@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}}, } @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{32183, author = {{Hou, W and Yao, Y and Li, Y and Peng, B and Shi, K and Zhou, Z and Pan, J and Liu, M and Hu, J}}, issn = {{2095-025x}}, journal = {{Frontiers of materials science}}, number = {{1}}, title = {{{Linearly shifting ferromagnetic resonance response of La0.7Sr0.3MnO3 thin film for body temperature sensors}}}, volume = {{16}}, year = {{2022}}, } @article{32234, author = {{Wojciechowski, M}}, issn = {{2352-3409}}, journal = {{Data Brief}}, pages = {{108318}}, title = {{{Dataset for random uniform distributions of 2D circles and 3D spheres.}}}, volume = {{43}}, year = {{2022}}, } @article{40523, abstract = {{AbstractTailored nanoscale quantum light sources, matching the specific needs of use cases, are crucial building blocks for photonic quantum technologies. Several different approaches to realize solid-state quantum emitters with high performance have been pursued and different concepts for energy tuning have been established. However, the properties of the emitted photons are always defined by the individual quantum emitter and can therefore not be controlled with full flexibility. Here we introduce an all-optical nonlinear method to tailor and control the single photon emission. We demonstrate a laser-controlled down-conversion process from an excited state of a semiconductor quantum three-level system. Based on this concept, we realize energy tuning and polarization control of the single photon emission with a control-laser field. Our results mark an important step towards tailored single photon emission from a photonic quantum system based on quantum optical principles.}}, author = {{Jonas, B. and Heinze, Dirk Florian and Schöll, E. and Kallert, P. and Langer, T. and Krehs, S. and Widhalm, A. and Jöns, Klaus and Reuter, Dirk and Schumacher, Stefan and Zrenner, Artur}}, issn = {{2041-1723}}, journal = {{Nature Communications}}, keywords = {{General Physics and Astronomy, General Biochemistry, Genetics and Molecular Biology, General Chemistry, Multidisciplinary}}, number = {{1}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{Nonlinear down-conversion in a single quantum dot}}}, doi = {{10.1038/s41467-022-28993-3}}, volume = {{13}}, year = {{2022}}, } @article{46121, author = {{Altenkort, Luis and Eller, Alexander M. and Kaczmarek, O. and Mazur, Lukas and Moore, Guy D. and Shu, Hai-Tao}}, issn = {{2470-0010}}, journal = {{Physical Review D}}, number = {{9}}, publisher = {{American Physical Society (APS)}}, title = {{{Lattice QCD noise reduction for bosonic correlators through blocking}}}, doi = {{10.1103/physrevd.105.094505}}, volume = {{105}}, year = {{2022}}, } @article{33226, abstract = {{A parallel hybrid quantum-classical algorithm for the solution of the quantum-chemical ground-state energy problem on gate-based quantum computers is presented. This approach is based on the reduced density-matrix functional theory (RDMFT) formulation of the electronic structure problem. For that purpose, the density-matrix functional of the full system is decomposed into an indirectly coupled sum of density-matrix functionals for all its subsystems using the adaptive cluster approximation to RDMFT. The approximations involved in the decomposition and the adaptive cluster approximation itself can be systematically converged to the exact result. The solutions for the density-matrix functionals of the effective subsystems involves a constrained minimization over many-particle states that are approximated by parametrized trial states on the quantum computer similarly to the variational quantum eigensolver. The independence of the density-matrix functionals of the effective subsystems introduces a new level of parallelization and allows for the computational treatment of much larger molecules on a quantum computer with a given qubit count. In addition, for the proposed algorithm techniques are presented to reduce the qubit count, the number of quantum programs, as well as its depth. The evaluation of a density-matrix functional as the essential part of our approach is demonstrated for Hubbard-like systems on IBM quantum computers based on superconducting transmon qubits.}}, author = {{Schade, Robert and Bauer, Carsten and Tamoev, Konstantin and Mazur, Lukas and Plessl, Christian and Kühne, Thomas}}, journal = {{Phys. Rev. Research}}, pages = {{033160}}, publisher = {{American Physical Society}}, title = {{{Parallel quantum chemistry on noisy intermediate-scale quantum computers}}}, doi = {{10.1103/PhysRevResearch.4.033160}}, volume = {{4}}, year = {{2022}}, } @article{33684, author = {{Schade, Robert and Kenter, Tobias and Elgabarty, Hossam and Lass, Michael and Schütt, Ole and Lazzaro, Alfio and Pabst, Hans and Mohr, Stephan and Hutter, Jürg and Kühne, Thomas and Plessl, Christian}}, issn = {{0167-8191}}, journal = {{Parallel Computing}}, keywords = {{Artificial Intelligence, Computer Graphics and Computer-Aided Design, Computer Networks and Communications, Hardware and Architecture, Theoretical Computer Science, Software}}, publisher = {{Elsevier BV}}, title = {{{Towards electronic structure-based ab-initio molecular dynamics simulations with hundreds of millions of atoms}}}, doi = {{10.1016/j.parco.2022.102920}}, volume = {{111}}, year = {{2022}}, } @article{27364, author = {{Meyer, Marius and Kenter, Tobias and Plessl, Christian}}, issn = {{0743-7315}}, journal = {{Journal of Parallel and Distributed Computing}}, title = {{{In-depth FPGA Accelerator Performance Evaluation with Single Node Benchmarks from the HPC Challenge Benchmark Suite for Intel and Xilinx FPGAs using OpenCL}}}, doi = {{10.1016/j.jpdc.2021.10.007}}, year = {{2022}}, } @article{50146, abstract = {{Recent advances in numerical methods significantly pushed forward the understanding of electrons coupled to quantized lattice vibrations. At this stage, it becomes increasingly important to also account for the effects of physically inevitable environments. In particular, we study the transport properties of the Hubbard-Holstein Hamiltonian that models a large class of materials characterized by strong electron-phonon coupling, in contact with a dissipative environment. Even in the one-dimensional and isolated case, simulating the quantum dynamics of such a system with high accuracy is very challenging due to the infinite dimensionality of the phononic Hilbert spaces. For this reason, the effects of dissipation on the conductance properties of such systems have not been investigated systematically so far. We combine the non-Markovian hierarchy of pure states method and the Markovian quantum jumps method with the newly introduced projected purified density-matrix renormalization group, creating powerful tensor-network methods for dissipative quantum many-body systems. Investigating their numerical properties, we find a significant speedup up to a factor $\sim 30$ compared to conventional tensor-network techniques. We apply these methods to study dissipative quenches, aiming for an in-depth understanding of the formation, stability, and quasi-particle properties of bipolarons. Surprisingly, our results show that in the metallic phase dissipation localizes the bipolarons, which is reminiscent of an indirect quantum Zeno effect. However, the bipolaronic binding energy remains mainly unaffected, even in the presence of strong dissipation, exhibiting remarkable bipolaron stability. These findings shed light on the problem of designing real materials exhibiting phonon-mediated high-$T_\mathrm{C}$ superconductivity.