[{"department":[{"_id":"27"}],"user_id":"75963","_id":"62034","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"language":[{"iso":"eng"}],"article_number":"132501","publication":"The Journal of Chemical Physics","type":"journal_article","status":"public","abstract":[{"text":"Effective single-particle theories, such as Hartree–Fock, density functional theory, and tight-binding, are limited by the computational cost of the self-consistent field (SCF) procedure, which typically scales cubically with the system size. This makes large-scale applications impractical without specialized algorithms and hardware. Here, we present the submatrix and graphical processing unit (GPU)-accelerated software implementation of the PTB tight-binding potential, realized in the open-source ptb codebase [M. Mueller, A. Katbashev, and S. Ehlert (2025). “grimme-lab/ptb: v3.8.1,” Zenodo. https://zenodo.org/records/17015872]. We first benchmark a traditional diagonalization-based SCF solver against density-matrix-based purification approaches, systematically varying both system size and computer hardware. Our findings show that the usage of GPUs permits shifting the boundaries to much larger systems than previously thought feasible, achieving an overall 10–15-fold performance speedup. Second, we introduce the implementation of a decomposition-type submatrix method, specifically designed for efficient operation on mid- to large-sized systems, to address the computational overhead associated with full-system diagonalization. We demonstrate that, from a certain dimension (≈104 basis functions) on, our submatrix method reduces the overall computational cost while maintaining acceptable numerical accuracy. Our study demonstrates the significance of the interplay between modern hardware, algorithmic considerations, and novel tight-binding methods, paving the way for further development in this direction.","lang":"eng"}],"volume":163,"author":[{"first_name":"Abylay","full_name":"Katbashev, Abylay","last_name":"Katbashev"},{"first_name":"Robert","id":"75963","full_name":"Schade, Robert","orcid":"0000-0002-6268-5397","last_name":"Schade"},{"id":"24135","full_name":"Laß, Michael","last_name":"Laß","orcid":"0000-0002-5708-7632","first_name":"Michael"},{"last_name":"Müller","full_name":"Müller, Marcel","first_name":"Marcel"},{"first_name":"Stefan","full_name":"Grimme, Stefan","last_name":"Grimme"},{"full_name":"Hansen, Andreas","last_name":"Hansen","first_name":"Andreas"},{"first_name":"Thomas","last_name":"Kühne","full_name":"Kühne, Thomas","id":"49079"}],"date_created":"2025-11-01T00:41:50Z","date_updated":"2025-11-01T00:43:19Z","publisher":"AIP Publishing","doi":"10.1063/5.0271379","title":"Submatrix and GPU-accelerated implementation of density matrix tight-binding","issue":"13","publication_identifier":{"issn":["0021-9606","1089-7690"]},"publication_status":"published","intvolume":"       163","citation":{"ieee":"A. Katbashev <i>et al.</i>, “Submatrix and GPU-accelerated implementation of density matrix tight-binding,” <i>The Journal of Chemical Physics</i>, vol. 163, no. 13, Art. no. 132501, 2025, doi: <a href=\"https://doi.org/10.1063/5.0271379\">10.1063/5.0271379</a>.","chicago":"Katbashev, Abylay, Robert Schade, Michael Laß, Marcel Müller, Stefan Grimme, Andreas Hansen, and Thomas Kühne. “Submatrix and GPU-Accelerated Implementation of Density Matrix Tight-Binding.” <i>The Journal of Chemical Physics</i> 163, no. 13 (2025). <a href=\"https://doi.org/10.1063/5.0271379\">https://doi.org/10.1063/5.0271379</a>.","ama":"Katbashev A, Schade R, Laß M, et al. Submatrix and GPU-accelerated implementation of density matrix tight-binding. <i>The Journal of Chemical Physics</i>. 2025;163(13). doi:<a href=\"https://doi.org/10.1063/5.0271379\">10.1063/5.0271379</a>","mla":"Katbashev, Abylay, et al. “Submatrix and GPU-Accelerated Implementation of Density Matrix Tight-Binding.” <i>The Journal of Chemical Physics</i>, vol. 163, no. 13, 132501, AIP Publishing, 2025, doi:<a href=\"https://doi.org/10.1063/5.0271379\">10.1063/5.0271379</a>.","bibtex":"@article{Katbashev_Schade_Laß_Müller_Grimme_Hansen_Kühne_2025, title={Submatrix and GPU-accelerated implementation of density matrix tight-binding}, volume={163}, DOI={<a href=\"https://doi.org/10.1063/5.0271379\">10.1063/5.0271379</a>}, number={13132501}, journal={The Journal of Chemical Physics}, publisher={AIP Publishing}, author={Katbashev, Abylay and Schade, Robert and Laß, Michael and Müller, Marcel and Grimme, Stefan and Hansen, Andreas and Kühne, Thomas}, year={2025} }","short":"A. Katbashev, R. Schade, M. Laß, M. Müller, S. Grimme, A. Hansen, T. Kühne, The Journal of Chemical Physics 163 (2025).","apa":"Katbashev, A., Schade, R., Laß, M., Müller, M., Grimme, S., Hansen, A., &#38; Kühne, T. (2025). Submatrix and GPU-accelerated implementation of density matrix tight-binding. <i>The Journal of Chemical Physics</i>, <i>163</i>(13), Article 132501. <a href=\"https://doi.org/10.1063/5.0271379\">https://doi.org/10.1063/5.0271379</a>"},"year":"2025"},{"type":"journal_article","publication":"Entropy","abstract":[{"text":"We present a novel approach to characterize and quantify microheterogeneity and microphase separation in computer simulations of complex liquid mixtures. Our post-processing method is based on local density fluctuations of the different constituents in sampling spheres of varying size. It can be easily applied to both molecular dynamics (MD) and Monte Carlo (MC) simulations, including periodic boundary conditions. Multidimensional correlation of the density distributions yields a clear picture of the domain formation due to the subtle balance of different interactions. We apply our approach to the example of force field molecular dynamics simulations of imidazolium-based ionic liquids with different side chain lengths at different temperatures, namely 1-ethyl-3-methylimidazolium chloride, 1-hexyl-3-methylimidazolium chloride, and 1-decyl-3-methylimidazolium chloride, which are known to form distinct liquid domains. We put the results into the context of existing microheterogeneity analyses and demonstrate the advantages and sensitivity of our novel method. Furthermore, we show how to estimate the configuration entropy from our analysis, and we investigate voids in the system. The analysis has been implemented into our program package TRAVIS and is thus available as free software.","lang":"eng"}],"status":"public","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"_id":"53474","user_id":"24135","department":[{"_id":"27"},{"_id":"518"},{"_id":"803"}],"article_number":"322","language":[{"iso":"eng"}],"publication_status":"published","publication_identifier":{"issn":["1099-4300"]},"issue":"4","year":"2024","citation":{"apa":"Lass, M., Kenter, T., Plessl, C., &#38; Brehm, M. (2024). Characterizing Microheterogeneity in Liquid Mixtures via Local Density Fluctuations. <i>Entropy</i>, <i>26</i>(4), Article 322. <a href=\"https://doi.org/10.3390/e26040322\">https://doi.org/10.3390/e26040322</a>","mla":"Lass, Michael, et al. “Characterizing Microheterogeneity in Liquid Mixtures via Local Density Fluctuations.” <i>Entropy</i>, vol. 26, no. 4, 322, MDPI AG, 2024, doi:<a href=\"https://doi.org/10.3390/e26040322\">10.3390/e26040322</a>.","short":"M. Lass, T. Kenter, C. Plessl, M. Brehm, Entropy 26 (2024).","bibtex":"@article{Lass_Kenter_Plessl_Brehm_2024, title={Characterizing Microheterogeneity in Liquid Mixtures via Local Density Fluctuations}, volume={26}, DOI={<a href=\"https://doi.org/10.3390/e26040322\">10.3390/e26040322</a>}, number={4322}, journal={Entropy}, publisher={MDPI AG}, author={Lass, Michael and Kenter, Tobias and Plessl, Christian and Brehm, Martin}, year={2024} }","chicago":"Lass, Michael, Tobias Kenter, Christian Plessl, and Martin Brehm. “Characterizing Microheterogeneity in Liquid Mixtures via Local Density Fluctuations.” <i>Entropy</i> 26, no. 4 (2024). <a href=\"https://doi.org/10.3390/e26040322\">https://doi.org/10.3390/e26040322</a>.","ieee":"M. Lass, T. Kenter, C. Plessl, and M. Brehm, “Characterizing Microheterogeneity in Liquid Mixtures via Local Density Fluctuations,” <i>Entropy</i>, vol. 26, no. 4, Art. no. 322, 2024, doi: <a href=\"https://doi.org/10.3390/e26040322\">10.3390/e26040322</a>.","ama":"Lass M, Kenter T, Plessl C, Brehm M. Characterizing Microheterogeneity in Liquid Mixtures via Local Density Fluctuations. <i>Entropy</i>. 2024;26(4). doi:<a href=\"https://doi.org/10.3390/e26040322\">10.3390/e26040322</a>"},"intvolume":"        26","publisher":"MDPI AG","date_updated":"2024-04-12T18:34:32Z","date_created":"2024-04-12T18:31:39Z","author":[{"first_name":"Michael","last_name":"Lass","orcid":"0000-0002-5708-7632","id":"24135","full_name":"Lass, Michael"},{"last_name":"Kenter","full_name":"Kenter, Tobias","id":"3145","first_name":"Tobias"},{"orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153","full_name":"Plessl, Christian","first_name":"Christian"},{"first_name":"Martin","last_name":"Brehm","full_name":"Brehm, Martin","id":"100167"}],"volume":26,"title":"Characterizing Microheterogeneity in Liquid Mixtures via Local Density Fluctuations","doi":"10.3390/e26040322"},{"language":[{"iso":"eng"}],"ddc":["004"],"keyword":["Noctua 2","Supercomputer","FPGA","PC2","Paderborn Center for Parallel Computing"],"file":[{"relation":"main_file","content_type":"application/pdf","access_level":"open_access","file_name":"Noctua2_Supercomputer.pdf","file_id":"53664","file_size":3825480,"creator":"deffel","date_created":"2024-04-26T07:30:20Z","date_updated":"2024-04-26T08:35:17Z"}],"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."