@inproceedings{50466, abstract = {{A key challenge in designing efficient optical phased arrays is the lack of a well-designed radiator. This work explores horn antennas numerically optimized to target high upward radiation efficiency to be employed in silicon-based phased arrays capable of producing elegant radiation patterns in the far-field.}}, author = {{Farheen, Henna and Joshi, S. and Scheytt, J. Christoph and Myroshnychenko, Viktor and Förstner, Jens}}, booktitle = {{2023 IEEE Photonics Conference (IPC)}}, keywords = {{tet_topic_opticalantenna}}, publisher = {{IEEE}}, title = {{{Increasing the upward radiation efficiency of optical phased arrays using asymmetric silicon horn antennas}}}, doi = {{10.1109/ipc57732.2023.10360519}}, year = {{2023}}, } @inproceedings{42163, abstract = {{The article shows how to learn models of dynamical systems from data which are governed by an unknown variational PDE. Rather than employing reduction techniques, we learn a discrete field theory governed by a discrete Lagrangian density $L_d$ that is modelled as a neural network. Careful regularisation of the loss function for training $L_d$ is necessary to obtain a field theory that is suitable for numerical computations: we derive a regularisation term which optimises the solvability of the discrete Euler--Lagrange equations. Secondly, we develop a method to find solutions to machine learned discrete field theories which constitute travelling waves of the underlying continuous PDE.}}, author = {{Offen, Christian and Ober-Blöbaum, Sina}}, booktitle = {{Geometric Science of Information}}, editor = {{Nielsen, F and Barbaresco, F}}, keywords = {{System identification, discrete Lagrangians, travelling waves}}, location = {{Saint-Malo, Palais du Grand Large, France}}, pages = {{569--579}}, publisher = {{Springer, Cham.}}, title = {{{Learning discrete Lagrangians for variational PDEs from data and detection of travelling waves}}}, doi = {{10.1007/978-3-031-38271-0_57}}, volume = {{14071}}, year = {{2023}}, } @article{43018, author = {{Alhaddad, Samer and Förstner, Jens and Grynko, Yevgen}}, issn = {{0022-4073}}, journal = {{Journal of Quantitative Spectroscopy and Radiative Transfer}}, keywords = {{tet_topic_scattering}}, publisher = {{Elsevier BV}}, title = {{{Numerical study of light backscattering from layers of absorbing irregular particles larger than the wavelength}}}, doi = {{10.1016/j.jqsrt.2023.108557}}, volume = {{302}}, year = {{2023}}, } @inproceedings{43229, author = {{Claes, Leander}}, booktitle = {{Fortschritte der Akustik - DAGA 2023}}, location = {{Hamburg}}, pages = {{7--14}}, title = {{{Bestimmung der Volumenviskosität mittels akustischer Absorptionsmessung}}}, year = {{2023}}, } @article{37280, author = {{Rose, Hendrik and Vasil'ev, A. N. and Tikhonova, O. V. and Meier, Torsten and Sharapova, Polina}}, issn = {{2469-9926}}, journal = {{Physical Review A}}, number = {{1}}, publisher = {{American Physical Society (APS)}}, title = {{{Quantum-optical excitations of semiconductor nanostructures in a microcavity using a two-band model and a single-mode quantum field}}}, doi = {{10.1103/physreva.107.013703}}, volume = {{107}}, year = {{2023}}, } @inproceedings{43393, author = {{Bernemann, Sören Antonius and Maćkowiak, Jan and Maćkowiak, Jerzy and Kenig, Eugeny}}, location = {{Paderborn}}, title = {{{Computerunterstützte Strömungsuntersuchung von landwirtschaftlichen Abfällen}}}, year = {{2023}}, } @inproceedings{43111, author = {{Dechert, Christopher and Kengni Nkouemou, Augustin and Kenig, Eugeny Y.}}, location = {{Frankfurt am Main}}, title = {{{Vergleichende Untersuchung der Wirkung verschiedener Mikrostrukturen auf die Flüssigkeitsausbreitung}}}, year = {{2023}}, } @article{45596, abstract = {{Dielectric metasurfaces provide a unique platform for efficient harmonic generation and optical wavefront manipulation at the nanoscale. Tailoring phase and amplitude of a nonlinearly generated wave with a high emission efficiency using resonance-based metasurfaces is a challenging task that often requires state-of-the-art numerical methods. Here, we propose a simple yet effective approach combining a sampling method with a Monte Carlo approach to design the third-harmonic wavefront generated by all-dielectric metasurfaces composed of elliptical silicon nanodisks. Using this approach, we theoretically demonstrate the full nonlinear 2π phase control with a uniform and highest possible amplitude in the considered parameter space, allowing us to design metasurfaces operating as third harmonic beam deflectors capable of steering light into a desired direction with high emission efficiency. The TH beam deflection with a record calculated average conversion efficiency of 1.2 × 10–1 W–2 is achieved. We anticipate that the proposed approach will be widely applied as alternative to commonly used optimization algorithms with higher complexity and implementation effort for the design of metasurfaces with other holographic functionalities.