--- _id: '46195' author: - first_name: Martin full_name: Karp, Martin last_name: Karp - first_name: Artur full_name: Podobas, Artur last_name: Podobas - first_name: Niclas full_name: Jansson, Niclas last_name: Jansson - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: Philipp full_name: Schlatter, Philipp last_name: Schlatter - first_name: Stefano full_name: Markidis, Stefano last_name: Markidis citation: ama: 'Karp M, Podobas A, Jansson N, et al. High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE; 2021. doi:10.1109/ipdps49936.2021.00116' apa: 'Karp, M., Podobas, A., Jansson, N., Kenter, T., Plessl, C., Schlatter, P., & Markidis, S. (2021). High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection. 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). https://doi.org/10.1109/ipdps49936.2021.00116' bibtex: '@inproceedings{Karp_Podobas_Jansson_Kenter_Plessl_Schlatter_Markidis_2021, title={High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection}, DOI={10.1109/ipdps49936.2021.00116}, booktitle={2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)}, publisher={IEEE}, author={Karp, Martin and Podobas, Artur and Jansson, Niclas and Kenter, Tobias and Plessl, Christian and Schlatter, Philipp and Markidis, Stefano}, year={2021} }' chicago: 'Karp, Martin, Artur Podobas, Niclas Jansson, Tobias Kenter, Christian Plessl, Philipp Schlatter, and Stefano Markidis. “High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection.” In 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 2021. https://doi.org/10.1109/ipdps49936.2021.00116.' ieee: 'M. Karp et al., “High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection,” 2021, doi: 10.1109/ipdps49936.2021.00116.' mla: 'Karp, Martin, et al. “High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection.” 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), IEEE, 2021, doi:10.1109/ipdps49936.2021.00116.' short: 'M. Karp, A. Podobas, N. Jansson, T. Kenter, C. Plessl, P. Schlatter, S. Markidis, in: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), IEEE, 2021.' date_created: 2023-07-28T12:04:27Z date_updated: 2023-07-28T12:05:15Z department: - _id: '27' - _id: '518' doi: 10.1109/ipdps49936.2021.00116 language: - iso: eng publication: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS) publication_status: published publisher: IEEE quality_controlled: '1' status: public title: 'High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection' type: conference user_id: '3145' year: '2021' ... --- _id: '29937' author: - first_name: Martin full_name: Karp, Martin last_name: Karp - first_name: Artur full_name: Podobas, Artur last_name: Podobas - first_name: Niclas full_name: Jansson, Niclas last_name: Jansson - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: Philipp full_name: Schlatter, Philipp last_name: Schlatter - first_name: Stefano full_name: Markidis, Stefano last_name: Markidis citation: ama: 'Karp M, Podobas A, Jansson N, et al. High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE; 2021. doi:10.1109/ipdps49936.2021.00116' apa: 'Karp, M., Podobas, A., Jansson, N., Kenter, T., Plessl, C., Schlatter, P., & Markidis, S. (2021). High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection. 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). https://doi.org/10.1109/ipdps49936.2021.00116' bibtex: '@inproceedings{Karp_Podobas_Jansson_Kenter_Plessl_Schlatter_Markidis_2021, title={High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection}, DOI={10.1109/ipdps49936.2021.00116}, booktitle={2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)}, publisher={IEEE}, author={Karp, Martin and Podobas, Artur and Jansson, Niclas and Kenter, Tobias and Plessl, Christian and Schlatter, Philipp and Markidis, Stefano}, year={2021} }' chicago: 'Karp, Martin, Artur Podobas, Niclas Jansson, Tobias Kenter, Christian Plessl, Philipp Schlatter, and Stefano Markidis. “High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection.” In 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 2021. https://doi.org/10.1109/ipdps49936.2021.00116.' ieee: 'M. Karp et al., “High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection,” 2021, doi: 10.1109/ipdps49936.2021.00116.' mla: 'Karp, Martin, et al. “High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection.” 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), IEEE, 2021, doi:10.1109/ipdps49936.2021.00116.' short: 'M. Karp, A. Podobas, N. Jansson, T. Kenter, C. Plessl, P. Schlatter, S. Markidis, in: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), IEEE, 2021.' date_created: 2022-02-21T14:26:37Z date_updated: 2024-01-22T09:59:13Z department: - _id: '27' - _id: '518' doi: 10.1109/ipdps49936.2021.00116 language: - iso: eng project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS) publication_status: published publisher: IEEE quality_controlled: '1' status: public title: 'High-Performance Spectral Element Methods on Field-Programmable Gate Arrays : Implementation, Evaluation, and Future Projection' type: conference user_id: '3145' year: '2021' ... --- _id: '32242' abstract: - lang: eng text: "We consider a resource-aware variant of the classical multi-armed bandit\r\nproblem: In each round, the learner selects an arm and determines a resource\r\nlimit. It then observes a corresponding (random) reward, provided the (random)\r\namount of consumed resources remains below the limit. Otherwise, the\r\nobservation is censored, i.e., no reward is obtained. For this problem setting,\r\nwe introduce a measure of regret, which incorporates the actual amount of\r\nallocated resources of each learning round as well as the optimality of\r\nrealizable rewards. Thus, to minimize regret, the learner needs to set a\r\nresource limit and choose an arm in such a way that the chance to realize a\r\nhigh reward within the predefined resource limit is high, while the resource\r\nlimit itself should be kept as low as possible. We derive the theoretical lower\r\nbound on the cumulative regret and propose a learning algorithm having a regret\r\nupper bound that matches the lower bound. In a simulation study, we show that\r\nour learning algorithm outperforms straightforward extensions of standard\r\nmulti-armed bandit algorithms." author: - first_name: Viktor full_name: Bengs, Viktor last_name: Bengs - first_name: Eyke full_name: Hüllermeier, Eyke last_name: Hüllermeier citation: ama: Bengs V, Hüllermeier E. Multi-Armed Bandits with Censored Consumption of Resources. arXiv:201100813. Published online 2020. apa: Bengs, V., & Hüllermeier, E. (2020). Multi-Armed Bandits with Censored Consumption of Resources. In arXiv:2011.00813. bibtex: '@article{Bengs_Hüllermeier_2020, title={Multi-Armed Bandits with Censored Consumption of Resources}, journal={arXiv:2011.00813}, author={Bengs, Viktor and Hüllermeier, Eyke}, year={2020} }' chicago: Bengs, Viktor, and Eyke Hüllermeier. “Multi-Armed Bandits with Censored Consumption of Resources.” ArXiv:2011.00813, 2020. ieee: V. Bengs and E. Hüllermeier, “Multi-Armed Bandits with Censored Consumption of Resources,” arXiv:2011.00813. 