@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}},
}

@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{46547,
  author       = {{Rogolino, Andrea and Filho, José B. G. and Fritsch, Lorena and Ardisson, José D. and da Silva, Marcos A. R. and Atta Diab, Gabriel Ali and Silva, Ingrid Fernandes and Moraes, Carlos André Ferreira and Forim, Moacir Rossi and Bauer, Matthias and Kühne, Thomas D. and Antonietti, Markus and Teixeira, Ivo F.}},
  issn         = {{2155-5435}},
  journal      = {{ACS Catalysis}},
  keywords     = {{Catalysis, General Chemistry, pc2-ressources, Computing Resources Provided by the Paderborn Center for Parallel Computing}},
  number       = {{13}},
  pages        = {{8662--8669}},
  publisher    = {{American Chemical Society (ACS)}},
  title        = {{{Direct Synthesis of Acetone by Aerobic Propane Oxidation Promoted by Photoactive Iron(III) Chloride under Mild Conditions}}},
  doi          = {{10.1021/acscatal.3c02092}},
  volume       = {{13}},
  year         = {{2023}},
}

@inproceedings{29946,
  author       = {{Schall, Christoph Wilhelm Theodor and Schöppner, Volker}},
  booktitle    = {{PPS36}},
  keywords     = {{Computing Resources Provided by the Paderborn Center for Parallel Computing}},
  title        = {{{Design of a test bench for measuring the degradation behavior of plastics during processing}}},
  year         = {{2023}},
}

@article{29947,
  author       = {{Schall, Christoph Wilhelm Theodor and Schöppner, Volker}},
  journal      = {{Polymer Engineering and Science}},
  keywords     = {{Computing Resources Provided by the Paderborn Center for Parallel Computing}},
  number       = {{3}},
  pages        = {{815--823}},
  title        = {{{Measurement of material degradation in dependence of shear rate, temperature, and residence time}}},
  doi          = {{10.1002/pen.25887}},
  volume       = {{62}},
  year         = {{2022}},
}

@article{29948,
  author       = {{Brüning, Florian and Schöppner, Volker}},
  journal      = {{Polymers 14}},
  keywords     = {{Computing Resources Provided by the Paderborn Center for Parallel Computing}},
  title        = {{{Numerical Simulation of Solids Conveying in Grooved Feed Sections of Single Screw Extruders}}},
  doi          = {{https://doi.org/10.3390/polym14020256}},
  year         = {{2022}},
}

@inproceedings{1590,
  abstract     = {{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.

We 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.}},
  author       = {{Lass, Michael and Mohr, Stephan and Wiebeler, Hendrik and Kühne, Thomas and Plessl, Christian}},
  booktitle    = {{Proc. Platform for Advanced Scientific Computing (PASC) Conference}},
  isbn         = {{978-1-4503-5891-0/18/07}},
  keywords     = {{approximate computing, linear algebra, matrix inversion, matrix p-th roots, numeric algorithm, parallel computing}},
  location     = {{Basel, Switzerland}},
  publisher    = {{ACM}},
  title        = {{{A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices}}},
  doi          = {{10.1145/3218176.3218231}},
  year         = {{2018}},
}