@inproceedings{46190, author = {{Opdenhövel, Jan-Oliver and Plessl, Christian and Kenter, Tobias}}, booktitle = {{Proceedings of the 13th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies}}, publisher = {{ACM}}, title = {{{Mutation Tree Reconstruction of Tumor Cells on FPGAs Using a Bit-Level Matrix Representation}}}, doi = {{10.1145/3597031.3597050}}, year = {{2023}}, } @inproceedings{46188, author = {{Faj, Jennifer and Kenter, Tobias and Faghih-Naini, Sara and Plessl, Christian and Aizinger, Vadym}}, booktitle = {{Proceedings of the Platform for Advanced Scientific Computing Conference}}, publisher = {{ACM}}, title = {{{Scalable Multi-FPGA Design of a Discontinuous Galerkin Shallow-Water Model on Unstructured Meshes}}}, doi = {{10.1145/3592979.3593407}}, year = {{2023}}, } @inproceedings{46189, author = {{Prouveur, Charles and Haefele, Matthieu and Kenter, Tobias and Voss, Nils}}, booktitle = {{Proceedings of the Platform for Advanced Scientific Computing Conference}}, publisher = {{ACM}}, title = {{{FPGA Acceleration for HPC Supercapacitor Simulations}}}, doi = {{10.1145/3592979.3593419}}, 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}}, } @unpublished{50172, abstract = {{Viscous hydrodynamics serves as a successful mesoscopic description of the Quark-Gluon Plasma produced in relativistic heavy-ion collisions. In order to investigate, how such an effective description emerges from the underlying microscopic dynamics we calculate the hydrodynamic and non-hydrodynamic modes of linear response in the sound channel from a first-principle calculation in kinetic theory. We do this with a new approach wherein we discretize the collision kernel to directly calculate eigenvalues and eigenmodes of the evolution operator. This allows us to study the Green's functions at any point in the complex frequency space. Our study focuses on scalar theory with quartic interaction and we find that the analytic structure of Green's functions in the complex plane is far more complicated than just poles or cuts which is a first step towards an equivalent study in QCD kinetic theory.}}, author = {{Ochsenfeld, Stephan and Schlichting, Sören}}, booktitle = {{arXiv:2308.04491}}, title = {{{Hydrodynamic and Non-hydrodynamic Excitations in Kinetic Theory -- A Numerical Analysis in Scalar Field Theory}}}, year = {{2023}}, } @unpublished{50221, abstract = {{Memory Gym presents a suite of 2D partially observable environments, namely Mortar Mayhem, Mystery Path, and Searing Spotlights, designed to benchmark memory capabilities in decision-making agents. These environments, originally with finite tasks, are expanded into innovative, endless formats, mirroring the escalating challenges of cumulative memory games such as ``I packed my bag''. This progression in task design shifts the focus from merely assessing sample efficiency to also probing the levels of memory effectiveness in dynamic, prolonged scenarios. To address the gap in available memory-based Deep Reinforcement Learning baselines, we introduce an implementation that integrates Transformer-XL (TrXL) with Proximal Policy Optimization. This approach utilizes TrXL as a form of episodic memory, employing a sliding window technique. Our comparative study between the Gated Recurrent Unit (GRU) and TrXL reveals varied performances across different settings. TrXL, on the finite environments, demonstrates superior sample efficiency in Mystery Path and outperforms in Mortar Mayhem. However, GRU is more efficient on Searing Spotlights. Most notably, in all endless tasks, GRU makes a remarkable resurgence, consistently outperforming TrXL by significant margins. Website and Source Code: https://github.com/MarcoMeter/endless-memory-gym/}}, author = {{Pleines, Marco and Pallasch, Matthias and Zimmer, Frank and Preuss, Mike}}, booktitle = {{arXiv:2309.17207}}, title = {{{Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents}}}, year = {{2023}}, } @unpublished{43439, abstract = {{This preprint makes the claim of having computed the $9^{th}$ Dedekind Number. This was done by building an efficient FPGA Accelerator for the core operation of the process, and parallelizing it on the Noctua 2 Supercluster at Paderborn University. The resulting value is 286386577668298411128469151667598498812366. This value can be verified in two steps. We have made the data file containing the 490M results available, each of which can be verified separately on CPU, and the whole file sums to our proposed value.}}, author = {{Van Hirtum, Lennart and De Causmaecker, Patrick and Goemaere, Jens and Kenter, Tobias and Riebler, Heinrich and Lass, Michael and Plessl, Christian}}, booktitle = {{arXiv:2304.03039}}, title = {{{A computation of D(9) using FPGA Supercomputing}}}, year = {{2023}}, } @unpublished{32177, abstract = {{We investigate the early time development of the anisotropic transverse flow and spatial eccentricities of a fireball with various particle-based transport approaches using a fixed initial condition. In numerical simulations ranging from the quasi-collisionless case to the hydrodynamic regime, we find that the onset of $v_n$ and of related measures of anisotropic flow can be described with a simple power-law ansatz, with an exponent that depends on the amount of rescatterings in the system. In the few-rescatterings regime we perform semi-analytical calculations, based on a systematic expansion in powers of time and the cross section, which can reproduce the numerical findings.}}, author = {{Borghini, Nicolas and Borrell, Marc and Roch, Hendrik}}, booktitle = {{arXiv:2201.13294}}, title = {{{Early time behavior of spatial and momentum anisotropies in kinetic theory across different Knudsen numbers}}}, year = {{2022}}, } @unpublished{32178, abstract = {{We test the ability of the "escape mechanism" to create the anisotropic flow observed in high-energy nuclear collisions. We compare the flow harmonics $v_n$ in the few-rescatterings regime from two types of transport simulations, with $2\to 2$ and $2\to 0$ collision kernels respectively, and from analytical calculations neglecting the gain term of the Boltzmann equation. We find that the even flow harmonics are similar in the three approaches, while the odd harmonics differ significantly.}}, author = {{Bachmann, Benedikt and Borghini, Nicolas and Feld, Nina and Roch, Hendrik}}, booktitle = {{arXiv:2203.13306}}, title = {{{Even anisotropic-flow harmonics are from Venus, odd ones are from Mars}}}, year = {{2022}}, } @unpublished{36879, abstract = {{The Julia programming language has evolved into a modern alternative to fill existing gaps in scientific computing and data science applications. Julia leverages a unified and coordinated single-language and ecosystem paradigm and has a proven track record of achieving high performance without sacrificing user productivity. These aspects make Julia a viable alternative to high-performance computing's (HPC's) existing and increasingly costly many-body workflow composition strategy in which traditional HPC languages (e.g., Fortran, C, C++) are used for simulations, and higher-level languages (e.g., Python, R, MATLAB) are used for data analysis and interactive computing. Julia's rapid growth in language capabilities, package ecosystem, and community make it a promising universal language for HPC. This paper presents the views of a multidisciplinary group of researchers from academia, government, and industry that advocate for an HPC software development paradigm that emphasizes developer productivity, workflow portability, and low barriers for entry. We believe that the Julia programming language, its ecosystem, and its community provide modern and powerful capabilities that enable this group's objectives. Crucially, we believe that Julia can provide a feasible and less costly approach to programming scientific applications and workflows that target HPC facilities. In this work, we examine the current practice and role of Julia as a common, end-to-end programming model to address major challenges in scientific reproducibility, data-driven AI/machine learning, co-design and workflows, scalability and performance portability in heterogeneous computing, network communication, data management, and community education. As a result, the diversification of current investments to fulfill the needs of the upcoming decade is crucial as more supercomputing centers prepare for the exascale era.}}, author = {{Churavy, Valentin and Godoy, William F and Bauer, Carsten and Ranocha, Hendrik and Schlottke-Lakemper, Michael and Räss, Ludovic and Blaschke, Johannes and Giordano, Mosè and Schnetter, Erik and Omlin, Samuel and Vetter, Jeffrey S and Edelman, Alan}}, title = {{{Bridging HPC Communities through the Julia Programming Language}}}, year = {{2022}}, } @unpublished{33493, abstract = {{Electronic structure calculations have been instrumental in providing many important insights into a range of physical and chemical properties of various molecular and solid-state systems. Their importance to various fields, including materials science, chemical sciences, computational chemistry and device physics, is underscored by the large fraction of available public supercomputing resources devoted to these calculations. As we enter the exascale era, exciting new opportunities to increase simulation numbers, sizes, and accuracies present themselves. In order to realize these promises, the community of electronic structure software developers will however first have to tackle a number of challenges pertaining to the efficient use of new architectures that will rely heavily on massive parallelism and hardware accelerators. This roadmap provides a broad overview of the state-of-the-art in electronic structure calculations and of the various new directions being pursued by the community. It covers 14 electronic structure codes, presenting their current status, their development priorities over the next five years, and their plans towards tackling the challenges and leveraging the opportunities presented by the advent of exascale computing.}}, author = {{Gavini, Vikram and Baroni, Stefano and Blum, Volker and Bowler, David R. and Buccheri, Alexander and Chelikowsky, James R. and Das, Sambit and Dawson, William and Delugas, Pietro and Dogan, Mehmet and Draxl, Claudia and Galli, Giulia and Genovese, Luigi and Giannozzi, Paolo and Giantomassi, Matteo and Gonze, Xavier and Govoni, Marco and Gulans, Andris and Gygi, François and Herbert, John M. and Kokott, Sebastian and Kühne, Thomas and Liou, Kai-Hsin and Miyazaki, Tsuyoshi and Motamarri, Phani and Nakata, Ayako and Pask, John E. and Plessl, Christian and Ratcliff, Laura E. and Richard, Ryan M. and Rossi, Mariana and Schade, Robert and Scheffler, Matthias and Schütt, Ole and Suryanarayana, Phanish and Torrent, Marc and Truflandier, Lionel and Windus, Theresa L. and Xu, Qimen and Yu, Victor W. -Z. and Perez, Danny}}, booktitle = {{arXiv:2209.12747}}, title = {{{Roadmap on Electronic Structure Codes in the Exascale Era}}}, year = {{2022}}, } @inproceedings{46193, author = {{Karp, Martin and Podobas, Artur and Kenter, Tobias and Jansson, Niclas and Plessl, Christian and Schlatter, Philipp and Markidis, Stefano}}, booktitle = {{International Conference on High Performance Computing in Asia-Pacific Region}}, publisher = {{ACM}}, title = {{{A High-Fidelity Flow Solver for Unstructured Meshes on Field-Programmable Gate Arrays: Design, Evaluation, and Future Challenges}}}, doi = {{10.1145/3492805.3492808}}, year = {{2022}}, } @unpublished{32404, abstract = {{The CP2K program package, which can be considered as the swiss army knife of atomistic simulations, is presented with a special emphasis on ab-initio molecular dynamics using the second-generation Car-Parrinello method. After outlining current and near-term development efforts with regards to massively parallel low-scaling post-Hartree-Fock and eigenvalue solvers, novel approaches on how we plan to take full advantage of future low-precision hardware architectures are introduced. Our focus here is on combining our submatrix method with the approximate computing paradigm to address the immanent exascale era.}}, author = {{Kühne, Thomas and Plessl, Christian and Schade, Robert and Schütt, Ole}}, booktitle = {{arXiv:2205.14741}}, title = {{{CP2K on the road to exascale}}}, year = {{2022}}, } @unpublished{46275, abstract = {{Electronic structure calculations have been instrumental in providing many important insights into a range of physical and chemical properties of various molecular and solid-state systems. Their importance to various fields, including materials science, chemical sciences, computational chemistry and device physics, is underscored by the large fraction of available public supercomputing resources devoted to these calculations. As we enter the exascale era, exciting new opportunities to increase simulation numbers, sizes, and accuracies present themselves. In order to realize these promises, the community of electronic structure software developers will however first have to tackle a number of challenges pertaining to the efficient use of new architectures that will rely heavily on massive parallelism and hardware accelerators. This roadmap provides a broad overview of the state-of-the-art in electronic structure calculations and of the various new directions being pursued by the community. It covers 14 electronic structure codes, presenting their current status, their development priorities over the next five years, and their plans towards tackling the challenges and leveraging the opportunities presented by the advent of exascale computing.}}, author = {{Gavini, Vikram and Baroni, Stefano and Blum, Volker and Bowler, David R. and Buccheri, Alexander and Chelikowsky, James R. and Das, Sambit and Dawson, William and Delugas, Pietro and Dogan, Mehmet and Draxl, Claudia and Galli, Giulia and Genovese, Luigi and Giannozzi, Paolo and Giantomassi, Matteo and Gonze, Xavier and Govoni, Marco and Gulans, Andris and Gygi, François and Herbert, John M. and Kokott, Sebastian and Kühne, Thomas and Liou, Kai-Hsin and Miyazaki, Tsuyoshi and Motamarri, Phani and Nakata, Ayako and Pask, John E. and Plessl, Christian and Ratcliff, Laura E. and Richard, Ryan M. and Rossi, Mariana and Schade, Robert and Scheffler, Matthias and Schütt, Ole and Suryanarayana, Phanish and Torrent, Marc and Truflandier, Lionel and Windus, Theresa L. and Xu, Qimen and Yu, Victor W. -Z. and Perez, Danny}}, booktitle = {{arXiv:2209.12747}}, title = {{{Roadmap on Electronic Structure Codes in the Exascale Era}}}, year = {{2022}}, } @inproceedings{27365, author = {{Meyer, Marius}}, booktitle = {{Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies}}, title = {{{Towards Performance Characterization of FPGAs in Context of HPC using OpenCL Benchmarks}}}, doi = {{10.1145/3468044.3468058}}, year = {{2021}}, } @inproceedings{20886, author = {{Nickchen, Tobias and Heindorf, Stefan and Engels, Gregor}}, booktitle = {{Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision}}, location = {{Hawaii}}, pages = {{1994--2002}}, title = {{{Generating Physically Sound Training Data for Image Recognition of Additively Manufactured Parts}}}, year = {{2021}}, } @unpublished{32244, abstract = {{We push the boundaries of electronic structure-based \textit{ab-initio} molecular dynamics (AIMD) beyond 100 million atoms. This scale is otherwise barely reachable with classical force-field methods or novel neural network and machine learning potentials. We achieve this breakthrough by combining innovations in linear-scaling AIMD, efficient and approximate sparse linear algebra, low and mixed-precision floating-point computation on GPUs, and a compensation scheme for the errors introduced by numerical approximations. The core of our work is the non-orthogonalized local submatrix method (NOLSM), which scales very favorably to massively parallel computing systems and translates large sparse matrix operations into highly parallel, dense matrix operations that are ideally suited to hardware accelerators. We demonstrate that the NOLSM method, which is at the center point of each AIMD step, is able to achieve a sustained performance of 324 PFLOP/s in mixed FP16/FP32 precision corresponding to an efficiency of 67.7% when running on 1536 NVIDIA A100 GPUs.