2020. mla: Bengs, Viktor, and Eyke Hüllermeier. “Multi-Armed Bandits with Censored Consumption of Resources.” ArXiv:2011.00813, 2020. short: V. Bengs, E. Hüllermeier, ArXiv:2011.00813 (2020). date_created: 2022-06-28T07:26:54Z date_updated: 2022-06-28T07:27:19Z department: - _id: '27' external_id: arxiv: - '2011.00813' language: - iso: eng project: - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: arXiv:2011.00813 status: public title: Multi-Armed Bandits with Censored Consumption of Resources type: preprint user_id: '15278' year: '2020' ... --- _id: '16898' abstract: - lang: eng text: "Electronic structure calculations based on density-functional theory (DFT)\r\nrepresent a significant part of today's HPC workloads and pose high demands on\r\nhigh-performance computing resources. To perform these quantum-mechanical DFT\r\ncalculations on complex large-scale systems, so-called linear scaling methods\r\ninstead of conventional cubic scaling methods are required. In this work, we\r\ntake up the idea of the submatrix method and apply it to the DFT computations\r\nin the software package CP2K. For that purpose, we transform the underlying\r\nnumeric operations on distributed, large, sparse matrices into computations on\r\nlocal, much smaller and nearly dense matrices. This allows us to exploit the\r\nfull floating-point performance of modern CPUs and to make use of dedicated\r\naccelerator hardware, where performance has been limited by memory bandwidth\r\nbefore. We demonstrate both functionality and performance of our implementation\r\nand show how it can be accelerated with GPUs and FPGAs." author: - first_name: Michael full_name: Lass, Michael id: '24135' last_name: Lass orcid: 0000-0002-5708-7632 - first_name: Robert full_name: Schade, Robert id: '75963' last_name: Schade orcid: 0000-0002-6268-539 - first_name: Thomas full_name: Kühne, Thomas id: '49079' last_name: Kühne - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Lass M, Schade R, Kühne T, Plessl C. A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K. In: Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC). IEEE Computer Society; 2020:1127-1140. doi:10.1109/SC41405.2020.00084' apa: Lass, M., Schade, R., Kühne, T., & Plessl, C. (2020). A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K. Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 1127–1140. https://doi.org/10.1109/SC41405.2020.00084 bibtex: '@inproceedings{Lass_Schade_Kühne_Plessl_2020, place={Los Alamitos, CA, USA}, title={A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K}, DOI={10.1109/SC41405.2020.00084}, booktitle={Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC)}, publisher={IEEE Computer Society}, author={Lass, Michael and Schade, Robert and Kühne, Thomas and Plessl, Christian}, year={2020}, pages={1127–1140} }' chicago: 'Lass, Michael, Robert Schade, Thomas Kühne, and Christian Plessl. “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K.” In Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 1127–40. Los Alamitos, CA, USA: IEEE Computer Society, 2020. https://doi.org/10.1109/SC41405.2020.00084.' ieee: 'M. Lass, R. Schade, T. Kühne, and C. Plessl, “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K,” in Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), Atlanta, GA, US, 2020, pp. 1127–1140, doi: 10.1109/SC41405.2020.00084.' mla: Lass, Michael, et al. “A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K.” Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), IEEE Computer Society, 2020, pp. 1127–40, doi:10.1109/SC41405.2020.00084. short: 'M. Lass, R. Schade, T. Kühne, C. Plessl, in: Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC), IEEE Computer Society, Los Alamitos, CA, USA, 2020, pp. 1127–1140.' conference: location: Atlanta, GA, US name: 'SC20: International Conference for High Performance Computing, Networking, Storage and Analysis (SC)' date_created: 2020-04-28T14:44:21Z date_updated: 2023-08-02T14:55:59Z department: - _id: '27' - _id: '518' - _id: '304' doi: 10.1109/SC41405.2020.00084 external_id: arxiv: - '2004.10811' language: - iso: eng main_file_link: - url: https://ieeexplore.ieee.org/document/9355245 page: 1127-1140 place: Los Alamitos, CA, USA project: - _id: '52' name: Computing Resources Provided by the Paderborn Center for Parallel Computing - _id: '32' grant_number: PL 595/2-1 / 320898746 name: Performance and Efficiency in HPC with Custom Computing - _id: '52' name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing' publication: Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (SC) publisher: IEEE Computer Society quality_controlled: '1' status: public title: A Submatrix-Based Method for Approximate Matrix Function Evaluation in the Quantum Chemistry Code CP2K type: conference user_id: '75963' year: '2020' ... --- _id: '21632' abstract: - lang: eng text: 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: - first_name: Marius full_name: Meyer, Marius id: '40778' last_name: Meyer - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Meyer M, Kenter T, Plessl C. Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite. In: 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC). ; 2020. doi:10.1109/h2rc51942.2020.00007' apa: Meyer, M., Kenter, T., & Plessl, C. (2020). Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite. 