@article{60565,
  author       = {{Bocchini, Adriana and Gerstmann, Uwe and Schmidt, Wolf Gero}},
  issn         = {{2469-9950}},
  journal      = {{Physical Review B}},
  number       = {{10}},
  publisher    = {{American Physical Society (APS)}},
  title        = {{{Microscopic origin of gray tracks in <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msub><mml:mi>KTiOPO</mml:mi><mml:mn>4</mml:mn></mml:msub></mml:math>}}},
  doi          = {{10.1103/physrevb.111.104103}},
  volume       = {{111}},
  year         = {{2025}},
}

@article{60580,
  abstract     = {{<jats:title>Abstract</jats:title><jats:p>AlInP (001) is widely utilized as a window layer in optoelectronic devices, including world‐record III‐V multi‐junction solar cells and photoelectrochemical (PEC) cells. The chemical and electronic properties of AlInP (001) depend on its surface reconstruction, which impacts its interaction with electrolytes in PEC applications and passivation layers. This study investigates AlInP (001) surface reconstructions using density functional theory and experimental methods. Phosphorus‐rich (P‐rich) and indium‐rich (In‐rich) AlInP surfaces are prepared with in situ monitoring of the process by reflection anisotropy (RA) spectroscopy and confirmed by low‐energy electron diffraction and photoemission spectroscopy. The experimental RA spectra closely match the theoretical predictions obtained by solving the Bethe–Salpeter equation. It is shown that missing hydrogen on P‐rich surfaces and formation of In–In 1D atomic chains on In‐rich surfaces introduce mid‐gap surface states that pin the Fermi level and induce band bending. Time‐resolved two‐photon photoemission measurements reveal ultrafast near‐surface electron dynamics for both P‐rich and In‐rich surfaces, demonstrating photoexcited electrons reaching the surface conduction band minimum and relaxing to mid‐gap surface states on about hundreds of fs. This work provides the most extensive AlInP surface analysis to date, allowing for more targeted surface and interface engineering, which is crucial for the optimization and design of III‐V heterostructures.</jats:p>}},
  author       = {{Zare Pour, Mohammad Amin and Shekarabi, Sahar and Ruiz Alvarado, Isaac Azahel and Diederich, Jonathan and Gao, Yuyings and Paszuk, Agnieszka and Moritz, Dominik C. and Jaegermann, Wolfram and Friedrich, Dennis and van de Krol, Roel and Schmidt, Wolf Gero and Hannappel, Thomas}},
  issn         = {{1616-301X}},
  journal      = {{Advanced Functional Materials}},
  publisher    = {{Wiley}},
  title        = {{{Exploring Electronic States and Ultrafast Electron Dynamics in AlInP Window Layers: The Role of Surface Reconstruction}}},
  doi          = {{10.1002/adfm.202423702}},
  year         = {{2025}},
}

@article{58642,
  abstract     = {{We present a cost-effective self-assembly method to fabricate low-density dimer NPs in an NPoM architecture, using the M13 phage as a spacer layer. This will enable the development of dynamic plasmonic devices and advanced sensing applications.}},
  author       = {{Devaraj, Vasanthan and Ruiz Alvarado, Isaac Azahel and Lee, Jong-Min and Oh, Jin-Woo and Gerstmann, Uwe and Schmidt, Wolf Gero and Zentgraf, Thomas}},
  issn         = {{2055-6756}},
  journal      = {{Nanoscale Horizons}},
  pages        = {{537--548}},
  publisher    = {{Royal Society of Chemistry (RSC)}},
  title        = {{{Self-assembly of isolated plasmonic dimers with sub-5 nm gaps on a metallic mirror}}},
  doi          = {{10.1039/d4nh00546e}},
  volume       = {{10}},
  year         = {{2025}},
}

@article{60566,
  author       = {{Bocchini, Adriana and Rüsing, Michael and Bollmers, Laura and Lengeling, Sebastian and Mues, Philipp and Padberg, Laura and Gerstmann, Uwe and Silberhorn, Christine and Eigner, Christof and Schmidt, Wolf Gero}},
  issn         = {{2475-9953}},
  journal      = {{Physical Review Materials}},
  number       = {{7}},
  publisher    = {{American Physical Society (APS)}},
  title        = {{{Mg dopants in lithium niobate: Defect models and impact on domain inversion}}},
  doi          = {{10.1103/5wz1-bjyr}},
  volume       = {{9}},
  year         = {{2025}},
}