}}, 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 D. and Plessl, Christian}}, booktitle = {{arXiv:2104.08245}}, title = {{{Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms}}}, year = {{2021}}, } @unpublished{32245, abstract = {{Optical travelling wave antennas offer unique opportunities to control and selectively guide light into a specific direction which renders them as excellent candidates for optical communication and sensing. These applications require state of the art engineering to reach optimized functionalities such as high directivity and radiation efficiency, low side lobe level, broadband and tunable capabilities, and compact design. In this work we report on the numerical optimization of the directivity of optical travelling wave antennas made from low-loss dielectric materials using full-wave numerical simulations in conjunction with a particle swarm optimization algorithm. The antennas are composed of a reflector and a director deposited on a glass substrate and an emitter placed in the feed gap between them serves as an internal source of excitation. In particular, we analysed antennas with rectangular- and horn-shaped directors made of either Hafnium dioxide or Silicon. The optimized antennas produce highly directional emission due to the presence of two dominant guided TE modes in the director in addition to leaky modes. These guided modes dominate the far-field emission pattern and govern the direction of the main lobe emission which predominately originates from the end facet of the director. Our work also provides a comprehensive analysis of the modes, radiation patterns, parametric influences, and bandwidths of the antennas that highlights their robust nature.}}, author = {{Farheen, Henna and Leuteritz, Till and Linden, Stefan and Myroshnychenko, Viktor and Förstner, Jens}}, booktitle = {{arXiv:2106.02468}}, title = {{{Optimization of optical waveguide antennas for directive emission of light}}}, year = {{2021}}, } @unpublished{32236, abstract = {{The interaction between quantum light and matter is being intensively studied for systems that are enclosed in high-$Q$ cavities which strongly enhance the light-matter coupling. However, for many applications, cavities with lower $Q$-factors are preferred due to the increased spectral width of the cavity mode. Here, we investigate the interaction between quantum light and matter represented by a $\Lambda$-type three-level system in lossy cavities, assuming that cavity losses are the dominant loss mechanism. We demonstrate that cavity losses lead to non-trivial steady states of the electronic occupations that can be controlled by the loss rate and the initial statistics of the quantum fields. The mechanism of formation of such steady states can be understood on the basis of the equations of motion. Analytical expressions for steady states and their numerical simulations are presented and discussed.}}, author = {{Rose, H. and Tikhonova, O. V. and Meier, T. and Sharapova, P. }}, booktitle = {{arXiv:2109.00842}}, title = {{{Steady states of $Λ$-type three-level systems excited by quantum light in lossy cavities}}}, year = {{2021}}, } @inproceedings{46194, author = {{Kenter, Tobias and Shambhu, Adesh and Faghih-Naini, Sara and Aizinger, Vadym}}, booktitle = {{Proceedings of the Platform for Advanced Scientific Computing Conference}}, publisher = {{ACM}}, title = {{{Algorithm-hardware co-design of a discontinuous Galerkin shallow-water model for a dataflow architecture on FPGA}}}, doi = {{10.1145/3468267.3470617}}, year = {{2021}}, } @inproceedings{46195, author = {{Karp, Martin and Podobas, Artur and Jansson, Niclas and Kenter, Tobias and Plessl, Christian and Schlatter, Philipp and Markidis, Stefano}}, booktitle = {{2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)}}, publisher = {{IEEE}}, title = {{{High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection}}}, doi = {{10.1109/ipdps49936.2021.00116}}, year = {{2021}}, } @inproceedings{29937, author = {{Karp, Martin and Podobas, Artur and Jansson, Niclas and Kenter, Tobias and Plessl, Christian and Schlatter, Philipp and Markidis, Stefano}}, booktitle = {{2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)}}, publisher = {{IEEE}}, title = {{{High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection}}}, doi = {{10.1109/ipdps49936.2021.00116}}, year = {{2021}}, } @unpublished{32242, abstract = {{We consider a resource-aware variant of the classical multi-armed bandit problem: In each round, the learner selects an arm and determines a resource limit. It then observes a corresponding (random) reward, provided the (random) amount of consumed resources remains below the limit. Otherwise, the observation is censored, i.e., no reward is obtained. For this problem setting, we introduce a measure of regret, which incorporates the actual amount of allocated resources of each learning round as well as the optimality of realizable rewards. Thus, to minimize regret, the learner needs to set a resource limit and choose an arm in such a way that the chance to realize a high reward within the predefined resource limit is high, while the resource limit itself should be kept as low as possible. We derive the theoretical lower bound on the cumulative regret and propose a learning algorithm having a regret upper bound that matches the lower bound. In a simulation study, we show that our learning algorithm outperforms straightforward extensions of standard multi-armed bandit algorithms.}}, author = {{Bengs, Viktor and Hüllermeier, Eyke}}, booktitle = {{arXiv:2011.00813}}, title = {{{Multi-Armed Bandits with Censored Consumption of Resources}}}, year = {{2020}}, } @inproceedings{16898, abstract = {{Electronic structure calculations based on density-functional theory (DFT) represent a significant part of today's HPC workloads and pose high demands on high-performance computing resources. To perform these quantum-mechanical DFT calculations on complex large-scale systems, so-called linear scaling methods instead of conventional cubic scaling methods are required. In this work, we take up the idea of the submatrix method and apply it to the DFT computations in the software package CP2K. For that purpose, we transform the underlying numeric operations on distributed, large, sparse matrices into computations on local, much smaller and nearly dense matrices. This allows us to exploit the full floating-point performance of modern CPUs and to make use of dedicated accelerator hardware, where performance has been limited by memory bandwidth before. We demonstrate both functionality and performance of our implementation and show how it can be accelerated with GPUs and FPGAs.}}, author = {{Lass, Michael and Schade, Robert and Kühne, Thomas and Plessl, Christian}}, booktitle = {{Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)}}, location = {{Atlanta, GA, US}}, pages = {{1127--1140}}, publisher = {{IEEE Computer Society}}, title = {{{A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K}}}, doi = {{10.1109/SC41405.2020.00084}}, year = {{2020}}, } @inproceedings{21632, abstract = {{FPGAs have found increasing adoption in data center applications since a new generation of high-level tools have become available which noticeably reduce development time for FPGA accelerators and still provide high-quality results. There is, however, no high-level benchmark suite available, which specifically enables a comparison of FPGA architectures, programming tools, and libraries for HPC applications. To fill this gap, we have developed an OpenCL-based open-source implementation of the HPCC benchmark suite for Xilinx and Intel FPGAs. This benchmark can serve to analyze the current capabilities of FPGA devices, cards, and development tool flows, track progress over time, and point out specific difficulties for FPGA acceleration in the HPC domain. Additionally, the benchmark documents proven performance optimization patterns. We will continue optimizing and porting the benchmark for new generations of FPGAs and design tools and encourage active participation to create a valuable tool for the community. To fill this gap, we have developed an OpenCL-based open-source implementation of the HPCC benchmark suite for Xilinx and Intel FPGAs. This benchmark can serve to analyze the current capabilities of FPGA devices, cards, and development tool flows, track progress over time, and point out specific difficulties for FPGA acceleration in the HPC domain. Additionally, the benchmark documents proven performance optimization patterns. We will continue optimizing and porting the benchmark for new generations of FPGAs and design tools and encourage active participation to create a valuable tool for the community.}}, author = {{Meyer, Marius and Kenter, Tobias and Plessl, Christian}}, booktitle = {{2020 IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC)}}, isbn = {{9781665415927}}, keywords = {{FPGA, OpenCL, High Level Synthesis, HPC benchmarking}}, title = {{{Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite}}}, doi = {{10.1109/h2rc51942.2020.00007}}, year = {{2020}}, } @inproceedings{15478, abstract = {{Stratix 10 FPGA cards have a good potential for the acceleration of HPC workloads since the Stratix 10 product line introduces devices with a large number of DSP and memory blocks. The high level synthesis of OpenCL codes can play a fundamental role for FPGAs in HPC, because it allows to implement different designs with lower development effort compared to hand optimized HDL. However, Stratix 10 cards are still hard to fully exploit using the Intel FPGA SDK for OpenCL. The implementation of designs with thousands of concurrent arithmetic operations often suffers from place and route problems that limit the maximum frequency or entirely prevent a successful synthesis. In order to overcome these issues for the implementation of the matrix multiplication, we formulate Cannon's matrix multiplication algorithm with regard to its efficient synthesis within the FPGA logic. We obtain a two-level block algorithm, where the lower level sub-matrices are multiplied using our Cannon's algorithm implementation. Following this design approach with multiple compute units, we are able to get maximum frequencies close to and above 300 MHz with high utilization of DSP and memory blocks. This allows for performance results above 1 TeraFLOPS.}}, author = {{Gorlani, Paolo and Kenter, Tobias and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on Field-Programmable Technology (FPT)}}, publisher = {{IEEE}}, title = {{{OpenCL Implementation of Cannon's Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs}}}, doi = {{10.1109/ICFPT47387.2019.00020}}, year = {{2019}}, } @inproceedings{22, abstract = {{This paper describes a data structure and a heuristic to plan and map arbitrary resources in complex combinations while applying time dependent constraints. The approach is used in the planning based workload manager OpenCCS at the Paderborn Center for Parallel Computing (PC\(^2\)) to operate heterogeneous clusters with up to 10000 cores. We also show performance results derived from four years of operation.}}, author = {{Keller, Axel}}, booktitle = {{Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP)}}, editor = {{Klusáček, D. and Cirne, W. and Desai, N.}}, isbn = {{978-3-319-77398-8}}, keywords = {{Scheduling Planning Mapping Workload management}}, location = {{Orlando, FL, USA}}, pages = {{132--151}}, publisher = {{Springer}}, title = {{{A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems}}}, doi = {{10.1007/978-3-319-77398-8_8}}, volume = {{10773}}, year = {{2018}}, } @inproceedings{1588, abstract = {{The exploration of FPGAs as accelerators for scientific simulations has so far mostly been focused on small kernels of methods working on regular data structures, for example in the form of stencil computations for finite difference methods. In computational sciences, often more advanced methods are employed that promise better stability, convergence, locality and scaling. Unstructured meshes are shown to be more effective and more accurate, compared to regular grids, in representing computation domains of various shapes. Using unstructured meshes, the discontinuous Galerkin method preserves the ability to perform explicit local update operations for simulations in the time domain. In this work, we investigate FPGAs as target platform for an implementation of the nodal discontinuous Galerkin method to find time-domain solutions of Maxwell's equations in an unstructured mesh. When maximizing data reuse and fitting constant coefficients into suitably partitioned on-chip memory, high computational intensity allows us to implement and feed wide data paths with hundreds of floating point operators. By decoupling off-chip memory accesses from the computations, high memory bandwidth can be sustained, even for the irregular access pattern required by parts of the application. Using the Intel/Altera OpenCL SDK for FPGAs, we present different implementation variants for different polynomial orders of the method. In different phases of the algorithm, either computational or bandwidth limits of the Arria 10 platform are almost reached, thus outperforming a highly multithreaded CPU implementation by around 2x.}}, author = {{Kenter, Tobias and Mahale, Gopinath and Alhaddad, Samer and Grynko, Yevgen and Schmitt, Christian and Afzal, Ayesha and Hannig, Frank and Förstner, Jens and Plessl, Christian}}, booktitle = {{Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)}}, keywords = {{tet_topic_hpc}}, publisher = {{IEEE}}, title = {{{OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes}}}, doi = {{10.1109/FCCM.2018.00037}}, year = {{2018}}, } @inproceedings{1590, abstract = {{We present the submatrix method, a highly parallelizable method for the approximate calculation of inverse p-th roots of large sparse symmetric matrices which are required in different scientific applications. Following the idea of Approximate Computing, we allow imprecision in the final result in order to utilize the sparsity of the input matrix and to allow massively parallel execution. For an n x n matrix, the proposed algorithm allows to distribute the calculations over n nodes with only little communication overhead. The result matrix exhibits the same sparsity pattern as the input matrix, allowing for efficient reuse of allocated data structures. We evaluate the algorithm with respect to the error that it introduces into calculated results, as well as its performance and scalability. We demonstrate that the error is relatively limited for well-conditioned matrices and that results are still valuable for error-resilient applications like preconditioning even for ill-conditioned matrices. We discuss the execution time and scaling of the algorithm on a theoretical level and present a distributed implementation of the algorithm using MPI and OpenMP. We demonstrate the scalability of this implementation by running it on a high-performance compute cluster comprised of 1024 CPU cores, showing a speedup of 665x compared to single-threaded execution.}}, author = {{Lass, Michael and Mohr, Stephan and Wiebeler, Hendrik and Kühne, Thomas and Plessl, Christian}}, booktitle = {{Proc. Platform for Advanced Scientific Computing (PASC) Conference}}, isbn = {{978-1-4503-5891-0/18/07}}, keywords = {{approximate computing, linear algebra, matrix inversion, matrix p-th roots, numeric algorithm, parallel computing}}, location = {{Basel, Switzerland}}, publisher = {{ACM}}, title = {{{A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices}}}, doi = {{10.1145/3218176.3218231}}, year = {{2018}}, } @inproceedings{1204, author = {{Riebler, Heinrich and Vaz, Gavin Francis and Kenter, Tobias and Plessl, Christian}}, booktitle = {{Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP)}}, isbn = {{9781450349826}}, keywords = {{htrop}}, publisher = {{ACM}}, title = {{{Automated Code Acceleration Targeting Heterogeneous OpenCL Devices}}}, doi = {{10.1145/3178487.3178534}}, year = {{2018}}, } @inproceedings{1592, abstract = {{Compared to classical HDL designs, generating FPGA with high-level synthesis from an OpenCL specification promises easier exploration of different design alternatives and, through ready-to-use infrastructure and common abstractions for host and memory interfaces, easier portability between different FPGA families. In this work, we evaluate the extent of this promise. To this end, we present a parameterized FDTD implementation for photonic microcavity simulations. Our design can trade-off different forms of parallelism and works for two independent OpenCL-based FPGA design flows. Hence, we can target FPGAs from different vendors and different FPGA families. We describe how we used pre-processor macros to achieve this flexibility and to work around different shortcomings of the current tools. Choosing the right design configurations, we are able to present two extremely competitive solutions for very different FPGA targets, reaching up to 172 GFLOPS sustained performance. With the portability and flexibility demonstrated, code developers not only avoid vendor lock-in, but can even make best use of real trade-offs between different architectures.