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC). https://doi.org/10.1109/h2rc51942.2020.00007 bibtex: '@inproceedings{Meyer_Kenter_Plessl_2020, title={Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite}, DOI={10.1109/h2rc51942.2020.00007}, booktitle={2020 IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC)}, author={Meyer, Marius and Kenter, Tobias and Plessl, Christian}, year={2020} }' chicago: Meyer, Marius, Tobias Kenter, and Christian Plessl. “Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite.” In 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2020. https://doi.org/10.1109/h2rc51942.2020.00007. ieee: 'M. Meyer, T. Kenter, and C. Plessl, “Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite,” 2020, doi: 10.1109/h2rc51942.2020.00007.' mla: Meyer, Marius, et al. “Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite.” 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2020, doi:10.1109/h2rc51942.2020.00007. short: 'M. Meyer, T. Kenter, C. Plessl, in: 2020 IEEE/ACM International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2020.' date_created: 2021-04-16T10:17:22Z date_updated: 2023-09-26T11:42:53Z department: - _id: '27' - _id: '518' doi: 10.1109/h2rc51942.2020.00007 keyword: - FPGA - OpenCL - High Level Synthesis - HPC benchmarking language: - iso: eng main_file_link: - url: https://ieeexplore.ieee.org/document/9306963 project: - _id: '52' name: Computing Resources Provided by the Paderborn Center for Parallel Computing publication: 2020 IEEE/ACM International Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC) publication_identifier: isbn: - '9781665415927' publication_status: published quality_controlled: '1' related_material: link: - description: Official repository of the benchmark suite on GitHub relation: supplementary_material url: https://github.com/pc2/HPCC_FPGA status: public title: Evaluating FPGA Accelerator Performance with a Parameterized OpenCL Adaptation of Selected Benchmarks of the HPCChallenge Benchmark Suite type: conference user_id: '15278' year: '2020' ... --- _id: '15478' abstract: - lang: eng text: 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: - first_name: Paolo full_name: Gorlani, Paolo id: '72045' last_name: Gorlani - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Gorlani P, Kenter T, Plessl C. OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs. In: Proceedings of the International Conference on Field-Programmable Technology (FPT). IEEE; 2019. doi:10.1109/ICFPT47387.2019.00020' apa: Gorlani, P., Kenter, T., & Plessl, C. (2019). OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs. In Proceedings of the International Conference on Field-Programmable Technology (FPT). IEEE. https://doi.org/10.1109/ICFPT47387.2019.00020 bibtex: '@inproceedings{Gorlani_Kenter_Plessl_2019, title={OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs}, DOI={10.1109/ICFPT47387.2019.00020}, booktitle={Proceedings of the International Conference on Field-Programmable Technology (FPT)}, publisher={IEEE}, author={Gorlani, Paolo and Kenter, Tobias and Plessl, Christian}, year={2019} }' chicago: Gorlani, Paolo, Tobias Kenter, and Christian Plessl. “OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs.” In Proceedings of the International Conference on Field-Programmable Technology (FPT). IEEE, 2019. https://doi.org/10.1109/ICFPT47387.2019.00020. ieee: P. Gorlani, T. Kenter, and C. Plessl, “OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs,” in Proceedings of the International Conference on Field-Programmable Technology (FPT), 2019. mla: Gorlani, Paolo, et al. “OpenCL Implementation of Cannon’s Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs.” Proceedings of the International Conference on Field-Programmable Technology (FPT), IEEE, 2019, doi:10.1109/ICFPT47387.2019.00020. short: 'P. Gorlani, T. Kenter, C. Plessl, in: Proceedings of the International Conference on Field-Programmable Technology (FPT), IEEE, 2019.' conference: name: International Conference on Field-Programmable Technology (FPT) date_created: 2020-01-09T12:54:48Z date_updated: 2022-01-06T06:52:26Z ddc: - '004' department: - _id: '27' - _id: '518' doi: 10.1109/ICFPT47387.2019.00020 file: - access_level: closed content_type: application/pdf creator: plessl date_created: 2020-01-09T12:53:57Z date_updated: 2020-01-09T12:53:57Z file_id: '15479' file_name: gorlani19_fpt.pdf file_size: 250559 relation: main_file success: 1 file_date_updated: 2020-01-09T12:53:57Z has_accepted_license: '1' language: - iso: eng project: - _id: '33' grant_number: 01|H16005 name: HighPerMeshes - _id: '32' grant_number: PL 595/2-1 name: Performance and Efficiency in HPC with Custom Computing publication: Proceedings of the International Conference on Field-Programmable Technology (FPT) publisher: IEEE quality_controlled: '1' status: public title: OpenCL Implementation of Cannon's Matrix Multiplication Algorithm on Intel Stratix 10 FPGAs type: conference user_id: '3145' year: '2019' ... --- _id: '22' abstract: - lang: eng text: 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: - first_name: Axel full_name: Keller, Axel id: '15274' last_name: Keller citation: ama: 'Keller A. A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems. In: Klusáček D, Cirne W, Desai N, eds. Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP). Vol 10773. Lecture Notes in Computer Science. Springer; 2018:132-151. doi:10.1007/978-3-319-77398-8_8' apa: 'Keller, A. (2018). A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems. In D. Klusáček, W. Cirne, & N. Desai (Eds.), Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP) (Vol. 10773, pp. 132–151). Orlando, FL, USA: Springer. https://doi.org/10.1007/978-3-319-77398-8_8' bibtex: '@inproceedings{Keller_2018, series={Lecture Notes in Computer Science}, title={A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems}, volume={10773}, DOI={10.1007/978-3-319-77398-8_8}, booktitle={Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP)}, publisher={Springer}, author={Keller, Axel}, editor={Klusáček, D. and Cirne, W. and Desai, N.Editors}, year={2018}, pages={132–151}, collection={Lecture Notes in Computer Science} }' chicago: Keller, Axel. “A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems.” In Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), edited by D. Klusáček, W. Cirne, and N. Desai, 10773:132–51. Lecture Notes in Computer Science. Springer, 2018. https://doi.org/10.1007/978-3-319-77398-8_8. ieee: A. Keller, “A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems,” in Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), Orlando, FL, USA, 2018, vol. 10773, pp. 132–151. mla: Keller, Axel. “A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems.” Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), edited by D. Klusáček et al., vol. 10773, Springer, 2018, pp. 132–51, doi:10.1007/978-3-319-77398-8_8. short: 'A. Keller, in: D. Klusáček, W. Cirne, N. Desai (Eds.), Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), Springer, 2018, pp. 132–151.' conference: end_date: 2017-06-02 location: Orlando, FL, USA name: 21st Workshop on Job Scheduling Strategies for Parallel Processing start_date: 2017-06-02 date_created: 2017-07-25T14:54:08Z date_updated: 2022-01-06T06:55:22Z department: - _id: '27' doi: 10.1007/978-3-319-77398-8_8 editor: - first_name: D. full_name: Klusáček, D. last_name: Klusáček - first_name: W. full_name: Cirne, W. last_name: Cirne - first_name: N. full_name: Desai, N. last_name: Desai intvolume: ' 10773' keyword: - Scheduling Planning Mapping Workload management language: - iso: eng page: 132-151 publication: Proc. Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP) publication_identifier: isbn: - 978-3-319-77398-8 - 978-3-319-77397-1 publication_status: published publisher: Springer series_title: Lecture Notes in Computer Science status: public title: A Data Structure for Planning Based Workload Management of Heterogeneous HPC Systems type: conference user_id: '15274' volume: 10773 year: '2018' ... --- _id: '1588' abstract: - lang: eng text: 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: - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Gopinath full_name: Mahale, Gopinath last_name: Mahale - first_name: Samer full_name: Alhaddad, Samer id: '42456' last_name: Alhaddad - first_name: Yevgen full_name: Grynko, Yevgen id: '26059' last_name: Grynko - first_name: Christian full_name: Schmitt, Christian last_name: Schmitt - first_name: Ayesha full_name: Afzal, Ayesha last_name: Afzal - first_name: Frank full_name: Hannig, Frank last_name: Hannig - first_name: Jens full_name: Förstner, Jens id: '158' last_name: Förstner orcid: 0000-0001-7059-9862 - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Kenter T, Mahale G, Alhaddad S, et al. OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes. In: Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). IEEE; 2018. doi:10.1109/FCCM.2018.00037' apa: Kenter, T., Mahale, G., Alhaddad, S., Grynko, Y., Schmitt, C., Afzal, A., Hannig, F., Förstner, J., & Plessl, C. (2018). OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes. Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). https://doi.org/10.1109/FCCM.2018.00037 bibtex: '@inproceedings{Kenter_Mahale_Alhaddad_Grynko_Schmitt_Afzal_Hannig_Förstner_Plessl_2018, title={OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes}, DOI={10.1109/FCCM.2018.00037}, booktitle={Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM)}, publisher={IEEE}, 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}, year={2018} }' chicago: Kenter, Tobias, Gopinath Mahale, Samer Alhaddad, Yevgen Grynko, Christian Schmitt, Ayesha Afzal, Frank Hannig, Jens Förstner, and Christian Plessl. “OpenCL-Based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes.” In Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM). IEEE, 2018. https://doi.org/10.1109/FCCM.2018.00037. ieee: 'T. Kenter et al., “OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes,” presented at the Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM), 2018, doi: 10.1109/FCCM.2018.00037.' mla: Kenter, Tobias, et al. “OpenCL-Based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes.” Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM), IEEE, 2018, doi:10.1109/FCCM.2018.00037. short: 'T. Kenter, G. Mahale, S. Alhaddad, Y. Grynko, C. Schmitt, A. Afzal, F. Hannig, J. Förstner, C. Plessl, in: Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM), IEEE, 2018.' conference: name: Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM) date_created: 2018-03-22T10:48:01Z date_updated: 2023-09-26T11:47:52Z ddc: - '000' department: - _id: '27' - _id: '518' - _id: '61' doi: 10.1109/FCCM.2018.00037 file: - access_level: closed content_type: application/pdf creator: ups date_created: 2018-11-02T14:45:05Z date_updated: 2018-11-02T14:45:05Z file_id: '5282' file_name: 08457652.pdf file_size: 269130 relation: main_file success: 1 file_date_updated: 2018-11-02T14:45:05Z has_accepted_license: '1' keyword: - tet_topic_hpc language: - iso: eng project: - _id: '33' grant_number: 01|H16005A name: HighPerMeshes - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '4' name: SFB 901 - Project Area C - _id: '14' grant_number: '160364472' name: SFB 901 - Subproject C2 publication: Proc. Int. Symp. on Field-Programmable Custom Computing Machines (FCCM) publisher: IEEE quality_controlled: '1' status: public title: OpenCL-based FPGA Design to Accelerate the Nodal Discontinuous Galerkin Method for Unstructured Meshes type: conference user_id: '15278' year: '2018' ... --- _id: '1590' abstract: - lang: eng text: "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.\r\n\r\nWe 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: - first_name: Michael full_name: Lass, Michael id: '24135' last_name: Lass orcid: 0000-0002-5708-7632 - first_name: Stephan full_name: Mohr, Stephan last_name: Mohr - first_name: Hendrik full_name: Wiebeler, Hendrik last_name: Wiebeler - first_name: Thomas full_name: Kühne, Thomas id: '49079' last_name: Kühne - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Lass M, Mohr S, Wiebeler H, Kühne T, Plessl C. A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices. In: Proc. Platform for Advanced Scientific Computing (PASC) Conference. ACM; 2018. doi:10.1145/3218176.3218231' apa: Lass, M., Mohr, S., Wiebeler, H., Kühne, T., & Plessl, C. (2018). A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices. Proc. Platform for Advanced Scientific Computing (PASC) Conference. Platform for Advanced Scientific Computing Conference (PASC), Basel, Switzerland. https://doi.org/10.1145/3218176.3218231 bibtex: '@inproceedings{Lass_Mohr_Wiebeler_Kühne_Plessl_2018, place={New