi":"10.1109/fpl64840.2024.00018","language":[{"iso":"eng"}],"main_file_link":[{"url":"https://ieeexplore.ieee.org/document/10705609"}],"abstract":[{"text":"The computation of electron repulsion integrals (ERIs) is a key component for quantum chemical methods. The intensive computation and bandwidth demand for ERI evaluation presents a significant challenge for quantum-mechanics-based atomistic simulations with hybrid density functional theory: due to the tens of trillions of ERI computations in each time step, practical applications are usually limited to thousands of atoms. In this work, we propose SERI, a high-throughput streaming accelerator for ERI computation on HBM-based FPGAs. In contrast to prior buffer-based designs, SERI proposes a novel streaming architecture to address the on-chip buffer limitation and the floorplanning challenge, and leverages the high-bandwidth memory to overcome the bandwidth bottleneck in prior designs. Moreover, to meet the varying computation, bandwidth, and floorplanning requirements between the 55 canonical quartet classes in ERI calculation, we design an automation tool, together with an accurate performance model, to automatically customize the architecture and floorplanning strategy for each canonical quartet class to maximize their throughput. Our performance evaluation on the AMD/Xilinx Alveo U280 FPGA board shows that, SERI achieves an average speedup of 9.80 x over the previous best-performing FPGA design, a 3.21x speedup over a 64-core AMD EPYC 7713 CPU, and a 15.64x speedup over an Nvidia A40 GPU. It reaches a peak throughput of 23.8 GERIS ($10^9$ ERIs per second) on one Alveo U280 FPGA. SERI will be released soon at https://github.com/SFU-HiAccel/SERI.","lang":"eng"}],"publication":"2024 34th International Conference on Field-Programmable Logic and Applications (FPL)","department":[{"_id":"27"},{"_id":"518"}],"type":"conference","date_created":"2024-10-14T08:44:44Z","status":"public","user_id":"77439","_id":"56609","publisher":"IEEE","page":"60-68","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"quality_controlled":"1","citation":{"mla":"Stachura, Philip, et al. “SERI: High-Throughput Streaming Acceleration of Electron Repulsion Integral Computation in Quantum Chemistry Using HBM-Based FPGAs.” 2024 34th International Conference on Field-Programmable Logic and Applications (FPL), IEEE, 2024, pp. 60–68, doi:10.1109/fpl64840.2024.00018.","bibtex":"@inproceedings{Stachura_Li_Wu_Plessl_Fang_2024, title={SERI: High-Throughput Streaming Acceleration of Electron Repulsion Integral Computation in Quantum Chemistry using HBM-based FPGAs}, DOI={10.1109/fpl64840.2024.00018}, booktitle={2024 34th International Conference on Field-Programmable Logic and Applications (FPL)}, publisher={IEEE}, author={Stachura, Philip and Li, Guanyu and Wu, Xin and Plessl, Christian and Fang, Zhenman}, year={2024}, pages={60–68} }","ama":"Stachura P, Li G, Wu X, Plessl C, Fang Z. SERI: High-Throughput Streaming Acceleration of Electron Repulsion Integral Computation in Quantum Chemistry using HBM-based FPGAs. In: 2024 34th International Conference on Field-Programmable Logic and Applications (FPL). IEEE; 2024:60-68. doi:10.1109/fpl64840.2024.00018","ieee":"P. Stachura, G. Li, X. Wu, C. Plessl, and Z. Fang, “SERI: High-Throughput Streaming Acceleration of Electron Repulsion Integral Computation in Quantum Chemistry using HBM-based FPGAs,” in 2024 34th International Conference on Field-Programmable Logic and Applications (FPL), 2024, pp. 60–68, doi: 10.1109/fpl64840.2024.00018.","apa":"Stachura, P., Li, G., Wu, X., Plessl, C., & Fang, Z. (2024). SERI: High-Throughput Streaming Acceleration of Electron Repulsion Integral Computation in Quantum Chemistry using HBM-based FPGAs. 2024 34th International Conference on Field-Programmable Logic and Applications (FPL), 60–68. https://doi.org/10.1109/fpl64840.2024.00018","chicago":"Stachura, Philip, Guanyu Li, Xin Wu, Christian Plessl, and Zhenman Fang. “SERI: High-Throughput Streaming Acceleration of Electron Repulsion Integral Computation in Quantum Chemistry Using HBM-Based FPGAs.” In 2024 34th International Conference on Field-Programmable Logic and Applications (FPL), 60–68. IEEE, 2024. https://doi.org/10.1109/fpl64840.2024.00018.","short":"P. Stachura, G. Li, X. Wu, C. Plessl, Z. Fang, in: 2024 34th International Conference on Field-Programmable Logic and Applications (FPL), IEEE, 2024, pp. 60–68."}},{"citation":{"short":"M. Meyer, T. Kenter, L. Petrica, K. O’Brien, M. Blott, C. Plessl, in: Lecture Notes in Computer Science, Springer Nature Switzerland, Cham, 2024.","chicago":"Meyer, Marius, Tobias Kenter, Lucian Petrica, Kenneth O’Brien, Michaela Blott, and Christian Plessl. “Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL.” In Lecture Notes in Computer Science. Cham: Springer Nature Switzerland, 2024. https://doi.org/10.1007/978-3-031-69766-1_9.","ieee":"M. Meyer, T. Kenter, L. Petrica, K. O’Brien, M. Blott, and C. Plessl, “Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL,” in Lecture Notes in Computer Science, Cham: Springer Nature Switzerland, 2024.","apa":"Meyer, M., Kenter, T., Petrica, L., O’Brien, K., Blott, M., & Plessl, C. (2024). Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL. In Lecture Notes in Computer Science. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-69766-1_9","bibtex":"@inbook{Meyer_Kenter_Petrica_O’Brien_Blott_Plessl_2024, place={Cham}, title={Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL}, DOI={10.1007/978-3-031-69766-1_9}, booktitle={Lecture Notes in Computer Science}, publisher={Springer Nature Switzerland}, author={Meyer, Marius and Kenter, Tobias and Petrica, Lucian and O’Brien, Kenneth and Blott, Michaela and Plessl, Christian}, year={2024} }","ama":"Meyer M, Kenter T, Petrica L, O’Brien K, Blott M, Plessl C. Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL. In: Lecture Notes in Computer Science. Springer Nature Switzerland; 2024. doi:10.1007/978-3-031-69766-1_9","mla":"Meyer, Marius, et al. “Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL.” Lecture Notes in Computer Science, Springer Nature Switzerland, 2024, doi:10.1007/978-3-031-69766-1_9."