}}, author = {{Kenter, Tobias and Förstner, Jens and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)}}, keywords = {{tet_topic_hpc}}, publisher = {{IEEE}}, title = {{{Flexible FPGA design for FDTD using OpenCL}}}, doi = {{10.23919/FPL.2017.8056844}}, year = {{2017}}, } @inproceedings{34, author = {{Dellnitz, Michael and Eckstein, Julian and Flaßkamp, Kathrin and Friedel, Patrick and Horenkamp, Christian and Köhler, Ulrich and Ober-Blöbaum, Sina and Peitz, Sebastian and Tiemeyer, Sebastian}}, booktitle = {{Progress in Industrial Mathematics at ECMI}}, issn = {{2212-0173}}, pages = {{633--641}}, publisher = {{Springer International Publishing}}, title = {{{Multiobjective Optimal Control Methods for the Development of an Intelligent Cruise Control}}}, doi = {{10.1007/978-3-319-23413-7_87}}, volume = {{22}}, year = {{2016}}, } @inproceedings{19, abstract = {{Version Control Systems (VCS) are a valuable tool for software development and document management. Both client/server and distributed (Peer-to-Peer) models exist, with the latter (e.g., Git and Mercurial) becoming increasingly popular. Their distributed nature introduces complications, especially concerning security: it is hard to control the dissemination of contents stored in distributed VCS as they rely on replication of complete repositories to any involved user. We overcome this issue by designing and implementing a concept for cryptography-enforced access control which is transparent to the user. Use of field-tested schemes (end-to-end encryption, digital signatures) allows for strong security, while adoption of convergent encryption and content-defined chunking retains storage efficiency. The concept is seamlessly integrated into Mercurial---respecting its distributed storage concept---to ensure practical usability and compatibility to existing deployments.}}, author = {{Lass, Michael and Leibenger, Dominik and Sorge, Christoph}}, booktitle = {{Proc. 41st Conference on Local Computer Networks (LCN)}}, isbn = {{978-1-5090-2054-6}}, keywords = {{access control, distributed version control systems, mercurial, peer-to-peer, convergent encryption, confidentiality, authenticity}}, publisher = {{IEEE}}, title = {{{Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension}}}, doi = {{10.1109/lcn.2016.11}}, year = {{2016}}, } @inproceedings{31, author = {{Riebler, Heinrich and Vaz, Gavin Francis and Plessl, Christian and Trainiti, Ettore M. G. and Durelli, Gianluca C. and Bolchini, Cristiana}}, booktitle = {{Proc. HiPEAC Workshop on Reonfigurable Computing (WRC)}}, title = {{{Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems}}}, year = {{2016}}, } @inproceedings{24, author = {{Kenter, Tobias and Plessl, Christian}}, booktitle = {{Proc. Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC)}}, title = {{{Microdisk Cavity FDTD Simulation on FPGA using OpenCL}}}, year = {{2016}}, } @inproceedings{25, author = {{Lass, Michael and Kühne, Thomas and Plessl, Christian}}, booktitle = {{Workshop on Approximate Computing (AC)}}, title = {{{Using Approximate Computing in Scientific Codes}}}, year = {{2016}}, } @inproceedings{138, abstract = {{Hardware accelerators are becoming popular in academia and industry. To move one step further from the state-of-the-art multicore plus accelerator approaches, we present in this paper our innovative SAVEHSA architecture. It comprises of a heterogeneous hardware platform with three different high-end accelerators attached over PCIe (GPGPU, FPGA and Intel MIC). Such systems can process parallel workloads very efficiently whilst being more energy efficient than regular CPU systems. To leverage the heterogeneity, the workload has to be distributed among the computing units in a way that each unit is well-suited for the assigned task and executable code must be available. To tackle this problem we present two software components; the first can perform resource allocation at runtime while respecting system and application goals (in terms of throughput, energy, latency, etc.) and the second is able to analyze an application and generate executable code for an accelerator at runtime. We demonstrate the first proof-of-concept implementation of our framework on the heterogeneous platform, discuss different runtime policies and measure the introduced overheads.}}, author = {{Riebler, Heinrich and Vaz, Gavin Francis and Plessl, Christian and Trainiti, Ettore M. G. and Durelli, Gianluca C. and Del Sozzo, Emanuele and Santambrogio, Marco D. and Bolchini, Christina}}, booktitle = {{Proceedings of International Forum on Research and Technologies for Society and Industry (RTSI)}}, pages = {{1--5}}, publisher = {{IEEE}}, title = {{{Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems}}}, doi = {{10.1109/RTSI.2016.7740545}}, year = {{2016}}, } @inproceedings{168, abstract = {{The use of heterogeneous computing resources, such as Graphic Processing Units or other specialized coprocessors, has become widespread in recent years because of their per- formance and energy efficiency advantages. Approaches for managing and scheduling tasks to heterogeneous resources are still subject to research. Although queuing systems have recently been extended to support accelerator resources, a general solution that manages heterogeneous resources at the operating system- level to exploit a global view of the system state is still missing.In this paper we present a user space scheduler that enables task scheduling and migration on heterogeneous processing resources in Linux. Using run queues for available resources we perform scheduling decisions based on the system state and on task characterization from earlier measurements. With a pro- gramming pattern that supports the integration of checkpoints into applications, we preempt tasks and migrate them between three very different compute resources. Considering static and dynamic workload scenarios, we show that this approach can gain up to 17% performance, on average 7%, by effectively avoiding idle resources. We demonstrate that a work-conserving strategy without migration is no suitable alternative.}}, author = {{Lösch, Achim and Beisel, Tobias and Kenter, Tobias and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE)}}, pages = {{912--917}}, publisher = {{EDA Consortium / IEEE}}, title = {{{Performance-centric scheduling with task migration for a heterogeneous compute node in the data center}}}, year = {{2016}}, } @inproceedings{171, author = {{Kenter, Tobias and Vaz, Gavin Francis and Riebler, Heinrich and Plessl, Christian}}, booktitle = {{Workshop on Reconfigurable Computing (WRC)}}, title = {{{Opportunities for deferring application partitioning and accelerator synthesis to runtime (extended abstract)}}}, year = {{2016}}, } @inproceedings{303, abstract = {{This paper introduces Binary Acceleration At Runtime(BAAR), an easy-to-use on-the-fly binary acceleration mechanismwhich aims to tackle the problem of enabling existentsoftware to automatically utilize accelerators at runtime. BAARis based on the LLVM Compiler Infrastructure and has aclient-server architecture. The client runs the program to beaccelerated in an environment which allows program analysisand profiling. Program parts which are identified as suitable forthe available accelerator are exported and sent to the server.The server optimizes these program parts for the acceleratorand provides RPC execution for the client. The client transformsits program to utilize accelerated execution on the server foroffloaded program parts. We evaluate our work with a proofof-concept implementation of BAAR that uses an Intel XeonPhi 5110P as the acceleration target and performs automaticoffloading, parallelization and vectorization of suitable programparts. The practicality of BAAR for real-world examples is shownbased on a study of stencil codes. Our results show a speedup ofup to 4 without any developer-provided hints and 5.77 withhints over the same code compiled with the Intel Compiler atoptimization level O2 and running on an Intel Xeon E5-2670machine. Based on our insights gained during implementationand evaluation we outline future directions of research, e.g.,offloading more fine-granular program parts than functions, amore sophisticated communication mechanism or introducing onstack-replacement.}}, author = {{Damschen, Marvin and Plessl, Christian}}, booktitle = {{Proceedings of the 5th International Workshop on Adaptive Self-tuning Computing Systems (ADAPT)}}, title = {{{Easy-to-Use On-The-Fly Binary Program Acceleration on Many-Cores}}}, year = {{2015}}, } @inproceedings{1773, author = {{Schumacher, Jörn and T. 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, Giovanna and Levinson, L. and Narevicius, J. and Plessl, Christian and Roich, A. and Ryu, S. and P. Schreuder, F. and Vandelli, Wainer and Vermeulen, J. and Zhang, J.}}, booktitle = {{Proc. Int. Conf. on Distributed Event-Based Systems (DEBS)}}, publisher = {{ACM}}, title = {{{Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm}}}, doi = {{10.1145/2675743.2771824}}, year = {{2015}}, } @inproceedings{238, abstract = {{In this paper, we study how binary applications can be transparently accelerated with novel heterogeneous computing resources without requiring any manual porting or developer-provided hints. Our work is based on Binary Acceleration At Runtime (BAAR), our previously introduced binary acceleration mechanism that uses the LLVM Compiler Infrastructure. BAAR is designed as a client-server architecture. The client runs the program to be accelerated in an environment, which allows program analysis and profiling and identifies and extracts suitable program parts to be offloaded. The server compiles and optimizes these offloaded program parts for the accelerator and offers access to these functions to the client with a remote procedure call (RPC) interface. Our previous work proved the feasibility of our approach, but also showed that communication time and overheads limit the granularity of functions that can be meaningfully offloaded. In this work, we motivate the importance of a lightweight, high-performance communication between server and client and present a communication mechanism based on the Message Passing Interface (MPI). We evaluate our approach by using an Intel Xeon Phi 5110P as the acceleration target and show that the communication overhead can be reduced from 40% to 10%, thus enabling even small hotspots to benefit from offloading to an accelerator.}}, author = {{Damschen, Marvin and Riebler, Heinrich and Vaz, Gavin Francis and Plessl, Christian}}, booktitle = {{Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE)}}, pages = {{1078--1083}}, publisher = {{EDA Consortium / IEEE}}, title = {{{Transparent offloading of computational hotspots from binary code to Xeon Phi}}}, doi = {{10.7873/DATE.2015.1124}}, year = {{2015}}, } @inproceedings{1781, abstract = {{In light of an increasing awareness of environmental challenges, extensive research is underway to develop new light-weight materials. A problem arising with these materials is their increased response to vibration. This can be solved using a new composite material that contains embedded hollow spheres that are partially filled with particles. Progress on the adaptation of molecular dynamics towards a particle-based numerical simulation of this material is reported. This includes the treatment of specific boundary conditions and the adaption of the force computation. First results are presented that showcase the damping properties of such particle-filled spheres in a bouncing experiment.}}, author = {{Steinle, Tobias and Vrabec, Jadran and Walther, Andrea}}, booktitle = {{Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC)}}, editor = {{Bock, Hans Georg and Hoang, Xuan Phu and Rannacher, Rolf and Schlöder, Johannes P.}}, isbn = {{978-3-319-09063-4}}, pages = {{233--243}}, publisher = {{Springer International Publishing}}, title = {{{Numerical Simulation of the Damping Behavior of Particle-Filled Hollow Spheres}}}, doi = {{10.1007/978-3-319-09063-4_19}}, year = {{2014}}, } @inproceedings{1782, author = {{Graf, Tobias and Schaefers, Lars and Platzner, Marco}}, booktitle = {{Proc. Conf. on Computers and Games (CG)}}, number = {{8427}}, pages = {{14--25}}, publisher = {{Springer}}, title = {{{On Semeai Detection in Monte-Carlo Go}}}, doi = {{10.1007/978-3-319-09165-5_2}}, year = {{2014}}, } @inproceedings{388, abstract = {{In order to leverage the use of reconfigurable architectures in general-purpose computing, quick and automated methods to find suitable accelerator designs are required. We tackle this challenge in both regards. In order to avoid long synthesis times, we target a vector copro- cessor, implemented on the FPGAs of a Convey HC-1. Previous studies showed that existing tools were not able to accelerate a real-world application with low effort. We present a toolflow to automatically identify suitable loops for vectorization, generate a corresponding hardware/software bipartition, and generate coprocessor code. Where applicable, we leverage outer-loop vectorization. We evaluate our tools with a set of characteristic loops, systematically analyzing different dependency and data layout properties.}}, author = {{Kenter, Tobias and Vaz, Gavin Francis and Plessl, Christian}}, booktitle = {{Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC)}}, pages = {{144--155}}, publisher = {{Springer International Publishing}}, title = {{{Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer}}}, doi = {{10.1007/978-3-319-05960-0_13}}, volume = {{8405}}, year = {{2014}}, } @inproceedings{377, abstract = {{In this paper, we study how AES key schedules can be reconstructed from decayed memory. This operation is a crucial and time consuming operation when trying to break encryption systems with cold-boot attacks. In software, the reconstruction of the AES master key can be performed using a recursive, branch-and-bound tree-search algorithm that exploits redundancies in the key schedule for constraining the search space. In this work, we investigate how this branch-and-bound algorithm can be accelerated with FPGAs. We translated the recursive search procedure to a state machine with an explicit stack for each recursion level and create optimized datapaths to accelerate in particular the processing of the most frequently accessed tree levels. We support two different decay models, of which especially the more realistic non-idealized asymmetric decay model causes very high runtimes in software. Our implementation on a Maxeler dataflow computing system outperforms a software implementation for this model by up to 27x, which makes cold-boot attacks against AES practical even for high error rates.}}, author = {{Riebler, Heinrich and Kenter, Tobias and Plessl, Christian and Sorge, Christoph}}, booktitle = {{Proceedings of Field-Programmable Custom Computing Machines (FCCM)}}, keywords = {{coldboot}}, pages = {{222--229}}, publisher = {{IEEE}}, title = {{{Reconstructing AES Key Schedules from Decayed Memory with FPGAs}}}, doi = {{10.1109/FCCM.2014.67}}, year = {{2014}}, } @inproceedings{1778, author = {{C. Durelli, Gianluca and Pogliani, Marcello and Miele, Antonio and Plessl, Christian and Riebler, Heinrich and Vaz, Gavin Francis and D. Santambrogio, Marco and Bolchini, Cristiana}}, booktitle = {{Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA)}}, pages = {{142--149}}, publisher = {{IEEE}}, title = {{{Runtime Resource Management in Heterogeneous System Architectures: The SAVE Approach}}}, doi = {{10.1109/ISPA.2014.27}}, year = {{2014}}, } @inproceedings{439, abstract = {{Reconfigurable architectures provide an opportunityto accelerate a wide range of applications, frequentlyby exploiting data-parallelism, where the same operations arehomogeneously executed on a (large) set of data. However, whenthe sequential code is executed on a host CPU and only dataparallelloops are executed on an FPGA coprocessor, a sufficientlylarge number of loop iterations (trip counts) is required, such thatthe control- and data-transfer overheads to the coprocessor canbe amortized. However, the trip count of large data-parallel loopsis frequently not known at compile time, but only at runtime justbefore entering a loop. Therefore, we propose to generate codeboth for the CPU and the coprocessor, and to defer the decisionwhere to execute the appropriate code to the runtime of theapplication when the trip count of the loop can be determinedjust at runtime. We demonstrate how an LLVM compiler basedtoolflow can automatically insert appropriate decision blocks intothe application code. Analyzing popular benchmark suites, weshow that this kind of runtime decisions is often applicable. Thepractical feasibility of our approach is demonstrated by a toolflowthat automatically identifies loops suitable for vectorization andgenerates code for the FPGA coprocessor of a Convey HC-1. Thetoolflow adds decisions based on a comparison of the runtimecomputedtrip counts to thresholds for specific loops and alsoincludes support to move just the required data to the coprocessor.We evaluate the integrated toolflow with characteristic loopsexecuted on different input data sizes.