@inproceedings{65102,
  abstract     = {{Efficient graph processing is essential for a wide range of applications. Scalability and memory access patterns are still a challenge, especially with the Breadth-First Search algorithm. This work focuses on leveraging HPC systems with multiple GPUs available in a single node with peer-to-peer functionality of the Intel oneAPI implementation of SYCL. We propose three GPU-based load-balancing methods: work-group localisation for efficient data access, even workload distribution for higher GPU occupancy, and a hybrid strided-access approach for heuristic balancing. These methods ensure performance, portability, and productivity with a unified codebase. Our proposed methodologies outperform state-of-the-art single-GPU implementations based on CUDA on synthetic RMAT graphs. We analysed BFS performance across NVIDIA A100, Intel Max 1550, and AMD MI300X GPUs, achieving a peak performance of 153.27 GTEPS on an RMAT25-64 graph using 8 GPUs on the NVIDIA A100. Furthermore, our work demonstrates the capability to handle RMAT graphs up to scale 29, achieving superior performance on synthetic graphs and competitive results on real-world datasets.}},
  author       = {{Olgu, Kaan and Kenter, Tobias and Nunez-Yanez, Jose and McIntosh-Smith, Simon and Deakin, Tom}},
  booktitle    = {{Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis}},
  publisher    = {{ACM}},
  title        = {{{Towards Efficient Load Balancing BFS on GPUs: One Code for AMD, Intel & Nvidia}}},
  doi          = {{10.1145/3731599.3767570}},
  year         = {{2025}},
}

@techreport{62981,
  abstract     = {{Otus is a high-performance computing cluster that was launched in 2025 and is operated by the Paderborn Center for Parallel Computing (PC2) at Paderborn University in Germany. The system is part of the National High Performance Computing (NHR) initiative. Otus complements the previous supercomputer Noctua 2, offering approximately twice the computing power while retaining the three node types that were characteristic of Noctua 2: 1) CPU compute nodes with different memory capacities, 2) high-end GPU nodes, and 3) HPC-grade FPGA nodes. On the Top500 list, which ranks the 500 most powerful supercomputers in the world, Otus is in position 164 with the CPU partition and in position 255 with the GPU partition (June 2025). On the Green500 list, ranking the 500 most energy-efficient supercomputers in the world, Otus is in position 5 with the GPU partition (June 2025).


This article provides a comprehensive overview of the system in terms of its hardware, software, system integration, and its overall integration into the data center building to ensure energy-efficient operation. The article aims to provide unique insights for scientists using the system and for other centers operating HPC clusters. The article will be continuously updated to reflect the latest system setup and measurements. }},
  author       = {{Ehtesabi, Sadaf and Hossain, Manoar and Kenter, Tobias and Krawinkel, Andreas and Ostermann, Lukas and Plessl, Christian and Riebler, Heinrich and Rohde, Stefan and Schade, Robert and Schwarz, Michael and Simon, Jens and Winnwa, Nils and Wiens, Alex and Wu, Xin}},
  keywords     = {{Otus, Supercomputer, FPGA, PC2, Paderborn Center for Parallel Computing, Noctua 2, HPC}},
  pages        = {{33}},
  publisher    = {{Paderborn Center for Parallel Computing (PC2)}},
  title        = {{{Otus Supercomputer}}},
  doi          = {{10.48550/ARXIV.2512.07401}},
  volume       = {{1}},
  year         = {{2025}},
}

@inproceedings{59816,
  author       = {{Pape, Gerrit and Wintermann, Bjarne and Jungemann, Linus and Lass, Michael and Meyer, Marius and Riebler, Heinrich and Plessl, Christian}},
  booktitle    = {{Proceedings of the 15th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies}},
  location     = {{Kumamoto, Japan}},
  title        = {{{AuroraFlow, an Easy-to-Use, Low-Latency FPGA Communication Solution Demonstrated on Multi-FPGA Neural Network Inference}}},
  doi          = {{10.1145/3728179.3728190}},
  year         = {{2025}},
}

@inproceedings{65618,
  author       = {{Bröker, Mika and Menzel, Johannes and Plessl, Christian}},
  booktitle    = {{Proceedings of the 15th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies}},
  publisher    = {{ACM}},
  title        = {{{Evaluating the Strong Scaling Potential of AI Engines for Molecular Dynamics Simulations}}},
  doi          = {{10.1145/3728179.3728187}},
  year         = {{2025}},
}