}],"publication":"Journal of large-scale research facilities","title":"Noctua 2 Supercomputer","date_created":"2024-04-26T07:39:41Z","year":"2024","file_date_updated":"2024-04-26T08:35:17Z","article_type":"original","user_id":"8961","department":[{"_id":"27"},{"_id":"518"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"53663","status":"public","type":"journal_article","doi":"10.17815/jlsrf-8-187 ","author":[{"first_name":"Carsten","last_name":"Bauer","id":"90082","full_name":"Bauer, Carsten"},{"last_name":"Kenter","id":"3145","full_name":"Kenter, Tobias","first_name":"Tobias"},{"orcid":"0000-0002-5708-7632","last_name":"Lass","full_name":"Lass, Michael","id":"24135","first_name":"Michael"},{"first_name":"Lukas","id":"90492","full_name":"Mazur, Lukas","last_name":"Mazur","orcid":" 0000-0001-6304-7082"},{"first_name":"Marius","last_name":"Meyer","full_name":"Meyer, Marius","id":"40778"},{"first_name":"Holger","id":"15272","full_name":"Nitsche, Holger","last_name":"Nitsche"},{"first_name":"Heinrich","id":"8961","full_name":"Riebler, Heinrich","last_name":"Riebler"},{"first_name":"Robert","last_name":"Schade","orcid":"0000-0002-6268-5397","id":"75963","full_name":"Schade, Robert"},{"first_name":"Michael","last_name":"Schwarz","id":"5312","full_name":"Schwarz, Michael"},{"full_name":"Winnwa, Nils","id":"61189","last_name":"Winnwa","first_name":"Nils"},{"last_name":"Wiens","orcid":"0000-0003-1764-9773","full_name":"Wiens, Alex","id":"23522","first_name":"Alex"},{"full_name":"Wu, Xin","id":"77439","last_name":"Wu","first_name":"Xin"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153","full_name":"Plessl, Christian"},{"first_name":"Jens","id":"15273","full_name":"Simon, Jens","last_name":"Simon"}],"volume":9,"date_updated":"2024-04-26T08:44:30Z","oa":"1","citation":{"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., &#38; Simon, J. (2024). Noctua 2 Supercomputer. <i>Journal of Large-Scale Research Facilities</i>, <i>9</i>. <a href=\"https://doi.org/10.17815/jlsrf-8-187 \">https://doi.org/10.17815/jlsrf-8-187 </a>","mla":"Bauer, Carsten, et al. “Noctua 2 Supercomputer.” <i>Journal of Large-Scale Research Facilities</i>, vol. 9, 2024, doi:<a href=\"https://doi.org/10.17815/jlsrf-8-187 \">10.17815/jlsrf-8-187 </a>.","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).","bibtex":"@article{Bauer_Kenter_Lass_Mazur_Meyer_Nitsche_Riebler_Schade_Schwarz_Winnwa_et al._2024, title={Noctua 2 Supercomputer}, volume={9}, DOI={<a href=\"https://doi.org/10.17815/jlsrf-8-187 \">10.17815/jlsrf-8-187 </a>}, 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} }","ieee":"C. Bauer <i>et al.</i>, “Noctua 2 Supercomputer,” <i>Journal of large-scale research facilities</i>, vol. 9, 2024, doi: <a href=\"https://doi.org/10.17815/jlsrf-8-187 \">10.17815/jlsrf-8-187 </a>.","chicago":"Bauer, Carsten, Tobias Kenter, Michael Lass, Lukas Mazur, Marius Meyer, Holger Nitsche, Heinrich Riebler, et al. “Noctua 2 Supercomputer.” <i>Journal of Large-Scale Research Facilities</i> 9 (2024). <a href=\"https://doi.org/10.17815/jlsrf-8-187 \">https://doi.org/10.17815/jlsrf-8-187 </a>.","ama":"Bauer C, Kenter T, Lass M, et al. Noctua 2 Supercomputer. <i>Journal of large-scale research facilities</i>. 2024;9. doi:<a href=\"https://doi.org/10.17815/jlsrf-8-187 \">10.17815/jlsrf-8-187 </a>"},"intvolume":"         9","publication_status":"published","has_accepted_license":"1"},{"department":[{"_id":"27"},{"_id":"518"}],"user_id":"3145","_id":"56604","project":[{"name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"type":"journal_article","status":"public","volume":17,"author":[{"last_name":"Van Hirtum","full_name":"Van Hirtum, Lennart","id":"100210","first_name":"Lennart"},{"full_name":"De Causmaecker, Patrick","last_name":"De Causmaecker","first_name":"Patrick"},{"first_name":"Jens","last_name":"Goemaere","full_name":"Goemaere, Jens"},{"first_name":"Tobias","last_name":"Kenter","id":"3145","full_name":"Kenter, Tobias"},{"first_name":"Heinrich","last_name":"Riebler","id":"8961","full_name":"Riebler, Heinrich"},{"id":"24135","full_name":"Lass, Michael","last_name":"Lass","orcid":"0000-0002-5708-7632","first_name":"Michael"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153","full_name":"Plessl, Christian"}],"oa":"1","date_updated":"2025-11-04T09:53:26Z","doi":"10.1145/3674147","main_file_link":[{"open_access":"1"}],"publication_identifier":{"issn":["1936-7406","1936-7414"]},"publication_status":"published","page":"1-28","intvolume":"        17","citation":{"ama":"Van Hirtum L, De Causmaecker P, Goemaere J, et al. A Computation of the Ninth Dedekind Number Using FPGA Supercomputing. <i>ACM Transactions on Reconfigurable Technology and Systems</i>. 2024;17(3):1-28. doi:<a href=\"https://doi.org/10.1145/3674147\">10.1145/3674147</a>","ieee":"L. Van Hirtum <i>et al.</i>, “A Computation of the Ninth Dedekind Number Using FPGA Supercomputing,” <i>ACM Transactions on Reconfigurable Technology and Systems</i>, vol. 17, no. 3, pp. 1–28, 2024, doi: <a href=\"https://doi.org/10.1145/3674147\">10.1145/3674147</a>.","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.” <i>ACM Transactions on Reconfigurable Technology and Systems</i> 17, no. 3 (2024): 1–28. <a href=\"https://doi.org/10.1145/3674147\">https://doi.org/10.1145/3674147</a>.","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.","mla":"Van Hirtum, Lennart, et al. “A Computation of the Ninth Dedekind Number Using FPGA Supercomputing.” <i>ACM Transactions on Reconfigurable Technology and Systems</i>, vol. 17, no. 3, Association for Computing Machinery (ACM), 2024, pp. 1–28, doi:<a href=\"https://doi.org/10.1145/3674147\">10.1145/3674147</a>.","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={<a href=\"https://doi.org/10.1145/3674147\">10.1145/3674147</a>}, 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} }","apa":"Van Hirtum, L., De Causmaecker, P., Goemaere, J., Kenter, T., Riebler, H., Lass, M., &#38; Plessl, C. (2024). A Computation of the Ninth Dedekind Number Using FPGA Supercomputing. <i>ACM Transactions on Reconfigurable Technology and Systems</i>, <i>17</i>(3), 1–28. <a href=\"https://doi.org/10.1145/3674147\">https://doi.org/10.1145/3674147</a>"},"language":[{"iso":"eng"}],"publication":"ACM Transactions on Reconfigurable Technology and Systems","abstract":[{"lang":"eng","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."}],"date_created":"2024-10-14T07:38:29Z","publisher":"Association for Computing Machinery (ACM)","title":"A Computation of the Ninth Dedekind Number Using FPGA Supercomputing","issue":"3","quality_controlled":"1","year":"2024"},{"department":[{"_id":"27"},{"_id":"623"},{"_id":"15"}],"user_id":"55629","_id":"53202","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"_id":"239","name":"ERC-Grant: QuESADILLA: Quantum Engineering Superconducting Array Detectors in Low-Light Applications"},{"_id":"191","name":"PhoQuant: Photonische Quantencomputer -  Quantencomputing Testplattform"}],"status":"public","type":"journal_article","doi":"10.1088/2058-9565/ad8511","main_file_link":[{"open_access":"1"}],"volume":10,"author":[{"first_name":"Timon","full_name":"Schapeler, Timon","id":"55629","last_name":"Schapeler","orcid":"0000-0001-7652-1716"},{"first_name":"Robert","orcid":"0000-0002-6268-5397","last_name":"Schade","full_name":"Schade, Robert","id":"75963"},{"id":"24135","full_name":"Lass, Michael","last_name":"Lass","orcid":"0000-0002-5708-7632","first_name":"Michael"},{"first_name":"Christian","full_name":"Plessl, Christian","id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982"},{"first_name":"Tim","last_name":"Bartley","full_name":"Bartley, Tim","id":"49683"}],"date_updated":"2025-12-16T11:32:12Z","oa":"1","intvolume":"        10","citation":{"apa":"Schapeler, T., Schade, R., Lass, M., Plessl, C., &#38; Bartley, T. (2024). Scalable quantum detector tomography by high-performance computing. <i>Quantum Science and Technology</i>, <i>10</i>(1). <a href=\"https://doi.org/10.1088/2058-9565/ad8511\">https://doi.org/10.1088/2058-9565/ad8511</a>","mla":"Schapeler, Timon, et al. “Scalable Quantum Detector Tomography by High-Performance Computing.” <i>Quantum Science and Technology</i>, vol. 10, no. 1, IOP Publishing, 2024, doi:<a href=\"https://doi.org/10.1088/2058-9565/ad8511\">10.1088/2058-9565/ad8511</a>.","short":"T. Schapeler, R. Schade, M. Lass, C. Plessl, T. Bartley, Quantum Science and Technology 10 (2024).","bibtex":"@article{Schapeler_Schade_Lass_Plessl_Bartley_2024, title={Scalable quantum detector tomography by high-performance computing}, volume={10}, DOI={<a href=\"https://doi.org/10.1088/2058-9565/ad8511\">10.1088/2058-9565/ad8511</a>}, number={1}, journal={Quantum Science and Technology}, publisher={IOP Publishing}, author={Schapeler, Timon and Schade, Robert and Lass, Michael and Plessl, Christian and Bartley, Tim}, year={2024} }","ama":"Schapeler T, Schade R, Lass M, Plessl C, Bartley T. Scalable quantum detector tomography by high-performance computing. <i>Quantum Science and Technology</i>. 2024;10(1). doi:<a href=\"https://doi.org/10.1088/2058-9565/ad8511\">10.1088/2058-9565/ad8511</a>","ieee":"T. Schapeler, R. Schade, M. Lass, C. Plessl, and T. Bartley, “Scalable quantum detector tomography by high-performance computing,” <i>Quantum Science and Technology</i>, vol. 10, no. 1, 2024, doi: <a href=\"https://doi.org/10.1088/2058-9565/ad8511\">10.1088/2058-9565/ad8511</a>.","chicago":"Schapeler, Timon, Robert Schade, Michael Lass, Christian Plessl, and Tim Bartley. “Scalable Quantum Detector Tomography by High-Performance Computing.” <i>Quantum Science and Technology</i> 10, no. 1 (2024). <a href=\"https://doi.org/10.1088/2058-9565/ad8511\">https://doi.org/10.1088/2058-9565/ad8511</a>."