York, NY, USA}, title={A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices}, DOI={10.1145/3218176.3218231}, booktitle={Proc. Platform for Advanced Scientific Computing (PASC) Conference}, publisher={ACM}, author={Lass, Michael and Mohr, Stephan and Wiebeler, Hendrik and Kühne, Thomas and Plessl, Christian}, year={2018} }' chicago: 'Lass, Michael, Stephan Mohr, Hendrik Wiebeler, Thomas Kühne, and Christian Plessl. “A Massively Parallel Algorithm for the Approximate Calculation of Inverse P-Th Roots of Large Sparse Matrices.” In Proc. Platform for Advanced Scientific Computing (PASC) Conference. New York, NY, USA: ACM, 2018. https://doi.org/10.1145/3218176.3218231.' ieee: 'M. Lass, S. Mohr, H. Wiebeler, T. Kühne, and C. Plessl, “A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices,” presented at the Platform for Advanced Scientific Computing Conference (PASC), Basel, Switzerland, 2018, doi: 10.1145/3218176.3218231.' mla: Lass, Michael, et al. “A Massively Parallel Algorithm for the Approximate Calculation of Inverse P-Th Roots of Large Sparse Matrices.” Proc. Platform for Advanced Scientific Computing (PASC) Conference, ACM, 2018, doi:10.1145/3218176.3218231. short: 'M. Lass, S. Mohr, H. Wiebeler, T. Kühne, C. Plessl, in: Proc. Platform for Advanced Scientific Computing (PASC) Conference, ACM, New York, NY, USA, 2018.' conference: end_date: 2018-07-04 location: Basel, Switzerland name: Platform for Advanced Scientific Computing Conference (PASC) start_date: 2018-07-02 date_created: 2018-03-22T10:53:01Z date_updated: 2023-09-26T11:48:12Z department: - _id: '27' - _id: '518' - _id: '304' doi: 10.1145/3218176.3218231 external_id: arxiv: - '1710.10899' keyword: - approximate computing - linear algebra - matrix inversion - matrix p-th roots - numeric algorithm - parallel computing language: - iso: eng place: New York, NY, USA project: - _id: '32' grant_number: PL 595/2-1 / 320898746 name: Performance and Efficiency in HPC with Custom Computing - _id: '52' name: Computing Resources Provided by the Paderborn Center for Parallel Computing publication: Proc. Platform for Advanced Scientific Computing (PASC) Conference publication_identifier: isbn: - 978-1-4503-5891-0/18/07 publisher: ACM quality_controlled: '1' status: public title: A Massively Parallel Algorithm for the Approximate Calculation of Inverse p-th Roots of Large Sparse Matrices type: conference user_id: '15278' year: '2018' ... --- _id: '1204' author: - first_name: Heinrich full_name: Riebler, Heinrich id: '8961' last_name: Riebler - first_name: Gavin Francis full_name: Vaz, Gavin Francis id: '30332' last_name: Vaz - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Riebler H, Vaz GF, Kenter T, Plessl C. Automated Code Acceleration Targeting Heterogeneous OpenCL Devices. In: Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). ACM; 2018. doi:10.1145/3178487.3178534' apa: Riebler, H., Vaz, G. F., Kenter, T., & Plessl, C. (2018). Automated Code Acceleration Targeting Heterogeneous OpenCL Devices. Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). https://doi.org/10.1145/3178487.3178534 bibtex: '@inproceedings{Riebler_Vaz_Kenter_Plessl_2018, title={Automated Code Acceleration Targeting Heterogeneous OpenCL Devices}, DOI={10.1145/3178487.3178534}, booktitle={Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP)}, publisher={ACM}, author={Riebler, Heinrich and Vaz, Gavin Francis and Kenter, Tobias and Plessl, Christian}, year={2018} }' chicago: Riebler, Heinrich, Gavin Francis Vaz, Tobias Kenter, and Christian Plessl. “Automated Code Acceleration Targeting Heterogeneous OpenCL Devices.” In Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). ACM, 2018. https://doi.org/10.1145/3178487.3178534. ieee: 'H. Riebler, G. F. Vaz, T. Kenter, and C. Plessl, “Automated Code Acceleration Targeting Heterogeneous OpenCL Devices,” 2018, doi: 10.1145/3178487.3178534.' mla: Riebler, Heinrich, et al. “Automated Code Acceleration Targeting Heterogeneous OpenCL Devices.” Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP), ACM, 2018, doi:10.1145/3178487.3178534. short: 'H. Riebler, G.F. Vaz, T. Kenter, C. Plessl, in: Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP), ACM, 2018.' date_created: 2018-03-08T14:45:18Z date_updated: 2023-09-26T11:47:23Z ddc: - '000' department: - _id: '27' - _id: '518' doi: 10.1145/3178487.3178534 file: - access_level: closed content_type: application/pdf creator: ups date_created: 2018-11-02T14:43:37Z date_updated: 2018-11-02T14:43:37Z file_id: '5281' file_name: p417-riebler.pdf file_size: 447769 relation: main_file success: 1 file_date_updated: 2018-11-02T14:43:37Z has_accepted_license: '1' keyword: - htrop language: - iso: eng project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '4' name: SFB 901 - Project Area C - _id: '14' grant_number: '160364472' name: SFB 901 - Subproject C2 publication: Proc. ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP) publication_identifier: isbn: - '9781450349826' publication_status: published publisher: ACM quality_controlled: '1' status: public title: Automated Code Acceleration Targeting Heterogeneous OpenCL Devices type: conference user_id: '15278' year: '2018' ... --- _id: '1592' abstract: - lang: eng text: 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: - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Jens full_name: Förstner, Jens id: '158' last_name: Förstner orcid: 0000-0001-7059-9862 - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Kenter T, Förstner J, Plessl C. Flexible FPGA design for FDTD using OpenCL. In: Proc. Int. Conf. on Field Programmable Logic and Applications (FPL). IEEE; 2017. doi:10.23919/FPL.2017.8056844' apa: Kenter, T., Förstner, J., & Plessl, C. (2017). Flexible FPGA design for FDTD using OpenCL. Proc. Int. Conf. on Field Programmable Logic and Applications (FPL). https://doi.org/10.23919/FPL.2017.8056844 bibtex: '@inproceedings{Kenter_Förstner_Plessl_2017, title={Flexible FPGA design for FDTD using OpenCL}, DOI={10.23919/FPL.2017.8056844}, booktitle={Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)}, publisher={IEEE}, author={Kenter, Tobias and Förstner, Jens and Plessl, Christian}, year={2017} }' chicago: Kenter, Tobias, Jens Förstner, and Christian Plessl. “Flexible FPGA Design for FDTD Using OpenCL.” In Proc. Int. Conf. on Field Programmable Logic and Applications (FPL). IEEE, 