}}, author = {{Moroder, Mattia and Grundner, Martin and Damanet, François and Schollwöck, Ulrich and Mardazad, Sam and Flannigan, Stuart and Köhler, Thomas and Paeckel, Sebastian}}, journal = {{Physical Review B 107, 214310 (2023)}}, title = {{{Stable bipolarons in open quantum systems}}}, doi = {{10.1103/PhysRevB.107.214310}}, year = {{2022}}, } @article{50148, abstract = {{We develop a general decomposition of an ensemble of initial density profiles in terms of an average state and a basis of modes that represent the event-by-event fluctuations of the initial state. The basis is determined such that the probability distributions of the amplitudes of different modes are uncorrelated. Based on this decomposition, we quantify the different types and probabilities of event-by-event fluctuations in Glauber and Saturation models and investigate how the various modes affect different characteristics of the initial state. We perform simulations of the dynamical evolution with KoMPoST and MUSIC to investigate the impact of the modes on final-state observables and their correlations.}}, author = {{Borghini, Nicolas and Borrell, Marc and Feld, Nina and Roch, Hendrik and Schlichting, Sören and Werthmann, Clemens}}, journal = {{Phys. Rev. C 107 (2023) 034905}}, title = {{{Statistical analysis of initial state and final state response in heavy-ion collisions}}}, doi = {{10.1103/PhysRevC.107.034905}}, year = {{2022}}, } @article{50149, abstract = {{Abstract RNA editing processes are strikingly different in animals and plants. Up to thousands of specific cytidines are converted into uridines in plant chloroplasts and mitochondria whereas up to millions of adenosines are converted into inosines in animal nucleo-cytosolic RNAs. It is unknown whether these two different RNA editing machineries are mutually incompatible. RNA-binding pentatricopeptide repeat (PPR) proteins are the key factors of plant organelle cytidine-to-uridine RNA editing. The complete absence of PPR mediated editing of cytosolic RNAs might be due to a yet unknown barrier that prevents its activity in the cytosol. Here, we transferred two plant mitochondrial PPR-type editing factors into human cell lines to explore whether they could operate in the nucleo-cytosolic environment. PPR56 and PPR65 not only faithfully edited their native, co-transcribed targets but also different sets of off-targets in the human background transcriptome. More than 900 of such off-targets with editing efficiencies up to 91%, largely explained by known PPR-RNA binding properties, were identified for PPR56. Engineering two crucial amino acid positions in its PPR array led to predictable shifts in target recognition. We conclude that plant PPR editing factors can operate in the entirely different genetic environment of the human nucleo-cytosol and can be intentionally re-engineered towards new targets.}}, author = {{Lesch, Elena and Schilling, Maximilian T and Brenner, Sarah and Yang, Yingying and Gruss, Oliver J and Knoop, Volker and Schallenberg-Rüdinger, Mareike}}, issn = {{0305-1048}}, journal = {{Nucleic Acids Research}}, keywords = {{Genetics}}, number = {{17}}, pages = {{9966--9983}}, publisher = {{Oxford University Press (OUP)}}, title = {{{Plant mitochondrial RNA editing factors can perform targeted C-to-U editing of nuclear transcripts in human cells}}}, doi = {{10.1093/nar/gkac752}}, volume = {{50}}, year = {{2022}}, } @article{28099, abstract = {{N-body methods are one of the essential algorithmic building blocks of high-performance and parallel computing. Previous research has shown promising performance for implementing n-body simulations with pairwise force calculations on FPGAs. However, to avoid challenges with accumulation and memory access patterns, the presented designs calculate each pair of forces twice, along with both force sums of the involved particles. Also, they require large problem instances with hundreds of thousands of particles to reach their respective peak performance, limiting the applicability for strong scaling scenarios. This work addresses both issues by presenting a novel FPGA design that uses each calculated force twice and overlaps data transfers and computations in a way that allows to reach peak performance even for small problem instances, outperforming previous single precision results even in double precision, and scaling linearly over multiple interconnected FPGAs. For a comparison across architectures, we provide an equally optimized CPU reference, which for large problems actually achieves higher peak performance per device, however, given the strong scaling advantages of the FPGA design, in parallel setups with few thousand particles per device, the FPGA platform achieves highest performance and power efficiency.}}, author = {{Menzel, Johannes and Plessl, Christian and Kenter, Tobias}}, issn = {{1936-7406}}, journal = {{ACM Transactions on Reconfigurable Technology and Systems}}, number = {{1}}, pages = {{1--30}}, title = {{{The Strong Scaling Advantage of FPGAs in HPC for N-body Simulations}}}, doi = {{10.1145/3491235}}, volume = {{15}}, year = {{2021}}, } @article{32243, abstract = {{Abstract The defining feature of active particles is that they constantly propel themselves by locally converting chemical energy into directed motion. This active self-propulsion prevents them from equilibrating with their thermal environment (e.g. an aqueous solution), thus keeping them permanently out of equilibrium. Nevertheless, the spatial dynamics of active particles might share certain equilibrium features, in particular in the steady state. We here focus on the time-reversal symmetry of individual spatial trajectories as a distinct equilibrium characteristic. We investigate to what extent the steady-state trajectories of a trapped active particle obey or break this time-reversal symmetry. Within the framework of active Ornstein–Uhlenbeck particles we find that the steady-state trajectories in a harmonic potential fulfill path-wise time-reversal symmetry exactly, while this symmetry is typically broken in anharmonic potentials.