},"project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"quality_controlled":"1","place":"Cham","oa":"1","status":"public","publisher":"Springer Nature Switzerland","_id":"62067","user_id":"3145","publication":"Lecture Notes in Computer Science","abstract":[{"text":"Most FPGA boards in the HPC domain are well-suited for parallel scaling because of the direct integration of versatile and high-throughput network ports. However, the utilization of their network capabilities is often challenging and error-prone because the whole network stack and communication patterns have to be implemented and managed on the FPGAs. Also, this approach conceptually involves a trade-off between the performance potential of improved communication and the impact of resource consumption for communication infrastructure, since the utilized resources on the FPGAs could otherwise be used for computations. In this work, we investigate this trade-off, firstly, by using synthetic benchmarks to evaluate the different configuration options of the communication framework ACCL and their impact on communication latency and throughput. Finally, we use our findings to implement a shallow water simulation whose scalability heavily depends on low-latency communication. With a suitable configuration of ACCL, good scaling behavior can be shown to all 48 FPGAs installed in the system. Overall, the results show that the availability of inter-FPGA communication frameworks as well as the configurability of framework and network stack are crucial to achieve the best application performance with low latency communication.","lang":"eng"}],"date_created":"2025-11-04T09:50:24Z","department":[{"_id":"27"},{"_id":"518"}],"type":"book_chapter","publication_identifier":{"isbn":["9783031697654","9783031697661"],"issn":["0302-9743","1611-3349"]},"author":[{"id":"40778","full_name":"Meyer, Marius","last_name":"Meyer","first_name":"Marius"},{"id":"3145","full_name":"Kenter, Tobias","last_name":"Kenter","first_name":"Tobias"},{"last_name":"Petrica","first_name":"Lucian","full_name":"Petrica, Lucian"},{"last_name":"O’Brien","first_name":"Kenneth","full_name":"O’Brien, Kenneth"},{"full_name":"Blott, Michaela","first_name":"Michaela","last_name":"Blott"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","full_name":"Plessl, Christian","id":"16153"}],"year":"2024","title":"Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL","date_updated":"2025-11-04T09:51:22Z","publication_status":"published","language":[{"iso":"eng"}],"main_file_link":[{"open_access":"1"}],"doi":"10.1007/978-3-031-69766-1_9"},{"status":"public","user_id":"3145","volume":17,"page":"1-28","_id":"56604","publisher":"Association for Computing Machinery (ACM)","quality_controlled":"1","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"citation":{"mla":"Van Hirtum, Lennart, et al. “A Computation of the Ninth Dedekind Number Using FPGA Supercomputing.” ACM Transactions on Reconfigurable Technology and Systems, vol. 17, no. 3, Association for Computing Machinery (ACM), 2024, pp. 1–28, doi:10.1145/3674147.","bibtex":"@article{Van Hirtum_De Causmaecker_Goemaere_Kenter_Riebler_Lass_Plessl_2024, title={A Computation of the Ninth Dedekind Number Using FPGA Supercomputing}, volume={17}, DOI={10.1145/3674147}, number={3}, journal={ACM Transactions on Reconfigurable Technology and Systems}, publisher={Association for Computing Machinery (ACM)}, author={Van Hirtum, Lennart and De Causmaecker, Patrick and Goemaere, Jens and Kenter, Tobias and Riebler, Heinrich and Lass, Michael and Plessl, Christian}, year={2024}, pages={1–28} }","ama":"Van Hirtum L, De Causmaecker P, Goemaere J, et al. A Computation of the Ninth Dedekind Number Using FPGA Supercomputing. ACM Transactions on Reconfigurable Technology and Systems. 2024;17(3):1-28. doi:10.1145/3674147","ieee":"L. Van Hirtum et al., “A Computation of the Ninth Dedekind Number Using FPGA Supercomputing,” ACM Transactions on Reconfigurable Technology and Systems, vol. 17, no. 3, pp. 1–28, 2024, doi: 10.1145/3674147.","apa":"Van Hirtum, L., De Causmaecker, P., Goemaere, J., Kenter, T., Riebler, H., Lass, M., & Plessl, C. (2024). A Computation of the Ninth Dedekind Number Using FPGA Supercomputing. ACM Transactions on Reconfigurable Technology and Systems, 17(3), 1–28. https://doi.org/10.1145/3674147","short":"L. Van Hirtum, P. De Causmaecker, J. Goemaere, T. Kenter, H. Riebler, M. Lass, C. Plessl, ACM Transactions on Reconfigurable Technology and Systems 17 (2024) 1–28.","chicago":"Van Hirtum, Lennart, Patrick De Causmaecker, Jens Goemaere, Tobias Kenter, Heinrich Riebler, Michael Lass, and Christian Plessl. “A Computation of the Ninth Dedekind Number Using FPGA Supercomputing.” ACM Transactions on Reconfigurable Technology and Systems 17, no. 3 (2024): 1–28. https://doi.org/10.1145/3674147."},"oa":"1","date_updated":"2025-11-04T09:53:26Z","publication_status":"published","intvolume":" 17","year":"2024","title":"A Computation of the Ninth Dedekind Number Using FPGA Supercomputing","author":[{"id":"100210","last_name":"Van Hirtum","first_name":"Lennart","full_name":"Van Hirtum, Lennart"},{"full_name":"De Causmaecker, Patrick","last_name":"De Causmaecker","first_name":"Patrick"},{"full_name":"Goemaere, Jens","last_name":"Goemaere","first_name":"Jens"},{"last_name":"Kenter","first_name":"Tobias","full_name":"Kenter, Tobias","id":"3145"},{"id":"8961","full_name":"Riebler, Heinrich","last_name":"Riebler","first_name":"Heinrich"},{"full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","last_name":"Lass","first_name":"Michael","id":"24135"},{"orcid":"0000-0001-5728-9982","first_name":"Christian","last_name":"Plessl","full_name":"Plessl, Christian","id":"16153"}],"publication_identifier":{"issn":["1936-7406","1936-7414"]},"doi":"10.1145/3674147","main_file_link":[{"open_access":"1"}],"language":[{"iso":"eng"}],"abstract":[{"text":"This manuscript makes the claim of having computed the 9th Dedekind number, D(9). This was done by accelerating the core operation of the process with an efficient FPGA design that outperforms an optimized 64-core CPU reference by 95x. The FPGA execution was parallelized on the Noctua 2 supercomputer at Paderborn University. The resulting value for D(9) is 286386577668298411128469151667598498812366. This value can be verified in two steps. We have made the data file containing the 490 M results available, each of which can be verified separately on CPU, and the whole file sums to our proposed value. The paper explains the mathematical approach in the first part, before putting the focus on a deep dive into the FPGA accelerator implementation followed by a performance analysis. The FPGA implementation was done in Register-Transfer Level using a dual-clock architecture and shows how we achieved an impressive FMax of 450 MHz on the targeted Stratix 10 GX 2,800 FPGAs. The total compute time used was 