@inbook{45884, author = {{Hanselle, Jonas Manuel and Hüllermeier, Eyke and Mohr, Felix and Ngonga Ngomo, Axel-Cyrille and Sherif, Mohamed and Tornede, Alexander and Wever, Marcel Dominik}}, booktitle = {{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}, editor = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{85--104}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{Configuration and Evaluation}}}, doi = {{10.5281/zenodo.8068466}}, volume = {{412}}, year = {{2023}}, } @inbook{45878, author = {{Haake, Claus-Jochen and Hehenkamp, Burkhard and Polevoy, Gleb}}, booktitle = {{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}, editor = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{21--44}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{The Market for Services: Incentives, Algorithms, Implementation}}}, doi = {{10.5281/zenodo.8068414}}, volume = {{412}}, year = {{2023}}, } @inbook{45886, author = {{Wehrheim, Heike and Hüllermeier, Eyke and Becker, Steffen and Becker, Matthias and Richter, Cedric and Sharma, Arnab}}, booktitle = {{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}, editor = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{105--123}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{Composition Analysis in Unknown Contexts}}}, doi = {{10.5281/zenodo.8068510}}, volume = {{412}}, year = {{2023}}, } @misc{45917, author = {{Raeisi Nafchi, Masood}}, publisher = {{Paderborn University}}, title = {{{Reconfigurable Random Forest Implementation on FPGA}}}, year = {{2023}}, } @misc{45916, author = {{Yadalam Murali Kumar, Nihal}}, publisher = {{Paderborn University}}, title = {{{Data Analytics for Predictive Maintenance of Time Series Data}}}, year = {{2023}}, } @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}}, } @phdthesis{45781, author = {{Pukrop, Simon}}, title = {{{On Cloud Assisted, Restricted, and Reosurce Constrained Scheduling}}}, doi = {{10.17619/UNIPB/1-1768 }}, year = {{2023}}, } @misc{46053, author = {{Schneider, Fabian}}, title = {{{Utilizing Redundancy in Distributed Heterogeneous Storage}}}, year = {{2023}}, } @misc{46087, author = {{Ranade, Amruta}}, title = {{{Graph Neural Network-based Anomaly Detection in Smart Grid Energy Consumption}}}, year = {{2023}}, } @misc{46086, author = {{Ali, Osama}}, title = {{{Highly accurate deep compressed facial recognition}}}, year = {{2023}}, } @misc{46110, author = {{Ashri, Nivedita}}, title = {{{Virtual On-Demand Volunteer System Based on Delaunay Triangulation}}}, 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}}, } @misc{46221, author = {{N., N.}}, title = {{{Improving the End-of-Line Test of Custom-Built Geared Motors using Clustering based on Neural Networks}}}, year = {{2023}}, } @article{46251, author = {{Demir, Caglar and Ngonga Ngomo, Axel-Cyrille}}, journal = {{International Joint Conference on Artificial Intelligence}}, location = {{Macau}}, title = {{{Neuro-Symbolic Class Expression Learning}}}, 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}}, } @phdthesis{45780, author = {{Tornede, Alexander}}, title = {{{Advanced Algorithm Selection with Machine Learning: Handling Large Algorithm Sets, Learning From Censored Data, and Simplyfing Meta Level Decisions}}}, doi = {{10.17619/UNIPB/1-1780 }}, year = {{2023}}, } @unpublished{46579, abstract = {{The Koopman operator has become an essential tool for data-driven analysis, prediction and control of complex systems, the main reason being the enormous potential of identifying linear function space representations of nonlinear dynamics from measurements. Until now, the situation where for large-scale systems, we (i) only have access to partial observations (i.e., measurements, as is very common for experimental data) or (ii) deliberately perform coarse graining (for efficiency reasons) has not been treated to its full extent. In this paper, we address the pitfall associated with this situation, that the classical EDMD algorithm does not automatically provide a Koopman operator approximation for the underlying system if we do not carefully select the number of observables. Moreover, we show that symmetries in the system dynamics can be carried over to the Koopman operator, which allows us to massively increase the model efficiency. We also briefly draw a connection to domain decomposition techniques for partial differential equations and present numerical evidence using the Kuramoto--Sivashinsky equation.}}, author = {{Peitz, Sebastian and Harder, Hans and Nüske, Feliks and Philipp, Friedrich and Schaller, Manuel and Worthmann, Karl}}, booktitle = {{arXiv:2307.15325}}, title = {{{Partial observations, coarse graining and equivariance in Koopman operator theory for large-scale dynamical systems}}}, year = {{2023}}, } @article{23428, abstract = {{The Koopman operator has become an essential tool for data-driven approximation of dynamical (control) systems in recent years, e.g., via extended dynamic mode decomposition. Despite its popularity, convergence results and, in particular, error bounds are still quite scarce. In this paper, we derive probabilistic bounds for the approximation error and the prediction error depending on the number of training data points; for both ordinary and stochastic differential equations. Moreover, we extend our analysis to nonlinear control-affine systems using either ergodic trajectories or i.i.d. samples. Here, we exploit the linearity of the Koopman generator to obtain a bilinear system and, thus, circumvent the curse of dimensionality since we do not autonomize the system by augmenting the state by the control inputs. To the best of our knowledge, this is the first finite-data error analysis in the stochastic and/or control setting. Finally, we demonstrate the effectiveness of the proposed approach by comparing it with state-of-the-art techniques showing its superiority whenever state and control are coupled.}}, author = {{Nüske, Feliks and Peitz, Sebastian and Philipp, Friedrich and Schaller, Manuel and Worthmann, Karl}}, journal = {{Journal of Nonlinear Science}}, title = {{{Finite-data error bounds for Koopman-based prediction and control}}}, doi = {{10.1007/s00332-022-09862-1}}, volume = {{33}}, year = {{2023}}, } @article{21600, abstract = {{Many problems in science and engineering require an efficient numerical approximation of integrals or solutions to differential equations. For systems with rapidly changing dynamics, an equidistant discretization is often inadvisable as it results in prohibitively large errors or computational effort. To this end, adaptive schemes, such as solvers based on Runge–Kutta pairs, have been developed which adapt the step size based on local error estimations at each step. While the classical schemes apply very generally and are highly efficient on regular systems, they can behave suboptimally when an inefficient step rejection mechanism is triggered by structurally complex systems such as chaotic systems. To overcome these issues, we propose a method to tailor numerical schemes to the problem class at hand. This is achieved by combining simple, classical quadrature rules or ODE solvers with data-driven time-stepping controllers. Compared with learning solution operators to ODEs directly, it generalizes better to unseen initial data as our approach employs classical numerical schemes as base methods. At the same time it can make use of identified structures of a problem class and, therefore, outperforms state-of-the-art adaptive schemes. Several examples demonstrate superior efficiency. Source code is available at https://github.com/lueckem/quadrature-ML.}}, author = {{Dellnitz, Michael and Hüllermeier, Eyke and Lücke, Marvin and Ober-Blöbaum, Sina and Offen, Christian and Peitz, Sebastian and Pfannschmidt, Karlson}}, journal = {{SIAM Journal on Scientific Computing}}, number = {{2}}, pages = {{A579--A595}}, title = {{{Efficient time stepping for numerical integration using reinforcement learning}}}, doi = {{10.1137/21M1412682}}, volume = {{45}}, year = {{2023}}, }