},"language":[{"iso":"eng"}],"external_id":{"arxiv":["2404.02844"]},"abstract":[{"text":"At large scales, quantum systems may become advantageous over their classical counterparts at performing certain tasks. Developing tools to analyze these systems at the relevant scales, in a manner consistent with quantum mechanics, is therefore critical to benchmarking performance and characterizing their operation. While classical computational approaches cannot perform like-for-like computations of quantum systems beyond a certain scale, classical high-performance computing (HPC) may nevertheless be useful for precisely these characterization and certification tasks. By developing open-source customized algorithms using high-performance computing, we perform quantum tomography on a megascale quantum photonic detector covering a Hilbert space of 106. This requires finding 108 elements of the matrix corresponding to the positive operator valued measure (POVM), the quantum description of the detector, and is achieved in minutes of computation time. Moreover, by exploiting the structure of the problem, we achieve highly efficient parallel scaling, paving the way for quantum objects up to a system size of 1012 elements to be reconstructed using this method. In general, this shows that a consistent quantum mechanical description of quantum phenomena is applicable at everyday scales. More concretely, this enables the reconstruction of large-scale quantum sources, processes and detectors used in computation and sampling tasks, which may be necessary to prove their nonclassical character or quantum computational advantage.","lang":"eng"}],"publication":"Quantum Science and Technology","title":"Scalable quantum detector tomography by high-performance computing","date_created":"2024-04-04T08:43:18Z","publisher":"IOP Publishing","year":"2024","issue":"1"},{"citation":{"ama":"Van Hirtum L, De Causmaecker P, Goemaere J, et al. A computation of D(9) using FPGA Supercomputing. <i>arXiv:230403039</i>. Published online 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.” <i>ArXiv:2304.03039</i>, 2023.","ieee":"L. Van Hirtum <i>et al.</i>, “A computation of D(9) using FPGA Supercomputing,” <i>arXiv:2304.03039</i>. 2023.","apa":"Van Hirtum, L., De Causmaecker, P., Goemaere, J., Kenter, T., Riebler, H., Lass, M., &#38; Plessl, C. (2023). A computation of D(9) using FPGA Supercomputing. In <i>arXiv:2304.03039</i>.","short":"L. Van Hirtum, P. De Causmaecker, J. Goemaere, T. Kenter, H. Riebler, M. Lass, C. Plessl, ArXiv:2304.03039 (2023).","mla":"Van Hirtum, Lennart, et al. “A Computation of D(9) Using FPGA Supercomputing.” <i>ArXiv:2304.03039</i>, 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} }"},"year":"2023","author":[{"first_name":"Lennart","full_name":"Van Hirtum, Lennart","last_name":"Van Hirtum"},{"first_name":"Patrick","full_name":"De Causmaecker, Patrick","last_name":"De Causmaecker"},{"first_name":"Jens","last_name":"Goemaere","full_name":"Goemaere, Jens"},{"first_name":"Tobias","last_name":"Kenter","full_name":"Kenter, Tobias","id":"3145"},{"first_name":"Heinrich","last_name":"Riebler","full_name":"Riebler, Heinrich","id":"8961"},{"last_name":"Lass","orcid":"0000-0002-5708-7632","id":"24135","full_name":"Lass, Michael","first_name":"Michael"},{"id":"16153","full_name":"Plessl, Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"date_created":"2023-04-08T11:05:29Z","date_updated":"2024-01-22T09:56:42Z","title":"A computation of D(9) using FPGA Supercomputing","type":"preprint","publication":"arXiv:2304.03039","status":"public","abstract":[{"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.","lang":"eng"}],"user_id":"3145","department":[{"_id":"27"},{"_id":"518"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"43439","external_id":{"arxiv":["2304.03039"]},"language":[{"iso":"eng"}]},{"date_created":"2023-05-30T09:19:09Z","publisher":"SAGE Publications","title":"Breaking the exascale barrier for the electronic structure problem in ab-initio molecular dynamics","quality_controlled":"1","year":"2023","language":[{"iso":"eng"}],"keyword":["Hardware and Architecture","Theoretical Computer Science","Software"],"publication":"The International Journal of High Performance Computing Applications","abstract":[{"text":"<jats:p> 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. </jats:p>","lang":"eng"}],"author":[{"first_name":"Robert","last_name":"Schade","orcid":"0000-0002-6268-539","id":"75963","full_name":"Schade, Robert"},{"last_name":"Kenter","id":"3145","full_name":"Kenter, Tobias","first_name":"Tobias"},{"first_name":"Hossam","full_name":"Elgabarty, Hossam","id":"60250","orcid":"0000-0002-4945-1481","last_name":"Elgabarty"},{"id":"24135","full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","last_name":"Lass","first_name":"Michael"},{"last_name":"Kühne","id":"49079","full_name":"Kühne, Thomas","first_name":"Thomas"},{"first_name":"Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","id":"16153"}],"date_updated":"2023-08-02T15:04:53Z","oa":"1","main_file_link":[{"open_access":"1","url":"https://journals.sagepub.com/doi/10.1177/10943420231177631"}],"doi":"10.1177/10943420231177631","publication_status":"published","publication_identifier":{"issn":["1094-3420","1741-2846"]},"citation":{"apa":"Schade, R., Kenter, T., Elgabarty, H., Lass, M., Kühne, T., &#38; Plessl, C. (2023). Breaking the exascale barrier for the electronic structure problem in ab-initio molecular dynamics. <i>The International Journal of High Performance Computing Applications</i>, Article 109434202311776. <a href=\"https://doi.org/10.1177/10943420231177631\">https://doi.org/10.1177/10943420231177631</a>","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. <i>The International Journal of High Performance Computing Applications</i>. Published online 2023. doi:<a href=\"https://doi.org/10.1177/10943420231177631\">10.1177/10943420231177631</a>","short":"R. Schade, T. Kenter, H. Elgabarty, M. Lass, T. Kühne, C. Plessl, The International Journal of High Performance Computing Applications (2023).","mla":"Schade, Robert, et al. “Breaking the Exascale Barrier for the Electronic Structure Problem in Ab-Initio Molecular Dynamics.” <i>The International Journal of High Performance Computing Applications</i>, 109434202311776, SAGE Publications, 2023, doi:<a href=\"https://doi.org/10.1177/10943420231177631\">10.1177/10943420231177631</a>.","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={<a href=\"https://doi.org/10.1177/10943420231177631\">10.1177/10943420231177631</a>}, 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.” <i>The International Journal of High Performance Computing Applications</i>, 2023. <a href=\"https://doi.org/10.1177/10943420231177631\">https://doi.org/10.1177/10943420231177631</a>.","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,” <i>The International Journal of High Performance Computing Applications</i>, Art. no. 109434202311776, 2023, doi: <a href=\"https://doi.org/10.1177/10943420231177631\">10.1177/10943420231177631</a>."},"user_id":"75963","department":[{"_id":"27"},{"_id":"518"}],"project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"45361","article_number":"109434202311776","article_type":"original","type":"journal_article","status":"public"},{"status":"public","type":"dissertation","language":[{"iso":"eng"}],"_id":"32414","department":[{"_id":"27"},{"_id":"518"}],"user_id":"24135","place":"Paderborn","year":"2022","citation":{"chicago":"Lass, Michael. <i>Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations</i>. Paderborn: Universität Paderborn, 2022. <a href=\"https://doi.org/10.17619/UNIPB/1-1281\">https://doi.org/10.17619/UNIPB/1-1281</a>.","ieee":"M. Lass, <i>Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations</i>. Paderborn: Universität Paderborn, 2022.","ama":"Lass M. <i>Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations</i>. Universität Paderborn; 2022. doi:<a href=\"https://doi.org/10.17619/UNIPB/1-1281\">10.17619/UNIPB/1-1281</a>","bibtex":"@book{Lass_2022, place={Paderborn}, title={Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations}, DOI={<a href=\"https://doi.org/10.17619/UNIPB/1-1281\">10.17619/UNIPB/1-1281</a>}, 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.","mla":"Lass, Michael. <i>Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations</i>. Universität Paderborn, 2022, doi:<a href=\"https://doi.org/10.17619/UNIPB/1-1281\">10.17619/UNIPB/1-1281</a>.","apa":"Lass, M. (2022). <i>Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations</i>. Universität Paderborn. <a href=\"https://doi.org/10.17619/UNIPB/1-1281\">https://doi.org/10.17619/UNIPB/1-1281</a>"},"title":"Bringing Massive Parallelism and Hardware Acceleration to Linear Scaling Density Functional Theory Through Targeted Approximations","doi":"10.17619/UNIPB/1-1281","date_updated":"2022-07-25T18:14:23Z","publisher":"Universität Paderborn","date_created":"2022-07-25T18:13:51Z","author":[{"orcid":"0000-0002-5708-7632","last_name":"Lass","id":"24135","full_name":"Lass, Michael","first_name":"Michael"}],"supervisor":[{"first_name":"Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982","id":"16153","full_name":"Plessl, Christian"}]},{"publication":"Parallel Computing","keyword":["Artificial Intelligence","Computer Graphics and Computer-Aided Design","Computer Networks and Communications","Hardware and Architecture","Theoretical Computer Science","Software"],"language":[{"iso":"eng"}],"year":"2022","quality_controlled":"1","title":"Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms","publisher":"Elsevier BV","date_created":"2022-10-11T08:17:02Z","status":"public","type":"journal_article","article_number":"102920","project":[{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"33684","user_id":"75963","department":[{"_id":"613"},{"_id":"27"},{"_id":"518"}],"citation":{"mla":"Schade, Robert, et al. “Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms.” <i>Parallel Computing</i>, vol. 111, 102920, Elsevier BV, 2022, doi:<a href=\"https://doi.org/10.1016/j.parco.2022.102920\">10.1016/j.parco.2022.102920</a>.","bibtex":"@article{Schade_Kenter_Elgabarty_Lass_Schütt_Lazzaro_Pabst_Mohr_Hutter_Kühne_et al._2022, title={Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms}, volume={111}, DOI={<a href=\"https://doi.org/10.1016/j.parco.2022.102920\">10.1016/j.parco.2022.102920</a>}, number={102920}, journal={Parallel Computing}, publisher={Elsevier BV}, author={Schade, Robert and Kenter, Tobias and Elgabarty, Hossam and Lass, Michael and Schütt, Ole and Lazzaro, Alfio and Pabst, Hans and Mohr, Stephan and Hutter, Jürg and Kühne, Thomas and et al.