}}, author = {{Dabelow, Lennart and Bo, Stefano and Eichhorn, Ralf}}, issn = {{1742-5468}}, journal = {{Journal of Statistical Mechanics: Theory and Experiment}}, keywords = {{Statistics, Probability and Uncertainty, Statistics and Probability, Statistical and Nonlinear Physics}}, number = {{3}}, publisher = {{IOP Publishing}}, title = {{{How irreversible are steady-state trajectories of a trapped active particle?}}}, doi = {{10.1088/1742-5468/abe6fd}}, volume = {{2021}}, year = {{2021}}, } @article{46122, author = {{Kaczmarek, Olaf and Mazur, Lukas and Sharma, Sayantan}}, issn = {{2470-0010}}, journal = {{Physical Review D}}, number = {{9}}, publisher = {{American Physical Society (APS)}}, title = {{{Eigenvalue spectra of QCD and the fate of UA(1) breaking towards the chiral limit}}}, doi = {{10.1103/physrevd.104.094518}}, volume = {{104}}, year = {{2021}}, } @article{46124, author = {{Altenkort, Luis and Eller, Alexander M. and Kaczmarek, O. and Mazur, Lukas and Moore, Guy D. and Shu, H.-T.}}, issn = {{2470-0010}}, journal = {{Physical Review D}}, number = {{1}}, publisher = {{American Physical Society (APS)}}, title = {{{Heavy quark momentum diffusion from the lattice using gradient flow}}}, doi = {{10.1103/physrevd.103.014511}}, volume = {{103}}, year = {{2021}}, } @article{46123, author = {{Altenkort, Luis and Eller, Alexander M. and Kaczmarek, O. and Mazur, Lukas and Moore, Guy D. and Shu, H.-T.}}, issn = {{2470-0010}}, journal = {{Physical Review D}}, number = {{11}}, publisher = {{American Physical Society (APS)}}, title = {{{Sphaleron rate from Euclidean lattice correlators: An exploration}}}, doi = {{10.1103/physrevd.103.114513}}, volume = {{103}}, year = {{2021}}, } @article{24788, author = {{Alhaddad, Samer and Förstner, Jens and Groth, Stefan and Grünewald, Daniel and Grynko, Yevgen and Hannig, Frank and Kenter, Tobias and Pfreundt, Franz‐Josef and Plessl, Christian and Schotte, Merlind and Steinke, Thomas and Teich, Jürgen and Weiser, Martin and Wende, Florian}}, issn = {{1532-0626}}, journal = {{Concurrency and Computation: Practice and Experience}}, keywords = {{tet_topic_hpc}}, pages = {{e6616}}, title = {{{The HighPerMeshes framework for numerical algorithms on unstructured grids}}}, doi = {{10.1002/cpe.6616}}, year = {{2021}}, } @article{32240, abstract = {{

The effect of traces of ethanol in supercritical carbon dioxide on the mixture's thermodynamic properties is studied by molecular simulations and Taylor dispersion measurements.

}}, author = {{Chatwell, René Spencer and Guevara-Carrion, Gabriela and Gaponenko, Yuri and Shevtsova, Valentina and Vrabec, Jadran}}, issn = {{1463-9076}}, journal = {{Physical Chemistry Chemical Physics}}, keywords = {{Physical and Theoretical Chemistry, General Physics and Astronomy}}, number = {{4}}, pages = {{3106--3115}}, publisher = {{Royal Society of Chemistry (RSC)}}, title = {{{Diffusion of the carbon dioxide–ethanol mixture in the extended critical region}}}, doi = {{10.1039/d0cp04985a}}, volume = {{23}}, year = {{2021}}, } @article{32246, abstract = {{

State-of-the-art methods in materials science such as artificial intelligence and data-driven techniques advance the investigation of photovoltaic materials.

}}, author = {{Mirhosseini, Hossein and Kormath Madam Raghupathy, Ramya and Sahoo, Sudhir K. and Wiebeler, Hendrik and Chugh, Manjusha and Kühne, Thomas D.}}, issn = {{1463-9076}}, journal = {{Physical Chemistry Chemical Physics}}, keywords = {{Physical and Theoretical Chemistry, General Physics and Astronomy}}, number = {{46}}, pages = {{26682--26701}}, publisher = {{Royal Society of Chemistry (RSC)}}, title = {{{In silico investigation of Cu(In,Ga)Se2-based solar cells}}}, doi = {{10.1039/d0cp04712k}}, volume = {{22}}, year = {{2020}}, } @article{16277, abstract = {{CP2K is an open source electronic structure and molecular dynamics software package to perform atomistic simulations of solid-state, liquid, molecular, and biological systems. It is especially aimed at massively parallel and linear-scaling electronic structure methods and state-of-theart ab initio molecular dynamics simulations. Excellent performance for electronic structure calculations is achieved using novel algorithms implemented for modern high-performance computing systems. This review revisits the main capabilities of CP2K to perform efficient and accurate electronic structure simulations. The emphasis is put on density functional theory and multiple post–Hartree–Fock methods using the Gaussian and plane wave approach and its augmented all-electron extension.}}, author = {{Kühne, Thomas and Iannuzzi, Marcella and Ben, Mauro Del and Rybkin, Vladimir V. and Seewald, Patrick and Stein, Frederick and Laino, Teodoro and Khaliullin, Rustam Z. and Schütt, Ole and Schiffmann, Florian and Golze, Dorothea and Wilhelm, Jan and Chulkov, Sergey and Mohammad Hossein Bani-Hashemian, Mohammad Hossein Bani-Hashemian and Weber, Valéry and Borstnik, Urban and Taillefumier, Mathieu and Jakobovits, Alice Shoshana and Lazzaro, Alfio and Pabst, Hans and Müller, Tiziano and Schade, Robert and Guidon, Manuel and Andermatt, Samuel and Holmberg, Nico and Schenter, Gregory K. and Hehn, Anna and Bussy, Augustin and Belleflamme, Fabian and Tabacchi, Gloria and Glöß, Andreas and Lass, Michael and Bethune, Iain and Mundy, Christopher J. and Plessl, Christian and Watkins, Matt and VandeVondele, Joost and Krack, Matthias and Hutter, Jürg}}, journal = {{The Journal of Chemical Physics}}, number = {{19}}, title = {{{CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations}}}, doi = {{10.1063/5.0007045}}, volume = {{152}}, year = {{2020}}, } @article{12878, abstract = {{In scientific computing, the acceleration of atomistic computer simulations by means of custom hardware is finding ever-growing application. A major limitation, however, is that the high efficiency in terms of performance and low power consumption entails the massive usage of low precision computing units. Here, based on the approximate computing paradigm, we present an algorithmic method to compensate for numerical inaccuracies due to low accuracy arithmetic operations rigorously, yet still obtaining exact expectation values using a properly modified Langevin-type equation.