[{"title":"Multi-FPGA Designs and Scaling of HPC Challenge Benchmarks via MPI and Circuit-Switched Inter-FPGA Networks","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"name":"SFB 901 - C: SFB 901 - Project Area C","_id":"4"},{"_id":"1","name":"SFB 901: SFB 901","grant_number":"160364472"},{"name":"SFB 901 - C2: SFB 901 - Subproject C2","grant_number":"160364472","_id":"14"}],"publication_identifier":{"issn":["1936-7406","1936-7414"]},"publication_status":"published","department":[{"_id":"27"},{"_id":"518"}],"oa":"1","doi":"10.1145/3576200","date_updated":"2023-07-28T08:02:05Z","language":[{"iso":"eng"}],"user_id":"24135","abstract":[{"lang":"eng","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."}],"date_created":"2023-01-23T08:40:42Z","status":"public","publication":"ACM Transactions on Reconfigurable Technology and Systems","keyword":["General Computer Science"],"publisher":"Association for Computing Machinery (ACM)","quality_controlled":"1","author":[{"first_name":"Marius","full_name":"Meyer, Marius","last_name":"Meyer","id":"40778"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"}],"_id":"38041","year":"2023","type":"journal_article","citation":{"short":"M. Meyer, T. Kenter, C. Plessl, ACM Transactions on Reconfigurable Technology and Systems (2023).","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.","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.","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","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","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} }","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."},"main_file_link":[{"open_access":"1","url":"https://dl.acm.org/doi/10.1145/3576200"}]},{"type":"book_chapter","citation":{"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.","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.","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} }","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.","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","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","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."},"year":"2023","page":"165-182","_id":"45893","intvolume":" 412","file":[{"date_created":"2023-07-07T08:15:35Z","file_name":"C2-Chapter-SFB-Buch-Final.pdf","access_level":"open_access","creator":"florida","file_id":"45894","file_size":2288788,"relation":"main_file","content_type":"application/pdf","date_updated":"2023-07-07T11:17:33Z"}],"author":[{"first_name":"Tim","orcid":"0000-0003-1377-3339","full_name":"Hansmeier, Tim","last_name":"Hansmeier","id":"49992"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"first_name":"Marius","full_name":"Meyer, Marius","last_name":"Meyer","id":"40778"},{"last_name":"Riebler","id":"8961","first_name":"Heinrich","full_name":"Riebler, Heinrich"},{"full_name":"Platzner, Marco","first_name":"Marco","id":"398","last_name":"Platzner"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"}],"publisher":"Heinz Nixdorf Institut, Universität Paderborn","file_date_updated":"2023-07-07T11:17:33Z","publication":"On-The-Fly Computing -- Individualized IT-services in dynamic markets","has_accepted_license":"1","status":"public","date_created":"2023-07-07T08:15:45Z","volume":412,"user_id":"3145","ddc":["004"],"series_title":"Verlagsschriftenreihe des Heinz Nixdorf Instituts","language":[{"iso":"eng"}],"date_updated":"2023-07-28T09:38:14Z","oa":"1","doi":"10.5281/zenodo.8068642","department":[{"_id":"7"},{"_id":"27"},{"_id":"518"}],"project":[{"name":"SFB 901: SFB 901: On-The-Fly Computing - Individualisierte IT-Dienstleistungen in dynamischen Märkten ","grant_number":"160364472","_id":"1"},{"name":"SFB 901 - C: SFB 901 - Project Area C","_id":"4"},{"name":"SFB 901 - C2: SFB 901 - On-The-Fly Compute Centers I: Heterogene Ausführungsumgebungen (Subproject C2)","grant_number":"160364472","_id":"14"}],"editor":[{"first_name":"Claus-Jochen","full_name":"Haake, Claus-Jochen","last_name":"Haake"},{"full_name":"Meyer auf der Heide, Friedhelm","first_name":"Friedhelm","last_name":"Meyer auf der Heide"},{"full_name":"Platzner, Marco","first_name":"Marco","last_name":"Platzner"},{"last_name":"Wachsmuth","full_name":"Wachsmuth, Henning","first_name":"Henning"},{"full_name":"Wehrheim, Heike","first_name":"Heike","last_name":"Wehrheim"}],"place":"Paderborn","title":"Compute Centers I: Heterogeneous Execution Environments"},{"language":[{"iso":"eng"}],"citation":{"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","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.","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.","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} }","short":"J.-O. Opdenhövel, C. Plessl, T. Kenter, in: Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies, ACM, 2023.","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."