}}, author = {{Vaz, Gavin Francis and Riebler, Heinrich and Kenter, Tobias and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)}}, pages = {{1--8}}, publisher = {{IEEE}}, title = {{{Deferring Accelerator Offloading Decisions to Application Runtime}}}, doi = {{10.1109/ReConFig.2014.7032509}}, year = {{2014}}, } @inproceedings{406, abstract = {{Stereo-matching algorithms recently received a lot of attention from the FPGA acceleration community. Presented solutions range from simple, very resource efficient systems with modest matching quality for small embedded systems to sophisticated algorithms with several processing steps, implemented on big FPGAs. In order to achieve high throughput, most implementations strongly focus on pipelining and data reuse between different computation steps. This approach leads to high efficiency, but limits the supported computation patterns and due the high integration of the implementation, adaptions to the algorithm are difficult. In this work, we present a stereo-matching implementation, that starts by offloading individual kernels from the CPU to the FPGA. Between subsequent compute steps on the FPGA, data is stored off-chip in on-board memory of the FPGA accelerator card. This enables us to accelerate the AD-census algorithm with cross-based aggregation and scanline optimization for the first time without algorithmic changes and for up to full HD image dimensions. Analyzing throughput and bandwidth requirements, we outline some trade-offs that are involved with this approach, compared to tighter integration of more kernel loops into one design.}}, author = {{Kenter, Tobias and Schmitz, Henning and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)}}, pages = {{1--8}}, publisher = {{IEEE}}, title = {{{Kernel-Centric Acceleration of High Accuracy Stereo-Matching}}}, doi = {{10.1109/ReConFig.2014.7032535}}, year = {{2014}}, } @inproceedings{1780, author = {{C. Durelli, Gianluca and Copolla, Marcello and Djafarian, Karim and Koranaros, George and Miele, Antonio and Paolino, Michele and Pell, Oliver and Plessl, Christian and D. Santambrogio, Marco and Bolchini, Cristiana}}, booktitle = {{Proc. Int. Conf. on Reconfigurable Computing: Architectures, Tools and Applications (ARC)}}, publisher = {{Springer}}, title = {{{SAVE: Towards efficient resource management in heterogeneous system architectures}}}, doi = {{10.1007/978-3-319-05960-0_38}}, year = {{2014}}, } @inproceedings{1784, author = {{Kaiser, Jürgen and Meister, Dirk and Gottfried, Viktor and Brinkmann, André}}, booktitle = {{Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS)}}, pages = {{88--97}}, publisher = {{IEEE Computer Society}}, title = {{{MCD: Overcoming the Data Download Bottleneck in Data Centers}}}, doi = {{10.1109/NAS.2013.18}}, year = {{2013}}, } @inproceedings{1786, author = {{Kasap, Server and Redif, Soydan}}, booktitle = {{Proc. IEEE Signal Processing and Communications Conf. (SUI)}}, publisher = {{IEEE}}, title = {{{FPGA Implementation of a Second-Order Convolutive Blind Signal Separation Algorithm}}}, doi = {{10.1109/SIU.2013.6531530}}, year = {{2013}}, } @inproceedings{1788, author = {{Berenbrink, Petra and Brinkmann, André and Friedetzky, Tom and Meister, Dirk and Nagel, Lars}}, booktitle = {{Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW)}}, publisher = {{IEEE}}, title = {{{Distributing Storage in Cloud Environments}}}, doi = {{10.1109/IPDPSW.2013.148}}, year = {{2013}}, } @inproceedings{1793, author = {{Meister, Dirk and Brinkmann, André and Süß, Tim}}, booktitle = {{Proc. USENIX Conference on File and Storage Technologies (FAST)}}, pages = {{175--182}}, publisher = {{USENIX Association}}, title = {{{File Recipe Compression in Data Deduplication Systems}}}, year = {{2013}}, } @inproceedings{528, abstract = {{Cold-boot attacks exploit the fact that DRAM contents are not immediately lost when a PC is powered off. Instead the contents decay rather slowly, in particular if the DRAM chips are cooled to low temperatures. This effect opens an attack vector on cryptographic applications that keep decrypted keys in DRAM. An attacker with access to the target computer can reboot it or remove the RAM modules and quickly copy the RAM contents to non-volatile memory. By exploiting the known cryptographic structure of the cipher and layout of the key data in memory, in our application an AES key schedule with redundancy, the resulting memory image can be searched for sections that could correspond to decayed cryptographic keys; then, the attacker can attempt to reconstruct the original key. However, the runtime of these algorithms grows rapidly with increasing memory image size, error rate and complexity of the bit error model, which limits the practicability of the approach.In this work, we study how the algorithm for key search can be accelerated with custom computing machines. We present an FPGA-based architecture on a Maxeler dataflow computing system that outperforms a software implementation up to 205x, which significantly improves the practicability of cold-attacks against AES.}}, author = {{Riebler, Heinrich and Kenter, Tobias and Sorge, Christoph and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on Field-Programmable Technology (FPT)}}, keywords = {{coldboot}}, pages = {{386--389}}, publisher = {{IEEE}}, title = {{{FPGA-accelerated Key Search for Cold-Boot Attacks against AES}}}, doi = {{10.1109/FPT.2013.6718394}}, year = {{2013}}, } @inproceedings{505, abstract = {{In this paper we introduce “On-The-Fly Computing”, our vision of future IT services that will be provided by assembling modular software components available on world-wide markets. After suitable components have been found, they are automatically integrated, configured and brought to execution in an On-The-Fly Compute Center. We envision that these future compute centers will continue to leverage three current trends in large scale computing which are an increasing amount of parallel processing, a trend to use heterogeneous computing resources, and—in the light of rising energy cost—energy-efficiency as a primary goal in the design and operation of computing systems. In this paper, we point out three research challenges and our current work in these areas.}}, author = {{Happe, Markus and Kling, Peter and Plessl, Christian and Platzner, Marco and Meyer auf der Heide, Friedhelm}}, booktitle = {{Proceedings of the 9th IEEE Workshop on Software Technology for Future embedded and Ubiquitous Systems (SEUS)}}, publisher = {{IEEE}}, title = {{{On-The-Fly Computing: A Novel Paradigm for Individualized IT Services}}}, doi = {{10.1109/ISORC.2013.6913232}}, year = {{2013}}, } @inproceedings{1787, author = {{Suess, Tim and Schoenrock, Andrew and Meisner, Sebastian and Plessl, Christian}}, booktitle = {{Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW)}}, isbn = {{978-0-7695-4979-8}}, pages = {{64--73}}, publisher = {{IEEE Computer Society}}, title = {{{Parallel Macro Pipelining on the Intel SCC Many-Core Computer}}}, doi = {{10.1109/IPDPSW.2013.136}}, year = {{2013}}, } @inproceedings{2097, author = {{Kasap, Server and Redif, Soydan}}, booktitle = {{Proc. Int. Conf. on Field Programmable Technology (ICFPT)}}, pages = {{135--140}}, publisher = {{IEEE Computer Society}}, title = {{{FPGA-based design and implementation of an approximate polynomial matrix EVD algorithm}}}, doi = {{10.1109/FPT.2012.6412125}}, year = {{2012}}, } @inproceedings{2098, author = {{Kaiser, Jürgen and Meister, Dirk and Hartung, Tim and Brinkmann, André}}, booktitle = {{Proc. IEEE Int. Conf. on Parallel and Distributed Systems (ICPADS)}}, pages = {{181--188}}, publisher = {{IEEE}}, title = {{{ESB: Ext2 Split Block Device}}}, doi = {{10.1109/ICPADS.2012.34}}, year = {{2012}}, } @inproceedings{2099, author = {{Meister, Dirk and Kaiser, Jürgen and Brinkmann, André and Kuhn, Michael and Kunkel, Julian and Cortes, Toni}}, booktitle = {{Proc. Int. Conf. on Supercomputing (SC)}}, pages = {{7:1--7:11}}, publisher = {{IEEE Computer Society}}, title = {{{A Study on Data Deduplication in HPC Storage Systems}}}, doi = {{10.1109/SC.2012.14}}, year = {{2012}}, } @inproceedings{2100, author = {{Kasap, Server and Redif, Soydan}}, booktitle = {{Int. Architecture and Engineering Symp. (ARCHENG)}}, title = {{{FPGA implementation of a second-order convolutive blind signal separation algorithm}}}, year = {{2012}}, } @inproceedings{2101, author = {{Grawinkel, Matthias and Süß, Tim and Best, Georg and Popov, Ivan and Brinkmann, André}}, booktitle = {{Proc. Parallel Data Storage Workshop (PDSW)}}, pages = {{13--17}}, publisher = {{IEEE}}, title = {{{Towards Dynamic Scripted pNFS Layouts}}}, doi = {{10.1109/SC.Companion.2012.13}}, year = {{2012}}, } @inproceedings{2103, author = {{Wistuba, Martin and Schaefers, Lars and Platzner, Marco}}, booktitle = {{Proc. IEEE Conf. on Computational Intelligence and Games (CIG)}}, pages = {{91--99}}, publisher = {{IEEE}}, title = {{{Comparison of Bayesian Move Prediction Systems for Computer Go}}}, doi = {{10.1109/CIG.2012.6374143}}, year = {{2012}}, } @inproceedings{2104, author = {{Schlemmer, Tobias and Grunzke, Richard and Gesing, Sandra and Krüger, Jens and Birkenheuer, Georg and Müller-Pfefferkorn, Ralph and Kohlbacher, Oliver}}, booktitle = {{Proc. EGI Technical Forum}}, title = {{{Generic User Management for Science Gateways via Virtual Organizations}}}, year = {{2012}}, } @inproceedings{2105, author = {{Congiu, Giuseppe and Grawinkel, Matthias and Narasimhamurthy, Sai and Brinkmann, André}}, booktitle = {{Proc. Workshop on Interfaces and Architectures for Scientific Data Storage (IASDS)}}, pages = {{16--24}}, publisher = {{IEEE}}, title = {{{One Phase Commit: A Low Overhead Atomic Commitment Protocol for Scalable Metadata Services}}}, doi = {{10.1109/ClusterW.2012.16}}, year = {{2012}}, } @inproceedings{2107, author = {{Grunzke, Richard and Birkenheuer, Georg and Blunk, Dirk and Breuers, Sebastian and Brinkmann, André and Gesing, Sandra and Herres-Pawlis, Sonja and Kohlbacher, Oliver and Krüger, Jens and Kruse, Martin and Müller-Pfefferkorn, Ralph and Schäfer, Patrick and Schuller, Bernd and Steinke, Thomas and Zink, Andreas}}, booktitle = {{Proc. UNICORE Summit}}, title = {{{A Data Driven Science Gateway for Computational Workflows}}}, year = {{2012}}, } @inproceedings{1789, author = {{Kaiser, Jürgen and Meister, Dirk and Brinkmann, André and Effert, Sascha}}, booktitle = {{Proc. Symp. on Mass Storage Systems and Technologies (MSST)}}, pages = {{1--12}}, publisher = {{IEEE}}, title = {{{Design of an exact data deduplication cluster}}}, doi = {{10.1109/MSST.2012.6232380}}, year = {{2012}}, } @inproceedings{2171, author = {{Gesing, Sandra and Herres-Pawlis, Sonja and Birkenheuer, Georg and Brinkmann, André and Grunzke, Richard and Kacsuk, Peter and Kohlbacher, Oliver and Kozlovszky, Miklos and Krüger, Jens and Müller-Pfefferkorn, Ralph and Schäfer, Patrick and Steinke, Thomas}}, booktitle = {{Proc. EGI Community Forum}}, title = {{{The MoSGrid Community From National to International Scale}}}, year = {{2012}}, } @inproceedings{2178, author = {{Gesing, Sandra and Herres-Pawlis, Sonja and Birkenheuer, Georg and Brinkmann, André and Grunzke, Richard and Kacsuk, Peter and Kohlbacher, Oliver and Kozlovszky, Miklos and Krüger, Jens and Müller-Pfefferkorn, Ralph and Schäfer, Patrick and Steinke, Thomas}}, booktitle = {{Proceedings of Science}}, title = {{{A Science Gateway Getting Ready for Serving the International Molecular Simulation Community}}}, volume = {{PoS(EGICF12-EMITC2)050}}, year = {{2012}}, } @inproceedings{2106, abstract = {{Although the benefits of FPGAs for accelerating scientific codes are widely acknowledged, the use of FPGA accelerators in scientific computing is not widespread because reaping these benefits requires knowledge of hardware design methods and tools that is typically not available with domain scientists. A promising but hardly investigated approach is to develop tool flows that keep the common languages for scientific code (C,C++, and Fortran) and allow the developer to augment the source code with OpenMPlike directives for instructing the compiler which parts of the application shall be offloaded the FPGA accelerator. In this work we study whether the promise of effective FPGA acceleration with an OpenMP-like programming effort can actually be held. Our target system is the Convey HC-1 reconfigurable computer for which an OpenMP-like programming environment exists. As case study we use an application from computational nanophotonics. Our results show that a developer without previous FPGA experience could create an FPGA-accelerated application that is competitive to an optimized OpenMP-parallelized CPU version running on a two socket quad-core server. Finally, we discuss our experiences with this tool flow and the Convey HC-1 from a productivity and economic point of view.}}, author = {{Meyer, Björn and Schumacher, Jörn and Plessl, Christian and Förstner, Jens}}, booktitle = {{Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)}}, keywords = {{funding-upb-forschungspreis, funding-maxup, tet_topic_hpc}}, pages = {{189--196}}, publisher = {{IEEE}}, title = {{{Convey Vector Personalities – FPGA Acceleration with an OpenMP-like Effort?}}}, doi = {{10.1109/FPL.2012.6339370}}, year = {{2012}}, } @inproceedings{615, 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, the accuracy of the simulations is to some extent questionable and they require a high computational effort if a detailed thermal model is used.For experimental evaluation of real-world temperature management methods, often synthetic heat sources are employed. Therefore, in this paper we investigated the question if we can create significant rises in temperature on modern FPGAs to enable future evaluation of thermal management techniques based on experiments in contrast to simulations. Therefore, we have developed eight different heat-generating cores that use different subsets of the FPGA resources. Our experimental results show that, according to the built-in thermal diode of our Xilinx Virtex-5 FPGA, we can increase the chip temperature by 134 degree C in less than 12 minutes by only utilizing about 21% of the slices.}}, author = {{Happe, Markus and Hangmann, Hendrik and Agne, Andreas and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on Reconfigurable Computing and FPGAs (ReConFig)}}, pages = {{1--8}}, publisher = {{IEEE}}, title = {{{Eight Ways to put your FPGA on Fire – A Systematic Study of Heat Generators}}}, doi = {{10.1109/ReConFig.2012.6416745}}, year = {{2012}}, } @inproceedings{591, abstract = {{One major obstacle for a wide spread FPGA usage in general-purpose computing is the development tool flow that requires much higher effort than for pure software solutions. Convey Computer promises a solution to this problem for their HC-1 platform, where the FPGAs are configured to run as a vector processor and the software source code can be annotated with pragmas that guide an automated vectorization process. We investigate this approach for a stereo matching algorithm that has abundant parallelism and a number of different computational patterns. We note that for this case study the automated vectorization in its current state doesn’t hold its productivity promise. However, we also show that using the Vector Personality can yield a significant speedups compared to CPU implementations in two of three investigated phases of the algorithm. Those speedups don’t match custom FPGA implementations, but can come with much reduced development effort.}}, author = {{Kenter, Tobias and Plessl, Christian and Schmitz, Henning}}, booktitle = {{Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)}}, pages = {{1--8}}, publisher = {{IEEE}}, title = {{{Pragma based parallelization - Trading hardware efficiency for ease of use?