}}, author = {{Rengaraj, Varadarajan and Lass, Michael and Plessl, Christian and Kühne, Thomas}}, journal = {{Computation}}, number = {{2}}, publisher = {{MDPI}}, title = {{{Accurate Sampling with Noisy Forces from Approximate Computing}}}, doi = {{10.3390/computation8020039}}, volume = {{8}}, year = {{2020}}, } @article{7689, author = {{Riebler, Heinrich and Vaz, Gavin Francis and Kenter, Tobias and Plessl, Christian}}, journal = {{ACM Trans. Archit. Code Optim. (TACO)}}, keywords = {{htrop}}, number = {{2}}, pages = {{14:1–14:26}}, publisher = {{ACM}}, title = {{{Transparent Acceleration for Heterogeneous Platforms with Compilation to OpenCL}}}, doi = {{10.1145/3319423}}, volume = {{16}}, year = {{2019}}, } @article{21, abstract = {{We address the general mathematical problem of computing the inverse p-th root of a given matrix in an efficient way. A new method to construct iteration functions that allow calculating arbitrary p-th roots and their inverses of symmetric positive definite matrices is presented. We show that the order of convergence is at least quadratic and that adaptively adjusting a parameter q always leads to an even faster convergence. In this way, a better performance than with previously known iteration schemes is achieved. The efficiency of the iterative functions is demonstrated for various matrices with different densities, condition numbers and spectral radii.}}, author = {{Richters, Dorothee and Lass, Michael and Walther, Andrea and Plessl, Christian and Kühne, Thomas}}, journal = {{Communications in Computational Physics}}, number = {{2}}, pages = {{564--585}}, publisher = {{Global Science Press}}, title = {{{A General Algorithm to Calculate the Inverse Principal p-th Root of Symmetric Positive Definite Matrices}}}, doi = {{10.4208/cicp.OA-2018-0053}}, volume = {{25}}, year = {{2019}}, } @article{12871, author = {{Platzner, Marco and Plessl, Christian}}, issn = {{0170-6012}}, journal = {{Informatik Spektrum}}, title = {{{FPGAs im Rechenzentrum}}}, doi = {{10.1007/s00287-019-01187-w}}, year = {{2019}}, } @article{20, abstract = {{Approximate computing has shown to provide new ways to improve performance and power consumption of error-resilient applications. While many of these applications can be found in image processing, data classification or machine learning, we demonstrate its suitability to a problem from scientific computing. Utilizing the self-correcting behavior of iterative algorithms, we show that approximate computing can be applied to the calculation of inverse matrix p-th roots which are required in many applications in scientific computing. Results show great opportunities to reduce the computational effort and bandwidth required for the execution of the discussed algorithm, especially when targeting special accelerator hardware.}}, author = {{Lass, Michael and Kühne, Thomas and Plessl, Christian}}, issn = {{1943-0671}}, journal = {{Embedded Systems Letters}}, number = {{2}}, pages = {{ 33--36}}, publisher = {{IEEE}}, title = {{{Using Approximate Computing for the Calculation of Inverse Matrix p-th Roots}}}, doi = {{10.1109/LES.2017.2760923}}, volume = {{10}}, year = {{2018}}, } @article{6516, author = {{Mertens, Jan Cedric and Boschmann, Alexander and Schmidt, M. and Plessl, Christian}}, issn = {{1369-7072}}, journal = {{Sports Engineering}}, number = {{4}}, pages = {{441--451}}, publisher = {{Springer Nature}}, title = {{{Sprint diagnostic with GPS and inertial sensor fusion}}}, doi = {{10.1007/s12283-018-0291-0}}, volume = {{21}}, year = {{2018}}, } @article{13348, author = {{Luk, Samuel M. H. and Lewandowski, P. and Kwong, N. H. and Baudin, E. and Lafont, O. and Tignon, J. and Leung, P. T. and Chan, Ch. K. P. and Babilon, M. and Schumacher, Stefan and Binder, R.}}, issn = {{0740-3224}}, journal = {{Journal of the Optical Society of America B}}, number = {{1}}, title = {{{Theory of optically controlled anisotropic polariton transport in semiconductor double microcavities}}}, doi = {{10.1364/josab.35.000146}}, volume = {{35}}, year = {{2018}}, } @article{18, abstract = {{Branch and bound (B&B) algorithms structure the search space as a tree and eliminate infeasible solutions early by pruning subtrees that cannot lead to a valid or optimal solution. Custom hardware designs significantly accelerate the execution of these algorithms. In this article, we demonstrate a high-performance B&B implementation on FPGAs. First, we identify general elements of B&B algorithms and describe their implementation as a finite state machine. Then, we introduce workers that autonomously cooperate using work stealing to allow parallel execution and full utilization of the target FPGA. Finally, we explore advantages of instance-specific designs that target a specific problem instance to improve performance. We evaluate our concepts by applying them to a branch and bound problem, the reconstruction of corrupted AES keys obtained from cold-boot attacks. The evaluation shows that our work stealing approach is scalable with the available resources and provides speedups proportional to the number of workers. Instance-specific designs allow us to achieve an overall speedup of 47 × compared to the fastest implementation of AES key reconstruction so far. Finally, we demonstrate how instance-specific designs can be generated just-in-time such that the provided speedups outweigh the additional time required for design synthesis.}}, author = {{Riebler, Heinrich and Lass, Michael and Mittendorf, Robert and Löcke, Thomas and Plessl, Christian}}, issn = {{1936-7406}}, journal = {{ACM Transactions on Reconfigurable Technology and Systems (TRETS)}}, keywords = {{coldboot}}, number = {{3}}, pages = {{24:1--24:23}}, publisher = {{Association for Computing Machinery (ACM)}}, title = {{{Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs}}}, doi = {{10.1145/3053687}}, volume = {{10}}, year = {{2017}}, } @article{1589, author = {{Schumacher, Jörn and Plessl, Christian and Vandelli, Wainer}}, journal = {{Journal of Physics: Conference Series}}, publisher = {{IOP Publishing}}, title = {{{High-Throughput and Low-Latency Network Communication with NetIO}}}, doi = {{10.1088/1742-6596/898/8/082003}}, volume = {{898}}, year = {{2017}}, } @article{165, abstract = {{A broad spectrum of applications can be accelerated by offloading computation intensive parts to reconfigurable hardware. However, to achieve speedups, the number of loop it- erations (trip count) needs to be sufficiently large to amortize offloading overheads. Trip counts are frequently not known at compile time, but only at runtime just before entering a loop. Therefore, we propose to generate code for both the CPU and the coprocessor, and defer the offloading decision to the application runtime. We demonstrate how a toolflow, based on the LLVM compiler framework, can automatically embed dynamic offloading de- cisions into the application code. We perform in-depth static and dynamic analysis of pop- ular benchmarks, which confirm the general potential of such an approach. We also pro- pose to optimize the offloading process by decoupling the runtime decision from the loop execution (decision slack). The feasibility of our approach is demonstrated by a toolflow that automatically identifies suitable data-parallel loops and generates code for the FPGA coprocessor of a Convey HC-1. We evaluate the integrated toolflow with representative loops executed for different input data sizes.