},"year":"2023","type":"conference","main_file_link":[{"url":"https://dl.acm.org/doi/pdf/10.1145/3597031.3597050","open_access":"1"}],"oa":"1","doi":"10.1145/3597031.3597050","_id":"46190","date_updated":"2023-07-28T09:58:06Z","date_created":"2023-07-28T09:49:23Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"status":"public","publication_status":"published","publication":"Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies","department":[{"_id":"27"},{"_id":"518"}],"author":[{"full_name":"Opdenhövel, Jan-Oliver","first_name":"Jan-Oliver","last_name":"Opdenhövel"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian"},{"first_name":"Tobias","full_name":"Kenter, Tobias","last_name":"Kenter","id":"3145"}],"quality_controlled":"1","publisher":"ACM","user_id":"3145","title":"Mutation Tree Reconstruction of Tumor Cells on FPGAs Using a Bit-Level Matrix Representation"},{"date_updated":"2023-07-28T09:48:19Z","_id":"46188","doi":"10.1145/3592979.3593407","oa":"1","main_file_link":[{"open_access":"1","url":"https://dl.acm.org/doi/pdf/10.1145/3592979.3593407"}],"year":"2023","type":"conference","citation":{"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.","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.","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} }","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.","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"},"language":[{"iso":"eng"}],"title":"Scalable Multi-FPGA Design of a Discontinuous Galerkin Shallow-Water Model on Unstructured Meshes","user_id":"3145","quality_controlled":"1","author":[{"full_name":"Faj, Jennifer","first_name":"Jennifer","id":"78722","last_name":"Faj"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"full_name":"Faghih-Naini, Sara","first_name":"Sara","last_name":"Faghih-Naini"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"},{"first_name":"Vadym","full_name":"Aizinger, Vadym","last_name":"Aizinger"}],"publisher":"ACM","publication":"Proceedings of the Platform for Advanced Scientific Computing Conference","department":[{"_id":"27"},{"_id":"518"}],"publication_status":"published","status":"public","date_created":"2023-07-28T09:42:14Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}]},{"user_id":"3145","title":"FPGA Acceleration for HPC Supercapacitor Simulations","date_created":"2023-07-28T09:46:25Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"status":"public","publication_status":"published","publication":"Proceedings of the Platform for Advanced Scientific Computing Conference","department":[{"_id":"27"},{"_id":"518"}],"publisher":"ACM","quality_controlled":"1","author":[{"last_name":"Prouveur","full_name":"Prouveur, Charles","first_name":"Charles"},{"last_name":"Haefele","first_name":"Matthieu","full_name":"Haefele, Matthieu"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"first_name":"Nils","full_name":"Voss, Nils","last_name":"Voss"}],"oa":"1","doi":"10.1145/3592979.3593419","date_updated":"2023-07-28T09:58:16Z","_id":"46189","language":[{"iso":"eng"}],"type":"conference","citation":{"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.","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} }","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.","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"},"year":"2023","main_file_link":[{"url":"https://dl.acm.org/doi/pdf/10.1145/3592979.3593419","open_access":"1"}]},{"language":[{"iso":"eng"}],"page":"162-173","year":"2023","type":"conference","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.","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} }","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.","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","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."},"main_file_link":[{"url":"https://ieeexplore.ieee.org/document/10171537"}],"doi":"10.1109/FCCM57271.2023.00026","_id":"43228","date_updated":"2023-08-02T15:05:42Z","date_created":"2023-03-30T11:15:40Z","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"status":"public","department":[{"_id":"27"},{"_id":"518"}],"publication":"2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","quality_controlled":"1","author":[{"id":"77439","last_name":"Wu","full_name":"Wu, Xin","first_name":"Xin"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"last_name":"Schade","id":"75963","first_name":"Robert","orcid":"0000-0002-6268-539","full_name":"Schade, Robert"},{"last_name":"Kühne","id":"49079","first_name":"Thomas","full_name":"Kühne, Thomas"},{"full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian","id":"16153","last_name":"Plessl"}],"user_id":"75963","title":"Computing and Compressing Electron Repulsion Integrals on FPGAs","external_id":{"arxiv":["2303.13632"]},"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"}]},{"article_number":"109434202311776","_id":"45361","citation":{"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","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","short":"R. Schade, T. Kenter, H. Elgabarty, M. Lass, T. Kühne, C. Plessl, The International Journal of High Performance Computing Applications (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.","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.","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} }","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."