}, year={2022} }","short":"R. Schade, T. Kenter, H. Elgabarty, M. Lass, O. Schütt, A. Lazzaro, H. Pabst, S. Mohr, J. Hutter, T. Kühne, C. Plessl, Parallel Computing 111 (2022).","apa":"Schade, R., Kenter, T., Elgabarty, H., Lass, M., Schütt, O., Lazzaro, A., Pabst, H., Mohr, S., Hutter, J., Kühne, T., &#38; Plessl, C. (2022). Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms. <i>Parallel Computing</i>, <i>111</i>, Article 102920. <a href=\"https://doi.org/10.1016/j.parco.2022.102920\">https://doi.org/10.1016/j.parco.2022.102920</a>","ama":"Schade R, Kenter T, Elgabarty H, et al. Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms. <i>Parallel Computing</i>. 2022;111. doi:<a href=\"https://doi.org/10.1016/j.parco.2022.102920\">10.1016/j.parco.2022.102920</a>","chicago":"Schade, Robert, Tobias Kenter, Hossam Elgabarty, Michael Lass, Ole Schütt, Alfio Lazzaro, Hans Pabst, et al. “Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms.” <i>Parallel Computing</i> 111 (2022). <a href=\"https://doi.org/10.1016/j.parco.2022.102920\">https://doi.org/10.1016/j.parco.2022.102920</a>.","ieee":"R. Schade <i>et al.</i>, “Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms,” <i>Parallel Computing</i>, vol. 111, Art. no. 102920, 2022, doi: <a href=\"https://doi.org/10.1016/j.parco.2022.102920\">10.1016/j.parco.2022.102920</a>."},"intvolume":"       111","publication_status":"published","publication_identifier":{"issn":["0167-8191"]},"main_file_link":[{"url":"https://www.sciencedirect.com/science/article/pii/S0167819122000242","open_access":"1"}],"doi":"10.1016/j.parco.2022.102920","date_updated":"2023-08-02T15:03:55Z","oa":"1","author":[{"first_name":"Robert","full_name":"Schade, Robert","id":"75963","orcid":"0000-0002-6268-539","last_name":"Schade"},{"first_name":"Tobias","full_name":"Kenter, Tobias","id":"3145","last_name":"Kenter"},{"full_name":"Elgabarty, Hossam","id":"60250","last_name":"Elgabarty","orcid":"0000-0002-4945-1481","first_name":"Hossam"},{"first_name":"Michael","full_name":"Lass, Michael","id":"24135","orcid":"0000-0002-5708-7632","last_name":"Lass"},{"first_name":"Ole","full_name":"Schütt, Ole","last_name":"Schütt"},{"full_name":"Lazzaro, Alfio","last_name":"Lazzaro","first_name":"Alfio"},{"first_name":"Hans","full_name":"Pabst, Hans","last_name":"Pabst"},{"last_name":"Mohr","full_name":"Mohr, Stephan","first_name":"Stephan"},{"first_name":"Jürg","last_name":"Hutter","full_name":"Hutter, Jürg"},{"first_name":"Thomas","id":"49079","full_name":"Kühne, Thomas","last_name":"Kühne"},{"first_name":"Christian","id":"16153","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl"}],"volume":111},{"citation":{"ieee":"T. Kühne <i>et al.</i>, “CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations,” <i>The Journal of Chemical Physics</i>, vol. 152, no. 19, Art. no. 194103, 2020, doi: <a href=\"https://doi.org/10.1063/5.0007045\">10.1063/5.0007045</a>.","chicago":"Kühne, Thomas, Marcella Iannuzzi, Mauro Del Ben, Vladimir V. Rybkin, Patrick Seewald, Frederick Stein, Teodoro Laino, et al. “CP2K: An Electronic Structure and Molecular Dynamics Software Package - Quickstep: Efficient and Accurate Electronic Structure Calculations.” <i>The Journal of Chemical Physics</i> 152, no. 19 (2020). <a href=\"https://doi.org/10.1063/5.0007045\">https://doi.org/10.1063/5.0007045</a>.","ama":"Kühne T, Iannuzzi M, Ben MD, et al. CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations. <i>The Journal of Chemical Physics</i>. 2020;152(19). doi:<a href=\"https://doi.org/10.1063/5.0007045\">10.1063/5.0007045</a>","apa":"Kühne, T., Iannuzzi, M., Ben, M. D., Rybkin, V. V., Seewald, P., Stein, F., Laino, T., Khaliullin, R. Z., Schütt, O., Schiffmann, F., Golze, D., Wilhelm, J., Chulkov, S., Mohammad Hossein Bani-Hashemian, M. H. B.-H., Weber, V., Borstnik, U., Taillefumier, M., Jakobovits, A. S., Lazzaro, A., … Hutter, J. (2020). CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations. <i>The Journal of Chemical Physics</i>, <i>152</i>(19), Article 194103. <a href=\"https://doi.org/10.1063/5.0007045\">https://doi.org/10.1063/5.0007045</a>","short":"T. Kühne, M. Iannuzzi, M.D. Ben, V.V. Rybkin, P. Seewald, F. Stein, T. Laino, R.Z. Khaliullin, O. Schütt, F. Schiffmann, D. Golze, J. Wilhelm, S. Chulkov, M.H.B.-H. Mohammad Hossein Bani-Hashemian, V. Weber, U. Borstnik, M. Taillefumier, A.S. Jakobovits, A. Lazzaro, H. Pabst, T. Müller, R. Schade, M. Guidon, S. Andermatt, N. Holmberg, G.K. Schenter, A. Hehn, A. Bussy, F. Belleflamme, G. Tabacchi, A. Glöß, M. Lass, I. Bethune, C.J. Mundy, C. Plessl, M. Watkins, J. VandeVondele, M. Krack, J. Hutter, The Journal of Chemical Physics 152 (2020).","mla":"Kühne, Thomas, et al. “CP2K: An Electronic Structure and Molecular Dynamics Software Package - Quickstep: Efficient and Accurate Electronic Structure Calculations.” <i>The Journal of Chemical Physics</i>, vol. 152, no. 19, 194103, 2020, doi:<a href=\"https://doi.org/10.1063/5.0007045\">10.1063/5.0007045</a>.","bibtex":"@article{Kühne_Iannuzzi_Ben_Rybkin_Seewald_Stein_Laino_Khaliullin_Schütt_Schiffmann_et al._2020, title={CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations}, volume={152}, DOI={<a href=\"https://doi.org/10.1063/5.0007045\">10.1063/5.0007045</a>}, number={19194103}, journal={The Journal of Chemical Physics}, author={Kühne, Thomas and Iannuzzi, Marcella and Ben, Mauro Del and Rybkin, Vladimir V. and Seewald, Patrick and Stein, Frederick and Laino, Teodoro and Khaliullin, Rustam Z. and Schütt, Ole and Schiffmann, Florian and et al.}, year={2020} }"},"intvolume":"       152","publication_status":"published","has_accepted_license":"1","main_file_link":[{"open_access":"1","url":"https://aip.scitation.org/doi/pdf/10.1063/5.0007045?download=true"}],"doi":"10.1063/5.0007045","oa":"1","date_updated":"2023-08-02T14:56:21Z","author":[{"first_name":"Thomas","last_name":"Kühne","id":"49079","full_name":"Kühne, Thomas"},{"first_name":"Marcella","full_name":"Iannuzzi, Marcella","last_name":"Iannuzzi"},{"first_name":"Mauro Del","last_name":"Ben","full_name":"Ben, Mauro Del"},{"first_name":"Vladimir V.","last_name":"Rybkin","full_name":"Rybkin, Vladimir V."},{"first_name":"Patrick","full_name":"Seewald, Patrick","last_name":"Seewald"},{"first_name":"Frederick","last_name":"Stein","full_name":"Stein, Frederick"},{"first_name":"Teodoro","last_name":"Laino","full_name":"Laino, Teodoro"},{"first_name":"Rustam Z.","full_name":"Khaliullin, Rustam Z.","last_name":"Khaliullin"},{"first_name":"Ole","last_name":"Schütt","full_name":"Schütt, Ole"},{"first_name":"Florian","last_name":"Schiffmann","full_name":"Schiffmann, Florian"},{"first_name":"Dorothea","last_name":"Golze","full_name":"Golze, Dorothea"},{"last_name":"Wilhelm","full_name":"Wilhelm, Jan","first_name":"Jan"},{"last_name":"Chulkov","full_name":"Chulkov, Sergey","first_name":"Sergey"},{"last_name":"Mohammad Hossein Bani-Hashemian","full_name":"Mohammad Hossein Bani-Hashemian, Mohammad Hossein Bani-Hashemian","first_name":"Mohammad Hossein Bani-Hashemian"},{"last_name":"Weber","full_name":"Weber, Valéry","first_name":"Valéry"},{"last_name":"Borstnik","full_name":"Borstnik, Urban","first_name":"Urban"},{"last_name":"Taillefumier","full_name":"Taillefumier, Mathieu","first_name":"Mathieu"},{"last_name":"Jakobovits","full_name":"Jakobovits, Alice Shoshana","first_name":"Alice Shoshana"},{"last_name":"Lazzaro","full_name":"Lazzaro, Alfio","first_name":"Alfio"},{"full_name":"Pabst, Hans","last_name":"Pabst","first_name":"Hans"},{"first_name":"Tiziano","last_name":"Müller","full_name":"Müller, Tiziano"},{"orcid":"0000-0002-6268-539","last_name":"Schade","full_name":"Schade, Robert","id":"75963","first_name":"Robert"},{"first_name":"Manuel","last_name":"Guidon","full_name":"Guidon, Manuel"},{"last_name":"Andermatt","full_name":"Andermatt, Samuel","first_name":"Samuel"},{"full_name":"Holmberg, Nico","last_name":"Holmberg","first_name":"Nico"},{"full_name":"Schenter, Gregory K.","last_name":"Schenter","first_name":"Gregory K."},{"first_name":"Anna","last_name":"Hehn","full_name":"Hehn, Anna"},{"last_name":"Bussy","full_name":"Bussy, Augustin","first_name":"Augustin"},{"first_name":"Fabian","last_name":"Belleflamme","full_name":"Belleflamme, Fabian"},{"full_name":"Tabacchi, Gloria","last_name":"Tabacchi","first_name":"Gloria"},{"full_name":"Glöß, Andreas","last_name":"Glöß","first_name":"Andreas"},{"first_name":"Michael","id":"24135","full_name":"Lass, Michael","last_name":"Lass","orcid":"0000-0002-5708-7632"},{"last_name":"Bethune","full_name":"Bethune, Iain","first_name":"Iain"},{"full_name":"Mundy, Christopher J.","last_name":"Mundy","first_name":"Christopher J."