@inproceedings{34138, abstract = {{Variational Quantum Algorithms (VQAs), such as the Quantum Approximate Optimization Algorithm (QAOA) of [Farhi, Goldstone, Gutmann, 2014], have seen intense study towards near-term applications on quantum hardware. A crucial parameter for VQAs is the depth of the variational ansatz used - the smaller the depth, the more amenable the ansatz is to near-term quantum hardware in that it gives the circuit a chance to be fully executed before the system decoheres. This potential for depth reduction has made VQAs a staple of Noisy Intermediate-Scale Quantum (NISQ)-era research. In this work, we show that approximating the optimal depth for a given VQA ansatz is intractable. Formally, we show that for any constant $\epsilon>0$, it is QCMA-hard to approximate the optimal depth of a VQA ansatz within multiplicative factor $N^{1-\epsilon}$, for $N$ denoting the encoding size of the VQA instance. (Here, Quantum Classical Merlin-Arthur (QCMA) is a quantum generalization of NP.) We then show that this hardness persists even in the "simpler" setting of QAOAs. To our knowledge, this yields the first natural QCMA-hard-to-approximate problems. To achieve these results, we bypass the need for a PCP theorem for QCMA by appealing to the disperser-based NP-hardness of approximation construction of [Umans, FOCS 1999].}}, author = {{Bittel, Lennart and Gharibian, Sevag and Kliesch, Martin}}, booktitle = {{Proceedings of the 38th Computational Complexity Conference (CCC)}}, number = {{34}}, pages = {{34:1--34:24}}, title = {{{The Optimal Depth of Variational Quantum Algorithms Is QCMA-Hard to Approximate}}}, doi = {{10.4230/LIPIcs.CCC.2023.34}}, volume = {{264}}, year = {{2023}}, } @article{46133, author = {{Bopp, Frederik and Schall, Johannes and Bart, Nikolai and Vögl, Florian and Cullip, Charlotte and Sbresny, Friedrich and Boos, Katarina and Thalacker, Christopher and Lienhart, Michelle and Rodt, Sven and Reuter, Dirk and Ludwig, Arne and Wieck, Andreas D. and Reitzenstein, Stephan and Müller, Kai and Finley, Jonathan J.}}, issn = {{2469-9950}}, journal = {{Physical Review B}}, number = {{16}}, publisher = {{American Physical Society (APS)}}, title = {{{Coherent driving of direct and indirect excitons in a quantum dot molecule}}}, doi = {{10.1103/physrevb.107.165426}}, volume = {{107}}, year = {{2023}}, } @article{46132, author = {{Littmann, Mario and Reuter, Dirk and As, Donat Josef}}, issn = {{0370-1972}}, journal = {{physica status solidi (b)}}, keywords = {{Condensed Matter Physics, Electronic, Optical and Magnetic Materials}}, number = {{7}}, publisher = {{Wiley}}, title = {{{Remote Epitaxy of Cubic Gallium Nitride on Graphene‐Covered 3C‐SiC Substrates by Plasma‐Assisted Molecular Beam Epitaxy}}}, doi = {{10.1002/pssb.202300034}}, volume = {{260}}, year = {{2023}}, } @article{46138, abstract = {{This work reports a fully guided setup for single-mode squeezing on integrated titanium-indiffused periodically poled nonlinear resonators. A continuous-wave laser beam is delivered and the squeezed field is collected by single-mode fibers; up to −3.17(9) dB of useful squeezing is available in fibers. To showcase the usefulness of such a fiber-coupled device, we applied the generated squeezed light in a fiber-based phase sensing experiment, showing a quantum enhancement in the signal-to-noise ratio of 0.35 dB. Moreover, our investigation of the effect of photorefraction on the cavity resonance condition suggests that it causes system instabilities at high powers.}}, author = {{Domeneguetti, Renato and Stefszky, Michael and Herrmann, Harald and Silberhorn, Christine and Andersen, Ulrik L. and Neergaard-Nielsen, Jonas S. and Gehring, Tobias}}, issn = {{0146-9592}}, journal = {{Optics Letters}}, keywords = {{Atomic and Molecular Physics, and Optics}}, number = {{11}}, publisher = {{Optica Publishing Group}}, title = {{{Fully guided and phase locked Ti:PPLN waveguide squeezing for applications in quantum sensing}}}, doi = {{10.1364/ol.486654}}, volume = {{48}}, year = {{2023}}, } @article{46120, abstract = {{The rise of exascale supercomputers has fueled competition among GPU vendors, driving lattice QCD developers to write code that supports multiple APIs. Moreover, new developments in algorithms