@article{53474,
  abstract     = {{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.}},
  author       = {{Lass, Michael and Kenter, Tobias and Plessl, Christian and Brehm, Martin}},
  issn         = {{1099-4300}},
  journal      = {{Entropy}},
  number       = {{4}},
  publisher    = {{MDPI AG}},
  title        = {{{Characterizing Microheterogeneity in Liquid Mixtures via Local Density Fluctuations}}},
  doi          = {{10.3390/e26040322}},
  volume       = {{26}},
  year         = {{2024}},
}

@article{53663,
  abstract     = {{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.}},
  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 Wiens, Alex and Wu, Xin and Plessl, Christian and Simon, Jens}},
  journal      = {{Journal of large-scale research facilities}},
  keywords     = {{Noctua 2, Supercomputer, FPGA, PC2, Paderborn Center for Parallel Computing}},
  title        = {{{Noctua 2 Supercomputer}}},
  doi          = {{10.17815/jlsrf-8-187 }},
  volume       = {{9}},
  year         = {{2024}},
}

@article{55267,
  author       = {{Schäfer, F. and Trautmann, A. and Ngo, C. and Steiner, J. T. and Fuchs, C. and Volz, K. and Dobener, F. and Stein, M. and Meier, Torsten and Chatterjee, S.}},
  issn         = {{2469-9950}},
  journal      = {{Physical Review B}},
  number       = {{7}},
  publisher    = {{American Physical Society (APS)}},
  title        = {{{Optical Stark effect in type-II semiconductor heterostructures}}},
  doi          = {{10.1103/physrevb.109.075301}},
  volume       = {{109}},
  year         = {{2024}},
}

@inbook{56606,
  abstract     = {{<jats:title>Abstract</jats:title><jats:p>Most FPGA boards in the HPC domain are well-suited for parallel scaling because of the direct integration of versatile and high-throughput network ports. However, the utilization of their network capabilities is often challenging and error-prone because the whole network stack and communication patterns have to be implemented and managed on the FPGAs. Also, this approach conceptually involves a trade-off between the performance potential of improved communication and the impact of resource consumption for communication infrastructure, since the utilized resources on the FPGAs could otherwise be used for computations. In this work, we investigate this trade-off, firstly, by using synthetic benchmarks to evaluate the different configuration options of the communication framework ACCL and their impact on communication latency and throughput. Finally, we use our findings to implement a shallow water simulation whose scalability heavily depends on low-latency communication. With a suitable configuration of ACCL, good scaling behavior can be shown to all 48 FPGAs installed in the system. Overall, the results show that the availability of inter-FPGA communication frameworks as well as the configurability of framework and network stack are crucial to achieve the best application performance with low latency communication.</jats:p>}},
  author       = {{Meyer, Marius and Kenter, Tobias and Petrica, Lucian and O’Brien, Kenneth and Blott, Michaela and Plessl, Christian}},
  booktitle    = {{Lecture Notes in Computer Science}},
  isbn         = {{9783031697654}},
  issn         = {{0302-9743}},
  publisher    = {{Springer Nature Switzerland}},
  title        = {{{Optimizing Communication for Latency Sensitive HPC Applications on up to 48 FPGAs Using ACCL}}},
  doi          = {{10.1007/978-3-031-69766-1_9}},
  year         = {{2024}},
}

@inproceedings{56605,
  author       = {{Opdenhövel, Jan-Oliver and Alt, Christoph and Plessl, Christian and Kenter, Tobias}},
  booktitle    = {{2024 34th International Conference on Field-Programmable Logic and Applications (FPL)}},
  publisher    = {{IEEE}},
  title        = {{{StencilStream: A SYCL-based Stencil Simulation Framework Targeting FPGAs}}},
  doi          = {{10.1109/fpl64840.2024.00023}},
  year         = {{2024}},
}

@inproceedings{56607,
  author       = {{Tareen, Abdul Rehman and Meyer, Marius and Plessl, Christian and Kenter, Tobias}},
  booktitle    = {{2024 IEEE 32nd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)}},
  publisher    = {{IEEE}},
  title        = {{{HiHiSpMV: Sparse Matrix Vector Multiplication with Hierarchical Row Reductions on FPGAs with High Bandwidth Memory}}},
  doi          = {{10.1109/fccm60383.2024.00014}},
  volume       = {{35}},
  year         = {{2024}},
}