},{"full_name":"Plessl, Christian","id":"16153","orcid":"0000-0001-5728-9982","last_name":"Plessl","first_name":"Christian"},{"first_name":"Matt","last_name":"Watkins","full_name":"Watkins, Matt"},{"last_name":"VandeVondele","full_name":"VandeVondele, Joost","first_name":"Joost"},{"full_name":"Krack, Matthias","last_name":"Krack","first_name":"Matthias"},{"full_name":"Hutter, Jürg","last_name":"Hutter","first_name":"Jürg"}],"volume":152,"status":"public","type":"journal_article","article_number":"194103","file_date_updated":"2020-05-25T15:21:56Z","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"name":"Performance and Efficiency in HPC with Custom Computing","_id":"32","grant_number":"PL 595/2-1 / 320898746"},{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"_id":"16277","user_id":"75963","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"year":"2020","quality_controlled":"1","issue":"19","title":"CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations","date_created":"2020-03-10T15:12:31Z","abstract":[{"text":"CP2K is an open source electronic structure and molecular dynamics software package to perform atomistic simulations of solid-state, liquid, molecular, and biological systems. It is especially aimed at massively parallel and linear-scaling electronic structure methods and state-of-theart ab initio molecular dynamics simulations. Excellent performance for electronic structure calculations is achieved using novel algorithms implemented for modern high-performance computing systems. This review revisits the main capabilities of CP2K to perform efficient and accurate electronic structure simulations. The emphasis is put on density functional theory and multiple post–Hartree–Fock methods using the Gaussian and plane wave approach and its augmented all-electron extension.","lang":"eng"}],"file":[{"date_created":"2020-05-25T15:21:56Z","creator":"lass","date_updated":"2020-05-25T15:21:56Z","file_id":"17061","access_level":"closed","file_name":"5.0007045.pdf","file_size":4887650,"content_type":"application/pdf","relation":"main_file","success":1}],"publication":"The Journal of Chemical Physics","ddc":["540"],"language":[{"iso":"eng"}],"external_id":{"arxiv":["2003.03868"]}},{"language":[{"iso":"eng"}],"external_id":{"arxiv":["2004.10811"]},"abstract":[{"text":"Electronic structure calculations based on density-functional theory (DFT)\r\nrepresent a significant part of today's HPC workloads and pose high demands on\r\nhigh-performance computing resources. To perform these quantum-mechanical DFT\r\ncalculations on complex large-scale systems, so-called linear scaling methods\r\ninstead of conventional cubic scaling methods are required. In this work, we\r\ntake up the idea of the submatrix method and apply it to the DFT computations\r\nin the software package CP2K. For that purpose, we transform the underlying\r\nnumeric operations on distributed, large, sparse matrices into computations on\r\nlocal, much smaller and nearly dense matrices. This allows us to exploit the\r\nfull floating-point performance of modern CPUs and to make use of dedicated\r\naccelerator hardware, where performance has been limited by memory bandwidth\r\nbefore. We demonstrate both functionality and performance of our implementation\r\nand show how it can be accelerated with GPUs and FPGAs.","lang":"eng"}],"publication":"Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","title":"A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K","publisher":"IEEE Computer Society","date_created":"2020-04-28T14:44:21Z","year":"2020","quality_controlled":"1","_id":"16898","project":[{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"},{"grant_number":"PL 595/2-1 / 320898746","name":"Performance and Efficiency in HPC with Custom Computing","_id":"32"},{"_id":"52","name":"PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"user_id":"75963","status":"public","type":"conference","doi":"10.1109/SC41405.2020.00084","conference":{"name":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","location":"Atlanta, GA, US"},"main_file_link":[{"url":"https://ieeexplore.ieee.org/document/9355245"}],"date_updated":"2023-08-02T14:55:59Z","author":[{"first_name":"Michael","full_name":"Lass, Michael","id":"24135","orcid":"0000-0002-5708-7632","last_name":"Lass"},{"id":"75963","full_name":"Schade, Robert","orcid":"0000-0002-6268-539","last_name":"Schade","first_name":"Robert"},{"first_name":"Thomas","last_name":"Kühne","full_name":"Kühne, Thomas","id":"49079"},{"orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153","full_name":"Plessl, Christian","first_name":"Christian"}],"place":"Los Alamitos, CA, USA","page":"1127-1140","citation":{"ama":"Lass M, Schade R, Kühne T, Plessl C. A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K. In: <i>Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)</i>. IEEE Computer Society; 2020:1127-1140. doi:<a href=\"https://doi.org/10.1109/SC41405.2020.00084\">10.1109/SC41405.2020.00084</a>","ieee":"M. Lass, R. Schade, T. Kühne, and C. Plessl, “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K,” in <i>Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)</i>, Atlanta, GA, US, 2020, pp. 1127–1140, doi: <a href=\"https://doi.org/10.1109/SC41405.2020.00084\">10.1109/SC41405.2020.00084</a>.","chicago":"Lass, Michael, Robert Schade, Thomas Kühne, and Christian Plessl. “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K.” In <i>Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)</i>, 1127–40. Los Alamitos, CA, USA: IEEE Computer Society, 2020. <a href=\"https://doi.org/10.1109/SC41405.2020.00084\">https://doi.org/10.1109/SC41405.2020.00084</a>.","apa":"Lass, M., Schade, R., Kühne, T., &#38; Plessl, C. (2020). A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K. <i>Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)</i>, 1127–1140. <a href=\"https://doi.org/10.1109/SC41405.2020.00084\">https://doi.org/10.1109/SC41405.2020.00084</a>","mla":"Lass, Michael, et al. “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K.” <i>Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)</i>, IEEE Computer Society, 2020, pp. 1127–40, doi:<a href=\"https://doi.org/10.1109/SC41405.2020.00084\">10.1109/SC41405.2020.00084</a>.","bibtex":"@inproceedings{Lass_Schade_Kühne_Plessl_2020, place={Los Alamitos, CA, USA}, title={A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K}, DOI={<a href=\"https://doi.org/10.1109/SC41405.2020.00084\">10.1109/SC41405.2020.00084</a>}, booktitle={Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)}, publisher={IEEE Computer Society}, author={Lass, Michael and Schade, Robert and Kühne, Thomas and Plessl, Christian}, year={2020}, pages={1127–1140} }","short":"M. Lass, R. Schade, T. Kühne, C. Plessl, in: Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), IEEE Computer Society, Los Alamitos, CA, USA, 2020, pp. 1127–1140."}},{"status":"public","type":"journal_article","article_number":"39","_id":"12878","project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"},{"grant_number":"PL 595/2-1 / 320898746","name":"Performance and Efficiency in HPC with Custom Computing","_id":"32"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"user_id":"15278","intvolume":"         8","citation":{"chicago":"Rengaraj, Varadarajan, Michael Lass, Christian Plessl, and Thomas Kühne. “Accurate Sampling with Noisy Forces from Approximate Computing.” <i>Computation</i> 8, no. 2 (2020). <a href=\"https://doi.org/10.3390/computation8020039\">https://doi.org/10.3390/computation8020039</a>.","ieee":"V. Rengaraj, M. Lass, C. Plessl, and T. Kühne, “Accurate Sampling with Noisy Forces from Approximate Computing,” <i>Computation</i>, vol. 8, no. 2, Art. no. 39, 2020, doi: <a href=\"https://doi.org/10.3390/computation8020039\">10.3390/computation8020039</a>.","ama":"Rengaraj V, Lass M, Plessl C, Kühne T. Accurate Sampling with Noisy Forces from Approximate Computing. <i>Computation</i>. 2020;8(2). doi:<a href=\"https://doi.org/10.3390/computation8020039\">10.3390/computation8020039</a>","mla":"Rengaraj, Varadarajan, et al. “Accurate Sampling with Noisy Forces from Approximate Computing.” <i>Computation</i>, vol. 8, no. 2, 39, MDPI, 2020, doi:<a href=\"https://doi.org/10.3390/computation8020039\">10.3390/computation8020039</a>.","short":"V. Rengaraj, M. Lass, C. Plessl, T. Kühne, Computation 8 (2020).","bibtex":"@article{Rengaraj_Lass_Plessl_Kühne_2020, title={Accurate Sampling with Noisy Forces from Approximate Computing}, volume={8}, DOI={<a href=\"https://doi.org/10.3390/computation8020039\">10.3390/computation8020039</a>}, number={239}, journal={Computation}, publisher={MDPI}, author={Rengaraj, Varadarajan and Lass, Michael and Plessl, Christian and Kühne, Thomas}, year={2020} }","apa":"Rengaraj, V., Lass, M., Plessl, C., &#38; Kühne, T. (2020). Accurate Sampling with Noisy Forces from Approximate Computing. <i>Computation</i>, <i>8</i>(2), Article 39. <a href=\"https://doi.org/10.3390/computation8020039\">https://doi.org/10.3390/computation8020039</a>"},"doi":"10.3390/computation8020039","main_file_link":[{"url":"https://www.mdpi.com/2079-3197/8/2/39/pdf","open_access":"1"}],"oa":"1","date_updated":"2023-09-26T11:43:52Z","volume":8,"author":[{"first_name":"Varadarajan","last_name":"Rengaraj","full_name":"Rengaraj, Varadarajan"},{"first_name":"Michael","full_name":"Lass, Michael","id":"24135","last_name":"Lass","orcid":"0000-0002-5708-7632"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153","full_name":"Plessl, Christian"},{"id":"49079","full_name":"Kühne, Thomas","last_name":"Kühne","first_name":"Thomas"}],"abstract":[{"text":"In scientific computing, the acceleration of atomistic computer simulations by means of custom hardware is finding ever-growing application. A major limitation, however, is that the high efficiency in terms of performance and low power consumption entails the massive usage of low precision computing units. Here, based on the approximate computing paradigm, we present an algorithmic method to compensate for numerical inaccuracies due to low accuracy arithmetic operations rigorously, yet still obtaining exact expectation values using a properly modified Langevin-type equation.","lang":"eng"}],"publication":"Computation","language":[{"iso":"eng"}],"external_id":{"arxiv":["1907.08497"]},"year":"2020","quality_controlled":"1","issue":"2","title":"Accurate Sampling with Noisy Forces from Approximate Computing","publisher":"MDPI","date_created":"2019-07-23T12:03:07Z"},{"status":"public","type":"journal_article","user_id":"15278","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"},{"_id":"104"}],"project":[{"name":"Performance and Efficiency in HPC with Custom Computing","_id":"32","grant_number":"PL 595/2-1 / 320898746"},{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"_id":"21","citation":{"ama":"Richters D, Lass M, Walther A, Plessl C, Kühne T. A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices. <i>Communications in Computational Physics</i>. 