47,000 FPGA hours.","lang":"eng"}],"issue":"3","publication":"ACM Transactions on Reconfigurable Technology and Systems","type":"journal_article","department":[{"_id":"27"},{"_id":"518"}],"date_created":"2024-10-14T07:38:29Z"},{"doi":"10.1145/3648115.3648134","user_id":"3145","_id":"53503","publisher":"ACM","language":[{"iso":"eng"}],"date_updated":"2025-11-04T09:53:59Z","publication_status":"published","status":"public","title":"Optimisation and Evaluation of Breadth First Search with oneAPI/SYCL on Intel FPGAs: from Describing Algorithms to Describing Architectures","year":"2024","author":[{"first_name":"Kaan","last_name":"Olgu","full_name":"Olgu, Kaan"},{"id":"3145","first_name":"Tobias","last_name":"Kenter","full_name":"Kenter, Tobias"},{"full_name":"Nunez-Yanez, Jose","first_name":"Jose","last_name":"Nunez-Yanez"},{"first_name":"Simon","last_name":"Mcintosh-Smith","full_name":"Mcintosh-Smith, Simon"}],"type":"conference","department":[{"_id":"27"},{"_id":"518"}],"date_created":"2024-04-15T07:41:21Z","quality_controlled":"1","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"publication":"Proceedings of the 12th International Workshop on OpenCL and SYCL","citation":{"ieee":"K. Olgu, T. Kenter, J. Nunez-Yanez, and S. Mcintosh-Smith, “Optimisation and Evaluation of Breadth First Search with oneAPI/SYCL on Intel FPGAs: from Describing Algorithms to Describing Architectures,” 2024, doi: 10.1145/3648115.3648134.","apa":"Olgu, K., Kenter, T., Nunez-Yanez, J., & Mcintosh-Smith, S. (2024). Optimisation and Evaluation of Breadth First Search with oneAPI/SYCL on Intel FPGAs: from Describing Algorithms to Describing Architectures. Proceedings of the 12th International Workshop on OpenCL and SYCL. https://doi.org/10.1145/3648115.3648134","short":"K. Olgu, T. Kenter, J. Nunez-Yanez, S. Mcintosh-Smith, in: Proceedings of the 12th International Workshop on OpenCL and SYCL, ACM, 2024.","chicago":"Olgu, Kaan, Tobias Kenter, Jose Nunez-Yanez, and Simon Mcintosh-Smith. “Optimisation and Evaluation of Breadth First Search with OneAPI/SYCL on Intel FPGAs: From Describing Algorithms to Describing Architectures.” In Proceedings of the 12th International Workshop on OpenCL and SYCL. ACM, 2024. https://doi.org/10.1145/3648115.3648134.","mla":"Olgu, Kaan, et al. “Optimisation and Evaluation of Breadth First Search with OneAPI/SYCL on Intel FPGAs: From Describing Algorithms to Describing Architectures.” Proceedings of the 12th International Workshop on OpenCL and SYCL, ACM, 2024, doi:10.1145/3648115.3648134.","bibtex":"@inproceedings{Olgu_Kenter_Nunez-Yanez_Mcintosh-Smith_2024, title={Optimisation and Evaluation of Breadth First Search with oneAPI/SYCL on Intel FPGAs: from Describing Algorithms to Describing Architectures}, DOI={10.1145/3648115.3648134}, booktitle={Proceedings of the 12th International Workshop on OpenCL and SYCL}, publisher={ACM}, author={Olgu, Kaan and Kenter, Tobias and Nunez-Yanez, Jose and Mcintosh-Smith, Simon}, year={2024} }","ama":"Olgu K, Kenter T, Nunez-Yanez J, Mcintosh-Smith S. Optimisation and Evaluation of Breadth First Search with oneAPI/SYCL on Intel FPGAs: from Describing Algorithms to Describing Architectures. In: Proceedings of the 12th International Workshop on OpenCL and SYCL. ACM; 2024. doi:10.1145/3648115.3648134"}},{"publisher":"ACM","_id":"54312","language":[{"iso":"eng"}],"article_number":"11","doi":"10.1145/3659914.3659925","user_id":"16153","author":[{"full_name":"Büttner, Markus","first_name":"Markus","last_name":"Büttner"},{"last_name":"Alt","first_name":"Christoph","full_name":"Alt, Christoph","id":"100625"},{"id":"3145","full_name":"Kenter, Tobias","first_name":"Tobias","last_name":"Kenter"},{"full_name":"Köstler, Harald","last_name":"Köstler","first_name":"Harald"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","full_name":"Plessl, Christian","id":"16153"},{"first_name":"Vadym","last_name":"Aizinger","full_name":"Aizinger, Vadym"}],"title":"Enabling Performance Portability for Shallow Water Equations on CPUs, GPUs, and FPGAs with SYCL","year":"2024","status":"public","date_updated":"2024-11-27T22:50:19Z","publication_status":"published","date_created":"2024-05-16T13:24:49Z","department":[{"_id":"27"},{"_id":"518"}],"type":"conference","citation":{"mla":"Büttner, Markus, et al. “Enabling Performance Portability for Shallow Water Equations on CPUs, GPUs, and FPGAs with SYCL.” Proceedings of the Platform for Advanced Scientific Computing Conference (PASC), 11, ACM, 2024, doi:10.1145/3659914.3659925.","bibtex":"@inproceedings{Büttner_Alt_Kenter_Köstler_Plessl_Aizinger_2024, title={Enabling Performance Portability for Shallow Water Equations on CPUs, GPUs, and FPGAs with SYCL}, DOI={10.1145/3659914.3659925}, number={11}, booktitle={Proceedings of the Platform for Advanced Scientific Computing Conference (PASC)}, publisher={ACM}, author={Büttner, Markus and Alt, Christoph and Kenter, Tobias and Köstler, Harald and Plessl, Christian and Aizinger, Vadym}, year={2024} }","ama":"Büttner M, Alt C, Kenter T, Köstler H, Plessl C, Aizinger V. Enabling Performance Portability for Shallow Water Equations on CPUs, GPUs, and FPGAs with SYCL. In: Proceedings of the Platform for Advanced Scientific Computing Conference (PASC). ACM; 2024. doi:10.1145/3659914.3659925","ieee":"M. Büttner, C. Alt, T. Kenter, H. Köstler, C. Plessl, and V. Aizinger, “Enabling Performance Portability for Shallow Water Equations on CPUs, GPUs, and FPGAs with SYCL,” 2024, doi: 10.1145/3659914.3659925.","apa":"Büttner, M., Alt, C., Kenter, T., Köstler, H., Plessl, C., & Aizinger, V. (2024). Enabling Performance Portability for Shallow Water Equations on CPUs, GPUs, and FPGAs with SYCL. Proceedings of the Platform for Advanced Scientific Computing Conference (PASC), Article 11. https://doi.org/10.1145/3659914.3659925","short":"M. Büttner, C. Alt, T. Kenter, H. Köstler, C. Plessl, V. Aizinger, in: Proceedings of the Platform for Advanced Scientific Computing Conference (PASC), ACM, 2024.","chicago":"Büttner, Markus, Christoph Alt, Tobias Kenter, Harald Köstler, Christian Plessl, and Vadym Aizinger. “Enabling Performance Portability for Shallow Water Equations on CPUs, GPUs, and FPGAs with SYCL.” In Proceedings of the Platform for Advanced Scientific Computing Conference (PASC). ACM, 2024. https://doi.org/10.1145/3659914.3659925."