@inproceedings{56609,
  abstract     = {{The computation of electron repulsion integrals (ERIs) is a key component for quantum chemical methods. The intensive computation and bandwidth demand for ERI evaluation presents a significant challenge for quantum-mechanics-based atomistic simulations with hybrid density functional theory: due to the tens of trillions of ERI computations in each time step, practical applications are usually limited to thousands of atoms. In this work, we propose SERI, a high-throughput streaming accelerator for ERI computation on HBM-based FPGAs. In contrast to prior buffer-based designs, SERI proposes a novel streaming architecture to address the on-chip buffer limitation and the floorplanning challenge, and leverages the high-bandwidth memory to overcome the bandwidth bottleneck in prior designs. Moreover, to meet the varying computation, bandwidth, and floorplanning requirements between the 55 canonical quartet classes in ERI calculation, we design an automation tool, together with an accurate performance model, to automatically customize the architecture and floorplanning strategy for each canonical quartet class to maximize their throughput. Our performance evaluation on the AMD/Xilinx Alveo U280 FPGA board shows that, SERI achieves an average speedup of 9.80 x over the previous best-performing FPGA design, a 3.21x speedup over a 64-core AMD EPYC 7713 CPU, and a 15.64x speedup over an Nvidia A40 GPU. It reaches a peak throughput of 23.8 GERIS ($10^9$ ERIs per second) on one Alveo U280 FPGA. SERI will be released soon at https://github.com/SFU-HiAccel/SERI.}},
  author       = {{Stachura, Philip and Li, Guanyu and Wu, Xin and Plessl, Christian and Fang, Zhenman}},
  booktitle    = {{2024 34th International Conference on Field-Programmable Logic and Applications (FPL)}},
  pages        = {{60--68}},
  publisher    = {{IEEE}},
  title        = {{{SERI: High-Throughput Streaming Acceleration of Electron Repulsion Integral Computation in Quantum Chemistry using HBM-based FPGAs}}},
  doi          = {{10.1109/fpl64840.2024.00018}},
  year         = {{2024}},
}

@article{61251,
  abstract     = {{<jats:p>We theoretically investigate strategies for the deterministic creation of trains of time-bin entangled photons using an individual quantum emitter described by a Λ-type electronic system. We explicitly demonstrate the theoretical generation of linear cluster states with substantial numbers of entangled photonic qubits in full microscopic numerical simulations. The underlying scheme is based on the manipulation of ground state coherences through precise optical driving. One important finding is that the most easily accessible quality metrics, the achievable rotation fidelities, fall short in assessing the actual quantum correlations of the emitted photons in the face of losses. To address this, we explicitly calculate stabilizer generator expectation values as a superior gauge for the quantum properties of the generated many-photon state. With widespread applicability in other emitter and excitation–emission schemes also, our work lays the conceptual foundations for an in-depth practical analysis of time-bin entanglement based on full numerical simulations with predictive capabilities for realistic systems and setups, including losses and imperfections. The specific results shown in the present work illustrate that with controlled minimization of losses and realistic system parameters for quantum-dot type systems, useful linear cluster states of significant lengths can be generated in the calculations, discussing the possibility of scalability for quantum information processing endeavors.</jats:p>}},
  author       = {{Bauch, David and Köcher, Nikolas and Heinisch, Nils and Schumacher, Stefan}},
  issn         = {{2835-0103}},
  journal      = {{APL Quantum}},
  number       = {{3}},
  publisher    = {{AIP Publishing}},
  title        = {{{Time-bin entanglement in the deterministic generation of linear photonic cluster states}}},
  doi          = {{10.1063/5.0214197}},
  volume       = {{1}},
  year         = {{2024}},
}

@article{61253,
  abstract     = {{<jats:p>In the SUPER scheme (Swing-UP of the quantum EmitteR population), excitation of a quantum emitter is achieved with two off-resonant, red-detuned laser pulses. This allows the generation of high-quality single photons without the need of complex laser stray light suppression or careful spectral filtering. In the present work, we extend this promising method to quantum emitters, specifically semiconductor quantum dots, inside a resonant optical cavity. A significant advantage of the SUPER scheme is identified in that it eliminates re-excitation of the quantum emitter by suppressing photon emission during the excitation cycle. This, in turn, leads to almost ideal single-photon purity, overcoming a major factor typically limiting the quality of photons generated with quantum emitters in high-quality cavities. We further find that for cavity-mediated biexciton emission of degenerate photon pairs, the SUPER scheme leads to near-perfect biexciton initialization with very high values of polarization entanglement of emitted photon pairs.</jats:p>
          <jats:sec>
            <jats:title/>
            <jats:supplementary-material>
              <jats:permissions>
                <jats:copyright-statement>Published by the American Physical Society</jats:copyright-statement>
                <jats:copyright-year>2024</jats:copyright-year>
              </jats:permissions>
            </jats:supplementary-material>
          </jats:sec>}},
  author       = {{Heinisch, Nils and Köcher, Nikolas and Bauch, David and Schumacher, Stefan}},
  issn         = {{2643-1564}},
  journal      = {{Physical Review Research}},
  number       = {{1}},
  publisher    = {{American Physical Society (APS)}},
  title        = {{{Swing-up dynamics in quantum emitter cavity systems: Near ideal single photons and entangled photon pairs}}},
  doi          = {{10.1103/physrevresearch.6.l012017}},
  volume       = {{6}},
  year         = {{2024}},
}