}}}, doi = {{10.1109/ReConFig.2012.6416773}}, year = {{2012}}, } @inproceedings{609, abstract = {{Today's design and operation principles and methods do not scale well with future reconfigurable computing systems due to an increased complexity in system architectures and applications, run-time dynamics and corresponding requirements. Hence, novel design and operation principles and methods are needed that possibly break drastically with the static ones we have built into our systems and the fixed abstraction layers we have cherished over the last decades. Thus, we propose a HW/SW platform that collects and maintains information about its state and progress which enables the system to reason about its behavior (self-awareness) and utilizes its knowledge to effectively and autonomously adapt its behavior to changing requirements (self-expression).To enable self-awareness, our compute nodes collect information using a variety of sensors, i.e. performance counters and thermal diodes, and use internal self-awareness models that process these information. For self-awareness, on-line learning is crucial such that the node learns and continuously updates its models at run-time to react to changing conditions. To enable self-expression, we break with the classic design-time abstraction layers of hardware, operating system and software. In contrast, our system is able to vertically migrate functionalities between the layers at run-time to exploit trade-offs between abstraction and optimization.This paper presents a heterogeneous multi-core architecture, that enables self-awareness and self-expression, an operating system for our proposed hardware/software platform and a novel self-expression method.}}, author = {{Happe, Markus and Agne, Andreas and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proceedings of the Workshop on Self-Awareness in Reconfigurable Computing Systems (SRCS)}}, pages = {{8--9}}, title = {{{Hardware/Software Platform for Self-aware Compute Nodes}}}, year = {{2012}}, } @inproceedings{567, abstract = {{Heterogeneous machines are gaining momentum in the High Performance Computing field, due to the theoretical speedups and power consumption. In practice, while some applications meet the performance expectations, heterogeneous architectures still require a tremendous effort from the application developers. This work presents a code generation method to port codes into heterogeneous platforms, based on transformations of the control flow into function calls. The results show that the cost of the function-call mechanism is affordable for the tested HPC kernels. The complete toolchain, based on the LLVM compiler infrastructure, is fully automated once the sequential specification is provided.}}, author = {{Barrio, Pablo and Carreras, Carlos and Sierra, Roberto and Kenter, Tobias and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on High Performance Computing and Simulation (HPCS)}}, pages = {{559--565}}, publisher = {{IEEE}}, title = {{{Turning control flow graphs into function calls: Code generation for heterogeneous architectures}}}, doi = {{10.1109/HPCSim.2012.6266973}}, year = {{2012}}, } @inproceedings{612, abstract = {{While numerous publications have presented ring oscillator designs for temperature measurements a detailed study of the ring oscillator's design space is still missing. In this work, we introduce metrics for comparing the performance and area efficiency of ring oscillators and a methodology for determining these metrics. As a result, we present a systematic study of the design space for ring oscillators for a Xilinx Virtex-5 platform FPGA.}}, author = {{Rüthing, Christoph and Happe, Markus and Agne, Andreas and Plessl, Christian}}, booktitle = {{Proceedings of the International Conference on Field Programmable Logic and Applications (FPL)}}, pages = {{559--562}}, publisher = {{IEEE}}, title = {{{Exploration of Ring Oscillator Design Space for Temperature Measurements on FPGAs}}}, doi = {{10.1109/FPL.2012.6339370}}, year = {{2012}}, } @inproceedings{2180, author = {{Beisel, Tobias and Wiersema, Tobias and Plessl, Christian and Brinkmann, André}}, booktitle = {{Proc. Workshop on Computer Architecture and Operating System Co-design (CAOS)}}, keywords = {{funding-enhance}}, title = {{{Programming and Scheduling Model for Supporting Heterogeneous Accelerators in Linux}}}, year = {{2012}}, } @inproceedings{1968, abstract = {{Infrastructure as a Service providers use virtualization to abstract their hardware and to create a dynamic data center. Virtualization enables the consolidation of virtual machines as well as the migration of them to other hosts during runtime. Each provider has its own strategy to efficiently operate a data center. We present a rule based mapping algorithm for VMs, which is able to automatically adapt the mapping between VMs and physical hosts. 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. We extended the open source IaaS solution Eucalyptus and we evaluated it with typical policies: maximizing the compute performance and VM locality to achieve a high performance and minimizing energy consumption. The evaluation was done on state-of-the-art servers in our own data center and by simulations using a workload of the Parallel Workload Archive. The results show that our algorithm performs well in dynamic data centers environments.}}, author = {{Kleineweber, Christoph and Keller, Axel and Niehörster, Oliver and Brinkmann, André}}, booktitle = {{Proc. Int. Conf. on Parallel, Distributed and Network-Based Computing (PDP)}}, title = {{{Rule Based Mapping of Virtual Machines in Clouds}}}, doi = {{10.1109/PDP.2011.69}}, year = {{2011}}, } @inproceedings{1972, abstract = {{We present a multi-agent system on top of the IaaS layer consisting of a scheduler agent and multiple worker agents. Each job is controlled by an autonomous worker agent, which is equipped with application specific knowledge (e.g., performance functions) allowing it to estimate the type and number of necessary resources. During runtime, the 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. All worker agents interact with the scheduler agent, which takes care of limited resources and does a cost-aware scheduling by assigning jobs to times with low energy costs. The whole architecture is self-optimizing and able to use public or private clouds.}}, author = {{Niehörster, Oliver and Keller, Axel and Brinkmann, André}}, booktitle = {{Proc. Int. Meeting of the IEEE Int. Symp. on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)}}, title = {{{An Energy-Aware SaaS Stack}}}, doi = {{10.1109/MASCOTS.2011.52}}, year = {{2011}}, } @inproceedings{2188, author = {{Miranda, Alberto and Effert, Sascha and Kang, Yangwook and Miller, Ethan and Brinkmann, André and Cortes, Toni}}, booktitle = {{Proc. Int. Conf. on High Performance Computing (HIPC)}}, pages = {{1--10}}, publisher = {{IEEE Computer Society}}, title = {{{Reliable and Randomized Data Distribution Strategies for Large Scale Storage Systems}}}, doi = {{10.1109/HiPC.2011.6152745}}, year = {{2011}}, } @inproceedings{2189, author = {{Grawinkel, Matthias and Pargmann, Markus and Dömer, Hubert and Brinkmann, André}}, booktitle = {{Proc. IEEE Int. Conf. on Parallel and Distributed Systems (ICPADS)}}, pages = {{380--387}}, publisher = {{IEEE}}, title = {{{Lonestar: An Energy-Aware Disk Based Long-Term Archival Storage System}}}, doi = {{10.1109/ICPADS.2011.77}}, year = {{2011}}, } @inproceedings{2190, author = {{Niehörster, Oliver and Brinkmann, André}}, booktitle = {{Proc. IEEE Int. Conf. on Cloud Computing Technology and Science (CloudCom)}}, pages = {{138--145}}, publisher = {{IEEE Computer Society}}, title = {{{Autonomic Resource Management Handling Delayed Configuration Effects}}}, doi = {{10.1109/CloudCom.2011.28}}, year = {{2011}}, } @inproceedings{2191, author = {{Kenter, Tobias and Plessl, Christian and Platzner, Marco and Kauschke, Michael}}, booktitle = {{Intel European Research and Innovation Conference}}, keywords = {{funding-intel}}, title = {{{Estimation and Partitioning for CPU-Accelerator Architectures}}}, year = {{2011}}, } @inproceedings{2195, author = {{Grawinkel, Matthias and Schäfer, Thorsten and Brinkmann, André and Hagemeyer, Jens and Porrmann, Mario}}, booktitle = {{Proc. Int. Symp. on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)}}, pages = {{297--306}}, publisher = {{IEEE Computer Society}}, title = {{{Evaluation of Applied Intra-Disk Redundancy Schemes to Improve Single Disk Reliability}}}, doi = {{10.1109/mascots.2011.13}}, year = {{2011}}, } @inproceedings{2196, author = {{Brinkmann, André and Gao, Yan and Korzeniowski, Miroslaw and Meister, Dirk}}, booktitle = {{Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS)}}, pages = {{53--62}}, publisher = {{IEEE}}, title = {{{Request Load Balancing for Highly Skewed Traffic in P2P Networks}}}, doi = {{10.1109/NAS.2011.25}}, year = {{2011}}, } @inproceedings{2197, author = {{Gesing, Sandra and Grunzke, Richard and Balaskó, Ákos and Birkenheuer, Georg and Blunk, Dirk and Breuers, Sebastian and Brinkmann, André and Fels, Gregor and Herres-Pawlis, Sonja and Kacsuk, Peter and Kozlovszky, Miklos and Krüger, Jens and Packschies, Lars and Schäfer, Patrick and Schuller, Bernd and Schuster, Johannes and Steinke, Thomas and Szikszay Fabri, Anna and Wewior, Martin and Müller-Pfefferkorn, Ralph and Kohlbacher, Oliver}}, booktitle = {{Proc. Int. Workshop on Scientific Gateways (IWSG)}}, publisher = {{Consorzio COMETA}}, title = {{{Granular Security for a Science Gateway in Structural Bioinformatics}}}, year = {{2011}}, } @inproceedings{2199, author = {{Gesing, Sandra and Kacsuk, Peter and Kozlovszky, Miklos and Birkenheuer, Georg and Blunk, Dirk and Breuers, Sebastian and Brinkmann, André and Fels, Gregor and Grunzke, Richard and Herres-Pawlis, Sonja and Krüger, Jens and Packschies, Lars and Müller-Pfefferkorn, Ralph and Schäfer, Patrick and Steinke, Thomas and Szikszay Fabri, Anna and Warzecha, Klaus-Dieter and Wewior, Martin and Kohlbacher, Oliver}}, booktitle = {{Proc. EGI User Forum}}, pages = {{94--95}}, title = {{{A Science Gateway for Molecular Simulations}}}, year = {{2011}}, } @inproceedings{2203, author = {{Niehörster, Oliver and Simon, Jens and Brinkmann, André and Krieger, Alexaner}}, booktitle = {{Proc. IEEE/ACM Int. Conf. on Grid Computing (GRID)}}, isbn = {{978-0-7695-4572-1}}, pages = {{157--164}}, publisher = {{IEEE Computer Society}}, title = {{{Autonomic Resource Management with Support Vector Machines}}}, doi = {{10.1109/Grid.2011.28}}, year = {{2011}}, } @inproceedings{2204, author = {{Graf, Tobias and Lorenz, Ulf and Platzner, Marco and Schaefers, Lars}}, booktitle = {{Proc. European Conf. on Parallel Processing (Euro-Par)}}, publisher = {{Springer}}, title = {{{Parallel Monte-Carlo Tree Search for HPC Systems}}}, doi = {{10.1007/978-3-642-23397-5_36}}, volume = {{6853}}, year = {{2011}}, } @inproceedings{2205, author = {{Birkenheuer, Georg and Blunk, Dirk and Breuers, Sebastian and Brinkmann, André and Fels, Gregor and Gesing, Sandra and Grunzke, Richard and Herres-Pawlis, Sonja and Kohlbacher, Oliver and Krüger, Jens and Lang, Ulrich and Packschies, Lars and Müller-Pfefferkorn, Ralph and Schäfer, Patrick and Schuster, Johannes and Steinke, Thomas and Warzecha, Klaus-Dieter and Wewior, Martin}}, booktitle = {{Proc. of Grid Workflow Workshop (GWW)}}, title = {{{MoSGrid: Progress of Workflow driven Chemical Simulations}}}, volume = {{829}}, year = {{2011}}, } @inproceedings{2194, author = {{Meyer, Björn and Plessl, Christian and Förstner, Jens}}, booktitle = {{Symp. on Application Accelerators in High Performance Computing (SAAHPC)}}, keywords = {{tet_topic_hpc}}, pages = {{60--63}}, publisher = {{IEEE Computer Society}}, title = {{{Transformation of scientific algorithms to parallel computing code: subdomain support in a MPI-multi-GPU backend}}}, doi = {{10.1109/SAAHPC.2011.12}}, year = {{2011}}, } @inproceedings{2193, author = {{Beisel, Tobias and Wiersema, Tobias and Plessl, Christian and Brinkmann, André}}, booktitle = {{Proc. Int. Conf. on Application-Specific Systems, Architectures, and Processors (ASAP)}}, pages = {{223--226}}, publisher = {{IEEE Computer Society}}, title = {{{Cooperative multitasking for heterogeneous accelerators in the Linux Completely Fair Scheduler}}}, doi = {{10.1109/ASAP.2011.6043273}}, year = {{2011}}, } @inproceedings{656, abstract = {{In the next decades, hybrid multi-cores will be the predominant architecture for reconfigurable FPGA-based systems. Temperature-aware thread mapping strategies are key for providing dependability in such systems. These strategies rely on measuring the temperature distribution and redicting the thermal behavior of the system when there are changes to the hardware and software running on the FPGA. While there are a number of tools that use thermal models to predict temperature distributions at design time, these tools lack the flexibility to autonomously adjust to changing FPGA configurations. To address this problem we propose a temperature-aware system that empowers FPGA-based reconfigurable multi-cores to autonomously predict the on-chip temperature distribution for pro-active thread remapping. Our system obtains temperature measurements through a self-calibrating grid of sensors and uses area constrained heat-generating circuits in order to generate spatial and temporal temperature gradients. The generated temperature variations are then used to learn the free parameters of the system's thermal model. The system thus acquires an understanding of its own thermal characteristics. We implemented an FPGA system containing a net of 144 temperature sensors on a Xilinx Virtex-6 LX240T FPGA that is aware of its thermal model. Finally, we show that the temperature predictions vary less than 0.72 degree C on average compared to the measured temperature distributions at run-time.}}, author = {{Happe, Markus and Agne, Andreas and Plessl, Christian}}, booktitle = {{Proceedings of the 2011 International Conference on Reconfigurable Computing and FPGAs (ReConFig)}}, pages = {{55--60}}, publisher = {{IEEE}}, title = {{{Measuring and Predicting Temperature Distributions on FPGAs at Run-Time}}}, doi = {{10.1109/ReConFig.2011.59}}, year = {{2011}}, } @inproceedings{2200, author = {{Kenter, Tobias and Platzner, Marco and Plessl, Christian and Kauschke, Michael}}, booktitle = {{Proc. Int. Symp. on Field-Programmable Gate Arrays (FPGA)}}, isbn = {{978-1-4503-0554-9}}, keywords = {{design space exploration, LLVM, partitioning, performance, estimation, funding-intel}}, pages = {{177--180}}, publisher = {{ACM}}, title = {{{Performance Estimation Framework for Automated Exploration of CPU-Accelerator Architectures}}}, doi = {{10.1145/1950413.1950448}}, year = {{2011}}, } @inproceedings{2198, author = {{Grad, Mariusz and Plessl, Christian}}, booktitle = {{Proc. Reconfigurable Architectures Workshop (RAW)}}, pages = {{278--285}}, publisher = {{IEEE Computer Society}}, title = {{{Just-in-time Instruction Set Extension – Feasibility and Limitations for an FPGA-based Reconfigurable ASIP Architecture}}}, doi = {{10.1109/IPDPS.2011.153}}, year = {{2011}}, } @inproceedings{2217, author = {{Bienkowski, Marcin and Brinkmann, André and Klonowski, Marek and Korzeniowski, Miroslaw}}, booktitle = {{Proceedings of the 14th International Conference On Principles Of Distributed Systems (Opodis)}}, publisher = {{Springer}}, title = {{{SkewCCC+: A Heterogeneous Distributed Hash Table}}}, doi = {{10.1007/978-3-642-17653-1_18}}, volume = {{6490}}, year = {{2010}}, } @inproceedings{2218, author = {{Wewior, Martin and Packschies, Lars and Blunk, Dirk and Wickeroth, Daniel and Warzecha, Klaus-Dieter and Herres-Pawlis, Sonja and Gesing, Sandra and Breuers, Sebastian and Krüger, Jens and Birkenheuer, Georg and Lang, Ulrich}}, booktitle = {{Proc. Int. Workshop on Scientific Gateways (IWSG)}}, pages = {{39--43}}, publisher = {{Consorzio COMETA}}, title = {{{The MoSGrid Gaussian Portlet - Technologies for the Implementation of Portlets for Molecular Simulations}}}, year = {{2010}}, } @inproceedings{2219, author = {{Gesing, Sandra and Marton, Istvan and Birkenheuer, Georg and Schuller, Bernd and Grunzke, Richard and Krüger, Jens and Breuers, Sebastian and Blunk, Dirk and Fels, Gregor and Packschies, Lars and Brinkmann, André and Kohlbacher, Oliver and Kozlovszky, Miklos}}, booktitle = {{Proc. Int. Workshop on Scientific Gateways (IWSG)}}, pages = {{44--48}}, publisher = {{Consorzio COMETA}}, title = {{{Workflow Interoperability in a Grid Portal for Molecular Simulations}}}, year = {{2010}}, } @inproceedings{2225, author = {{Gao, Yan and Meister, Dirk and Brinkmann, André}}, booktitle = {{Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS)}}, pages = {{126--134}}, publisher = {{IEEE}}, title = {{{Reliability Analysis of Declustered-Parity RAID 6 with Disk Scrubbing and Considering Irrecoverable Read Errors}}}, doi = {{10.1109/NAS.2010.11}}, year = {{2010}}, } @inproceedings{2229, author = {{Berenbrink, Petra and Brinkmann, André and Friedetzky, Tom and Nagel, Lars}}, booktitle = {{Proc. Int. Symp. on Parallelism in Algorithms and Architectures (SPAA)}}, pages = {{100--105}}, publisher = {{ACM}}, title = {{{Balls into Bins with Related Random Choices}}}, doi = {{10.1145/1810479.1810500}}, year = {{2010}}, } @inproceedings{2230, author = {{Meister, Dirk and Brinkmann, André}}, booktitle = {{Proc. Symp. on