},"publication":"Proceedings of the Platform for Advanced Scientific Computing Conference (PASC)","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"quality_controlled":"1"},{"external_id":{"arxiv":["2304.03039"]},"date_created":"2023-04-08T11:05:29Z","type":"preprint","department":[{"_id":"27"},{"_id":"518"}],"publication":"arXiv:2304.03039","citation":{"mla":"Van Hirtum, Lennart, et al. “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.","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} }","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.","ieee":"L. Van Hirtum 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.","short":"L. Van Hirtum, P. De Causmaecker, J. Goemaere, T. Kenter, H. Riebler, M. Lass, C. Plessl, ArXiv:2304.03039 (2023)."},"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."}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"language":[{"iso":"eng"}],"_id":"43439","user_id":"3145","year":"2023","status":"public","title":"A computation of D(9) using FPGA Supercomputing","author":[{"last_name":"Van Hirtum","first_name":"Lennart","full_name":"Van Hirtum, Lennart"},{"full_name":"De Causmaecker, Patrick","first_name":"Patrick","last_name":"De Causmaecker"},{"full_name":"Goemaere, Jens","first_name":"Jens","last_name":"Goemaere"},{"id":"3145","full_name":"Kenter, Tobias","last_name":"Kenter","first_name":"Tobias"},{"id":"8961","first_name":"Heinrich","last_name":"Riebler","full_name":"Riebler, Heinrich"},{"full_name":"Lass, Michael","last_name":"Lass","orcid":"0000-0002-5708-7632","first_name":"Michael","id":"24135"},{"full_name":"Plessl, Christian","first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"}],"date_updated":"2024-01-22T09:56:42Z"},{"date_updated":"2024-04-17T08:09:39Z","publication_status":"published","status":"public","title":"Scalable Multi-FPGA Design of a Discontinuous Galerkin Shallow-Water Model on Unstructured Meshes","year":"2023","author":[{"id":"78722","first_name":"Jennifer","last_name":"Faj","full_name":"Faj, Jennifer"},{"full_name":"Kenter, Tobias","first_name":"Tobias","last_name":"Kenter","id":"3145"},{"full_name":"Faghih-Naini, Sara","last_name":"Faghih-Naini","first_name":"Sara"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","full_name":"Plessl, Christian","id":"16153"},{"last_name":"Aizinger","first_name":"Vadym","full_name":"Aizinger, Vadym"}],"doi":"10.1145/3592979.3593407","user_id":"3145","main_file_link":[{"url":"https://dl.acm.org/doi/pdf/10.1145/3592979.3593407"}],"language":[{"iso":"eng"}],"_id":"46188","publisher":"ACM","related_material":{"link":[{"relation":"other","url":"https://www.sighpc.org/for-our-community/acm-open-tocs/pasc23-open-toc","description":"Open Access available via this link."}]},"quality_controlled":"1","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"publication":"Proceedings of the Platform for Advanced Scientific Computing Conference (PASC)","citation":{"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 (PASC). 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 (PASC), ACM, 2023.","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 (PASC). ACM, 2023. https://doi.org/10.1145/3592979.3593407.","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 (PASC), 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 (PASC). ACM; 2023. doi:10.1145/3592979.3593407","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 (PASC)}, publisher={ACM}, author={Faj, Jennifer and Kenter, Tobias and Faghih-Naini, Sara and Plessl, Christian and Aizinger, Vadym}, year={2023} }"},"type":"conference","department":[{"_id":"27"},{"_id":"518"}],"date_created":"2023-07-28T09:42:14Z"},{"publication_status":"published","date_updated":"2024-04-17T08:10:51Z","status":"public","year":"2023","title":"FPGA Acceleration for HPC Supercapacitor Simulations","author":[{"full_name":"Prouveur, Charles","first_name":"Charles","last_name":"Prouveur"},{"first_name":"Matthieu","last_name":"Haefele","full_name":"Haefele, Matthieu"},{"full_name":"Kenter, Tobias","first_name":"Tobias","last_name":"Kenter","id":"3145"},{"full_name":"Voss, Nils","first_name":"Nils","last_name":"Voss"}],"user_id":"3145","doi":"10.1145/3592979.3593419","main_file_link":[{"url":"https://dl.acm.org/doi/pdf/10.1145/3592979.3593419"}],"_id":"46189","language":[{"iso":"eng"}],"publisher":"ACM","quality_controlled":"1","related_material":{"link":[{"description":"Open Access available via this link.","relation":"other","url":" https://www.sighpc.org/for-our-community/acm-open-tocs/pasc23-open-toc "}]},"project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"publication":"Proceedings of the Platform for Advanced Scientific Computing Conference (PASC)","citation":{"mla":"Prouveur, Charles, et al. “FPGA Acceleration for HPC Supercapacitor Simulations.” Proceedings of the Platform for Advanced Scientific Computing Conference (PASC), ACM, 2023, doi: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 (PASC). 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 (PASC)}, publisher={ACM}, author={Prouveur, Charles and Haefele, Matthieu and Kenter, Tobias and Voss, Nils}, year={2023} }","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 (PASC). https://doi.org/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 (PASC), ACM, 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 (PASC). ACM, 2023. https://doi.org/10.1145/3592979.3593419."},"type":"conference","department":[{"_id":"27"},{"_id":"518"}],"date_created":"2023-07-28T09:46:25Z"},{"file":[{"creator":"florida","date_created":"2023-07-07T08:15:35Z","file_size":2288788,"access_level":"open_access","file_name":"C2-Chapter-SFB-Buch-Final.pdf","date_updated":"2023-07-07T11:17:33Z","relation":"main_file","content_type":"application/pdf","file_id":"45894"}],"date_created":"2023-07-07T08:15:45Z","type":"book_chapter","department":[{"_id":"7"},{"_id":"27"},{"_id":"518"},{"_id":"78"}],"publication":"On-The-Fly Computing -- Individualized IT-services in dynamic markets","language":[{"iso":"eng"}],"series_title":"Verlagsschriftenreihe des Heinz Nixdorf Instituts","doi":"10.5281/zenodo.8068642","year":"2023","title":"Compute Centers I: Heterogeneous Execution Environments","author":[{"id":"49992","full_name":"Hansmeier, Tim","last_name":"Hansmeier","orcid":"0000-0003-1377-3339","first_name":"Tim"},{"id":"3145","full_name":"Kenter, Tobias","first_name":"Tobias","last_name":"Kenter"},{"first_name":"Marius","last_name":"Meyer","full_name":"Meyer, Marius","id":"40778"},{"id":"8961","full_name":"Riebler, Heinrich","last_name":"Riebler","first_name":"Heinrich"},{"id":"398","last_name":"Platzner","first_name":"Marco","full_name":"Platzner, Marco"},{"id":"16153","full_name":"Plessl, Christian","first_name":"Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982"}],"date_updated":"2024-05-02T10:33:00Z","intvolume":" 412","place":"Paderborn","oa":"1","file_date_updated":"2023-07-07T11:17:33Z","citation":{"chicago":"Hansmeier, Tim, Tobias Kenter, Marius Meyer, Heinrich Riebler, Marco Platzner, and Christian Plessl. “Compute Centers I: Heterogeneous Execution Environments.” In On-The-Fly Computing -- Individualized IT-Services in Dynamic Markets, edited by Claus-Jochen Haake, Friedhelm Meyer auf der Heide, Marco Platzner, Henning Wachsmuth, and Heike Wehrheim, 412:165–82. Verlagsschriftenreihe Des Heinz Nixdorf Instituts. Paderborn: Heinz Nixdorf Institut, Universität Paderborn, 2023. https://doi.org/10.5281/zenodo.8068642.","short":"T. Hansmeier, T. Kenter, M. Meyer, H. Riebler, M. Platzner, C. Plessl, in: C.