},"year":"2023","type":"journal_article","main_file_link":[{"open_access":"1","url":"https://journals.sagepub.com/doi/10.1177/10943420231177631"}],"user_id":"75963","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"}],"article_type":"original","date_created":"2023-05-30T09:19:09Z","status":"public","keyword":["Hardware and Architecture","Theoretical Computer Science","Software"],"publication":"The International Journal of High Performance Computing Applications","author":[{"first_name":"Robert","orcid":"0000-0002-6268-539","full_name":"Schade, Robert","last_name":"Schade","id":"75963"},{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"first_name":"Hossam","orcid":"0000-0002-4945-1481","full_name":"Elgabarty, Hossam","last_name":"Elgabarty","id":"60250"},{"id":"24135","last_name":"Lass","full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","first_name":"Michael"},{"first_name":"Thomas","full_name":"Kühne, Thomas","last_name":"Kühne","id":"49079"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"}],"quality_controlled":"1","publisher":"SAGE Publications","oa":"1","doi":"10.1177/10943420231177631","date_updated":"2023-08-02T15:04:53Z","language":[{"iso":"eng"}],"title":"Breaking the exascale barrier for the electronic structure problem in ab-initio molecular dynamics","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"publication_status":"published","publication_identifier":{"issn":["1094-3420","1741-2846"]},"department":[{"_id":"27"},{"_id":"518"}]},{"doi":"10.1007/978-3-031-32041-5_5","_id":"46191","date_updated":"2024-01-22T09:58:49Z","type":"book_chapter","year":"2023","citation":{"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","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.","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","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.","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.","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."},"language":[{"iso":"eng"}],"title":"Shallow Water DG Simulations on FPGAs: Design and Comparison of a Novel Code Generation Pipeline","user_id":"3145","place":"Cham","publication_identifier":{"issn":["0302-9743","1611-3349"],"isbn":["9783031320408","9783031320415"]},"publication_status":"published","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_created":"2023-07-28T09:53:21Z","status":"public","department":[{"_id":"27"},{"_id":"518"}],"publication":"Lecture Notes in Computer Science","author":[{"id":"100625","last_name":"Alt","full_name":"Alt, Christoph","first_name":"Christoph"},{"first_name":"Tobias","full_name":"Kenter, Tobias","last_name":"Kenter","id":"3145"},{"last_name":"Faghih-Naini","full_name":"Faghih-Naini, Sara","first_name":"Sara"},{"last_name":"Faj","id":"78722","first_name":"Jennifer","full_name":"Faj, Jennifer"},{"first_name":"Jan-Oliver","full_name":"Opdenhövel, Jan-Oliver","last_name":"Opdenhövel"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"},{"full_name":"Aizinger, Vadym","first_name":"Vadym","last_name":"Aizinger"},{"first_name":"Jan","full_name":"Hönig, Jan","last_name":"Hönig"},{"first_name":"Harald","full_name":"Köstler, Harald","last_name":"Köstler"}],"quality_controlled":"1","publisher":"Springer Nature Switzerland"},{"date_created":"2023-04-08T11:05:29Z","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"status":"public","publication":"arXiv:2304.03039","department":[{"_id":"27"},{"_id":"518"}],"author":[{"last_name":"Van Hirtum","full_name":"Van Hirtum, Lennart","first_name":"Lennart"},{"last_name":"De Causmaecker","full_name":"De Causmaecker, Patrick","first_name":"Patrick"},{"first_name":"Jens","full_name":"Goemaere, Jens","last_name":"Goemaere"},{"last_name":"Kenter","id":"3145","first_name":"Tobias","full_name":"Kenter, Tobias"},{"last_name":"Riebler","id":"8961","first_name":"Heinrich","full_name":"Riebler, Heinrich"},{"orcid":"0000-0002-5708-7632","full_name":"Lass, Michael","first_name":"Michael","id":"24135","last_name":"Lass"},{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"}],"user_id":"3145","title":"A computation of D(9) using FPGA Supercomputing","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."}],"language":[{"iso":"eng"}],"type":"preprint","year":"2023","citation":{"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.","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.","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.","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)."},"date_updated":"2024-01-22T09:56:42Z","_id":"43439"},{"publisher":"Universität Paderborn","author":[{"full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","first_name":"Michael","id":"24135","last_name":"Lass"}],"department":[{"_id":"27"},{"_id":"518"}],"status":"public","date_created":"2022-07-25T18:13:51Z","place":"Paderborn","title":"Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations","user_id":"24135","type":"dissertation","year":"2022","citation":{"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","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","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.","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.","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} }","short":"M. Lass, Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations, Universität Paderborn, Paderborn, 2022.","ieee":"M. Lass, Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations. Paderborn: Universität Paderborn, 2022."},"language":[{"iso":"eng"}],"supervisor":[{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"_id":"32414","date_updated":"2022-07-25T18:14:23Z","doi":"10.17619/UNIPB/1-1281"}]