2019;25(2):564-585. doi:<a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">10.4208/cicp.OA-2018-0053</a>","chicago":"Richters, Dorothee, Michael Lass, Andrea Walther, Christian Plessl, and Thomas Kühne. “A General Algorithm to Calculate the Inverse Principal P-Th Root of Symmetric Positive Definite Matrices.” <i>Communications in Computational Physics</i> 25, no. 2 (2019): 564–85. <a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">https://doi.org/10.4208/cicp.OA-2018-0053</a>.","ieee":"D. Richters, M. Lass, A. Walther, C. Plessl, and T. Kühne, “A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices,” <i>Communications in Computational Physics</i>, vol. 25, no. 2, pp. 564–585, 2019, doi: <a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">10.4208/cicp.OA-2018-0053</a>.","short":"D. Richters, M. Lass, A. Walther, C. Plessl, T. Kühne, Communications in Computational Physics 25 (2019) 564–585.","bibtex":"@article{Richters_Lass_Walther_Plessl_Kühne_2019, title={A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices}, volume={25}, DOI={<a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">10.4208/cicp.OA-2018-0053</a>}, number={2}, journal={Communications in Computational Physics}, publisher={Global Science Press}, author={Richters, Dorothee and Lass, Michael and Walther, Andrea and Plessl, Christian and Kühne, Thomas}, year={2019}, pages={564–585} }","mla":"Richters, Dorothee, et al. “A General Algorithm to Calculate the Inverse Principal P-Th Root of Symmetric Positive Definite Matrices.” <i>Communications in Computational Physics</i>, vol. 25, no. 2, Global Science Press, 2019, pp. 564–85, doi:<a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">10.4208/cicp.OA-2018-0053</a>.","apa":"Richters, D., Lass, M., Walther, A., Plessl, C., &#38; Kühne, T. (2019). A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices. <i>Communications in Computational Physics</i>, <i>25</i>(2), 564–585. <a href=\"https://doi.org/10.4208/cicp.OA-2018-0053\">https://doi.org/10.4208/cicp.OA-2018-0053</a>"},"page":"564-585","intvolume":"        25","doi":"10.4208/cicp.OA-2018-0053","author":[{"first_name":"Dorothee","last_name":"Richters","full_name":"Richters, Dorothee"},{"first_name":"Michael","id":"24135","full_name":"Lass, Michael","orcid":"0000-0002-5708-7632","last_name":"Lass"},{"last_name":"Walther","full_name":"Walther, Andrea","first_name":"Andrea"},{"first_name":"Christian","id":"16153","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl"},{"first_name":"Thomas","last_name":"Kühne","full_name":"Kühne, Thomas","id":"49079"}],"volume":25,"date_updated":"2023-09-26T11:45:02Z","abstract":[{"text":"We address the general mathematical problem of computing the inverse p-th\r\nroot of a given matrix in an efficient way. A new method to construct iteration\r\nfunctions that allow calculating arbitrary p-th roots and their inverses of\r\nsymmetric positive definite matrices is presented. We show that the order of\r\nconvergence is at least quadratic and that adaptively adjusting a parameter q\r\nalways leads to an even faster convergence. In this way, a better performance\r\nthan with previously known iteration schemes is achieved. The efficiency of the\r\niterative functions is demonstrated for various matrices with different\r\ndensities, condition numbers and spectral radii.","lang":"eng"}],"publication":"Communications in Computational Physics","language":[{"iso":"eng"}],"external_id":{"arxiv":["1703.02456"]},"year":"2019","issue":"2","quality_controlled":"1","title":"A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices","date_created":"2017-07-25T14:48:26Z","publisher":"Global Science Press"},{"abstract":[{"lang":"eng","text":"Approximate computing has shown to provide new ways to improve performance\r\nand power consumption of error-resilient applications. While many of these\r\napplications can be found in image processing, data classification or machine\r\nlearning, we demonstrate its suitability to a problem from scientific\r\ncomputing. Utilizing the self-correcting behavior of iterative algorithms, we\r\nshow that approximate computing can be applied to the calculation of inverse\r\nmatrix p-th roots which are required in many applications in scientific\r\ncomputing. Results show great opportunities to reduce the computational effort\r\nand bandwidth required for the execution of the discussed algorithm, especially\r\nwhen targeting special accelerator hardware."}],"publication":"Embedded Systems Letters","language":[{"iso":"eng"}],"external_id":{"arxiv":["1703.02283"]},"year":"2018","issue":"2","title":"Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots","date_created":"2017-07-25T14:41:08Z","publisher":"IEEE","status":"public","type":"journal_article","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"user_id":"16153","_id":"20","project":[{"grant_number":"PL 595/2-1","name":"Performance and Efficiency in HPC with Custom Computing","_id":"32"},{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"page":" 33-36","intvolume":"        10","citation":{"bibtex":"@article{Lass_Kühne_Plessl_2018, title={Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots}, volume={10}, DOI={<a href=\"https://doi.org/10.1109/LES.2017.2760923\">10.1109/LES.2017.2760923</a>}, number={2}, journal={Embedded Systems Letters}, publisher={IEEE}, author={Lass, Michael and Kühne, Thomas and Plessl, Christian}, year={2018}, pages={33–36} }","short":"M. Lass, T. Kühne, C. Plessl, Embedded Systems Letters 10 (2018) 33–36.","mla":"Lass, Michael, et al. “Using Approximate Computing for the Calculation of Inverse Matrix P-Th Roots.” <i>Embedded Systems Letters</i>, vol. 10, no. 2, IEEE, 2018, pp. 33–36, doi:<a href=\"https://doi.org/10.1109/LES.2017.2760923\">10.1109/LES.2017.2760923</a>.","apa":"Lass, M., Kühne, T., &#38; Plessl, C. (2018). Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots. <i>Embedded Systems Letters</i>, <i>10</i>(2), 33–36. <a href=\"https://doi.org/10.1109/LES.2017.2760923\">https://doi.org/10.1109/LES.2017.2760923</a>","ieee":"M. Lass, T. Kühne, and C. Plessl, “Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots,” <i>Embedded Systems Letters</i>, vol. 10, no. 2, pp. 33–36, 2018.","chicago":"Lass, Michael, Thomas Kühne, and Christian Plessl. “Using Approximate Computing for the Calculation of Inverse Matrix P-Th Roots.” <i>Embedded Systems Letters</i> 10, no. 2 (2018): 33–36. <a href=\"https://doi.org/10.1109/LES.2017.2760923\">https://doi.org/10.1109/LES.2017.2760923</a>.","ama":"Lass M, Kühne T, Plessl C. Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots. <i>Embedded Systems Letters</i>. 2018;10(2):33-36. doi:<a href=\"https://doi.org/10.1109/LES.2017.2760923\">10.1109/LES.2017.2760923</a>"},"publication_identifier":{"issn":["1943-0663"],"eissn":["1943-0671"]},"publication_status":"published","doi":"10.1109/LES.2017.2760923","volume":10,"author":[{"orcid":"0000-0002-5708-7632","last_name":"Lass","full_name":"Lass, Michael","id":"24135","first_name":"Michael"},{"first_name":"Thomas","last_name":"Kühne","full_name":"Kühne, Thomas","id":"49079"},{"id":"16153","full_name":"Plessl, Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"date_updated":"2022-01-06T06:54:18Z"},{"keyword":["approximate computing","linear algebra","matrix inversion","matrix p-th roots","numeric algorithm","parallel computing"],"language":[{"iso":"eng"}],"external_id":{"arxiv":["1710.10899"]},"abstract":[{"text":"We present the submatrix method, a highly parallelizable method for the approximate calculation of inverse p-th roots of large sparse symmetric matrices which are required in different scientific applications. Following the idea of Approximate Computing, we allow imprecision in the final result in order to utilize the sparsity of the input matrix and to allow massively parallel execution. For an n x n matrix, the proposed algorithm allows to distribute the calculations over n nodes with only little communication overhead. The result matrix exhibits the same sparsity pattern as the input matrix, allowing for efficient reuse of allocated data structures.