}}, author = {{Hähnel, David and Förstner, Jens and Myroshnychenko, Viktor}}, issn = {{2330-4022}}, journal = {{ACS Photonics}}, keywords = {{tet_topic_meta}}, publisher = {{American Chemical Society (ACS)}}, title = {{{Efficient Modeling and Tailoring of Nonlinear Wavefronts in Dielectric Metasurfaces}}}, doi = {{10.1021/acsphotonics.2c01967}}, year = {{2023}}, } @article{43827, abstract = {{A series of new organic donor–π–acceptor dyes incorporating a diquat moiety as a novel electron-acceptor unit have been synthesized and characterized. The analytical data were supported by DFT calculations. These dyes were explored in the aerobic thiocyanation of indoles and pyrroles. Here they showed a high photocatalytic activity under visible light, giving isolated yields of up to 97 %. In addition, the photocatalytic activity of standalone diquat and methyl viologen through formation of an electron donor acceptor complex is presented.}}, author = {{Meier, Armin and Badalov, Sabuhi and Biktagirov, Timur and Schmidt, Wolf Gero and Wilhelm, René}}, issn = {{0947-6539}}, journal = {{Chemistry – A European Journal}}, keywords = {{General Chemistry, Catalysis, Organic Chemistry}}, number = {{22}}, pages = {{ e202203541}}, publisher = {{Wiley}}, title = {{{Diquat Based Dyes: A New Class of Photoredox Catalysts and Their Use in Aerobic Thiocyanation}}}, doi = {{10.1002/chem.202203541}}, volume = {{ 29}}, year = {{2023}}, } @article{38041, abstract = {{While FPGA accelerator boards and their respective high-level design tools are maturing, there is still a lack of multi-FPGA applications, libraries, and not least, benchmarks and reference implementations towards sustained HPC usage of these devices. As in the early days of GPUs in HPC, for workloads that can reasonably be decoupled into loosely coupled working sets, multi-accelerator support can be achieved by using standard communication interfaces like MPI on the host side. However, for performance and productivity, some applications can profit from a tighter coupling of the accelerators. FPGAs offer unique opportunities here when extending the dataflow characteristics to their communication interfaces. In this work, we extend the HPCC FPGA benchmark suite by multi-FPGA support and three missing benchmarks that particularly characterize or stress inter-device communication: b_eff, PTRANS, and LINPACK. With all benchmarks implemented for current boards with Intel and Xilinx FPGAs, we established a baseline for multi-FPGA performance. Additionally, for the communication-centric benchmarks, we explored the potential of direct FPGA-to-FPGA communication with a circuit-switched inter-FPGA network that is currently only available for one of the boards. The evaluation with parallel execution on up to 26 FPGA boards makes use of one of the largest academic FPGA installations.}}, author = {{Meyer, Marius and Kenter, Tobias and Plessl, Christian}}, issn = {{1936-7406}}, journal = {{ACM Transactions on Reconfigurable Technology and Systems}}, keywords = {{General Computer Science}}, publisher = {{Association for Computing Machinery (ACM)}}, title = {{{Multi-FPGA Designs and Scaling of HPC Challenge Benchmarks via MPI and Circuit-Switched Inter-FPGA Networks}}}, doi = {{10.1145/3576200}}, year = {{2023}}, } @inproceedings{43228, abstract = {{The computation of electron repulsion integrals (ERIs) over Gaussian-type orbitals (GTOs) is a challenging problem in quantum-mechanics-based atomistic simulations. In practical simulations, several trillions of ERIs may have to be computed for every time step. In this work, we investigate FPGAs as accelerators for the ERI computation. We use template parameters, here within the Intel oneAPI tool flow, to create customized designs for 256 different ERI quartet classes, based on their orbitals. To maximize data reuse, all intermediates are buffered in FPGA on-chip memory with customized