and physics research require frequent updates to existing software. These challenges have to be balanced against constantly changing personnel. At the same time, there is a wide range of applications for HISQ fermions in QCD studies. This situation encourages the development of software featuring a HISQ action that is flexible, high-performing, open source, easy to use, and easy to adapt. In this technical paper, we explain the design strategy, provide implementation details, list available algorithms and modules, and show key performance indicators for SIMULATeQCD, a simple multi-GPU lattice code for large-scale QCD calculations, mainly developed and used by the HotQCD collaboration. The code is publicly available on GitHub.}}, author = {{Mazur, Lukas and Bollweg, Dennis and Clarke, David A. and Altenkort, Luis and Kaczmarek, Olaf and Larsen, Rasmus and Shu, Hai-Tao and Goswami, Jishnu and Scior, Philipp and Sandmeyer, Hauke and Neumann, Marius and Dick, Henrik and Ali, Sajid and Kim, Jangho and Schmidt, Christian and Petreczky, Peter and Mukherjee, Swagato}}, journal = {{Computer Physics Communications}}, title = {{{SIMULATeQCD: A simple multi-GPU lattice code for QCD calculations}}}, doi = {{10.48550/ARXIV.2306.01098}}, year = {{2023}}, } @article{46119, author = {{Altenkort, Luis and Eller, Alexander M. and Francis, Anthony and Kaczmarek, Olaf and Mazur, Lukas and Moore, Guy D. and Shu, Hai-Tao}}, issn = {{2470-0010}}, journal = {{Physical Review D}}, number = {{1}}, publisher = {{American Physical Society (APS)}}, title = {{{Viscosity of pure-glue QCD from the lattice}}}, doi = {{10.1103/physrevd.108.014503}}, volume = {{108}}, 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}}, } @article{46278, abstract = {{Site-controlled Ga droplets on AlGaAs substrates are fabricated using area-selective deposition of Ga through apertures in a mask during molecular beam epitaxy (MBE). The Ga droplets can be crystallized into GaAs quantum dots using a crystallization step under As flux. In order to model the complex process, including the masked deposition of the droplets and a reduction of their number during a thermal annealing step, a multiscale kinetic Monte Carlo (mkMC) simulation of self-assembled Ga droplet formation on AlGaAs is expanded for area-selective deposition. The simulation has only two free model parameters: the activation energy for surface diffusion and the activation energy for thermal escape of adatoms from a droplet. Simulated droplet numbers within the opening of the aperture agree quantitatively with the experimental results down to the perfect site-control, with one droplet per aperture. However, the model parameters are different compared to those of the self-assembled droplet growth. We attribute this to the presence of the mask in close proximity to the surface, which modifies the local process temperature and the As background. This approach also explains the dependence of the model parameters on the size of the aperture.}}, author = {{Feddersen, Stefan and Zolatanosha, Viktoryia and Alshaikh, Ahmed and Reuter, Dirk and Heyn, Christian}}, issn = {{2079-4991}}, journal = {{Nanomaterials}}, keywords = {{General Materials Science, General Chemical Engineering}}, number = {{3}}, publisher = {{MDPI AG}}, title = {{{Modeling of Masked Droplet Deposition for Site-Controlled Ga Droplets}}}, doi = {{10.3390/nano13030466}}, volume = {{13}}, year = {{2023}}, } @inproceedings{46485, abstract = {{We present a miniaturized pulse shaping device that creates an arbitrary dispersion through the interaction of multiple metasurfaces on less than 2 mm3 volume. For this, a metalens and a grating-metasurface between two silver mirrors are fabricated. The grating contains further phase information to achieve the device's pulse shaping functionality.