}}, author = {{Vaz, Gavin Francis and Riebler, Heinrich and Kenter, Tobias and Plessl, Christian}}, issn = {{0045-7906}}, journal = {{Computers and Electrical Engineering}}, pages = {{91--111}}, publisher = {{Elsevier}}, title = {{{Potential and Methods for Embedding Dynamic Offloading Decisions into Application Code}}}, doi = {{10.1016/j.compeleceng.2016.04.021}}, volume = {{55}}, year = {{2016}}, } @article{1769, abstract = {{Große zylindrische Stahlprüflinge werden mittels der Methode der finiten Differenzen im Zeitbereich (engl. finite differences in time domain, FDTD) simulativ untersucht. Dabei werden Pitch-Catch-Messanordnungen verwendet. Es werden zwei Bildgebungsansätze vorgestellt: ersterer basiert auf dem Imaging Principle nach Claerbout, letzterer basiert auf gradientenbasierter Optimierung eines Zielfunktionals.}}, author = {{Hegler, Sebastian and Statz, Christoph and Mütze, Marco and Mooshofer, Hubert and Goldammer, Matthias and Fendt, Karl and Schwarzer, Stefan and Feldhoff, Kim and Flehmig, Martin and Markwardt, Ulf and E. Nagel, Wolfgang and Schütte, Maria and Walther, Andrea and Meinel, Michael and Basermann, Achim and Plettemeier, Dirk}}, journal = {{tm - Technisches Messen}}, number = {{9}}, pages = {{440--450}}, publisher = {{Walter de Gruyter}}, title = {{{Simulative Ultraschall-Untersuchung von Pitch-Catch-Messanordnungen für große zylindrische Stahl-Prüflinge und gradientenbasierte Bildgebung}}}, doi = {{doi:10.1515/teme-2015-0031}}, volume = {{82}}, year = {{2015}}, } @article{1772, author = {{Torresen, Jim and Plessl, Christian and Yao, Xin}}, journal = {{IEEE Computer}}, keywords = {{self-awareness, self-expression}}, number = {{7}}, pages = {{18--20}}, publisher = {{IEEE Computer Society}}, title = {{{Self-Aware and Self-Expressive Systems – Guest Editor's Introduction}}}, doi = {{10.1109/MC.2015.205}}, volume = {{48}}, year = {{2015}}, } @article{1774, abstract = {{In this article an efficient numerical method to solve multiobjective optimization problems for fluid flow governed by the Navier Stokes equations is presented. In order to decrease the computational effort, a reduced order model is introduced using Proper Orthogonal Decomposition and a corresponding Galerkin Projection. A global, derivative free multiobjective optimization algorithm is applied to compute the Pareto set (i.e. the set of optimal compromises) for the concurrent objectives minimization of flow field fluctuations and control cost. The method is illustrated for a 2D flow around a cylinder at Re = 100.}}, author = {{Peitz, Sebastian and Dellnitz, Michael}}, issn = {{1617-7061}}, journal = {{PAMM}}, number = {{1}}, pages = {{613--614}}, publisher = {{WILEY-VCH Verlag}}, title = {{{Multiobjective Optimization of the Flow Around a Cylinder Using Model Order Reduction}}}, doi = {{10.1002/pamm.201510296}}, volume = {{15}}, year = {{2015}}, } @article{296, abstract = {{FPGAs are known to permit huge gains in performance and efficiency for suitable applications but still require reduced design efforts and shorter development cycles for wider adoption. In this work, we compare the resulting performance of two design concepts that in different ways promise such increased productivity. As common starting point, we employ a kernel-centric design approach, where computational hotspots in an application are identified and individually accelerated on FPGA. By means of a complex stereo matching application, we evaluate two fundamentally different design philosophies and approaches for implementing the required kernels on FPGAs. In the first implementation approach, we designed individually specialized data flow kernels in a spatial programming language for a Maxeler FPGA platform; in the alternative design approach, we target a vector coprocessor with large vector lengths, which is implemented as a form of programmable overlay on the application FPGAs of a Convey HC-1. We assess both approaches in terms of overall system performance, raw kernel performance, and performance relative to invested resources. After compensating for the effects of the underlying hardware platforms, the specialized dataflow kernels on the Maxeler platform are around 3x faster than kernels executing on the Convey vector coprocessor. In our concrete scenario, due to trade-offs between reconfiguration overheads and exposed parallelism, the advantage of specialized dataflow kernels is reduced to around 2.5x.}}, author = {{Kenter, Tobias and Schmitz, Henning and Plessl, Christian}}, journal = {{International Journal of Reconfigurable Computing (IJRC)}}, publisher = {{Hindawi}}, title = {{{Exploring Tradeoffs between Specialized Kernels and a Reusable Overlay in a Stereo-Matching Case Study}}}, doi = {{10.1155/2015/859425}}, volume = {{2015}}, year = {{2015}}, } @article{1768, author = {{Plessl, Christian and Platzner, Marco and Schreier, Peter J.}}, journal = {{Informatik Spektrum}}, keywords = {{approximate computing, survey}}, number = {{5}}, pages = {{396--399}}, publisher = {{Springer}}, title = {{{Aktuelles Schlagwort: Approximate Computing}}}, doi = {{10.1007/s00287-015-0911-z}}, year = {{2015}}, } @article{1775, abstract = {{The ATLAS experiment at CERN is planning full deployment of a new unified optical link technology for connecting detector front end electronics on the timescale of the LHC Run 4 (2025). It is estimated that roughly 8000 GBT (GigaBit Transceiver) links, with transfer rates up to 10.24 Gbps, will replace existing links used for readout, detector control and distribution of timing and trigger information. A new class of devices will be needed to interface many GBT links to the rest of the trigger, data-acquisition and detector control systems. In this paper FELIX (Front End LInk eXchange) is presented, a PC-based device to route data from and to multiple GBT links via a high-performance general purpose network capable of a total throughput up to O(20 Tbps). FELIX implies architectural changes to the ATLAS data acquisition system, such as the use of industry standard COTS components early in the DAQ chain. Additionally the design and implementation of a FELIX demonstration platform is presented and hardware and software aspects will be discussed.