layout. The pre-calculation of intermediates also helps to overcome data dependencies caused by multi-dimensional recurrence relations. The involved loop structures are partially or even fully unrolled for high throughput of FPGA kernels. Furthermore, a lossy compression algorithm utilizing arbitrary bitwidth integers is integrated in the FPGA kernels. To our best knowledge, this is the first work on ERI computation on FPGAs that supports more than just the single most basic quartet class. Also, the integration of ERI computation and compression it a novelty that is not even covered by CPU or GPU libraries so far. Our evaluation shows that using 16-bit integer for the ERI compression, the fastest FPGA kernels exceed the performance of 10 GERIS ($10 \times 10^9$ ERIs per second) on one Intel Stratix 10 GX 2800 FPGA, with maximum absolute errors around $10^{-7}$ - $10^{-5}$ Hartree. The measured throughput can be accurately explained by a performance model. The FPGA kernels deployed on 2 FPGAs outperform similar computations using the widely used libint reference on a two-socket server with 40 Xeon Gold 6148 CPU cores of the same process technology by factors up to 6.0x and on a new two-socket server with 128 EPYC 7713 CPU cores by up to 1.9x.}}, author = {{Wu, Xin and Kenter, Tobias and Schade, Robert and Kühne, Thomas and Plessl, Christian}}, booktitle = {{2023 IEEE 31st Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)}}, pages = {{162--173}}, title = {{{Computing and Compressing Electron Repulsion Integrals on FPGAs}}}, doi = {{10.1109/FCCM57271.2023.00026}}, year = {{2023}}, } @article{45361, abstract = {{ 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. }}, author = {{Schade, Robert and Kenter, Tobias and Elgabarty, Hossam and Lass, Michael and Kühne, Thomas and Plessl, Christian}}, issn = {{1094-3420}}, journal = {{The International Journal of High Performance Computing Applications}}, keywords = {{Hardware and Architecture, Theoretical Computer Science, Software}}, publisher = {{SAGE Publications}}, title = {{{Breaking the exascale barrier for the electronic structure problem in ab-initio molecular dynamics}}}, doi = {{10.1177/10943420231177631}}, year = {{2023}}, } @inproceedings{28941, author = {{Afsahnoudeh, Reza and Holzmüller, Maik and Bader, Fabian and Homberg, Werner and Kenig, Eugeny Y.}}, location = {{Frankfurt am Main}}, title = {{{Numerische Untersuchung von Oberflächenstrukturierung zur Erhöhung der Effizienz von Kissenplatten-Wärmeübertragern}}}, year = {{2023}}, } @article{55900, author = {{Scharwald, Dennis and Meier, Torsten and Sharapova, Polina}}, issn = {{2643-1564}}, journal = {{Physical Review Research}}, number = {{4}}, publisher = {{American Physical Society (APS)}}, title = {{{Phase sensitivity of spatially broadband high-gain SU(1,1) interferometers}}}, doi = {{10.1103/physrevresearch.5.043158}}, volume = {{5}}, year = {{2023}}, } @inproceedings{49111, abstract = {{Due to the high variation in the application requirements of sound event detection (SED) systems, it is not sufficient to evaluate systems only in a single operating mode. Therefore, the community recently adopted the polyphonic sound detection score (PSDS) as an evaluation metric, which is the normalized area under the PSD receiver operating characteristic (PSD-ROC). It summarizes the system performance over a range of operating modes resulting from varying the decision threshold that is used to translate the system output scores into a binary detection output. Hence, it provides a more complete picture of the overall system behavior and is less biased by specific threshold tuning. However, besides the decision threshold there is also the post-processing that can be changed to enter another operating mode. In this paper we propose the post-processing independent PSDS (piPSDS) as a generalization of the PSDS. Here, the post-processing independent PSD-ROC includes operating points from varying post-processings with varying decision thresholds. Thus, it summarizes even more operating modes of an SED system and allows for system comparison without the need of implementing a post-processing and without a bias due to different post-processings. While piPSDS can in principle combine different types of post-processing, we here, as a first step, present median filter independent PSDS (miPSDS) results for this year’s DCASE Challenge Task4a systems. Source code is publicly available in our sed_scores_eval package (https://github.com/fgnt/sed_scores_eval).