-J. Haake, F. Meyer auf der Heide, M. Platzner, H. Wachsmuth, H. Wehrheim (Eds.), On-The-Fly Computing -- Individualized IT-Services in Dynamic Markets, Heinz Nixdorf Institut, Universität Paderborn, Paderborn, 2023, pp. 165–182.","ieee":"T. Hansmeier, T. Kenter, M. Meyer, H. Riebler, M. Platzner, and C. Plessl, “Compute Centers I: Heterogeneous Execution Environments,” in On-The-Fly Computing -- Individualized IT-services in dynamic markets, vol. 412, C.-J. Haake, F. Meyer auf der Heide, M. Platzner, H. Wachsmuth, and H. Wehrheim, Eds. Paderborn: Heinz Nixdorf Institut, Universität Paderborn, 2023, pp. 165–182.","apa":"Hansmeier, T., Kenter, T., Meyer, M., Riebler, H., Platzner, M., & Plessl, C. (2023). Compute Centers I: Heterogeneous Execution Environments. In C.-J. Haake, F. Meyer auf der Heide, M. Platzner, H. Wachsmuth, & H. Wehrheim (Eds.), On-The-Fly Computing -- Individualized IT-services in dynamic markets (Vol. 412, pp. 165–182). Heinz Nixdorf Institut, Universität Paderborn. https://doi.org/10.5281/zenodo.8068642","bibtex":"@inbook{Hansmeier_Kenter_Meyer_Riebler_Platzner_Plessl_2023, place={Paderborn}, series={Verlagsschriftenreihe des Heinz Nixdorf Instituts}, title={Compute Centers I: Heterogeneous Execution Environments}, volume={412}, DOI={10.5281/zenodo.8068642}, booktitle={On-The-Fly Computing -- Individualized IT-services in dynamic markets}, publisher={Heinz Nixdorf Institut, Universität Paderborn}, author={Hansmeier, Tim and Kenter, Tobias and Meyer, Marius and Riebler, Heinrich and Platzner, Marco and Plessl, Christian}, editor={Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}, year={2023}, pages={165–182}, collection={Verlagsschriftenreihe des Heinz Nixdorf Instituts} }","ama":"Hansmeier T, Kenter T, Meyer M, Riebler H, Platzner M, Plessl C. Compute Centers I: Heterogeneous Execution Environments. In: Haake C-J, Meyer auf der Heide F, Platzner M, Wachsmuth H, Wehrheim H, eds. On-The-Fly Computing -- Individualized IT-Services in Dynamic Markets. Vol 412. Verlagsschriftenreihe des Heinz Nixdorf Instituts. Heinz Nixdorf Institut, Universität Paderborn; 2023:165-182. doi:10.5281/zenodo.8068642","mla":"Hansmeier, Tim, et al. “Compute Centers I: Heterogeneous Execution Environments.” On-The-Fly Computing -- Individualized IT-Services in Dynamic Markets, edited by Claus-Jochen Haake et al., vol. 412, Heinz Nixdorf Institut, Universität Paderborn, 2023, pp. 165–82, doi:10.5281/zenodo.8068642."},"project":[{"_id":"1","grant_number":"160364472","name":"SFB 901: SFB 901: On-The-Fly Computing - Individualisierte IT-Dienstleistungen in dynamischen Märkten "},{"_id":"4","name":"SFB 901 - C: SFB 901 - Project Area C"},{"name":"SFB 901 - C2: SFB 901 - On-The-Fly Compute Centers I: Heterogene Ausführungsumgebungen (Subproject C2)","grant_number":"160364472","_id":"14"}],"page":"165-182","_id":"45893","publisher":"Heinz Nixdorf Institut, Universität Paderborn","user_id":"398","ddc":["004"],"volume":412,"editor":[{"full_name":"Haake, Claus-Jochen","first_name":"Claus-Jochen","last_name":"Haake"},{"first_name":"Friedhelm","last_name":"Meyer auf der Heide","full_name":"Meyer auf der Heide, Friedhelm"},{"first_name":"Marco","last_name":"Platzner","full_name":"Platzner, Marco"},{"full_name":"Wachsmuth, Henning","first_name":"Henning","last_name":"Wachsmuth"},{"full_name":"Wehrheim, Heike","last_name":"Wehrheim","first_name":"Heike"}],"status":"public","has_accepted_license":"1"},{"date_created":"2023-01-23T08:40:42Z","department":[{"_id":"27"},{"_id":"518"}],"keyword":["General Computer Science"],"type":"journal_article","publication":"ACM Transactions on Reconfigurable Technology and Systems","abstract":[{"text":"While FPGA accelerator boards and their respective high-level design tools are maturing, there is still a lack of multi-FPGA applications, libraries, and not least, benchmarks and reference implementations towards sustained HPC usage of these devices. As in the early days of GPUs in HPC, for workloads that can reasonably be decoupled into loosely coupled working sets, multi-accelerator support can be achieved by using standard communication interfaces like MPI on the host side. However, for performance and productivity, some applications can profit from a tighter coupling of the accelerators. FPGAs offer unique opportunities here when extending the dataflow characteristics to their communication interfaces.\r\n In this work, we extend the HPCC FPGA benchmark suite by multi-FPGA support and three missing benchmarks that particularly characterize or stress inter-device communication: b_eff, PTRANS, and LINPACK. With all benchmarks implemented for current boards with Intel and Xilinx FPGAs, we established a baseline for multi-FPGA performance. Additionally, for the communication-centric benchmarks, we explored the potential of direct FPGA-to-FPGA communication with a circuit-switched inter-FPGA network that is currently only available for one of the boards. The evaluation with parallel execution on up to 26 FPGA boards makes use of one of the largest academic FPGA installations.","lang":"eng"}],"language":[{"iso":"eng"}],"main_file_link":[{"open_access":"1","url":"https://dl.acm.org/doi/10.1145/3576200"}],"doi":"10.1145/3576200","author":[{"last_name":"Meyer","first_name":"Marius","full_name":"Meyer, Marius","id":"40778"},{"id":"3145","full_name":"Kenter, Tobias","first_name":"Tobias","last_name":"Kenter"},{"id":"16153","orcid":"0000-0001-5728-9982","first_name":"Christian","last_name":"Plessl","full_name":"Plessl, Christian"}],"publication_identifier":{"issn":["1936-7406","1936-7414"]},"title":"Multi-FPGA Designs and Scaling of HPC Challenge Benchmarks via MPI and Circuit-Switched Inter-FPGA