}}, author = {{Anderson, J and Borga, A and Boterenbrood, H and Chen, H and Chen, K and Drake, G and Francis, D and Gorini, B and Lanni, F and Lehmann Miotto, G and Levinson, L and Narevicius, J and Plessl, Christian and Roich, A and Ryu, S and Schreuder, F and Schumacher, Jörn and Vandelli, Wainer and Vermeulen, J and Zhang, J}}, journal = {{Journal of Physics: Conference Series}}, publisher = {{IOP Publishing}}, title = {{{FELIX: a High-Throughput Network Approach for Interfacing to Front End Electronics for ATLAS Upgrades}}}, doi = {{10.1088/1742-6596/664/8/082050}}, volume = {{664}}, year = {{2015}}, } @article{363, abstract = {{Due to the continuously shrinking device structures and increasing densities of FPGAs, thermal aspects have become the new focus for many research projects over the last years. Most researchers rely on temperature simulations to evaluate their novel thermal management techniques. However, these temperature simulations require a high computational effort if a detailed thermal model is used and their accuracies are often unclear. In contrast to simulations, the use of synthetic heat sources allows for experimental evaluation of temperature management methods. In this paper we investigate the creation of significant rises in temperature on modern FPGAs to enable future evaluation of thermal management techniques based on experiments. To that end, we have developed seven different heat-generating cores that use different subsets of FPGA resources. Our experimental results show that, according to external temperature probes connected to the FPGA’s heat sink, we can increase the temperature by an average of 81 !C. This corresponds to an average increase of 156.3 !C as measured by the built-in thermal diodes of our Virtex-5 FPGAs in less than 30 min by only utilizing about 21 percent of the slices.}}, author = {{Agne, Andreas and Hangmann, Hendrik and Happe, Markus and Platzner, Marco and Plessl, Christian}}, journal = {{Microprocessors and Microsystems}}, number = {{8, Part B}}, pages = {{911--919}}, publisher = {{Elsevier}}, title = {{{Seven Recipes for Setting Your FPGA on Fire – A Cookbook on Heat Generators}}}, doi = {{10.1016/j.micpro.2013.12.001}}, volume = {{38}}, year = {{2014}}, } @article{365, abstract = {{Self-aware computing is a paradigm for structuring and simplifying the design and operation of computing systems that face unprecedented levels of system dynamics and thus require novel forms of adaptivity. The generality of the paradigm makes it applicable to many types of computing systems and, previously, researchers started to introduce concepts of self-awareness to multicore architectures. In our work we build on a recent reference architectural framework as a model for self-aware computing and instantiate it for an FPGA-based heterogeneous multicore running the ReconOS reconfigurable architecture and operating system. After presenting the model for self-aware computing and ReconOS, we demonstrate with a case study how a multicore application built on the principle of self-awareness, autonomously adapts to changes in the workload and system state. Our work shows that the reference architectural framework as a model for self-aware computing can be practically applied and allows us to structure and simplify the design process, which is essential for designing complex future computing systems.}}, author = {{Agne, Andreas and Happe, Markus and Lösch, Achim and Plessl, Christian and Platzner, Marco}}, journal = {{ACM Transactions on Reconfigurable Technology and Systems (TRETS)}}, number = {{2}}, publisher = {{ACM}}, title = {{{Self-awareness as a Model for Designing and Operating Heterogeneous Multicores}}}, doi = {{10.1145/2617596}}, volume = {{7}}, year = {{2014}}, } @article{328, abstract = {{The ReconOS operating system for reconfigurable computing offers a unified multi-threaded programming model and operating system services for threads executing in software and threads mapped to reconfigurable hardware. The operating system interface allows hardware threads to interact with software threads using well-known mechanisms such as semaphores, mutexes, condition variables, and message queues. By semantically integrating hardware accelerators into a standard operating system environment, ReconOS allows for rapid design space exploration, supports a structured application development process and improves the portability of applications}}, author = {{Agne, Andreas and Happe, Markus and Keller, Ariane and Lübbers, Enno and Plattner, Bernhard and Platzner, Marco and Plessl, Christian}}, journal = {{IEEE Micro}}, number = {{1}}, pages = {{60--71}}, publisher = {{IEEE}}, title = {{{ReconOS - An Operating System Approach for Reconfigurable Computing}}}, doi = {{10.1109/MM.2013.110}}, volume = {{34}}, year = {{2014}}, } @article{1779, author = {{Giefers, Heiner and Plessl, Christian and Förstner, Jens}}, issn = {{0163-5964}}, journal = {{ACM SIGARCH Computer Architecture News}}, keywords = {{funding-maxup, tet_topic_hpc}}, number = {{5}}, pages = {{65--70}}, publisher = {{ACM}}, title = {{{Accelerating Finite Difference Time Domain Simulations with Reconfigurable Dataflow Computers}}}, doi = {{10.1145/2641361.2641372}}, volume = {{41}}, year = {{2014}}, } @article{1792, author = {{Kasap, Server and Redif, Soydan}}, journal = {{IEEE Trans. on Very Large Scale Integration (VLSI) Systems}}, number = {{3}}, pages = {{522--536}}, publisher = {{IEEE}}, title = {{{Novel Field-Programmable Gate Array Architecture for Computing the Eigenvalue Decomposition of Para-Hermitian Polynomial Matrices}}}, doi = {{10.1109/TVLSI.2013.2248069}}, volume = {{22}}, year = {{2013}}, } @article{1965, abstract = {{Virtualization technology makes data centers more dynamic and easier to administrate. Today, cloud providers offer customers access to complex applications running on virtualized hardware. Nevertheless, big virtualized data centers become stochastic environments and the simplification on the user side leads to many challenges for the provider. He has to find cost-efficient configurations and has to deal with dynamic environments to ensure service level objectives (SLOs). We introduce a