}}, author = {{Ebbers, Janek and Haeb-Umbach, Reinhold and Serizel, Romain}}, booktitle = {{Proceedings of the 8th Detection and Classification of Acoustic Scenes and Events 2023 Workshop (DCASE2023)}}, pages = {{36–40}}, title = {{{Post-Processing Independent Evaluation of Sound Event Detection Systems}}}, year = {{2023}}, } @inproceedings{48281, abstract = {{ We propose a general framework to compute the word error rate (WER) of ASR systems that process recordings containing multiple speakers at their input and that produce multiple output word sequences (MIMO). Such ASR systems are typically required, e.g., for meeting transcription. We provide an efficient implementation based on a dynamic programming search in a multi-dimensional Levenshtein distance tensor under the constraint that a reference utterance must be matched consistently with one hypothesis output. This also results in an efficient implementation of the ORC WER which previously suffered from exponential complexity. We give an overview of commonly used WER definitions for multi-speaker scenarios and show that they are specializations of the above MIMO WER tuned to particular application scenarios. We conclude with a discussion of the pros and cons of the various WER definitions and a recommendation when to use which.}}, author = {{von Neumann, Thilo and Boeddeker, Christoph and Kinoshita, Keisuke and Delcroix, Marc and Haeb-Umbach, Reinhold}}, booktitle = {{ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}}, keywords = {{Word Error Rate, Meeting Recognition, Levenshtein Distance}}, publisher = {{IEEE}}, title = {{{On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech Recognition Systems}}}, doi = {{10.1109/icassp49357.2023.10094784}}, year = {{2023}}, } @inproceedings{48275, abstract = {{MeetEval is an open-source toolkit to evaluate all kinds of meeting transcription systems. It provides a unified interface for the computation of commonly used Word Error Rates (WERs), specifically cpWER, ORC WER and MIMO WER along other WER definitions. We extend the cpWER computation by a temporal constraint to ensure that only words are identified as correct when the temporal alignment is plausible. This leads to a better quality of the matching of the hypothesis string to the reference string that more closely resembles the actual transcription quality, and a system is penalized if it provides poor time annotations. Since word-level timing information is often not available, we present a way to approximate exact word-level timings from segment-level timings (e.g., a sentence) and show that the approximation leads to a similar WER as a matching with exact word-level annotations. At the same time, the time constraint leads to a speedup of the matching algorithm, which outweighs the additional overhead caused by processing the time stamps.}}, author = {{von Neumann, Thilo and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}}, booktitle = {{Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments}}, keywords = {{Speech Recognition, Word Error Rate, Meeting Transcription}}, location = {{Dublin}}, title = {{{MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems}}}, year = {{2023}}, } @inproceedings{47128, author = {{Cord-Landwehr, Tobias and Boeddeker, Christoph and Zorilă, Cătălin and Doddipatla, Rama and Haeb-Umbach, Reinhold}}, booktitle = {{ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}}, location = {{Rhodes}}, publisher = {{IEEE}}, title = {{{Frame-Wise and Overlap-Robust Speaker Embeddings for Meeting Diarization}}}, doi = {{10.1109/icassp49357.2023.10095370}}, year = {{2023}}, } @inproceedings{47129, author = {{Cord-Landwehr, Tobias and Boeddeker, Christoph and Zorilă, Cătălin and Doddipatla, Rama and Haeb-Umbach, Reinhold}}, booktitle = {{INTERSPEECH 2023}}, publisher = {{ISCA}}, title = {{{A Teacher-Student Approach for Extracting Informative Speaker Embeddings From Speech Mixtures}}}, doi = {{10.21437/interspeech.2023-1379}}, year = {{2023}}, } @inproceedings{54439, author = {{Boeddeker, Christoph and Cord-Landwehr, Tobias and von Neumann, Thilo and Haeb-Umbach, Reinhold}}, booktitle = {{7th International Workshop on Speech Processing in Everyday Environments (CHiME 2023)}}, publisher = {{ISCA}}, title = {{{Multi-stage diarization refinement for the CHiME-7 DASR scenario}}}, doi = {{10.21437/chime.2023-10}}, year = {{2023}}, }