\r\n\r\nWe evaluate the algorithm with respect to the error that it introduces into calculated results, as well as its performance and scalability. We demonstrate that the error is relatively limited for well-conditioned matrices and that results are still valuable for error-resilient applications like preconditioning even for ill-conditioned matrices. We discuss the execution time and scaling of the algorithm on a theoretical level and present a distributed implementation of the algorithm using MPI and OpenMP. We demonstrate the scalability of this implementation by running it on a high-performance compute cluster comprised of 1024 CPU cores, showing a speedup of 665x compared to single-threaded execution.","lang":"eng"}],"publication":"Proc. Platform for Advanced Scientific Computing (PASC) Conference","title":"A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices","publisher":"ACM","date_created":"2018-03-22T10:53:01Z","year":"2018","quality_controlled":"1","_id":"1590","project":[{"_id":"32","name":"Performance and Efficiency in HPC with Custom Computing","grant_number":"PL 595/2-1 / 320898746"},{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"user_id":"15278","status":"public","type":"conference","doi":"10.1145/3218176.3218231","conference":{"location":"Basel, Switzerland","end_date":"2018-07-04","start_date":"2018-07-02","name":"Platform for Advanced Scientific Computing Conference (PASC)"},"date_updated":"2023-09-26T11:48:12Z","author":[{"first_name":"Michael","orcid":"0000-0002-5708-7632","last_name":"Lass","id":"24135","full_name":"Lass, Michael"},{"last_name":"Mohr","full_name":"Mohr, Stephan","first_name":"Stephan"},{"first_name":"Hendrik","full_name":"Wiebeler, Hendrik","last_name":"Wiebeler"},{"last_name":"Kühne","full_name":"Kühne, Thomas","id":"49079","first_name":"Thomas"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153","full_name":"Plessl, Christian"}],"place":"New York, NY, USA","citation":{"apa":"Lass, M., Mohr, S., Wiebeler, H., Kühne, T., &#38; Plessl, C. (2018). A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices. <i>Proc. Platform for Advanced Scientific Computing (PASC) Conference</i>. Platform for Advanced Scientific Computing Conference (PASC), Basel, Switzerland. <a href=\"https://doi.org/10.1145/3218176.3218231\">https://doi.org/10.1145/3218176.3218231</a>","mla":"Lass, Michael, et al. “A Massively Parallel Algorithm for the Approximate Calculation of Inverse P-Th Roots of Large Sparse Matrices.” <i>Proc. Platform for Advanced Scientific Computing (PASC) Conference</i>, ACM, 2018, doi:<a href=\"https://doi.org/10.1145/3218176.3218231\">10.1145/3218176.3218231</a>.","short":"M. Lass, S. Mohr, H. Wiebeler, T. Kühne, C. Plessl, in: Proc. Platform for Advanced Scientific Computing (PASC) Conference, ACM, New York, NY, USA, 2018.","bibtex":"@inproceedings{Lass_Mohr_Wiebeler_Kühne_Plessl_2018, place={New York, NY, USA}, title={A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices}, DOI={<a href=\"https://doi.org/10.1145/3218176.3218231\">10.1145/3218176.3218231</a>}, booktitle={Proc. Platform for Advanced Scientific Computing (PASC) Conference}, publisher={ACM}, author={Lass, Michael and Mohr, Stephan and Wiebeler, Hendrik and Kühne, Thomas and Plessl, Christian}, year={2018} }","ama":"Lass M, Mohr S, Wiebeler H, Kühne T, Plessl C. A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices. In: <i>Proc. Platform for Advanced Scientific Computing (PASC) Conference</i>. ACM; 2018. doi:<a href=\"https://doi.org/10.1145/3218176.3218231\">10.1145/3218176.3218231</a>","chicago":"Lass, Michael, Stephan Mohr, Hendrik Wiebeler, Thomas Kühne, and Christian Plessl. “A Massively Parallel Algorithm for the Approximate Calculation of Inverse P-Th Roots of Large Sparse Matrices.” In <i>Proc. Platform for Advanced Scientific Computing (PASC) Conference</i>. New York, NY, USA: ACM, 2018. <a href=\"https://doi.org/10.1145/3218176.3218231\">https://doi.org/10.1145/3218176.3218231</a>.","ieee":"M. Lass, S. Mohr, H. Wiebeler, T. Kühne, and C. Plessl, “A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices,” presented at the Platform for Advanced Scientific Computing Conference (PASC), Basel, Switzerland, 2018, doi: <a href=\"https://doi.org/10.1145/3218176.3218231\">10.1145/3218176.3218231</a>."},"publication_identifier":{"isbn":["978-1-4503-5891-0/18/07"]}},{"quality_controlled":"1","issue":"3","year":"2017","publisher":"Association for Computing Machinery (ACM)","date_created":"2017-07-25T14:17:32Z","title":"Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs","publication":"ACM Transactions on Reconfigurable Technology and Systems (TRETS)","abstract":[{"text":"Branch and bound (B&B) algorithms structure the search space as a tree and eliminate infeasible solutions early by pruning subtrees that cannot lead to a valid or optimal solution. Custom hardware designs significantly accelerate the execution of these algorithms. In this article, we demonstrate a high-performance B&B implementation on FPGAs. First, we identify general elements of B&B algorithms and describe their implementation as a finite state machine. Then, we introduce workers that autonomously cooperate using work stealing to allow parallel execution and full utilization of the target FPGA. Finally, we explore advantages of instance-specific designs that target a specific problem instance to improve performance.\r\n\r\nWe evaluate our concepts by applying them to a branch and bound problem, the reconstruction of corrupted AES keys obtained from cold-boot attacks. The evaluation shows that our work stealing approach is scalable with the available resources and provides speedups proportional to the number of workers. Instance-specific designs allow us to achieve an overall speedup of 47 × compared to the fastest implementation of AES key reconstruction so far. Finally, we demonstrate how instance-specific designs can be generated just-in-time such that the provided speedups outweigh the additional time required for design synthesis.","lang":"eng"}],"file":[{"content_type":"application/pdf","relation":"main_file","success":1,"date_created":"2018-11-02T16:04:14Z","creator":"ups","date_updated":"2018-11-02T16:04:14Z","file_id":"5322","access_level":"closed","file_name":"a24-riebler.pdf","file_size":2131617}],"ddc":["000"],"keyword":["coldboot"],"language":[{"iso":"eng"}],"publication_status":"published","has_accepted_license":"1","publication_identifier":{"issn":["1936-7406"]},"citation":{"chicago":"Riebler, Heinrich, Michael Lass, Robert Mittendorf, Thomas Löcke, and Christian Plessl. “Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs.” <i>ACM Transactions on Reconfigurable Technology and Systems (TRETS)</i> 10, no. 3 (2017): 24:1-24:23. <a href=\"https://doi.org/10.1145/3053687\">https://doi.org/10.1145/3053687</a>.","ieee":"H. Riebler, M. Lass, R. Mittendorf, T. Löcke, and C. Plessl, “Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs,” <i>ACM Transactions on Reconfigurable Technology and Systems (TRETS)</i>, vol. 10, no. 3, p. 24:1-24:23, 2017, doi: <a href=\"https://doi.org/10.1145/3053687\">10.1145/3053687</a>.","ama":"Riebler H, Lass M, Mittendorf R, Löcke T, Plessl C. Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs. <i>ACM Transactions on Reconfigurable Technology and Systems (TRETS)</i>. 2017;10(3):24:1-24:23. doi:<a href=\"https://doi.org/10.1145/3053687\">10.1145/3053687</a>","apa":"Riebler, H., Lass, M., Mittendorf, R., Löcke, T., &#38; Plessl, C. (2017). Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs. <i>ACM Transactions on Reconfigurable Technology and Systems (TRETS)</i>, <i>10</i>(3), 24:1-24:23. <a href=\"https://doi.org/10.1145/3053687\">https://doi.org/10.1145/3053687</a>","short":"H. Riebler, M. Lass, R. Mittendorf, T. Löcke, C. Plessl, ACM Transactions on Reconfigurable Technology and Systems (TRETS) 10 (2017) 24:1-24:23.","bibtex":"@article{Riebler_Lass_Mittendorf_Löcke_Plessl_2017, title={Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs}, volume={10}, DOI={<a href=\"https://doi.org/10.1145/3053687\">10.1145/3053687</a>}, number={3}, journal={ACM Transactions on Reconfigurable Technology and Systems (TRETS)}, publisher={Association for Computing Machinery (ACM)}, author={Riebler, Heinrich and Lass, Michael and Mittendorf, Robert and Löcke, Thomas and Plessl, Christian}, year={2017}, pages={24:1-24:23} }","mla":"Riebler, Heinrich, et al. “Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs.” <i>ACM Transactions on Reconfigurable Technology and Systems (TRETS)</i>, vol. 10, no. 3, Association for Computing Machinery (ACM), 2017, p. 24:1-24:23, doi:<a href=\"https://doi.org/10.1145/3053687\">10.1145/3053687</a>."},"page":"24:1-24:23","intvolume":"        10","date_updated":"2023-09-26T13:23:58Z","author":[{"full_name":"Riebler, Heinrich","id":"8961","last_name":"Riebler","first_name":"Heinrich"},{"id":"24135","full_name":"Lass, Michael","last_name":"Lass","orcid":"0000-0002-5708-7632","first_name":"Michael"},{"first_name":"Robert","last_name":"Mittendorf","full_name":"Mittendorf, Robert"},{"full_name":"Löcke, Thomas","last_name":"Löcke","first_name":"Thomas"},{"first_name":"Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","id":"16153"}],"volume":10,"doi":"10.1145/3053687","type":"journal_article","status":"public","project":[{"grant_number":"160364472","name":"SFB 901","_id":"1"},{"_id":"4","name":"SFB 901 - Project Area C"},{"_id":"14","name":"SFB 901 - Subproject C2","grant_number":"160364472"},{"name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","_id":"34","grant_number":"610996"},{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"_id":"18","user_id":"15278","department":[{"_id":"27"},{"_id":"518"}],"file_date_updated":"2018-11-02T16:04:14Z"},{"publication_identifier":{"isbn":["978-1-5090-2054-6"]},"publication_status":"published","citation":{"mla":"Lass, Michael, et al. “Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension.” <i>Proc. 41st Conference on Local Computer Networks (LCN)</i>, IEEE, 2016, doi:<a href=\"https://doi.org/10.1109/lcn.2016.11\">10.1109/lcn.2016.11</a>.","bibtex":"@inproceedings{Lass_Leibenger_Sorge_2016, title={Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension}, DOI={<a href=\"https://doi.org/10.1109/lcn.2016.11\">10.1109/lcn.2016.11</a>}, booktitle={Proc. 41st Conference on Local Computer Networks (LCN)}, publisher={IEEE}, author={Lass, Michael and Leibenger, Dominik and Sorge, Christoph}, year={2016} }","short":"M. Lass, D. Leibenger, C. Sorge, in: Proc. 41st Conference on Local Computer Networks (LCN), IEEE, 2016.","apa":"Lass, M., Leibenger, D., &#38; Sorge, C. (2016). Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension. In <i>Proc. 41st Conference on Local Computer Networks (LCN)</i>. IEEE. <a href=\"https://doi.org/10.1109/lcn.2016.11\">https://doi.org/10.1109/lcn.2016.11</a>","ama":"Lass M, Leibenger D, Sorge C. Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension. In: <i>Proc. 41st Conference on Local Computer Networks (LCN)</i>. IEEE; 2016. doi:<a href=\"https://doi.org/10.1109/lcn.2016.11\">10.1109/lcn.2016.11</a>","ieee":"M. Lass, D. Leibenger, and C. Sorge, “Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension,” in <i>Proc. 41st Conference on Local Computer Networks (LCN)</i>, 2016.","chicago":"Lass, Michael, Dominik Leibenger, and Christoph Sorge. “Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension.” In <i>Proc. 41st Conference on Local Computer Networks (LCN)</i>. IEEE, 2016. <a href=\"https://doi.org/10.1109/lcn.2016.11\">https://doi.org/10.1109/lcn.2016.11</a>."},"year":"2016","author":[{"full_name":"Lass, Michael","id":"24135","orcid":"0000-0002-5708-7632","last_name":"Lass","first_name":"Michael"},{"first_name":"Dominik","last_name":"Leibenger","full_name":"Leibenger, Dominik"},{"full_name":"Sorge, Christoph","last_name":"Sorge","first_name":"Christoph"}],"date_created":"2017-07-25T14:36:16Z","publisher":"IEEE","date_updated":"2022-01-06T06:53:56Z","doi":"10.1109/lcn.2016.11","title":"Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension","publication":"Proc. 41st Conference on Local Computer Networks (LCN)","type":"conference","status":"public","abstract":[{"lang":"eng","text":"Version Control Systems (VCS) are a valuable tool for software development\r\nand document management. Both client/server and distributed (Peer-to-Peer)\r\nmodels exist, with the latter (e.g., Git and Mercurial) becoming\r\nincreasingly popular. Their distributed nature introduces complications,\r\nespecially concerning security: it is hard to control the dissemination of\r\ncontents stored in distributed VCS as they rely on replication of complete\r\nrepositories to any involved user.\r\n\r\nWe overcome this issue by designing and implementing a concept for\r\ncryptography-enforced access control which is transparent to the user. Use\r\nof field-tested schemes (end-to-end encryption, digital signatures) allows\r\nfor strong security, while adoption of convergent encryption and\r\ncontent-defined chunking retains storage efficiency. The concept is\r\nseamlessly integrated into Mercurial---respecting its distributed storage\r\nconcept---to ensure practical usability and compatibility to existing\r\ndeployments."}],"department":[{"_id":"27"},{"_id":"518"}],"user_id":"24135","_id":"19","language":[{"iso":"eng"}],"keyword":["access control","distributed version control systems","mercurial","peer-to-peer","convergent encryption","confidentiality","authenticity"]},{"date_created":"2017-07-26T15:02:20Z","author":[{"first_name":"Michael","full_name":"Lass, Michael","id":"24135","orcid":"0000-0002-5708-7632","last_name":"Lass"},{"full_name":"Kühne, Thomas","id":"49079","last_name":"Kühne","first_name":"Thomas"},{"first_name":"Christian","last_name":"Plessl","orcid":"0000-0001-5728-9982","id":"16153","full_name":"Plessl, Christian"}],"date_updated":"2023-09-26T13:25:17Z","title":"Using Approximate Computing in Scientific Codes","quality_controlled":"1","citation":{"apa":"Lass, M., Kühne, T., &#38; Plessl, C. (2016). Using Approximate Computing in Scientific Codes. <i>Workshop on Approximate Computing (AC)</i>.","short":"M. Lass, T. Kühne, C. Plessl, in: Workshop on Approximate Computing (AC), 2016.","bibtex":"@inproceedings{Lass_Kühne_Plessl_2016, title={Using Approximate Computing in Scientific Codes}, booktitle={Workshop on Approximate Computing (AC)}, author={Lass, Michael and Kühne, Thomas and Plessl, Christian}, year={2016} }","mla":"Lass, Michael, et al. “Using Approximate Computing in Scientific Codes.” <i>Workshop on Approximate Computing (AC)</i>, 2016.","ama":"Lass M, Kühne T, Plessl C. Using Approximate Computing in Scientific Codes. In: <i>Workshop on Approximate Computing (AC)</i>. ; 2016.","ieee":"M. Lass, T. Kühne, and C. Plessl, “Using Approximate Computing in Scientific Codes,” 2016.","chicago":"Lass, Michael, Thomas Kühne, and Christian Plessl. “Using Approximate Computing in Scientific Codes.” In <i>Workshop on Approximate Computing (AC)</i>, 2016."},"year":"2016","department":[{"_id":"27"},{"_id":"518"},{"_id":"304"}],"user_id":"15278","_id":"25","project":[{"_id":"52","name":"Computing Resources Provided by the Paderborn Center for Parallel Computing"}],"language":[{"iso":"eng"}],"publication":"Workshop on Approximate Computing (AC)","type":"conference","status":"public"},{"title":"Localization and Analysis of Code Paths Suitable for Acceleration using Approximate Computing","supervisor":[{"first_name":"Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","full_name":"Plessl, Christian","id":"16153"}],"date_created":"2018-03-26T15:24:10Z","author":[{"first_name":"Michael","orcid":"0000-0002-5708-7632","last_name":"Lass","id":"24135","full_name":"Lass, Michael"}],"publisher":"Paderborn University","date_updated":"2022-01-06T06:53:23Z","citation":{"chicago":"Lass, Michael. <i>Localization and Analysis of Code Paths Suitable for Acceleration Using Approximate Computing</i>. Paderborn: Paderborn University, 2015.","ieee":"M. Lass, <i>Localization and Analysis of Code Paths Suitable for Acceleration using Approximate Computing</i>. Paderborn: Paderborn University, 2015.","ama":"Lass M. <i>Localization and Analysis of Code Paths Suitable for Acceleration Using Approximate Computing</i>. Paderborn: Paderborn University; 2015.","mla":"Lass, Michael. <i>Localization and Analysis of Code Paths Suitable for Acceleration Using Approximate Computing</i>. Paderborn University, 2015.","bibtex":"@book{Lass_2015, place={Paderborn}, title={Localization and Analysis of Code Paths Suitable for Acceleration using Approximate Computing}, publisher={Paderborn University}, author={Lass, Michael}, year={2015} }","short":"M. Lass, Localization and Analysis of Code Paths Suitable for Acceleration Using Approximate Computing, Paderborn University, Paderborn, 2015.","apa":"Lass, M. (2015). <i>Localization and Analysis of Code Paths Suitable for Acceleration using Approximate Computing</i>. Paderborn: Paderborn University."},"place":"Paderborn","year":"2015","user_id":"24135","department":[{"_id":"27"},{"_id":"518"}],"_id":"1794","status":"public","abstract":[{"text":"Demands for computational power and energy efficiency of computing devices are steadily increasing. At the same time, following classic methods to increase speed and reduce energy consumption of these devices becomes increasingly difficult, bringing alternative methods into focus. One of these methods is approximate computing which utilizes the fact that small errors in computations are acceptable in many applications in order to allow acceleration of these computations or to increase energy efficiency. This thesis develops elements of a workflow that can be followed to apply approximate computing to existing applications. It proposes a novel heuristic approach to the localization of code paths that are suitable to approximate computing based on findings in recent research. Additionally, an approach to identification of approximable instructions within these code paths is proposed and used to implement simulation of approximation. The parts of the workflow are implemented with the goal to lay the foundation for a partly automated toolflow. Evaluation of the developed techniques shows that the proposed methods can help providing a convenient workflow, facilitating the first steps into the application of approximate computing.","lang":"eng"}],"type":"mastersthesis"},{"user_id":"24135","_id":"1795","status":"public","abstract":[{"text":"Distributed revision control is widespread throughout the software industry. Systems like git and mercurial gained a lot of users over the last years and started to supersede central systems like Subversion or CVS in some projects. While restricting access to those central systems is basically possible, it is difficult to control the propagation of contents in a distributed revision control system because every user has a local copy of the whole repository. In this thesis a concept is developed and implemented that allows secure storage of confidential data in a distributed revision control system and enables users to manage read and write permissions on single confidential files. Therefore different cryptographic methods are used, such as asymmetric encryption, digital signatures and convergent encryption. These techniques are applied in a manner that fits the special requirements of a revision control system and allows a space efficient storage of changes to the encrypted files.","lang":"eng"}],"type":"bachelorsthesis","title":"Sichere Speicherung vertraulicher Daten in verteilten Versionskontrollsystemen","author":[{"full_name":"Lass, Michael","id":"24135","orcid":"0000-0002-5708-7632","last_name":"Lass","first_name":"Michael"}],"supervisor":[{"full_name":"Sorge, Christoph","last_name":"Sorge","first_name":"Christoph"}],"date_created":"2018-03-26T15:25:01Z","publisher":"Paderborn University","date_updated":"2022-01-06T06:53:23Z","citation":{"apa":"Lass, M. (2013). <i>Sichere Speicherung vertraulicher Daten in verteilten Versionskontrollsystemen</i>. Paderborn: Paderborn University.","short":"M. Lass, Sichere Speicherung Vertraulicher Daten in Verteilten Versionskontrollsystemen, Paderborn University, Paderborn, 2013.","bibtex":"@book{Lass_2013, place={Paderborn}, title={Sichere Speicherung vertraulicher Daten in verteilten Versionskontrollsystemen}, publisher={Paderborn University}, author={Lass, Michael}, year={2013} }","mla":"Lass, Michael. <i>Sichere Speicherung Vertraulicher Daten in Verteilten Versionskontrollsystemen</i>. Paderborn University, 2013.","chicago":"Lass, Michael. <i>Sichere Speicherung Vertraulicher Daten in Verteilten Versionskontrollsystemen</i>. Paderborn: Paderborn University, 2013.","ieee":"M. Lass, <i>Sichere Speicherung vertraulicher Daten in verteilten Versionskontrollsystemen</i>. Paderborn: Paderborn University, 2013.","ama":"Lass M. <i>Sichere Speicherung Vertraulicher Daten in Verteilten Versionskontrollsystemen</i>. Paderborn: Paderborn University; 2013."},"year":"2013","place":"Paderborn"}]