software solution that reduces the degree of human intervention to manage clouds. It is designed as a multi-agent system (MAS) and placed on top of the Infrastructure as a Service (IaaS) layer. Worker agents allocate resources, configure applications, check the feasibility of requests, and generate cost estimates. They are equipped with application specific knowledge allowing it to estimate the type and number of necessary resources. During runtime, a worker agent monitors the job and adapts its resources to ensure the specified quality of service—even in noisy clouds where the job instances are influenced by other jobs. They interact with a scheduler agent, which takes care of limited resources and does a cost-aware scheduling by assigning jobs to times with low costs. The whole architecture is self-optimizing and able to use public or private clouds. Building a private cloud needs to face the challenge to find a mapping of virtual machines (VMs) to hosts. We present a rule-based mapping algorithm for VMs. It offers an interface where policies can be defined and combined in a generic way. The algorithm performs the initial mapping at request time as well as a remapping during runtime. It deals with policy and infrastructure changes. An energy-aware scheduler and the availability of cheap resources provided by a spot market are analyzed. We evaluated our approach by building up an SaaS stack, which assigns resources in consideration of an energy function and that ensures SLOs of two different applications, a brokerage system and a high-performance computing software. Experiments were done on a real cloud system and by simulations.}}, author = {{Niehörster, Oliver and Simon, Jens and Brinkmann, André and Keller, Axel and Krüger, Jens}}, journal = {{Journal of Grid Computing}}, number = {{3}}, pages = {{553--577}}, title = {{{Cost-aware and SLO Fulfilling Software as a Service}}}, doi = {{10.1007/s10723-012-9230-7}}, volume = {{10}}, year = {{2012}}, } @article{2102, author = {{Gesing, Sandra and Grunzke, Richard and Krüger, Jens and Birkenheuer, Georg and Wewior, Martin and Schäfer, Patrick and Schuller, Bernd and Schuster, Johannes and Herres-Pawlis, Sonja and Breuers, Sebastian and Balaskó, Ákos and Kozlovszky, Miklos and Szikszay Fabri, Anna and Packschies, Lars and Kacsuk, Peter and Blunk, Dirk and Steinke, Thomas and Brinkmann, André and Fels, Gregor and Müller-Pfefferkorn, Ralph and Jäkel, René and Kohlbacher, Oliver}}, journal = {{Journal of Grid Computing}}, number = {{4}}, pages = {{769--790}}, publisher = {{Springer}}, title = {{{A Single Sign-On Infrastructure for Science Gateways on a Use Case for Structural Bioinformatics}}}, doi = {{10.1007/s10723-012-9247-y}}, volume = {{10}}, year = {{2012}}, } @article{2172, author = {{Thielemans, Kris and Tsoumpas, Charalampos and Mustafovic, Sanida and Beisel, Tobias and Aguiar, Pablo and Dikaios, Nikolaos and W Jacobson, Matthew}}, journal = {{Physics in Medicine and Biology}}, number = {{4}}, pages = {{867--883}}, publisher = {{IOP Publishing}}, title = {{{STIR: Software for Tomographic Image Reconstruction Release 2}}}, doi = {{10.1088/0031-9155/57/4/867}}, volume = {{57}}, year = {{2012}}, } @article{2173, author = {{Redif, Soydan and Kasap, Server}}, journal = {{Int. Journal of Electronics}}, number = {{12}}, pages = {{1646--1651}}, publisher = {{Taylor & Francis}}, title = {{{Parallel algorithm for computation of second-order sequential best rotations}}}, doi = {{10.1080/00207217.2012.751343}}, volume = {{100}}, year = {{2012}}, } @article{2174, author = {{Kasap, Server and Benkrid, Khaled}}, journal = {{Journal of Computers}}, number = {{6}}, pages = {{1312--1328}}, publisher = {{Academy Publishers}}, title = {{{Parallel Processor Design and Implementation for Molecular Dynamics Simulations on a FPGA Parallel Computer}}}, volume = {{7}}, year = {{2012}}, } @article{2176, author = {{Herres-Pawlis, Sonja and Birkenheuer, Georg and Brinkmann, André and Gesing, Sandra and Grunzke, Richard and Jäkel, René and Kohlbacher, Oliver and Krüger, Jens and Dos Santos Vieira, Ines}}, journal = {{Studies in Health Technology and Informatics}}, pages = {{142--151}}, publisher = {{IOP Publishing}}, title = {{{Workflow-enhanced conformational analysis of guanidine zinc complexes via a science gateway}}}, doi = {{10.3233/978-1-61499-054-3-142}}, volume = {{175}}, year = {{2012}}, } @article{2108, author = {{Schumacher, Tobias and Plessl, Christian and Platzner, Marco}}, issn = {{0141-9331}}, journal = {{Microprocessors and Microsystems}}, keywords = {{funding-altera}}, number = {{2}}, pages = {{110--126}}, title = {{{IMORC: An Infrastructure and Architecture Template for Implementing High-Performance Reconfigurable FPGA Accelerators}}}, doi = {{10.1016/j.micpro.2011.04.002}}, volume = {{36}}, year = {{2012}}, } @article{2177, author = {{Grad, Mariusz and Plessl, Christian}}, journal = {{Int. Journal of Reconfigurable Computing (IJRC)}}, publisher = {{Hindawi Publishing Corp.}}, title = {{{On the Feasibility and Limitations of Just-In-Time Instruction Set Extension for FPGA-based Reconfigurable Processors}}}, doi = {{10.1155/2012/418315}}, year = {{2012}}, } @article{1971, abstract = {{System virtualization has become the enabling technology to manage the increasing number of different applications inside data centers. The abstraction from the underlying hardware and the provision of multiple virtual machines (VM) on a single physical server have led to a consolidation and more efficient usage of physical servers. The abstraction from the hardware also eases the provision of applications on different data centers, as applied in several cloud computing environments. In this case, the application need not adapt to the environment of the cloud computing provider, but can travel around with its own VM image, including its own operating system and libraries. System virtualization and cloud computing could also be very attractive in the context of high‐performance computing (HPC). Today, HPC centers have to cope with both, the management of the infrastructure and also the applications. Virtualization technology would enable these centers to focus on the infrastructure, while the users, collaborating inside their virtual organizations (VOs), would be able to provide the software. Nevertheless, there seems to be a contradiction between HPC and cloud computing, as there are very few successful approaches to virtualize HPC centers. This work discusses the underlying reasons, including the management and performance, and presents solutions to overcome the contradiction, including a set of new libraries. The viability of the presented approach is shown based on evaluating a selected parallel, scientific application in a virtualized HPC environment. }}, author = {{Birkenheuer, Georg and Brinkmann, André and Kaiser, Jürgen and Keller, Axel and Keller, Matthias and Kleineweber, Christoph and Konersmann, Christoph and Niehörster, Oliver and Schäfer, Thorsten and Simon, Jens and Wilhelm, Maximilan}}, journal = {{Software: Practice and Experience}}, publisher = {{John Wiley & Sons}}, title = {{{Virtualized HPC: a contradiction in terms?