Mass Storage Systems and Technologies (MSST)}}, pages = {{1--6}}, publisher = {{IEEE Computer Society}}, title = {{{dedupv1: Improving Deduplication Throughput using Solid State Drives (SSD)}}}, doi = {{10.1109/MSST.2010.5496992}}, year = {{2010}}, } @inproceedings{2231, author = {{Lensing, Paul Hermann and Meister, Dirk and Brinkmann, André}}, booktitle = {{Proc. Int. Worksh. on Storage Network Architecture and Parallel I/Os (SNAPI)}}, pages = {{33--42}}, publisher = {{IEEE}}, title = {{{hashFS: Applying Hashing to Optimized File Systems for Small File Reads}}}, doi = {{10.1109/SNAPI.2010.12}}, year = {{2010}}, } @inproceedings{2232, author = {{Berenbrink, Petra and Brinkmann, André and Friedetzky, Tom and Nagel, Lars}}, booktitle = {{Proc. Int. Symp. on Parallel and Distributed Processing (IPDPS)}}, pages = {{1--10}}, publisher = {{IEEE}}, title = {{{Balls into Non-uniform Bins}}}, doi = {{10.1109/IPDPS.2010.5470355}}, year = {{2010}}, } @inproceedings{2234, author = {{Bolte, Matthias and Sievers, Michael and Birkenheuer, Georg and Niehörster, Oliver and Brinkmann, André}}, booktitle = {{Proc. Design, Automation and Test in Europe Conf. (DATE)}}, publisher = {{EDA Consortium}}, title = {{{Non-intrusive Virtualization Management Using libvirt}}}, year = {{2010}}, } @inproceedings{2236, author = {{Birkenheuer, Georg and Breuers, Sebastian and Brinkmann, André and Blunk, Dirk and Fels, Gregor and Gesing, Sandra and Herres-Pawlis, Sonja and Kohlbacher, Oliver and Krüger, Jens and Packschies, Lars}}, booktitle = {{Proc. of Grid Workflow Workshop (GWW)}}, pages = {{177--184}}, publisher = {{Gesellschaft für Informatik (GI)}}, title = {{{Grid-Workflows in Molecular Science}}}, year = {{2010}}, } @inproceedings{2237, author = {{Niehörster, Oliver and Brinkmann, André and Fels, Gregor and Krüger, Jens and Simon, Jens}}, booktitle = {{Proc. Int. Conf. on Cluster Computing (CLUSTER)}}, issn = {{1552-5244}}, pages = {{178--187}}, publisher = {{IEEE}}, title = {{{Enforcing SLAs in Scientific Clouds}}}, doi = {{10.1109/CLUSTER.2010.42}}, year = {{2010}}, } @inproceedings{809, author = {{Birkenheuer, Georg and Brinkmann, Andre and Karl, Holger}}, booktitle = {{Job Scheduling Strategies for Parallel Processing - 15th International Workshop, JSSPP 2010, Atlanta, GA, USA, April 23, 2010, Revised Selected Papers}}, pages = {{51--76}}, title = {{{Risk Aware Overbooking for Commercial Grids}}}, doi = {{10.1007/978-3-642-16505-4_4}}, year = {{2010}}, } @inproceedings{2223, author = {{Lübbers, Enno and Platzner, Marco and Plessl, Christian and Keller, Ariane and Plattner, Bernhard}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-140-6}}, pages = {{225--231}}, publisher = {{CSREA Press}}, title = {{{Towards Adaptive Networking for Embedded Devices based on Reconfigurable Hardware}}}, year = {{2010}}, } @inproceedings{2216, author = {{Grad, Mariusz and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on ReConFigurable Computing and FPGAs (ReConFig)}}, pages = {{67--72}}, publisher = {{IEEE Computer Society}}, title = {{{Pruning the Design Space for Just-In-Time Processor Customization}}}, doi = {{10.1109/ReConFig.2010.19}}, year = {{2010}}, } @inproceedings{2224, author = {{Grad, Mariusz and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-140-6}}, pages = {{144--150}}, publisher = {{CSREA Press}}, title = {{{An Open Source Circuit Library with Benchmarking Facilities}}}, year = {{2010}}, } @inproceedings{2220, author = {{Andrews, David and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-140-6}}, pages = {{165}}, publisher = {{CSREA Press}}, title = {{{Configurable Processor Architectures: History and Trends}}}, year = {{2010}}, } @inproceedings{2226, author = {{Beisel, Tobias and Niekamp, Manuel and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on Application-Specific Systems, Architectures, and Processors (ASAP)}}, isbn = {{978-1-4244-6965-9}}, pages = {{65--72}}, publisher = {{IEEE Computer Society}}, title = {{{Using Shared Library Interposing for Transparent Acceleration in Systems with Heterogeneous Hardware Accelerators}}}, doi = {{10.1109/ASAP.2010.5540798}}, year = {{2010}}, } @inproceedings{2206, author = {{Keller, Ariane and Plattner, Bernhard and Lübbers, Enno and Platzner, Marco and Plessl, Christian}}, booktitle = {{Proc. IEEE Globecom Workshop on Network of the Future (FutureNet)}}, isbn = {{978-1-4244-8864-3}}, pages = {{372--376}}, publisher = {{IEEE}}, title = {{{Reconfigurable Nodes for Future Networks}}}, doi = {{10.1109/GLOCOMW.2010.5700341}}, year = {{2010}}, } @inproceedings{2227, author = {{Woehrle, Matthias and Plessl, Christian and Thiele, Lothar}}, booktitle = {{Proc. Int. Conf. Networked Sensing Systems (INSS)}}, isbn = {{978-1-4244-7911-5}}, pages = {{245--248}}, publisher = {{IEEE}}, title = {{{Rupeas: Ruby Powered Event Analysis DSL}}}, doi = {{10.1109/INSS.2010.5572211}}, year = {{2010}}, } @inproceedings{2228, author = {{Kenter, Tobias and Platzner, Marco and Plessl, Christian and Kauschke, Michael}}, booktitle = {{Proc. Workshop on Architectural Research Prototyping (WARP), International Symposium on Computer Architecture (ISCA)}}, editor = {{Hammami, Omar and Larrabee, Sandra}}, title = {{{Performance Estimation for the Exploration of CPU-Accelerator Architectures}}}, year = {{2010}}, } @inproceedings{2239, author = {{Höing, Andre and Scherp, Guido and Gudenkauf, Stefan and Meister, Dirk and Brinkmann, André}}, booktitle = {{Proc. Int. Conf. on Service Oriented Computing (ICSOC)}}, pages = {{301--315}}, publisher = {{Springer}}, title = {{{An Orchestration as a Service Infrastructure using Grid Technologies and WS-BPEL}}}, doi = {{0.1007/978-3-642-10383-4_20}}, volume = {{5900}}, year = {{2009}}, } @inproceedings{2240, author = {{Niehörster, Oliver and Birkenheuer, Georg and Brinkmann, André and Blunk, Dirk and Elsässer, Brigitta and Herres-Pawlis, Sonja and Krüger, Jens and Niehörster, Julia and Packschies, Lars and Fels, Gregor}}, booktitle = {{Proc. Cracow Grid Workshop (CGW)}}, isbn = {{978-83-61433-01-9}}, pages = {{55--63}}, title = {{{Providing Scientific Software as a Service in Consideration of Service Level Agreements}}}, year = {{2009}}, } @inproceedings{2260, author = {{Birkenheuer, Georg and Carlson, Arthur and Fölling, Alexander and Högqvist, Mikael and Hoheisel, Andreas and Papaspyrou, Alexander and Rieger, Klaus and Schott, Bernhard and Ziegler, Wolfgang}}, booktitle = {{Proc. Cracow Grid Workshop (CGW)}}, isbn = {{978-83-61433-01-9}}, pages = {{96--103}}, title = {{{Connecting Communities on the Meta-Scheduling Level: The DGSI Approach!}}}, year = {{2009}}, } @inproceedings{2264, author = {{Meister, Dirk and Brinkmann, André}}, booktitle = {{Proc. of the Israeli Experimental Systems Conference (SYSTOR)}}, pages = {{8:1--8:12}}, publisher = {{ACM}}, title = {{{Multi-Level Comparison of Data Deduplication in a Backup Scenario}}}, doi = {{10.1145/1534530.1534541}}, year = {{2009}}, } @inproceedings{818, author = {{Birkenheuer, Georg and Brinkmann, Andre and Karl, Holger}}, booktitle = {{Job Scheduling Strategies for Parallel Processing, 14th International Workshop, JSSPP 2009, Rome, Italy, May 29, 2009. Revised Papers}}, pages = {{80--100}}, title = {{{The Gain of Overbooking}}}, doi = {{10.1007/978-3-642-04633-9_5}}, year = {{2009}}, } @inproceedings{2350, abstract = {{Mapping applications that consist of a collection of cores to FPGA accelerators and optimizing their performance is a challenging task in high performance reconfigurable computing. We present IMORC, an architectural template and highly versatile on-chip interconnect. IMORC links provide asynchronous FIFOs and bitwidth conversion which allows for flexibly composing accelerators from cores running at full speed within their own clock domains, thus facilitating the re-use of cores and portability. Further, IMORC inserts performance counters for monitoring runtime data. In this paper, we first introduce the IMORC architectural template and the on-chip interconnect, and then demonstrate IMORC on the example of accelerating the k-th nearest neighbor thinning problem on an XD1000 reconfigurable computing system. Using IMORC's monitoring infrastructure, we gain insights into the data-dependent behavior of the application which, in turn, allow for optimizing the accelerator. }}, author = {{Schumacher, Tobias and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)}}, isbn = {{978-1-4244-4450-2}}, keywords = {{IMORC, interconnect, performance}}, pages = {{275--278}}, publisher = {{IEEE Computer Society}}, title = {{{IMORC: Application Mapping, Monitoring and Optimization for High-Performance Reconfigurable Computing}}}, doi = {{10.1109/FCCM.2009.25}}, year = {{2009}}, } @inproceedings{2262, abstract = {{In this work we present EvoCache, a novel approach for implementing application-specific caches. The key innovation of EvoCache is to make the function that maps memory addresses from the CPU address space to cache indices programmable. We support arbitrary Boolean mapping functions that are implemented within a small reconfigurable logic fabric. For finding suitable cache mapping functions we rely on techniques from the evolvable hardware domain and utilize an evolutionary optimization procedure. We evaluate the use of EvoCache in an embedded processor for two specific applications (JPEG and BZIP2 compression) with respect to execution time, cache miss rate and energy consumption. We show that the evolvable hardware approach for optimizing the cache functions not only significantly improves the cache performance for the training data used during optimization, but that the evolved mapping functions generalize very well. Compared to a conventional cache architecture, EvoCache applied to test data achieves a reduction in execution time of up to 14.31% for JPEG (10.98% for BZIP2), and in energy consumption by 16.43% for JPEG (10.70% for BZIP2). We also discuss the integration of EvoCache into the operating system and show that the area and delay overheads introduced by EvoCache are acceptable. }}, author = {{Kaufmann, Paul and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proc. NASA/ESA Conference on Adaptive Hardware and Systems (AHS)}}, keywords = {{EvoCache, evolvable hardware, computer architecture}}, pages = {{11--18}}, publisher = {{IEEE Computer Society}}, title = {{{EvoCaches: Application-specific Adaptation of Cache Mapping}}}, year = {{2009}}, } @inproceedings{2352, author = {{Beutel, Jan and Gruber, Stephan and Hasler, Andi and Lim, Roman and Meier, Andreas and Plessl, Christian and Talzi, Igor and Thiele, Lothar and Tschudin, Christian and Woehrle, Matthias and Yuecel, Mustafa}}, booktitle = {{Proc. Int. Conf. on Information Processing in Sensor Networks (IPSN)}}, isbn = {{978-1-4244-5108-1}}, keywords = {{WSN, PermaSense}}, pages = {{265--276}}, publisher = {{IEEE Computer Society}}, title = {{{PermaDAQ: A Scientific Instrument for Precision Sensing and Data Recovery in Environmental Extremes}}}, year = {{2009}}, } @inproceedings{2238, author = {{Schumacher, Tobias and Süß, Tim and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proc. Int. Conf. on ReConFigurable Computing and FPGAs (ReConFig)}}, isbn = {{978-0-7695-3917-1}}, keywords = {{IMORC, graphics}}, pages = {{119--124}}, publisher = {{IEEE Computer Society}}, title = {{{Communication Performance Characterization for Reconfigurable Accelerator Design on the XD1000}}}, doi = {{10.1109/ReConFig.2009.32}}, year = {{2009}}, } @inproceedings{2261, author = {{Schumacher, Tobias and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)}}, isbn = {{978-1-4244-3892-1}}, issn = {{1946-1488}}, keywords = {{IMORC, NOC, KNN, accelerator}}, pages = {{338--344}}, publisher = {{IEEE}}, title = {{{An Accelerator for k-th Nearest Neighbor Thinning Based on the IMORC Infrastructure}}}, year = {{2009}}, } @inproceedings{2263, abstract = {{In this paper, we introduce the Woolcano reconfigurable processor architecture. The architecture is based on the Xilinx Virtex-4 FX FPGA and leverages the Auxiliary Processing Unit (APU) as well as the partial reconfiguration capabilities to provide dynamically reconfigurable custom instructions. We also present a hardware tool flow that automatically translates software functions into custom instructions and a software tool flow that creates binaries using these instructions. While previous research on processors with reconfigurable functional units has been performed predominantly with simulation, the Woolcano architecture allows for exploring dynamic instruction set extension with commercially available hardware. Finally, we present a case study demonstrating a custom floating-point instruction generated with our approach, which achieves a 40x speedup over software-emulated floating-point operations and a 21% speedup over the Xilinx hardware floating-point unit. }}, author = {{Grad, Mariusz and Plessl, Christian}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-101-5}}, pages = {{319--322}}, publisher = {{CSREA Press}}, title = {{{Woolcano: An Architecture and Tool Flow for Dynamic Instruction Set Extension on Xilinx Virtex-4 FX}}}, year = {{2009}}, } @inproceedings{1974, author = {{Battré, Dominic and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Risks and Security of Internet and Systems}}, title = {{{Quality Assurance of Grid Service Provisioning by Risk Aware Managing of Resource Failures}}}, year = {{2008}}, } @inproceedings{1975, abstract = {{Service Level Agreements (SLAs) have focal importance if the commercial customer should be attracted to the Grid. An SLA-aware resource management system has already been realize, able to fulfill the SLA of jobs even in the case of resource failures. For this, it is able to migrate checkpointed jobs over the Grid. At this, virtual execution environments allow to increase the number of potential migration targets significantly. In this paper we outline the concept of such virtual execution environments and focus on the SLA negotiation aspects.}}, author = {{Battré, Dominic and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Voss, Kerstin}}, booktitle = {{Proc. Int. DMTF Academic Alliance Workshop on Systems and Virtualization Management: Standards and New Technologies}}, title = {{{Virtual Execution Environments and the Negotiation of Service Level Agreements in Grid Systems}}}, doi = {{10.1007/978-3-540-88708-9_1}}, year = {{2008}}, } @inproceedings{1976, abstract = {{Abstract: Commercial Grid users demand for contractually fixed QoS levels. Service Level Agreements (SLAs) are powerful instruments for describing such contracts. SLA-aware resource management is the foundation for realizing SLA contracts within the Grid. OpenCCS is such an SLA-aware RMS, using transparent checkpointing to cope with resource outages. It generates a compatibility profile for each checkpoint dataset, so that the job can be resumed even on resources within the Grid. However, only a small number of Grid resources comply to such a profile. This paper describes the concept of virtual execution environments and how they increase the number of potential migration targets.The paper also describes how these virtual execution environments have been implemented within the OpenCCS resource management system.}}, author = {{Battré, Dominic and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Voss, Kerstin}}, booktitle = {{Proc. Int. Workshop on Scheduling and Resource Management for Parallel and Distributed Systems}}, title = {{{Implementation of Virtual Execution Environments for improving SLA-compliant Job Migration in Grids}}}, doi = {{10.1109/ICPP-W.2008.40}}, year = {{2008}}, } @inproceedings{1978, author = {{Battré, Dominic and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Grid Computing and Applications (GCA)}}, title = {{{Germany, Belgium, France, and Back Again: Job Migration using Globus}}}, year = {{2008}}, } @inproceedings{1980, abstract = {{OpenCCS is an SLA-aware resource management system which uses transparent checkpointing of applications and migration of checkpoint datasets for ensuring SLA-compliance also in case of resource outages. Migration of checkpoints presumes a high grade of compatibility between source and target resource. Hence, even in large Grid systems only a small number of resources are eligible migration targets. This short paper describes the concept of virtual execution environments and how they increase the number of potential migration targets. It will also outline an implementation within OpenCCS.