Networks","year":"2023","date_updated":"2023-07-28T08:02:05Z","publication_status":"published","oa":"1","citation":{"mla":"Meyer, Marius, et al. “Multi-FPGA Designs and Scaling of HPC Challenge Benchmarks via MPI and Circuit-Switched Inter-FPGA Networks.” ACM Transactions on Reconfigurable Technology and Systems, Association for Computing Machinery (ACM), 2023, doi:10.1145/3576200.","ama":"Meyer M, Kenter T, Plessl C. Multi-FPGA Designs and Scaling of HPC Challenge Benchmarks via MPI and Circuit-Switched Inter-FPGA Networks. ACM Transactions on Reconfigurable Technology and Systems. Published online 2023. doi:10.1145/3576200","bibtex":"@article{Meyer_Kenter_Plessl_2023, title={Multi-FPGA Designs and Scaling of HPC Challenge Benchmarks via MPI and Circuit-Switched Inter-FPGA Networks}, DOI={10.1145/3576200}, journal={ACM Transactions on Reconfigurable Technology and Systems}, publisher={Association for Computing Machinery (ACM)}, author={Meyer, Marius and Kenter, Tobias and Plessl, Christian}, year={2023} }","apa":"Meyer, M., Kenter, T., & Plessl, C. (2023). Multi-FPGA Designs and Scaling of HPC Challenge Benchmarks via MPI and Circuit-Switched Inter-FPGA Networks. ACM Transactions on Reconfigurable Technology and Systems. https://doi.org/10.1145/3576200","ieee":"M. Meyer, T. Kenter, and C. Plessl, “Multi-FPGA Designs and Scaling of HPC Challenge Benchmarks via MPI and Circuit-Switched Inter-FPGA Networks,” ACM Transactions on Reconfigurable Technology and Systems, 2023, doi: 10.1145/3576200.","short":"M. Meyer, T. Kenter, C. Plessl, ACM Transactions on Reconfigurable Technology and Systems (2023).","chicago":"Meyer, Marius, Tobias Kenter, and Christian Plessl. “Multi-FPGA Designs and Scaling of HPC Challenge Benchmarks via MPI and Circuit-Switched Inter-FPGA Networks.” ACM Transactions on Reconfigurable Technology and Systems, 2023. https://doi.org/10.1145/3576200."},"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"_id":"4","name":"SFB 901 - C: SFB 901 - Project Area C"},{"grant_number":"160364472","_id":"1","name":"SFB 901: SFB 901"},{"grant_number":"160364472","_id":"14","name":"SFB 901 - C2: SFB 901 - Subproject C2"}],"quality_controlled":"1","publisher":"Association for Computing Machinery (ACM)","_id":"38041","user_id":"24135","status":"public"},{"date_updated":"2023-08-02T15:05:42Z","author":[{"id":"77439","first_name":"Xin","last_name":"Wu","full_name":"Wu, Xin"},{"id":"3145","full_name":"Kenter, Tobias","last_name":"Kenter","first_name":"Tobias"},{"last_name":"Schade","first_name":"Robert","orcid":"0000-0002-6268-539","full_name":"Schade, Robert","id":"75963"},{"id":"49079","last_name":"Kühne","first_name":"Thomas","full_name":"Kühne, Thomas"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","first_name":"Christian","full_name":"Plessl, Christian"}],"status":"public","title":"Computing and Compressing Electron Repulsion Integrals on FPGAs","year":"2023","user_id":"75963","doi":"10.1109/FCCM57271.2023.00026","language":[{"iso":"eng"}],"_id":"43228","page":"162-173","main_file_link":[{"url":"https://ieeexplore.ieee.org/document/10171537"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"quality_controlled":"1","abstract":[{"lang":"eng","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."}],"citation":{"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.","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.","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","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} }","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.","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","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."},"publication":"2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","department":[{"_id":"27"},{"_id":"518"}],"type":"conference","date_created":"2023-03-30T11:15:40Z","external_id":{"arxiv":["2303.13632"]}},{"status":"public","publisher":"SAGE Publications","_id":"45361","user_id":"75963","citation":{"bibtex":"@article{Schade_Kenter_Elgabarty_Lass_Kühne_Plessl_2023, title={Breaking the exascale barrier for the electronic structure problem in ab-initio molecular dynamics}, DOI={10.1177/10943420231177631}, number={109434202311776}, journal={The International Journal of High Performance Computing Applications}, publisher={SAGE Publications}, author={Schade, Robert and Kenter, Tobias and Elgabarty, Hossam and Lass, Michael and Kühne, Thomas and Plessl, Christian}, year={2023} }","chicago":"Schade, Robert, Tobias Kenter, Hossam Elgabarty, Michael Lass, Thomas Kühne, and Christian Plessl. “Breaking the Exascale Barrier for the Electronic Structure Problem in Ab-Initio Molecular Dynamics.” The International Journal of High Performance Computing Applications, 2023. https://doi.org/10.1177/10943420231177631.","short":"R. Schade, T. Kenter, H. Elgabarty, M. Lass, T. Kühne, C. Plessl, The International Journal of High Performance Computing Applications (2023).","ama":"Schade R, Kenter T, Elgabarty H, Lass M, Kühne T, Plessl C. Breaking the exascale barrier for the electronic structure problem in ab-initio molecular dynamics. The International Journal of High Performance Computing Applications. Published online 2023. doi:10.1177/10943420231177631","ieee":"R. Schade, T. Kenter, H. Elgabarty, M. Lass, T. Kühne, and C. Plessl, “Breaking the exascale barrier for the electronic structure problem in ab-initio molecular dynamics,” The International Journal of High Performance Computing Applications, Art. no. 109434202311776, 2023, doi: 10.1177/10943420231177631.","mla":"Schade, Robert, et al. “Breaking the Exascale Barrier for the Electronic Structure Problem in Ab-Initio Molecular Dynamics.” The International Journal of High Performance Computing Applications, 109434202311776, SAGE Publications, 2023, doi:10.1177/10943420231177631.","apa":"Schade, R., Kenter, T., Elgabarty, H., Lass, M., Kühne, T., & Plessl, C. (2023). Breaking the exascale barrier for the electronic structure problem in ab-initio molecular dynamics. The International Journal of High Performance Computing Applications, Article 109434202311776. https://doi.org/10.1177/10943420231177631"},"quality_controlled":"1","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"oa":"1","year":"2023","title":"Breaking the exascale barrier for the electronic structure problem in ab-initio molecular