@article{61255,
  abstract     = {{<jats:title>Abstract</jats:title>
               <jats:p>Topological states have been widely investigated in different types of systems and lattices. In the present work, we report on topological edge states in double-wave (DW) chains, which can be described by a generalized Aubry-André-Harper (AAH) model. For the specific system of a driven-dissipative exciton polariton system we show that in such potential chains, different types of edge states can form. For resonant optical excitation, we further find that the optical nonlinearity leads to a multistability of different edge states. This includes topologically protected edge states evolved directly from individual linear eigenstates as well as additional edge states that originate from nonlinearity-induced localization of bulk states. Extending the system into two dimensions (2D) by stacking horizontal DW chains in the vertical direction, we also create 2D multi-wave lattices. In such 2D lattices multiple Su–Schrieffer–Heeger (SSH) chains appear along the vertical direction. The combination of DW chains in the horizonal and SSH chains in the vertical direction then results in the formation of higher-order topological insulator corner states. Multistable corner states emerge in the nonlinear regime.</jats:p>}},
  author       = {{Schneider, Tobias and Gao, Wenlong and Zentgraf, Thomas and Schumacher, Stefan and Ma, Xuekai}},
  issn         = {{2192-8614}},
  journal      = {{Nanophotonics}},
  number       = {{4}},
  pages        = {{509--518}},
  publisher    = {{Walter de Gruyter GmbH}},
  title        = {{{Topological edge and corner states in coupled wave lattices in nonlinear polariton condensates}}},
  doi          = {{10.1515/nanoph-2023-0556}},
  volume       = {{13}},
  year         = {{2024}},
}

@article{61257,
  abstract     = {{<jats:p>Exceptional points (EPs), with their intriguing spectral topology, have attracted considerable attention in a broad range of physical systems, with potential sensing applications driving much of the present research in this field. Here, we investigate spectral topology and EPs in systems with significant nonlinearity, exemplified by a nonequilibrium exciton-polariton condensate. With the possibility to control loss and gain and nonlinearity by optical means, this system allows for a comprehensive analysis of the interplay of nonlinearities (Kerr type and saturable gain) and non-Hermiticity. Not only do we find that EPs can be intentionally shifted in parameter space by the saturable gain, but we also observe intriguing rotations and intersections of Riemann surfaces and find nonlinearity-enhanced sensing capabilities. With this, our results illustrate the potential of tailoring spectral topology and related phenomena in non-Hermitian systems by nonlinearity.</jats:p>
          <jats:sec>
            <jats:title/>
            <jats:supplementary-material>
              <jats:permissions>
                <jats:copyright-statement>Published by the American Physical Society</jats:copyright-statement>
                <jats:copyright-year>2024</jats:copyright-year>
              </jats:permissions>
            </jats:supplementary-material>
          </jats:sec>}},
  author       = {{Wingenbach, Jan and Schumacher, Stefan and Ma, Xuekai}},
  issn         = {{2643-1564}},
  journal      = {{Physical Review Research}},
  number       = {{1}},
  publisher    = {{American Physical Society (APS)}},
  title        = {{{Manipulating spectral topology and exceptional points by nonlinearity in non-Hermitian polariton systems}}},
  doi          = {{10.1103/physrevresearch.6.013148}},
  volume       = {{6}},
  year         = {{2024}},
}

@article{61259,
  author       = {{Bauch, Fabian and Dong, Chuan-Ding and Schumacher, Stefan}},
  issn         = {{1932-7447}},
  journal      = {{The Journal of Physical Chemistry C}},
  number       = {{8}},
  pages        = {{3525--3532}},
  publisher    = {{American Chemical Society (ACS)}},
  title        = {{{Dynamics of Electron–Hole Coulomb Attractive Energy and Dipole Moment of Hot Excitons in Donor–Acceptor Polymers}}},
  doi          = {{10.1021/acs.jpcc.3c07513}},
  volume       = {{128}},
  year         = {{2024}},
}