}}, author = {{Geromel, René and Georgi, Philip and Protte, Maximilian and Bartley, Tim and Huang, Lingling and Zentgraf, Thomas}}, booktitle = {{CLEO: Fundamental Science 2023}}, location = {{San Jose, USA}}, publisher = {{Optica Publishing Group}}, title = {{{Dispersion control with integrated plasmonic metasurfaces}}}, doi = {{10.1364/cleo_fs.2023.fth4d.3}}, year = {{2023}}, } @article{44851, abstract = {{We present the fabrication of strain-free quantum dots in the In0.53Ga0.47As/In0.52Al0.48As-system lattice matched to InP, as future sources for single and entangled photons for long-haul fiber-based quantum communication in the optical C-band. We achieved these quantum dots by local droplet etching via InAl droplets in an In0.52Al0.48As layer and subsequent filling of the holes with In0.53Ga0.47As. Here, we present detailed investigations of the hole morphologies measured by atomic force microscopy. Statistical analysis of a set of nanoholes reveals a high degree of symmetry for nearly half of them when etched at optimized temperatures. Overgrowth with 50–150 nm In0.52Al0.48As increases their diameter and elongates the holes along the [01̄1]-direction. By systematically scanning the parameter space, we were able to fill the holes with In0.53Ga0.47As, and by capping the filled holes and performing photoluminescence measurements, we observe photoluminescence emission in the O-band up into the C-band depending on the filling height of the nanoholes.}}, author = {{Deutsch, D. and Buchholz, C. and Zolatanosha, V. and Jöns, K. D. and Reuter, D.}}, issn = {{2158-3226}}, journal = {{AIP Advances}}, keywords = {{General Physics and Astronomy}}, number = {{5}}, publisher = {{AIP Publishing}}, title = {{{Telecom C-band photon emission from (In,Ga)As quantum dots generated by filling nanoholes in In0.52Al0.48As layers}}}, doi = {{10.1063/5.0147281}}, volume = {{13}}, year = {{2023}}, } @inproceedings{42459, author = {{Ostermann, Moritz and Behm, Jonathan and Marten, Thorsten and Tröster, Thomas}}, booktitle = {{WerkstoffPlus Auto 13. Fachtagung für neue Fahrzeug- und Werkstoffkonzepte}}, location = {{Stuttgart}}, title = {{{NeMo.bil - Dekarbonisierung des Verkehrs mithilfe von Leichtbau-Fahrzeugschwärmen}}}, year = {{2023}}, } @article{46741, author = {{Zscherp, Mario Fabian and Jentsch, Silas Aurel and Müller, Marius Johannes and Lider, Vitalii and Becker, Celina and Chen, Limei and Littmann, Mario and Meier, Falco and Beyer, Andreas and Hofmann, Detlev Michael and As, Donat Josef and Klar, Peter Jens and Volz, Kerstin and Chatterjee, Sangam and Schörmann, Jörg}}, issn = {{1944-8244}}, journal = {{ACS Applied Materials & Interfaces}}, keywords = {{General Materials Science}}, number = {{33}}, pages = {{39513--39522}}, publisher = {{American Chemical Society (ACS)}}, title = {{{Overcoming the Miscibility Gap of GaN/InN in MBE Growth of Cubic InxGa1–xN}}}, doi = {{10.1021/acsami.3c06319}}, volume = {{15}}, year = {{2023}}, } @inproceedings{46762, author = {{Tchomgue Simeu, Arnold and Mahnken, Rolf}}, booktitle = {{XI International Conference on Adaptive Modeling and Simulation}}, publisher = {{CIMNE}}, title = {{{Mesh- and model adaptivity for elasto-plastic mean-field and full-field homogenization based on downwind and upwind approximations}}}, doi = {{10.23967/admos.2023.054}}, year = {{2023}}, } @article{46815, abstract = {{In this work, the influence of the filler–matrix adhesion on the tensile properties of laser-sintered parts built with Polyamide 613 filled with glass beads was investigated. For this purpose, dry blends of glass beads with and without organosilane coupling agents and polyamide powder were prepared and processed into tensile specimens on an EOS P396 laser sintering system. The samples were tested both in the dry state and after an accelerated conditioning in a climate chamber. Furthermore, finite element method (FEM) simulations were performed to model the extreme cases of optimum adhesion and no adhesion. By correlating the tensile tests with the simulation results and by analyzing the fracture surfaces, it was shown that the filler–matrix adhesion is sufficient in the dry state but is strongly degraded by conditioning. Even the presence of various organosilane thin films could not prevent a strong deterioration of the filler–matrix adhesion and the associated deterioration of the mechanical properties. Since a comparison with an injection-molded sample of the same polymer filler combination shows identical behavior after conditioning, it is assumed that this problem is not limited to additively manufactured parts.