dynamics","author":[{"full_name":"Schade, Robert","last_name":"Schade","orcid":"0000-0002-6268-539","first_name":"Robert","id":"75963"},{"id":"3145","last_name":"Kenter","first_name":"Tobias","full_name":"Kenter, Tobias"},{"full_name":"Elgabarty, Hossam","last_name":"Elgabarty","first_name":"Hossam","orcid":"0000-0002-4945-1481","id":"60250"},{"full_name":"Lass, Michael","first_name":"Michael","orcid":"0000-0002-5708-7632","last_name":"Lass","id":"24135"},{"full_name":"Kühne, Thomas","last_name":"Kühne","first_name":"Thomas","id":"49079"},{"first_name":"Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","id":"16153"}],"publication_identifier":{"issn":["1094-3420","1741-2846"]},"date_updated":"2023-08-02T15:04:53Z","publication_status":"published","article_type":"original","main_file_link":[{"url":"https://journals.sagepub.com/doi/10.1177/10943420231177631","open_access":"1"}],"article_number":"109434202311776","language":[{"iso":"eng"}],"doi":"10.1177/10943420231177631","publication":"The International Journal of High Performance Computing Applications","abstract":[{"text":" The non-orthogonal local submatrix method applied to electronic structure–based molecular dynamics simulations is shown to exceed 1.1 EFLOP/s in FP16/FP32-mixed floating-point arithmetic when using 4400 NVIDIA A100 GPUs of the Perlmutter system. This is enabled by a modification of the original method that pushes the sustained fraction of the peak performance to about 80%. Example calculations are performed for SARS-CoV-2 spike proteins with up to 83 million atoms. ","lang":"eng"}],"date_created":"2023-05-30T09:19:09Z","keyword":["Hardware and Architecture","Theoretical Computer Science","Software"],"type":"journal_article","department":[{"_id":"27"},{"_id":"518"}]},{"publication":"Lecture Notes in Computer Science","citation":{"short":"C. Alt, T. Kenter, S. Faghih-Naini, J. Faj, J.-O. Opdenhövel, C. Plessl, V. Aizinger, J. Hönig, H. Köstler, in: Lecture Notes in Computer Science, Springer Nature Switzerland, Cham, 2023.","chicago":"Alt, Christoph, Tobias Kenter, Sara Faghih-Naini, Jennifer Faj, Jan-Oliver Opdenhövel, Christian Plessl, Vadym Aizinger, Jan Hönig, and Harald Köstler. “Shallow Water DG Simulations on FPGAs: Design and Comparison of a Novel Code Generation Pipeline.” In Lecture Notes in Computer Science. Cham: Springer Nature Switzerland, 2023. https://doi.org/10.1007/978-3-031-32041-5_5.","apa":"Alt, C., Kenter, T., Faghih-Naini, S., Faj, J., Opdenhövel, J.-O., Plessl, C., Aizinger, V., Hönig, J., & Köstler, H. (2023). Shallow Water DG Simulations on FPGAs: Design and Comparison of a Novel Code Generation Pipeline. In Lecture Notes in Computer Science. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-32041-5_5","ieee":"C. Alt et al., “Shallow Water DG Simulations on FPGAs: Design and Comparison of a Novel Code Generation Pipeline,” in Lecture Notes in Computer Science, Cham: Springer Nature Switzerland, 2023.","ama":"Alt C, Kenter T, Faghih-Naini S, et al. Shallow Water DG Simulations on FPGAs: Design and Comparison of a Novel Code Generation Pipeline. In: Lecture Notes in Computer Science. Springer Nature Switzerland; 2023. doi:10.1007/978-3-031-32041-5_5","bibtex":"@inbook{Alt_Kenter_Faghih-Naini_Faj_Opdenhövel_Plessl_Aizinger_Hönig_Köstler_2023, place={Cham}, title={Shallow Water DG Simulations on FPGAs: Design and Comparison of a Novel Code Generation Pipeline}, DOI={10.1007/978-3-031-32041-5_5}, booktitle={Lecture Notes in Computer Science}, publisher={Springer Nature Switzerland}, author={Alt, Christoph and Kenter, Tobias and Faghih-Naini, Sara and Faj, Jennifer and Opdenhövel, Jan-Oliver and Plessl, Christian and Aizinger, Vadym and Hönig, Jan and Köstler, Harald}, year={2023} }","mla":"Alt, Christoph, et al. “Shallow Water DG Simulations on FPGAs: Design and Comparison of a Novel Code Generation Pipeline.” Lecture Notes in Computer Science, Springer Nature Switzerland, 2023, doi:10.1007/978-3-031-32041-5_5."},"quality_controlled":"1","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_created":"2023-07-28T09:53:21Z","place":"Cham","type":"book_chapter","department":[{"_id":"27"},{"_id":"518"}],"year":"2023","status":"public","title":"Shallow Water DG Simulations on FPGAs: Design and Comparison of a Novel Code Generation Pipeline","author":[{"id":"100625","last_name":"Alt","first_name":"Christoph","full_name":"Alt, Christoph"},{"id":"3145","last_name":"Kenter","first_name":"Tobias","full_name":"Kenter, Tobias"},{"first_name":"Sara","last_name":"Faghih-Naini","full_name":"Faghih-Naini, Sara"},{"id":"78722","full_name":"Faj, Jennifer","last_name":"Faj","first_name":"Jennifer"},{"last_name":"Opdenhövel","first_name":"Jan-Oliver","orcid":"0000-0003-2314-2784","full_name":"Opdenhövel, Jan-Oliver","id":"73960"},{"id":"16153","orcid":"0000-0001-5728-9982","last_name":"Plessl","first_name":"Christian","full_name":"Plessl, Christian"},{"last_name":"Aizinger","first_name":"Vadym","full_name":"Aizinger, Vadym"},{"last_name":"Hönig","first_name":"Jan","full_name":"Hönig, Jan"},{"full_name":"Köstler, Harald","first_name":"Harald","last_name":"Köstler"}],"publication_identifier":{"issn":["0302-9743","1611-3349"],"isbn":["9783031320408","9783031320415"]},"publication_status":"published","date_updated":"2025-11-04T09:32:49Z","_id":"46191","publisher":"Springer Nature Switzerland","language":[{"iso":"eng"}],"user_id":"3145","doi":"10.1007/978-3-031-32041-5_5"},{"user_id":"3145","doi":"10.1145/3597031.3597050","main_file_link":[{"open_access":"1","url":"https://dl.acm.org/doi/pdf/10.1145/3597031.3597050"}],"publisher":"ACM","_id":"46190","language":[{"iso":"eng"}],"publication_status":"published","date_updated":"2025-11-04T09:32:30Z","title":"Mutation Tree Reconstruction of Tumor Cells on FPGAs Using a Bit-Level Matrix Representation","status":"public","year":"2023","author":[{"id":"73960","orcid":"0000-0003-2314-2784","last_name":"Opdenhövel","first_name":"Jan-Oliver","full_name":"Opdenhövel, Jan-Oliver"},{"id":"16153","full_name":"Plessl, Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982","first_name":"Christian"},{"id":"3145","full_name":"Kenter, Tobias","first_name":"Tobias","last_name":"Kenter"}],"type":"conference","department":[{"_id":"27"},{"_id":"518"}],"oa":"1","date_created":"2023-07-28T09:49:23Z","quality_controlled":"1","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"publication":"Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies (HEART)","citation":{"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 (HEART). https://doi.org/10.1145/3597031.3597050","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 (HEART), ACM, 2023.","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 (HEART). ACM, 2023. https://doi.org/10.1145/3597031.3597050.","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 (HEART), ACM, 2023, doi: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 (HEART). ACM; 2023. doi:10.1145/3597031.3597050","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 (HEART)}, publisher={ACM}, author={Opdenhövel, Jan-Oliver and Plessl, Christian and Kenter, Tobias}, year={2023} }"}},{"date_updated":"2022-07-25T18:14:23Z","author":[{"full_name":"Lass, Michael","last_name":"Lass","first_name":"Michael","orcid":"0000-0002-5708-7632","id":"24135"}],"status":"public","title":"Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations","year":"2022","user_id":"24135","doi":"10.17619/UNIPB/1-1281","publisher":"Universität Paderborn","_id":"32414","language":[{"iso":"eng"}],"citation":{"apa":"Lass, M. (2022). Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations. Universität Paderborn. https://doi.org/10.17619/UNIPB/1-1281","ieee":"M. Lass, Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations. Paderborn: Universität Paderborn, 2022.","chicago":"Lass, Michael. Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations. Paderborn: Universität Paderborn, 2022. https://doi.org/10.17619/UNIPB/1-1281.","short":"M. Lass, Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations, Universität Paderborn, Paderborn, 2022.","mla":"Lass, Michael. Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations. Universität Paderborn, 2022, doi:10.17619/UNIPB/1-1281.","ama":"Lass M. Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations. Universität Paderborn; 2022. doi:10.17619/UNIPB/1-1281","bibtex":"@book{Lass_2022, place={Paderborn}, title={Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations}, DOI={10.17619/UNIPB/1-1281}, publisher={Universität Paderborn}, author={Lass, Michael}, year={2022} }"},"supervisor":[{"first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","full_name":"Plessl, Christian","id":"16153"}],"department":[{"_id":"27"},{"_id":"518"}],"type":"dissertation","date_created":"2022-07-25T18:13:51Z","place":"Paderborn"},{"_id":"33493","language":[{"iso":"eng"}],"user_id":"24135","author":[{"first_name":"Vikram","last_name":"Gavini","full_name":"Gavini, Vikram"},{"first_name":"Stefano","last_name":"Baroni","full_name":"Baroni, Stefano"},{"first_name":"Volker","last_name":"Blum","full_name":"Blum, Volker"},{"first_name":"David R.","last_name":"Bowler","full_name":"Bowler, David R."},{"first_name":"Alexander","last_name":"Buccheri","full_name":"Buccheri, Alexander"},{"full_name":"Chelikowsky, James R.","first_name":"James R.","last_name":"Chelikowsky"},{"full_name":"Das, Sambit","first_name":"Sambit","last_name":"Das"},{"full_name":"Dawson, William","first_name":"William","last_name":"Dawson"},{"last_name":"Delugas","first_name":"Pietro","full_name":"Delugas, Pietro"},{"first_name":"Mehmet","last_name":"Dogan","full_name":"Dogan, Mehmet"},{"full_name":"Draxl, Claudia","last_name":"Draxl","first_name":"Claudia"},{"full_name":"Galli, Giulia","first_name":"Giulia","last_name":"Galli"},{"last_name":"Genovese","first_name":"Luigi","full_name":"Genovese, Luigi"},{"full_name":"Giannozzi, Paolo","last_name":"Giannozzi","first_name":"Paolo"},{"full_name":"Giantomassi, Matteo","last_name":"Giantomassi","first_name":"Matteo"},{"full_name":"Gonze, Xavier","first_name":"Xavier","last_name":"Gonze"},{"full_name":"Govoni, Marco","last_name":"Govoni","first_name":"Marco"},{"full_name":"Gulans, Andris","last_name":"Gulans","first_name":"Andris"},{"last_name":"Gygi","first_name":"François","full_name":"Gygi, François"},{"first_name":"John M.","last_name":"Herbert","full_name":"Herbert, John M."},{"first_name":"Sebastian","last_name":"Kokott","full_name":"Kokott, Sebastian"},{"first_name":"Thomas","last_name":"Kühne","full_name":"Kühne, Thomas","id":"49079"},{"full_name":"Liou, Kai-Hsin","last_name":"Liou","first_name":"Kai-Hsin"},{"full_name":"Miyazaki, Tsuyoshi","first_name":"Tsuyoshi","last_name":"Miyazaki"},{"last_name":"Motamarri","first_name":"Phani","full_name":"Motamarri, Phani"},{"full_name":"Nakata, Ayako","first_name":"Ayako","last_name":"Nakata"},{"full_name":"Pask, John E.","last_name":"Pask","first_name":"John E."},{"id":"16153","full_name":"Plessl, Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982","first_name":"Christian"},{"first_name":"Laura E.","last_name":"Ratcliff","full_name":"Ratcliff, Laura E."},{"last_name":"Richard","first_name":"Ryan M.","full_name":"Richard, Ryan M."},{"full_name":"Rossi, Mariana","last_name":"Rossi","first_name":"Mariana"},{"id":"75963","first_name":"Robert","last_name":"Schade","orcid":"0000-0002-6268-539","full_name":"Schade, Robert"},{"last_name":"Scheffler","first_name":"Matthias","full_name":"Scheffler, Matthias"},{"last_name":"Schütt","first_name":"Ole","full_name":"Schütt, Ole"},{"last_name":"Suryanarayana","first_name":"Phanish","full_name":"Suryanarayana, Phanish"},{"first_name":"Marc","last_name":"Torrent","full_name":"Torrent, Marc"},{"full_name":"Truflandier, Lionel","last_name":"Truflandier","first_name":"Lionel"},{"full_name":"Windus, Theresa L.","last_name":"Windus","first_name":"Theresa L."},{"full_name":"Xu, Qimen","first_name":"Qimen","last_name":"Xu"},{"full_name":"Yu, Victor W. -Z.","first_name":"Victor W. -Z.","last_name":"Yu"},{"full_name":"Perez, Danny","first_name":"Danny","last_name":"Perez"}],"status":"public","title":"Roadmap on Electronic Structure Codes in the Exascale Era","year":"2022","date_updated":"2023-07-28T08:03:41Z","date_created":"2022-09-28T05:25:10Z","external_id":{"arxiv":["2209.12747"]},"department":[{"_id":"27"},{"_id":"518"}],"type":"preprint","citation":{"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} }","ama":"Gavini V, Baroni S, Blum V, et al. Roadmap on Electronic Structure Codes in the Exascale Era. arXiv:220912747. Published online 2022.","ieee":"V. Gavini et al., “Roadmap on Electronic Structure Codes in the Exascale Era,” arXiv:2209.12747. 2022.","apa":"Gavini, V., Baroni, S., Blum, V., Bowler, D. R., Buccheri, A., Chelikowsky, J. R., Das, S., Dawson, W., Delugas, P., Dogan, M., Draxl, C., Galli, G., Genovese, L., Giannozzi, P., Giantomassi, M., Gonze, X., Govoni, M., Gulans, A., Gygi, F., … Perez, D. (2022). Roadmap on Electronic Structure Codes in the Exascale Era. In arXiv:2209.12747.","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.","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)."},"publication":"arXiv:2209.12747","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"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."}]}]