}}, author = {{Battré, Dominic and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Services Computing (SCC)}}, title = {{{Virtual Execution Environments for ensuring SLA-compliant Job Migration in Grids}}}, doi = {{10.1109/SCC.2008.106}}, year = {{2008}}, } @inproceedings{1981, abstract = {{Contractually fixed service quality levels are mandatory prerequisites for attracting the commercial user to Grid environments. Service Level Agreements (SLAs) are powerful instruments for describing obligations and expectations in such a business relationship. At the level of local resource management systems, checkpointing and restart is an important instrument for realizing fault tolerance and SLA awareness. This paper highlights the concepts of migrating such checkpoint datasets to achieve the goal of SLA compliant job execution.}}, author = {{Battré, Dominic and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Grid and Pervasive Computing (GPC)}}, isbn = {{978-0-7695-3177-9}}, pages = {{43--48}}, title = {{{Job Migration and Fault Tolerance in SLA-aware Resource Management Systems}}}, doi = {{10.1109/GPC.WORKSHOPS.2008.71}}, year = {{2008}}, } @inproceedings{1983, author = {{Battré, Dominic and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Parallel and Distributed Computing and Systems (PDCS)}}, editor = {{Gonzalez, T. F.}}, isbn = {{978-0-88986-773-4}}, pages = {{212--218}}, title = {{{Enhancing SLA Provisioning by Utilizing Profit-Oriented Fault Tolerance}}}, year = {{2008}}, } @inproceedings{2355, author = {{Brinkmann, André and Effert, Sascha}}, booktitle = {{Proc. Int. Conf. on Principles Of DIstributed Systems (OPODIS)}}, pages = {{551--554}}, publisher = {{Springer}}, title = {{{Redundant Data Placement Strategies for Cluster Storage Environments}}}, doi = {{10.1007/978-3-540-92221-6_38}}, year = {{2008}}, } @inproceedings{2356, author = {{Brinkmann, André and Gudenkauf, Stefan and Hasselbring, Wilhelm and Höing, André and Karl, Holger and Kao, Odej and Nitsche, Holger and Scherp, Guido}}, booktitle = {{Proc. Cracow Grid Workshop (CGW)}}, pages = {{103--110}}, title = {{{Employing WS-BPEL Design Patterns for Grid Service Orchestration using a Standard WS-BPEL Engine and a Grid Middleware}}}, year = {{2008}}, } @inproceedings{2357, author = {{Birkenheuer, Georg and Brinkmann, André and Dömer, Hubert and Effert, Sascha and Konersmann, Christoph and Niehörster, Oliver and Simon, Jens}}, booktitle = {{Proc. Gemeinsamer Workshop der GI/ITG Fachgruppen "Betriebssysteme" und "KuVS": Virtualized IT infrastructures and their management}}, pages = {{37--49}}, publisher = {{Leibniz-Rechenzentrum}}, title = {{{Virtual Supercomputer for HPC and HTC}}}, year = {{2008}}, } @inproceedings{2358, author = {{Beisel, Tobias and Lietsch, Stefan and Thielemans, Kris}}, booktitle = {{IEEE Nuclear Science Symposium Conference Record (NSS)}}, pages = {{4161--4168}}, publisher = {{IEEE}}, title = {{{A method for OSEM PET reconstruction on parallel architectures using STIR}}}, doi = {{10.1109/NSSMIC.2008.4774198}}, year = {{2008}}, } @inproceedings{2359, author = {{Battré, Dominic and Birkenheuer, Georg and Deora, Vikas and Hovestadt, Matthias and Rana, Omer and Wäldrich, Oliver}}, booktitle = {{Proc. Cracow Grid Workshop (CGW)}}, pages = {{213--220}}, title = {{{Guarantee and Penalty Clauses for Service Level Agreements}}}, year = {{2008}}, } @inproceedings{2360, author = {{Richert, Willi and Niehörster, Oliver and Koch, Markus}}, booktitle = {{Proc. IEEE/RSJ Int.Conf. on Intelligent Robots and Systems (IROS)}}, publisher = {{IEEE}}, title = {{{Layered understanding for sporadic imitation in a multi-robot scenario}}}, doi = {{10.1109/IROS.2008.4650817}}, year = {{2008}}, } @inproceedings{2363, author = {{Lietsch, Stefan and Zabel, Henning and Laroque, Christoph}}, booktitle = {{Proc. ASME Computers and Information in Engineering Conference (CIE)}}, pages = {{1493--1502}}, publisher = {{ASME}}, title = {{{Computational Steering Of Interactive Material Flow Simulations}}}, doi = {{10.1115/DETC2008-49405}}, year = {{2008}}, } @inproceedings{2365, author = {{Platzner, Marco and Döhre, Sven and Happe, Markus and Kenter, Tobias and Lorenz, Ulf and Schumacher, Tobias and Send, Andre and Warkentin, Alexander}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-064-7}}, pages = {{245--251}}, publisher = {{CSREA Press}}, title = {{{The GOmputer: Accelerating GO with FPGAs}}}, year = {{2008}}, } @inproceedings{2368, author = {{Lietsch, Stefan and Hermann Lensing, Paul}}, booktitle = {{Proc. Int. Symp. on Image/Video Communications over fixed and mobile networks (ISVC)}}, isbn = {{978-84-9830-164-9}}, publisher = {{IEEE}}, title = {{{CUDA-based, parallel JPEG Compression for Remote Rendering}}}, year = {{2008}}, } @inproceedings{2369, author = {{Birkenheuer, Georg and Hovestadt, Matthias and Kao, Odej and Voß, Kerstin}}, booktitle = {{Proc. Int. Conf. on Grid Computing & Applications (GCA)}}, pages = {{242--248}}, publisher = {{CSREA Press}}, title = {{{Overbooking in Planning Based Scheduling Systems}}}, year = {{2008}}, } @inproceedings{2371, author = {{Brinkmann, André and Effert, Sascha}}, booktitle = {{Proc. Int. Symp. on Parallelism in Algorithms and Architectures (SPAA)}}, pages = {{191--193}}, publisher = {{ACM}}, title = {{{Data Replication in P2P Environments}}}, doi = {{10.1145/1378533.1378570}}, year = {{2008}}, } @inproceedings{2374, author = {{Griese, Björn and Brinkmann, André and Porrmann, Mario}}, booktitle = {{Proc. Int. Symp. on Parallel and Distributed Processing (IPDPS)}}, pages = {{1--8}}, publisher = {{IEEE}}, title = {{{SelfS – A Real-Time Protocol for Virtual Ring Topologies}}}, doi = {{10.1109/IPDPS.2008.4536571}}, year = {{2008}}, } @inproceedings{2375, author = {{Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Networking and Services (ICNS)}}, pages = {{223--229}}, publisher = {{IEEE}}, title = {{{Recursive Evaluation of Fault Tolerance Mechanisms for SLA Management}}}, doi = {{10.1109/ICNS.2008.22}}, year = {{2008}}, } @inproceedings{2380, author = {{Brinkmann, André and Effert, Sascha}}, booktitle = {{Proc. of the GI/ITG KuVS Fachgespr ̈ach Virtualisierung}}, pages = {{107--115}}, title = {{{Storage Cluster Architectures}}}, year = {{2008}}, } @inproceedings{2382, author = {{Richert, Willi and Klompmaker, Florian and Niehörster, Oliver}}, booktitle = {{Proc. IFIP Conf. on Biologically Inspired Cooperative Computing (BICC)}}, pages = {{233--244}}, publisher = {{Springer}}, title = {{{Guiding exploration by combining individual learning and imitation in societies of autonomous robots}}}, doi = {{10.1007/978-0-387-09655-1_21}}, year = {{2008}}, } @inproceedings{2383, author = {{Lietsch, Stefan and Hermann Lensing, Paul}}, booktitle = {{Proc. Int. Symp. on Visual Computing (ISVC)}}, pages = {{658--668}}, publisher = {{Springer}}, title = {{{GPU-Supported Image Compression for Remote Visualization - Realization and Benchmarking}}}, doi = {{10.1007/978-3-540-89639-5_63}}, volume = {{5358}}, year = {{2008}}, } @inproceedings{2386, author = {{Bienkowski, Marcin and Brinkmann, André and Korzeniowski, Miroslaw}}, booktitle = {{Proc. Int. Conf. on Principles Of DIstributed Systems (OPODIS)}}, pages = {{184--196}}, publisher = {{Springer}}, title = {{{Degree 3 Suffices: A Large-Scale Overlay for P2P Networks}}}, doi = {{10.1007/978-3-540-92221-6_13}}, year = {{2008}}, } @inproceedings{2387, author = {{Battre, Dominic and Birkenheuer, Georg and Hovestadt, Matthias and Kao, Odej and Voss, Kerstin}}, booktitle = {{Proc. Cracow Grid Workshop (CGW)}}, title = {{{Applying Risk Management to Support SLA Provisioning}}}, year = {{2008}}, } @inproceedings{2388, author = {{Battré, Dominic and Kao, Odej and Voss, Kerstin}}, booktitle = {{Proc. Usage of Service Level Agreements in Grids Workshop held in conjunction with International Conference on Grid Computing}}, pages = {{409--418}}, publisher = {{Springer}}, title = {{{Implementing WS-Agreement in a Globus Toolkit 4.0 Environment}}}, doi = {{10.1007/978-0-387-78446-5_28}}, year = {{2008}}, } @inproceedings{2370, author = {{Woehrle, Matthias and Plessl, Christian and Lim, Roman and Beutel, Jan and Thiele, Lothar}}, booktitle = {{IEEE Int. Conf. on Sensor Networks, Ubiquitous, and Trustworthy Computing (SUTC)}}, isbn = {{978-0-7695-3158-8}}, keywords = {{WSN, testing, verification}}, pages = {{201--208}}, publisher = {{IEEE Computer Society}}, title = {{{EvAnT: Analysis and Checking of event traces for Wireless Sensor Networks}}}, doi = {{10.1109/SUTC.2008.24}}, year = {{2008}}, } @inproceedings{2364, author = {{Schumacher, Tobias and Meiche, Robert and Kaufmann, Paul and Lübbers, Enno and Plessl, Christian and Platzner, Marco}}, booktitle = {{Proc. Int. Conf. on Engineering of Reconfigurable Systems and Algorithms (ERSA)}}, isbn = {{1-60132-064-7}}, pages = {{245--251}}, publisher = {{CSREA Press}}, title = {{{A Hardware Accelerator for k-th Nearest Neighbor Thinning}}}, year = {{2008}}, } @inproceedings{2372, author = {{Schumacher, Tobias and Plessl, Christian and Platzner, Marco}}, booktitle = {{Many-core and Reconfigurable Supercomputing Conference (MRSC)}}, keywords = {{IMORC, IP core, interconnect}}, title = {{{IMORC: An infrastructure for performance monitoring and optimization of reconfigurable computers}}}, year = {{2008}}, } @inproceedings{1986, abstract = {{Service level agreements (SLAs) are powerful instruments for describing all obligations and expectations in a business relationship. It is of focal importance for deploying Grid technology to commercial applications. The EC-funded project HPC4U (Highly Predictable Clusters for Internet Grids) aimed at introducing SLA-awareness in local resource management systems, while the EC-funded project AssessGrid introduced the notion of risk, which is associated with every business contract. This paper highlights the concept of planning based resource management and describes the SLA-aware scheduler developed and used in these projects.}}, author = {{Battré, Dominic and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Voss, Kerstin}}, booktitle = {{Proc. Workshop of the UK PLANNING AND SCHEDULING Special Interest Group (PlanSIG)}}, title = {{{Planning-based Scheduling for SLA-awareness and Grid Integration}}}, year = {{2007}}, } @inproceedings{1988, author = {{Battré, Dominic and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Voss, Kerstin}}, booktitle = {{Proc. Cracow Grid Workshop, Academic Computer Center CYFRNET}}, pages = {{334--341}}, title = {{{Transparent Cross Border Migration of Parallel Multi Node Applications}}}, year = {{2007}}, } @inproceedings{2389, author = {{Lietsch, Stefan and Marquardt, Oliver}}, booktitle = {{Proc. Int. Symp. on Visual Computing (ISVC)}}, isbn = {{978-3-540-76857-9}}, pages = {{724--733}}, publisher = {{Springer}}, title = {{{A CUDA-Supported Approach to Remote Rendering}}}, volume = {{4841}}, year = {{2007}}, } @inproceedings{2390, author = {{Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Semantics, Knowledge and Grid (SKG)}}, isbn = {{0-7695-3007-9}}, pages = {{50--55}}, publisher = {{IEEE Computer Society}}, title = {{{Comparing Fault Tolerance Mechanisms for Self-Organizing Resource Management in Grids}}}, doi = {{10.1109/SKG.2007.40}}, year = {{2007}}, } @inproceedings{2391, author = {{Battré, Dominic and Djemame, Karim and Kao, Odej and Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Security and Privacy in Communications Networks (SecureComm)}}, pages = {{193--198}}, publisher = {{IEEE}}, title = {{{Gaining Users' Trust by Publishing Failure Probabilities}}}, doi = {{10.1109/SECCOM.2007.4550331}}, year = {{2007}}, } @inproceedings{2396, author = {{Voss, Kerstin and Djemame, Karim and Gourlay, Iain and Padgett, James}}, booktitle = {{Proc. Int. Worksh. on Grid Economics and Business Models (GECON)}}, editor = {{Altmann, Jörn and Veit, Daniel}}, pages = {{170--175}}, publisher = {{Springer}}, title = {{{AssessGrid, Economic Issues Underlying Risk Awareness in Grids}}}, doi = {{10.1007/978-3-540-74430-6_14}}, volume = {{4685}}, year = {{2007}}, } @inproceedings{2397, author = {{Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Networking and Services (ICNS)}}, isbn = {{0-7695-2858-9}}, pages = {{27--32}}, publisher = {{IEEE Computer Society}}, title = {{{Enhance Self-managing Grids by Risk Management}}}, doi = {{10.1109/ICNS.2007.61}}, year = {{2007}}, } @inproceedings{2398, author = {{Lietsch, Stefan and Zabel, Henning and Berssenbruegge, Jan}}, booktitle = {{Proc. ASME Computers and Information in Engineering Conference (CIE)}}, isbn = {{0-7918-3806-4}}, publisher = {{ASME}}, title = {{{Computational Steering of Interactive and Distributed Virtual Reality Applications}}}, year = {{2007}}, } @inproceedings{2399, author = {{Birkenheuer, Georg and Majlender, Peter and Nitsche, Holger and Voss, Kerstin and Weber, Elmar}}, booktitle = {{Proc. Cracow Grid Workshop (CGW)}}, title = {{{Gather and Prepare Monitoring Data for Estimating Resource Stability}}}, year = {{2007}}, } @inproceedings{2400, author = {{Berssenbrügge, Jan and Lietsch, Stefan}}, booktitle = {{Proc. Worksh. Augmented & Virtual Reality in der Produktentstehung}}, isbn = {{978-3-939350-28-6}}, pages = {{67--80}}, publisher = {{Heinz Nixdorf Institut}}, title = {{{Verteilte Berechnung und Darstellung automobiler Scheinwerfer}}}, volume = {{209}}, year = {{2007}}, } @inproceedings{2392, author = {{Woehrle, Matthias and Plessl, Christian and Beutel, Jan and Thiele, Lothar}}, booktitle = {{Proc. Workshop on Embedded Networked Sensors (EmNets)}}, isbn = {{978-1-59593-694-3}}, keywords = {{WSN, testing, distributed, embedded}}, pages = {{93--97}}, publisher = {{ACM}}, title = {{{Increasing the Reliability of Wireless Sensor Networks with a Distributed Testing Framework}}}, doi = {{10.1145/1278972.1278996}}, year = {{2007}}, } @inproceedings{2393, author = {{Beutel, Jan and Dyer, Matthias and Lim, Roman and Plessl, Christian and Woehrle, Matthias and Yuecel, Mustafa and Thiele, Lothar}}, booktitle = {{Proc. Int. Conf. Networked Sensing Systems (INSS)}}, isbn = {{1-4244-1231-5}}, keywords = {{WSN, testing, verification}}, pages = {{303--303}}, publisher = {{IEEE}}, title = {{{Automated Wireless Sensor Network Testing}}}, doi = {{10.1109/INSS.2007.4297445}}, year = {{2007}}, } @inproceedings{2402, author = {{Djemame, Karim and Gourlay, Iain and Padgett, James and Birkenheuer, Georg and Hovestadt, Matthias and Kao, Odej and Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on e-Science and Grid Computing}}, isbn = {{0-7695-2734-5}}, pages = {{28}}, publisher = {{IEEE Computer Society}}, title = {{{Introducing Risk Management into the Grid}}}, doi = {{10.1109/E-SCIENCE.2006.261112}}, year = {{2006}}, } @inproceedings{2403, author = {{Hovestadt, Matthias and Kao, Odej and Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Services Computing (SCC)}}, isbn = {{0-7695-2670-5}}, pages = {{36--43}}, publisher = {{IEEE Computer Society}}, title = {{{The First Step of Introducing Risk Management for Prepossessing SLAs}}}, doi = {{10.1109/SCC.2006.102}}, year = {{2006}}, } @inproceedings{2406, author = {{Voss, Kerstin}}, booktitle = {{Proc. Int. Conf. on Networking and Services (ICNS)}}, isbn = {{0-7695-2622-5}}, pages = {{68}}, publisher = {{IEEE Computer Society}}, title = {{{Risk Aware Migrations for Prepossessing SLAs}}}, doi = {{10.1109/ICNS.2006.94}}, year = {{2006}}, } @inproceedings{2407, author = {{Lietsch, Stefan and Zabel, Henning and Berssenbruegge, Jan and Wittenberg, Veit and Eikermann, Martin}}, booktitle = {{Proc. Int. Symp. on Visual Computing (ISVC)}}, isbn = {{3-540-48628-3}}, pages = {{343--353}}, publisher = {{Springer}}, title = {{{Light Simulation in a Distributed Driving Simulator}}}, doi = {{10.1007/11919476_35}}, volume = {{4291}}, year = {{2006}}, } @inproceedings{2408, author = {{Lerch, Nicolas and Nitsche, Holger and Voss, Kerstin and Hovestadt, Matthias}}, booktitle = {{Proc. Cracow Grid Workshop (CGW)}}, pages = {{216--223}}, title = {{{First Steps of a Monitoring Framework to Empower Risk Assessment on Grids}}}, year = {{2006}}, } @inproceedings{2409, author = {{Birkenheuer, Georg and Döhre, Sven and Hovestadt, Matthias and Kao, Odej and Voss, Kerstin}}, booktitle = {{Proc. Cracow Grid Workshop (CGW)}}, title = {{{On Similarities of Grid Resources for Identifying Potential Migration Targets}}}, year = {{2006}}, } @inproceedings{2410, author = {{Birkenheuer, Georg and Djemame, Karim and Gourlay, Iain and Kao, Odej and Padgett, James and Voß, Kerstin}}, booktitle = {{Proc. WS-Agreement Workshop (Open Grid Forum 18)}}, title = {{{Using WS-Agreement for Risk Management in the Grid}}}, year = {{2006}}, } @inproceedings{1992, abstract = {{The next generation grid applications demand grid middleware for a flexible negotiation mechanism supporting various ways of quality-of-service (QoS) guarantees. In this context, a QoS guarantee covers simultaneous allocations of various kinds of different resources, such as processor runtime, storage capacity, or network bandwidth, which are specified in the form of service level agreements (SLA). Currently, a gap exists between the capabilities of grid middleware and the underlying resource management systems concerning their support for QoS and SLA negotiation. In this paper we present an approach which closes this gap. Introducing the architecture of the virtual resource manager, we highlight its main QoS management features like run-time responsibility, co-allocation, and fault tolerance.