}}, author = {{Kletetzka, Ivo and Kosanke, Maren and Meinderink, Dennis and Neßlinger, Vanessa and Grundmeier, Guido and Schmid, Hans-Joachim}}, issn = {{2363-9512}}, journal = {{Progress in Additive Manufacturing}}, keywords = {{Industrial and Manufacturing Engineering}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{Influence of the filler–matrix adhesion and the effects of conditioning on tensile properties of laser-sintered parts built with polyamide–glass bead dry blends}}}, doi = {{10.1007/s40964-023-00501-z}}, year = {{2023}}, } @unpublished{43049, abstract = {{Abstract In this work, the influence of the filler matrix adhesion on the tensile properties of laser-sintered parts built with Polyamide 613 filled with glass beads was investigated. For this purpose, dry blends of glass beads with and without organosilane coupling agents and polyamide powder were prepared and processed into tensile specimens on an EOS P396. The samples were tested both in the dry state and after an accelerated conditioning in a climate chamber. Furthermore, FEM simulations were performed to model the limiting cases of optimum adhesion and no adhesion. By correlating the tensile tests with the simulation results and by analyzing the fracture surfaces, it was shown that the filler matrix adhesion is sufficient in the dry state but is strongly degraded by conditioning. Even the presence of various organosilane thin films could not prevent a strong deterioration of the filler-matrix adhesion and the associated deterioration of the mechanical properties. Since a comparison with an injection molded sample of the same polymer filler combination shows identical behavior after conditioning, it is assumed that this problem is not limited to additively manufactured parts.}}, author = {{Kletetzka, Ivo and Kosanke, Maren and Meinderink, Dennis and Neßlinger, Vanessa and Grundmeier, Guido and Schmid, Hans-Joachim}}, publisher = {{Research Square Platform LLC}}, title = {{{Influence of the filler matrix adhesion and the effects of conditioning on tensile properties of laser sintered parts built with polyamide glass bead dry blends}}}, year = {{2023}}, } @inproceedings{45783, author = {{Kletetzka, Ivo}}, location = {{Berlin}}, title = {{{Tensile Testing for Polymer AM - Best Pratice at the DMRC}}}, year = {{2023}}, } @article{43046, abstract = {{In the laser sintering technology, the semi-crystalline polymer material is exposed to elevated temperatures during processing, which leads to serious material ageing for most materials. This has already been investigated intensively by various authors. However, the ageing of the material at ambient temperatures during shelf life has not been the focus so far. The need to analyse the shelf life can be derived from an ecological and economic point of view. This work is focusing on the shelf life of PA2200 (PA12). To reduce the potential influences of powder production fluctuations, two different powder batches stored for 5.5 years and 6.5 years are investigated and compared to a reference powder produced 0.5 years before these investigations. Multiple powder analyses and part characterisations have been performed. A significant yellowing and molecular chain length reduction can be derived from the measurement results. Whereas the influence on mechanical part performance was minor, the parts built with the stored powders are more yellowish. As it is most likely that this is due to the consumption of polyamide stabilisers, it can be assumed that these parts will be subject to significantly faster ageing. Therefore, it is still not recommended to use the stored powders for critical parts or light intense and humid environments.}}, author = {{Klippstein, Sven Helge and Kletetzka, Ivo and Sural, Ilknur and Schmid, Hans-Joachim}}, journal = {{The International Journal of Advanced Manufacturing Technology }}, keywords = {{Selective laser sintering, Shelf life, Polyamide 12, powder, PA2200, material ageing}}, publisher = {{Springer}}, title = {{{Influence of a prolonged shelf time on PA12 laser sintering powder and resulting part properties}}}, doi = {{https://doi.org/10.1007/s00170-023-11243-1}}, year = {{2023}}, } @misc{46861, author = {{Sajadi, Said}}, title = {{{Charakterisierung und Bewertung von flammgeschützten PA12 Pulvermischungen hinsichtlich der Verarbeitbarkeit im Lasersinter-Prozess}}}, year = {{2023}}, }