}}}, doi = {{10.1002/spe.1055}}, year = {{2011}}, } @article{2192, author = {{Birkenheuer, Georg and Brinkmann, André and Högqvist, Mikael and Papaspyrou, Alexander and Schott, Bernhard and Sommerfeld, Dietmar and Ziegler, Wolfgang}}, journal = {{Journal of Grid Computing}}, number = {{3}}, pages = {{355--377}}, publisher = {{Springer}}, title = {{{Infrastructure Federation Through Virtualized Delegation of Resources and Services}}}, doi = {{10.1007/s10723-011-9192-1}}, volume = {{9}}, year = {{2011}}, } @article{2201, author = {{Schumacher, Tobias and Süß, Tim and Plessl, Christian and Platzner, Marco}}, journal = {{Int. Journal of Recon- figurable Computing (IJRC)}}, keywords = {{funding-altera}}, publisher = {{Hindawi Publishing Corp.}}, title = {{{FPGA Acceleration of Communication-bound Streaming Applications: Architecture Modeling and a 3D Image Compositing Case Study}}}, doi = {{10.1155/2011/760954}}, year = {{2011}}, } @article{2235, author = {{Brinkmann, André and Battré, Dominic and Birkenheuer, Georg and Kao, Odej and Voß, Kerstin}}, journal = {{ForschungsForum Paderborn}}, number = {{13}}, publisher = {{Universität Paderborn}}, title = {{{Risikomanagement für verteilte Umgebungen}}}, volume = {{13}}, year = {{2010}}, } @article{2354, author = {{Brinkmann, André and Eschweiler, Dominic}}, journal = {{Journal of Supercomputing}}, pages = {{35:1--35:10}}, publisher = {{ACM}}, title = {{{A Microdriver Architecture for Error Correcting Codes inside the Linux Kernel}}}, doi = {{10.1145/1654059.1654095}}, year = {{2009}}, } @article{2405, author = {{Groppe, Sven and Böttcher, Stefan and Birkenheuer, Georg and Höing, André}}, journal = {{Data & Knowledge Engineering}}, number = {{1}}, pages = {{64--110}}, publisher = {{Elsevier}}, title = {{{Reformulating XPath queries and XSLT queries on XSLT views}}}, doi = {{10.1016/j.datak.2005.04.002}}, volume = {{57}}, year = {{2006}}, } @article{1999, abstract = {{Workstation clusters are often not only used for high-throughput computing in time-sharing mode but also for running complex parallel jobs in space-sharing mode. This poses several difficulties to the resource management system, which must be able to reserve computing resources for exclusive use and also to determine an optimal process mapping for a given system topology. On the basis of our CCS software, we describe the anatomy of a modern resource management system. Like Codine, Condor, and LSF, CCS provides mechanisms for the user-friendly system access and management of clusters. But unlike them, CCS is targeted at the effective support of space-sharing parallel computers and even metacomputers. Among other features, CCS provides a versatile resource description facility, topology-based process mapping, pluggable schedulers, and hooks to metacomputer management.}}, author = {{Keller, Axel and Reinefeld, Alexander}}, journal = {{Annual Review of Scalable Computing}}, pages = {{1--31}}, title = {{{Anatomy of a Resource Management System for HPC Clusters}}}, doi = {{10.1142/9789812810182_0001}}, volume = {{3}}, year = {{2001}}, } @article{2007, abstract = {{We present a software system for the management of geographically distributed high‐performance computers. It consists of three components: 1. The Computing Center Software (CCS) is a vendor‐independent resource management software for local HPC systems. It controls the mapping and scheduling of interactive and batch jobs on massively parallel systems; 2. The Resource and Service Description (RSD) is used by CCS for specifying and mapping hardware and software components of (meta‐)computing environments. It has a graphical user interface, a textual representation and an object‐oriented API; 3. The Service Coordination Layer (SCL) co‐ordinates the co‐operative use of resources in autonomous computing sites. It negotiates between the applications' requirements and the available system services. }}, author = {{Brune, Matthias and Gehring, Jörn and Keller, Axel and Reinefeld, Alexander}}, journal = {{Concurrency, Practice, and Experience}}, pages = {{887--911}}, title = {{{Managing Clusters of Geographically Distributed High-Performance Computers}}}, doi = {{10.1002/(SICI)1096-9128(19991225)11:15<887::AID-CPE459>3.0.CO;2-J}}, volume = {{II(15)}}, year = {{1999}}, } @article{2012, abstract = {{With a steadily increasing number of services, metacomputing is now gaining importance in science and industry. Virtual organizations, autonomous agents, mobile computing services, and high-performance client–server applications are among the many examples of metacomputing services. For all of them, resource description plays a major role in organizing access, use, and administration of the computing components and software services. We present a generic Resource and Service Description (RSD) for specifying the hardware and software components of (meta-) computing environments. Its graphical interface allows metacomputer users to specify their resource requests. Its textual counterpart gives service providers the necessary flexibility to specify topology and properties of the available system and software resources. Finally, its internal object-oriented representation is used to link different resource management systems and service tools. With these three representations, our generic RSD approach is a key component for building metacomputer environments.}}, author = {{Brune, Matthias and Gehring, Jörn and Keller, Axel and Monien, Burkhard}}, journal = {{Parallel Computing}}, pages = {{1751--1776}}, publisher = {{Elsevier}}, title = {{{Specifying Resources and Services in Metacomputing Environments}}}, doi = {{10.1016/S0167-8191(98)00076-3}}, volume = {{24}}, year = {{1998}}, } @article{2437, author = {{Simon, Jens and Wierum, Jens-Michael}}, issn = {{0020-0190}}, journal = {{Information Processing Letters - Special Issue on Models of Computation}}, number = {{5}}, pages = {{255--261}}, publisher = {{Elsevier}}, title = {{{The Latency-of-Data-Access model for Analyzing Parallel Computation}}}, doi = {{10.1016/S0020-0190(98)00062-3}}, volume = {{66}}, year = {{1998}}, }