}}, author = {{Burchard, Lars-Olof and Heine, Felix and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Linnert, Barry}}, booktitle = {{Proc. IEEE Int. Parallel & Distributed Processing Symposium (IPDPS)}}, pages = {{132a--132a}}, title = {{{A Quality-of-Service Architecture for Future Grid Computing Applications.}}}, doi = {{10.1109/IPDPS.2005.62}}, year = {{2005}}, } @inproceedings{2413, author = {{Lietsch, Stefan and Kao, Odej}}, booktitle = {{Proc. Intelligence in Communication Systems (INTELLCOMM)}}, pages = {{261--271}}, publisher = {{Springer}}, title = {{{CoLoS - A System for Device Unaware and Position Dependent Communication Based on the Session Initiation Protocol}}}, doi = {{10.1007/0-387-32015-6_24}}, volume = {{190}}, year = {{2005}}, } @inproceedings{2414, author = {{Birkenheuer, Georg and Hagelweide, Wilke and Hagemeier, Björn and Japs, Viktor and Keller, Matthias and Mayr, Nikolas and Meyer, Jan and Schumacher, Tobias and Voß, Kerstin and Zajac, Markus}}, booktitle = {{Proc. GI Informatiktage}}, pages = {{91--94}}, publisher = {{Gesellschaft für Informatik (GI)}}, title = {{{PIRANHA – Hunter of Idle Resources}}}, volume = {{2}}, year = {{2005}}, } @inproceedings{1993, author = {{Kao, Odej and Hovestadt, Matthias and Keller, Axel}}, booktitle = {{Proc. Advanced Research Workshop on High Perfomance Computing: Technology and Applications}}, title = {{{SLA-aware Job Migration in Grid Environments}}}, year = {{2004}}, } @inproceedings{1994, author = {{Burchard, Lars-Olof and Heiss, Hans-Ulrich and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Linnert, Barry}}, booktitle = {{Proceedings of the GI-Meeting on Operating Systems}}, title = {{{An Architecture for SLA-aware Resource Management}}}, year = {{2004}}, } @inproceedings{1995, abstract = {{The next generation Grid will demand the Grid middleware to provide flexibility, transparency, and reliability. This implies the appliance of service level agreements to guarantee a negotiated level of quality of service. These requirements also affect the local resource management systems providing resources for the Grid. At this a gap between these demands and the features of today's resource management systems becomes apparent. In this paper we present an approach which closes this gap. Introducing the architecture of the virtual resource manager we highlight its main features of runtime responsibility, resource virtualization, information hiding, autonomy provision, and smooth integration of existing resource management system installations.}}, author = {{Burchard, Lars-Olof and Hovestadt, Matthias and Kao, Odej and Keller, Axel and Linnert, Barry}}, booktitle = {{Proc. Int. Symposium on Cluster Computing and the Grid (CCGRID)}}, title = {{{Virtual Resource Manager: An Architecture for SLA-aware Resource Management}}}, doi = {{10.1109/CCGrid.2004.1336558}}, year = {{2004}}, } @inproceedings{2416, author = {{Groppe, Sven and Böttcher, Stefan and Birkenheuer, Georg}}, booktitle = {{Proc. Int. Conf. on Enterprise Information Systems (ICEIS)}}, pages = {{241--250}}, title = {{{Efficient Querying of Transformed XML Documents}}}, year = {{2004}}, } @inproceedings{2417, author = {{Groppe, Sven and Böttcher, Stefan and Heckel, Reiko and Birkenheuer, Georg}}, booktitle = {{Proc. East-European Conf. on Advances in Databases and Information Systems (ADBIS)}}, title = {{{Using XSLT Stylesheets to Transform XPath Queries}}}, year = {{2004}}, } @inproceedings{1998, abstract = {{Nearly all existing HPC systems are operated by resource management systems based on the queuing approach. With the increasing acceptance of grid middleware like Globus, new requirements for the underlying local resource management systems arise. Features like advanced reservation or quality of service are needed to implement high level functions like co-allocation. However it is difficult to realize these features with a resource management system based on the queuing concept since it considers only the present resource usage. In this paper we present an approach which closes this gap. By assigning start times to each resource request, a complete schedule is planned. Advanced reservations are now easily possible. Based on this planning approach functions like diffuse requests, automatic duration extension, or service level agreements are described. We think they are useful to increase the usability, acceptance and performance of HPC machines. In the second part of this paper we present a planning based resource management system which already covers some of the mentioned features.}}, author = {{Hovestadt, Matthias and Kao, Odej and Keller, Axel and Streit, Achim}}, booktitle = {{Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP)}}, keywords = {{High Performance Computing, Service Level Agreement, Grid Resource, Resource Management System, Advance Reservation}}, pages = {{1--20}}, title = {{{Scheduling in HPC Resource Management Systems: Queuing vs. Planning}}}, doi = {{10.1007/10968987_1}}, volume = {{2862}}, year = {{2003}}, } @inproceedings{2426, author = {{P. Miller, Barton and Labarta, Jesús and Schintke, Florian and Simon, Jens}}, booktitle = {{Proc. European Conf. on Parallel Processing (Euro-Par)}}, isbn = {{978-3-540-45706-0}}, pages = {{131}}, publisher = {{Springer}}, title = {{{Performance Evaluation, Analysis and Optimization}}}, doi = {{10.1007/3-540-45706-2_15}}, volume = {{2400}}, year = {{2002}}, } @inproceedings{2000, abstract = {{The Testbed and Applications working group of the European Grid Forum (EGrid) is actively building and experimenting with a grid infrastructure connecting several research-based supercomputing sites located in Europe. The paper reports on our first feasibility study: running a self-migrating version of the Cactus simulation code across the European grid testbed, including "live" remote data visualization and steering from different demonstration booths at Supercomputing 2000, in Dallas, TX. We report on the problems that had to be resolved for this endeavour and identify open research challenges for building production-grade grid environments.}}, author = {{Gehring, Jörn and Keller, Axel and Reinefeld, Alexander and Streit, Achim}}, booktitle = {{Proc. Int. Symposium on Cluster Computing and the Grid (CCGRID)}}, pages = {{130--137}}, title = {{{Early Experiences with the EGrid Testbed}}}, doi = {{10.1109/CCGRID.2001.923185}}, year = {{2001}}, } @inproceedings{2002, abstract = {{The availability of commodity high performance components for workstations and networks made it possible to build up large, PC based compute clusters at modest costs. These clusters seem to be a realistic alternative to proprietary, massively parallel systems with respect to the price/performance ratio. However, from the administration point of view, those systems are still often solely a collection of autonomous nodes, connected by a fast short area network. Therefore, aiming at providing the best possible performance in daily work to all users, a lot of work has to be done before obtaining the expected result. The paper describes the problem areas we had to cope with during the integration of two large SCI clusters (one with 64 and one with 192 processors) in the environment of the Paderborn Center for Parallel Computing.}}, author = {{Keller, Axel and Krawinkel, Andreas}}, booktitle = {{Proc. Int. Symposium on Cluster Computing and the Grid (CCGRID)}}, pages = {{303--310}}, title = {{{Lessons Learned While Operating Two Large SCI Clusters}}}, doi = {{10.1109/CCGRID.2001.923207}}, year = {{2001}}, } @inproceedings{2431, author = {{Schintke, Florian and Simon, Jens and Reinefeld, Alexander}}, booktitle = {{Proc. Int. Conf. on Computational Science (ICCS)}}, pages = {{569--578}}, publisher = {{Springer}}, title = {{{A Cache Simulator for Shared Memory Systems}}}, doi = {{10.1007/3-540-45718-6_62}}, volume = {{2074}}, year = {{2001}}, } @inproceedings{2003, abstract = {{RsdEditor is a graphical user interface which produces specifications of computational resources. It is used in the RSD (Resource and Service Description) environment for specifying, registering, requesting and accessing resources and services in a metacomputer. RsdEditor was designed to be used by the administrators and users of metacomputing environments. At the administrator level, the GUI is used to describe the available computing and networking components of a metacomputer. At the user level, RsdEditor can be used to specify which characteristics of the computational resources are needed to execute a meta-application. This paper is organized as follows: it first introduces RsdEditor. It then briefly describes the RSD environment, and finally, it highlights various features and implementation issues of RsdEditor.}}, author = {{Baraglia, Ranieri and Keller, Axel and Laforenza, Domenico and Reinefeld, Alexander}}, booktitle = {{Proc. Heterogenous Computing Workshop HCW at IPDPS}}, pages = {{336--348}}, title = {{{RsdEditor: A Graphical User Interface for Specifying Metacomputer Components}}}, doi = {{10.1109/HCW.2000.843756}}, year = {{2000}}, } @inproceedings{2004, abstract = {{With the recent availability of cost-effective network cards for the PCI bus, researchers have been tempted to build up large compute clusters with standard PCs. Many of them are operated with workstation cluster management software in high-throughput or single user mode. For very large clusters with more than 100 PEs, however, it becomes necessary to implement a full fledged resource management software that allows to partition the system for multi-user access. In this paper, we present our Computing Center Software (CCS), which was originally designed for managing massively parallel high-performance computers, and now adapted to modern workstation clusters. It provides - partitioning of exclusive and non-exclusive resources, - hardware-independent scheduling of interactive and batch jobs, - open, extensible interfaces to other resource management systems, - a high degree of reliability.}}, author = {{Brune, Matthias and Keller, Axel and Reinefeld, Alexander}}, booktitle = {{Proc. Int. Conf. on High-Performance Computing and Networking (HPCN)}}, pages = {{270--280}}, title = {{{Resource Management for High-Performance PC Clusters}}}, doi = {{10.1007/BFb0100588}}, year = {{1999}}, } @inproceedings{2436, author = {{Brune, Matthias and Reinefeld, Alexander and Varnholt, Jörg}}, booktitle = {{Proc. Int. Symp. High-Performance Distributed Computing (HPDC)}}, publisher = {{IEEE Computer Society}}, title = {{{A Resource Description Environment for Distributed Computing Systems}}}, year = {{1999}}, } @inproceedings{2009, abstract = {{RSD (Resource and Service Description) is a scheme for specifying resources and services in complex heterogeneous computing systems and metacomputing environments. At the system administrator level, RSD is used to specify the available system components, such as the number of nodes, their interconnection topology, CPU speeds, and available software packages. At the user level, a GUI provides a comfortable, high-level interface for specifying system requests. A textual editor can be used for defining repetitive and recursive structures. This gives service providers the necessary flexibility for fine-grained specification of system topologies, interconnection networks, system and software dependent properties. All these representations are mapped onto a single, coherent internal object-oriented resource representation. Dynamic aspects (like network performance, availability of compute nodes, and compute node loads) are traced at runtime and included in the resource description to allow for optimal process mapping and dynamic task load balancing at runtime at the metacomputer level. This is done in a self-organizing way, with human system operators becoming only involved when new hardware/software components are installed.}}, author = {{Brune, Matthias and Gehring, Jörn and Keller, Axel and Reinefeld, Alexander}}, booktitle = {{Proc. Int. Conf. on High-Performance Computing Systems (HPCS)}}, title = {{{RSD - Resource and Service Description}}}, doi = {{10.1007/978-1-4615-5611-4_18}}, year = {{1998}}, } @inproceedings{2011, abstract = {{CCS is a resource management system for parallel high-performance computers. At the user level, CCS provides vendor-independent access to parallel systems. At the system administrator level, CCS offers tools for controlling (i.e, specifying, configuring and scheduling) the system components that are operated in a computing center. Hence the name "Computing Center Software". CCS provides: hardware-independent scheduling of interactive and batch jobs; partitioning of exclusive and non-exclusive resources; open, extensible interfaces to other resource management systems; a high degree of reliability (e.g. automatic restart of crashed daemons); fault tolerance in the case of network breakdowns. The authors describe CCS as one important component for the access, job distribution, and administration of networked HPC systems in a metacomputing environment.}}, author = {{Keller, Axel and Reinefeld, Alexander}}, booktitle = {{Proc. Heterogenous Computing Workshop (HCW) at IPPS}}, pages = {{44--56}}, title = {{{CCS Resource Management in Networked HPC Systems}}}, doi = {{10.1109/HCW.1998.666544}}, year = {{1998}}, } @inproceedings{2013, author = {{Brune, Matthias and Hellmann, Christian and Keller, Axel}}, booktitle = {{Proc. Workshop Hypercomputing at ITG/GI-Conference Architekur von Rechensystemen}}, title = {{{A Closer Step towards Management of Metacomputing-Resources}}}, year = {{1997}}, } @inproceedings{2438, author = {{Simon, Jens and Weicker, Reinhold and Vieth, Marco}}, booktitle = {{Proc. European Conf. on Parallel Processing (Euro-Par)}}, isbn = {{978-3-540-69549-3}}, pages = {{971--984}}, publisher = {{Springer}}, title = {{{Workload Analysis of Computation Intensive Tasks: Case Study on SPEC CPU95 Benchmarks}}}, doi = {{10.1007/BFb0002841}}, volume = {{1300}}, year = {{1997}}, } @inproceedings{2439, author = {{Heinz, Oliver and Simon, Jens}}, booktitle = {{Proc. Int. Conf. on Architecture of Computing Systems (ARCS)}}, publisher = {{VDE Verlag}}, title = {{{Experiences with a SCI Multiprocessor Workstation Cluster}}}, year = {{1997}}, } @inproceedings{2440, author = {{Simon, Jens and Heinz, Oliver}}, booktitle = {{Proc. Workshops im Rahmen der 14. ITG/GI-Fachtagung Architektur von Rechensystemen}}, pages = {{189--199}}, title = {{{SCI multiprocessor PC cluster in a WindowsNT environment}}}, year = {{1997}}, } @inproceedings{2441, author = {{Fischer, Markus and Simon, Jens}}, booktitle = {{Proc. European Parallel Virtual Machine / Message Passing Interface Users’ Group Meeting (EuroPVM/MPI)}}, pages = {{175--184}}, publisher = {{Springer}}, title = {{{Embedding SCI into PVM}}}, doi = {{10.1007/3-540-63697-8_84}}, volume = {{1332}}, year = {{1997}}, } @inproceedings{2442, author = {{Reinefeld, Alexander and Baraglia, Ranieri and Decker, Thomas and Gehring, Jörn and Laforenza, Domenico and Ramme, Friedhelm and Römke, Thomas and Simon, Jens}}, booktitle = {{Proc. Heterogenous Computing Workshop (HCW)}}, pages = {{17--31}}, publisher = {{IEEE Computer Society}}, title = {{{The MOL Project: An Open, Extensible Metacomputer}}}, doi = {{10.1109/HCW.1997.581407}}, year = {{1997}}, } @inproceedings{2443, author = {{Simon, Jens and Wierum, Jens-Michael}}, booktitle = {{Proc. Int. Conf. on High-Performance Computing and Networking (HPCN-Europe)}}, isbn = {{978-3-540-61142-4}}, pages = {{627--632}}, publisher = {{Springer}}, title = {{{Sequential Performance versus Scalability: Optimizing Parallel LU-Decomposition}}}, doi = {{10.1007/3-540-61142-8_606}}, volume = {{1067}}, year = {{1996}}, } @inproceedings{2444, author = {{Simon, Jens and Wierum, Jens-Michael}}, booktitle = {{Proc. Annual Int. Conf. on High-Performance Computers (HPCS)}}, title = {{{Performance Prediction of Benchmark Programs for Massively Parallel Architectures}}}, year = {{1996}}, } @inproceedings{2445, author = {{Simon, Jens and Wierum, Jens-Michael}}, booktitle = {{Proc. European Conf. on Parallel Processing (Euro-Par)}}, pages = {{675--688}}, publisher = {{Springer}}, title = {{{Accurate Performance Prediction for Massively Parallel Systems and its Applications}}}, doi = {{10.1007/BFb0024764}}, volume = {{1124}}, year = {{1996}}, }