2017. https://doi.org/10.23919/FPL.2017.8056844. ieee: 'T. Kenter, J. Förstner, and C. Plessl, “Flexible FPGA design for FDTD using OpenCL,” 2017, doi: 10.23919/FPL.2017.8056844.' mla: Kenter, Tobias, et al. “Flexible FPGA Design for FDTD Using OpenCL.” Proc. Int. Conf. on Field Programmable Logic and Applications (FPL), IEEE, 2017, doi:10.23919/FPL.2017.8056844. short: 'T. Kenter, J. Förstner, C. Plessl, in: Proc. Int. Conf. on Field Programmable Logic and Applications (FPL), IEEE, 2017.' date_created: 2018-03-22T11:10:23Z date_updated: 2023-09-26T13:24:38Z ddc: - '000' department: - _id: '27' - _id: '518' - _id: '61' doi: 10.23919/FPL.2017.8056844 file: - access_level: closed content_type: application/pdf creator: ups date_created: 2018-11-02T15:02:28Z date_updated: 2018-11-02T15:02:28Z file_id: '5291' file_name: 08056844.pdf file_size: 230235 relation: main_file success: 1 file_date_updated: 2018-11-02T15:02:28Z has_accepted_license: '1' keyword: - tet_topic_hpc language: - iso: eng project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '4' name: SFB 901 - Project Area C - _id: '14' grant_number: '160364472' name: SFB 901 - Subproject C2 - _id: '33' grant_number: 01|H16005A name: HighPerMeshes - _id: '32' grant_number: PL 595/2-1 / 320898746 name: Performance and Efficiency in HPC with Custom Computing - _id: '52' name: Computing Resources Provided by the Paderborn Center for Parallel Computing publication: Proc. Int. Conf. on Field Programmable Logic and Applications (FPL) publisher: IEEE quality_controlled: '1' status: public title: Flexible FPGA design for FDTD using OpenCL type: conference user_id: '15278' year: '2017' ... --- _id: '34' author: - first_name: Michael full_name: Dellnitz, Michael last_name: Dellnitz - first_name: Julian full_name: Eckstein, Julian last_name: Eckstein - first_name: Kathrin full_name: Flaßkamp, Kathrin last_name: Flaßkamp - first_name: Patrick full_name: Friedel, Patrick last_name: Friedel - first_name: Christian full_name: Horenkamp, Christian last_name: Horenkamp - first_name: Ulrich full_name: Köhler, Ulrich last_name: Köhler - first_name: Sina full_name: Ober-Blöbaum, Sina last_name: Ober-Blöbaum - first_name: Sebastian full_name: Peitz, Sebastian last_name: Peitz - first_name: Sebastian full_name: Tiemeyer, Sebastian last_name: Tiemeyer citation: ama: 'Dellnitz M, Eckstein J, Flaßkamp K, et al. Multiobjective Optimal Control Methods for the Development of an Intelligent Cruise Control. In: Progress in Industrial Mathematics at ECMI. Vol 22. Mathematics in Industry. Cham: Springer International Publishing; 2016:633-641. doi:10.1007/978-3-319-23413-7_87' apa: 'Dellnitz, M., Eckstein, J., Flaßkamp, K., Friedel, P., Horenkamp, C., Köhler, U., … Tiemeyer, S. (2016). Multiobjective Optimal Control Methods for the Development of an Intelligent Cruise Control. In Progress in Industrial Mathematics at ECMI (Vol. 22, pp. 633–641). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-319-23413-7_87' bibtex: '@inproceedings{Dellnitz_Eckstein_Flaßkamp_Friedel_Horenkamp_Köhler_Ober-Blöbaum_Peitz_Tiemeyer_2016, place={Cham}, series={Mathematics in Industry}, title={Multiobjective Optimal Control Methods for the Development of an Intelligent Cruise Control}, volume={22}, DOI={10.1007/978-3-319-23413-7_87}, booktitle={Progress in Industrial Mathematics at ECMI}, publisher={Springer International Publishing}, 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}, year={2016}, pages={633–641}, collection={Mathematics in Industry} }' chicago: 'Dellnitz, Michael, Julian Eckstein, Kathrin Flaßkamp, Patrick Friedel, Christian Horenkamp, Ulrich Köhler, Sina Ober-Blöbaum, Sebastian Peitz, and Sebastian Tiemeyer. “Multiobjective Optimal Control Methods for the Development of an Intelligent Cruise Control.” In Progress in Industrial Mathematics at ECMI, 22:633–41. Mathematics in Industry. Cham: Springer International Publishing, 2016. https://doi.org/10.1007/978-3-319-23413-7_87.' ieee: M. Dellnitz et al., “Multiobjective Optimal Control Methods for the Development of an Intelligent Cruise Control,” in Progress in Industrial Mathematics at ECMI, 2016, vol. 22, pp. 633–641. mla: Dellnitz, Michael, et al. “Multiobjective Optimal Control Methods for the Development of an Intelligent Cruise Control.” Progress in Industrial Mathematics at ECMI, vol. 22, Springer International Publishing, 2016, pp. 633–41, doi:10.1007/978-3-319-23413-7_87. short: 'M. Dellnitz, J. Eckstein, K. Flaßkamp, P. Friedel, C. Horenkamp, U. Köhler, S. Ober-Blöbaum, S. Peitz, S. Tiemeyer, in: Progress in Industrial Mathematics at ECMI, Springer International Publishing, Cham, 2016, pp. 633–641.' date_created: 2017-07-26T15:25:33Z date_updated: 2022-01-06T06:59:14Z department: - _id: '27' - _id: '101' doi: 10.1007/978-3-319-23413-7_87 intvolume: ' 22' page: 633-641 place: Cham publication: Progress in Industrial Mathematics at ECMI publication_identifier: issn: - 2212-0173 publisher: Springer International Publishing series_title: Mathematics in Industry status: public title: Multiobjective Optimal Control Methods for the Development of an Intelligent Cruise Control type: conference user_id: '24135' volume: 22 year: '2016' ... --- _id: '19' abstract: - lang: eng text: "Version Control Systems (VCS) are a valuable tool for software development\r\nand document management. Both client/server and distributed (Peer-to-Peer)\r\nmodels exist, with the latter (e.g., Git and Mercurial) becoming\r\nincreasingly popular. Their distributed nature introduces complications,\r\nespecially concerning security: it is hard to control the dissemination of\r\ncontents stored in distributed VCS as they rely on replication of complete\r\nrepositories to any involved user.\r\n\r\nWe overcome this issue by designing and implementing a concept for\r\ncryptography-enforced access control which is transparent to the user. Use\r\nof field-tested schemes (end-to-end encryption, digital signatures) allows\r\nfor strong security, while adoption of convergent encryption and\r\ncontent-defined chunking retains storage efficiency. The concept is\r\nseamlessly integrated into Mercurial---respecting its distributed storage\r\nconcept---to ensure practical usability and compatibility to existing\r\ndeployments." author: - first_name: Michael full_name: Lass, Michael id: '24135' last_name: Lass orcid: 0000-0002-5708-7632 - first_name: Dominik full_name: Leibenger, Dominik last_name: Leibenger - first_name: Christoph full_name: Sorge, Christoph last_name: Sorge citation: ama: 'Lass M, Leibenger D, Sorge C. Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension. In: Proc. 41st Conference on Local Computer Networks (LCN). IEEE; 2016. doi:10.1109/lcn.2016.11' apa: Lass, M., Leibenger, D., & Sorge, C. (2016). Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension. In Proc. 41st Conference on Local Computer Networks (LCN). IEEE. https://doi.org/10.1109/lcn.2016.11 bibtex: '@inproceedings{Lass_Leibenger_Sorge_2016, title={Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension}, DOI={10.1109/lcn.2016.11}, booktitle={Proc. 41st Conference on Local Computer Networks (LCN)}, publisher={IEEE}, author={Lass, Michael and Leibenger, Dominik and Sorge, Christoph}, year={2016} }' chicago: Lass, Michael, Dominik Leibenger, and Christoph Sorge. “Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension.” In Proc. 41st Conference on Local Computer Networks (LCN). IEEE, 2016. https://doi.org/10.1109/lcn.2016.11. ieee: M. Lass, D. Leibenger, and C. Sorge, “Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension,” in Proc. 41st Conference on Local Computer Networks (LCN), 2016. mla: Lass, Michael, et al. “Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension.” Proc. 41st Conference on Local Computer Networks (LCN), IEEE, 2016, doi:10.1109/lcn.2016.11. short: 'M. Lass, D. Leibenger, C. Sorge, in: Proc. 41st Conference on Local Computer Networks (LCN), IEEE, 2016.' date_created: 2017-07-25T14:36:16Z date_updated: 2022-01-06T06:53:56Z department: - _id: '27' - _id: '518' doi: 10.1109/lcn.2016.11 keyword: - access control - distributed version control systems - mercurial - peer-to-peer - convergent encryption - confidentiality - authenticity language: - iso: eng publication: Proc. 41st Conference on Local Computer Networks (LCN) publication_identifier: isbn: - 978-1-5090-2054-6 publication_status: published publisher: IEEE status: public title: Confidentiality and Authenticity for Distributed Version Control Systems - A Mercurial Extension type: conference user_id: '24135' year: '2016' ... --- _id: '31' author: - first_name: Heinrich full_name: Riebler, Heinrich id: '8961' last_name: Riebler - first_name: Gavin Francis full_name: Vaz, Gavin Francis id: '30332' last_name: Vaz - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: Ettore M. G. full_name: Trainiti, Ettore M. G. last_name: Trainiti - first_name: Gianluca C. full_name: Durelli, Gianluca C. last_name: Durelli - first_name: Cristiana full_name: Bolchini, Cristiana last_name: Bolchini citation: ama: 'Riebler H, Vaz GF, Plessl C, Trainiti EMG, Durelli GC, Bolchini C. Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems. In: Proc. HiPEAC Workshop on Reonfigurable Computing (WRC). ; 2016.' apa: Riebler, H., Vaz, G. F., Plessl, C., Trainiti, E. M. G., Durelli, G. C., & Bolchini, C. (2016). Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems. Proc. HiPEAC Workshop on Reonfigurable Computing (WRC). bibtex: '@inproceedings{Riebler_Vaz_Plessl_Trainiti_Durelli_Bolchini_2016, title={Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems}, booktitle={Proc. HiPEAC Workshop on Reonfigurable Computing (WRC)}, author={Riebler, Heinrich and Vaz, Gavin Francis and Plessl, Christian and Trainiti, Ettore M. G. and Durelli, Gianluca C. and Bolchini, Cristiana}, year={2016} }' chicago: Riebler, Heinrich, Gavin Francis Vaz, Christian Plessl, Ettore M. G. Trainiti, Gianluca C. Durelli, and Cristiana Bolchini. “Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems.” In Proc. HiPEAC Workshop on Reonfigurable Computing (WRC), 2016. ieee: H. Riebler, G. F. Vaz, C. Plessl, E. M. G. Trainiti, G. C. Durelli, and C. Bolchini, “Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems,” 2016. mla: Riebler, Heinrich, et al. “Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems.” Proc. HiPEAC Workshop on Reonfigurable Computing (WRC), 2016. short: 'H. Riebler, G.F. Vaz, C. Plessl, E.M.G. Trainiti, G.C. Durelli, C. Bolchini, in: Proc. HiPEAC Workshop on Reonfigurable Computing (WRC), 2016.' date_created: 2017-07-26T15:16:31Z date_updated: 2023-09-26T13:25:59Z ddc: - '040' department: - _id: '27' - _id: '518' file: - access_level: closed content_type: application/pdf creator: deffel date_created: 2019-01-11T11:56:55Z date_updated: 2019-01-11T11:56:55Z file_id: '6626' file_name: wrc_upb_polimi_final.pdf file_size: 394563 relation: main_file success: 1 file_date_updated: 2019-01-11T11:56:55Z has_accepted_license: '1' language: - iso: eng project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '4' name: SFB 901 - Project Area C - _id: '14' grant_number: '160364472' name: SFB 901 - Subproject C2 - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: Proc. HiPEAC Workshop on Reonfigurable Computing (WRC) quality_controlled: '1' status: public title: Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems type: conference user_id: '15278' year: '2016' ... --- _id: '24' author: - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Kenter T, Plessl C. Microdisk Cavity FDTD Simulation on FPGA using OpenCL. In: Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC). ; 2016.' apa: Kenter, T., & Plessl, C. (2016). Microdisk Cavity FDTD Simulation on FPGA using OpenCL. Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC). bibtex: '@inproceedings{Kenter_Plessl_2016, title={Microdisk Cavity FDTD Simulation on FPGA using OpenCL}, booktitle={Proc. Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC)}, author={Kenter, Tobias and Plessl, Christian}, year={2016} }' chicago: Kenter, Tobias, and Christian Plessl. “Microdisk Cavity FDTD Simulation on FPGA Using OpenCL.” In Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2016. ieee: T. Kenter and C. Plessl, “Microdisk Cavity FDTD Simulation on FPGA using OpenCL,” 2016. mla: Kenter, Tobias, and Christian Plessl. “Microdisk Cavity FDTD Simulation on FPGA Using OpenCL.” Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2016. short: 'T. Kenter, C. Plessl, in: Proc. Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC), 2016.' date_created: 2017-07-26T15:00:43Z date_updated: 2023-09-26T13:26:17Z ddc: - '004' department: - _id: '27' - _id: '518' file: - access_level: closed content_type: application/pdf creator: kenter date_created: 2018-11-14T12:38:45Z date_updated: 2018-11-14T12:38:45Z file_id: '5602' file_name: paper_26.pdf file_size: 129552 relation: main_file success: 1 file_date_updated: 2018-11-14T12:38:45Z has_accepted_license: '1' language: - iso: eng project: - _id: '32' grant_number: PL 595/2-1 / 320898746 name: Performance and Efficiency in HPC with Custom Computing - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '4' name: SFB 901 - Project Area C - _id: '14' grant_number: '160364472' name: SFB 901 - Subproject C2 publication: Proc. Workshop on Heterogeneous High-performance Reconfigurable Computing (H2RC) quality_controlled: '1' status: public title: Microdisk Cavity FDTD Simulation on FPGA using OpenCL type: conference user_id: '15278' year: '2016' ... --- _id: '25' author: - first_name: Michael full_name: Lass, Michael id: '24135' last_name: Lass orcid: 0000-0002-5708-7632 - first_name: Thomas full_name: Kühne, Thomas id: '49079' last_name: Kühne - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Lass M, Kühne T, Plessl C. Using Approximate Computing in Scientific Codes. In: Workshop on Approximate Computing (AC). ; 2016.' apa: Lass, M., Kühne, T., & Plessl, C. (2016). Using Approximate Computing in Scientific Codes. Workshop on Approximate Computing (AC). bibtex: '@inproceedings{Lass_Kühne_Plessl_2016, title={Using Approximate Computing in Scientific Codes}, booktitle={Workshop on Approximate Computing (AC)}, author={Lass, Michael and Kühne, Thomas and Plessl, Christian}, year={2016} }' chicago: Lass, Michael, Thomas Kühne, and Christian Plessl. “Using Approximate Computing in Scientific Codes.” In Workshop on Approximate Computing (AC), 2016. ieee: M. Lass, T. Kühne, and C. Plessl, “Using Approximate Computing in Scientific Codes,” 2016. mla: Lass, Michael, et al. “Using Approximate Computing in Scientific Codes.” Workshop on Approximate Computing (AC), 2016. short: 'M. Lass, T. Kühne, C. Plessl, in: Workshop on Approximate Computing (AC), 2016.' date_created: 2017-07-26T15:02:20Z date_updated: 2023-09-26T13:25:17Z department: - _id: '27' - _id: '518' - _id: '304' language: - iso: eng project: - _id: '52' name: Computing Resources Provided by the Paderborn Center for Parallel Computing publication: Workshop on Approximate Computing (AC) quality_controlled: '1' status: public title: Using Approximate Computing in Scientific Codes type: conference user_id: '15278' year: '2016' ... --- _id: '138' abstract: - lang: eng text: 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: - first_name: Heinrich full_name: Riebler, Heinrich id: '8961' last_name: Riebler - first_name: Gavin Francis full_name: Vaz, Gavin Francis id: '30332' last_name: Vaz - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: 'Ettore M. G. ' full_name: 'Trainiti, Ettore M. G. ' last_name: Trainiti - first_name: Gianluca C. full_name: Durelli, Gianluca C. last_name: Durelli - first_name: Emanuele full_name: Del Sozzo, Emanuele last_name: Del Sozzo - first_name: 'Marco D. ' full_name: 'Santambrogio, Marco D. ' last_name: Santambrogio - first_name: Christina full_name: Bolchini, Christina last_name: Bolchini citation: ama: 'Riebler H, Vaz GF, Plessl C, et al. Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems. In: Proceedings of International Forum on Research and Technologies for Society and Industry (RTSI). IEEE; 2016:1-5. doi:10.1109/RTSI.2016.7740545' apa: Riebler, H., Vaz, G. F., Plessl, C., Trainiti, E. M. G., Durelli, G. C., Del Sozzo, E., Santambrogio, M. D., & Bolchini, C. (2016). Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems. Proceedings of International Forum on Research and Technologies for Society and Industry (RTSI), 1–5. https://doi.org/10.1109/RTSI.2016.7740545 bibtex: '@inproceedings{Riebler_Vaz_Plessl_Trainiti_Durelli_Del Sozzo_Santambrogio_Bolchini_2016, title={Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems}, DOI={10.1109/RTSI.2016.7740545}, booktitle={Proceedings of International Forum on Research and Technologies for Society and Industry (RTSI)}, publisher={IEEE}, 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}, year={2016}, pages={1–5} }' chicago: Riebler, Heinrich, Gavin Francis Vaz, Christian Plessl, Ettore M. G. Trainiti, Gianluca C. Durelli, Emanuele Del Sozzo, Marco D. Santambrogio, and Christina Bolchini. “Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems.” In Proceedings of International Forum on Research and Technologies for Society and Industry (RTSI), 1–5. IEEE, 2016. https://doi.org/10.1109/RTSI.2016.7740545. ieee: 'H. Riebler et al., “Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems,” in Proceedings of International Forum on Research and Technologies for Society and Industry (RTSI), 2016, pp. 1–5, doi: 10.1109/RTSI.2016.7740545.' mla: Riebler, Heinrich, et al. “Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems.” Proceedings of International Forum on Research and Technologies for Society and Industry (RTSI), IEEE, 2016, pp. 1–5, doi:10.1109/RTSI.2016.7740545. short: 'H. Riebler, G.F. Vaz, C. Plessl, E.M.G. Trainiti, G.C. Durelli, E. Del Sozzo, M.D. Santambrogio, C. Bolchini, in: Proceedings of International Forum on Research and Technologies for Society and Industry (RTSI), IEEE, 2016, pp. 1–5.' date_created: 2017-10-17T12:41:18Z date_updated: 2023-09-26T13:28:11Z ddc: - '040' department: - _id: '27' - _id: '518' doi: 10.1109/RTSI.2016.7740545 file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-21T13:01:09Z date_updated: 2018-03-21T13:01:09Z file_id: '1560' file_name: 138-07740545.pdf file_size: 184334 relation: main_file success: 1 file_date_updated: 2018-03-21T13:01:09Z has_accepted_license: '1' language: - iso: eng page: 1-5 project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '4' name: SFB 901 - Project Area C - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: Proceedings of International Forum on Research and Technologies for Society and Industry (RTSI) publisher: IEEE quality_controlled: '1' status: public title: Using Just-in-Time Code Generation for Transparent Resource Management in Heterogeneous Systems type: conference user_id: '15278' year: '2016' ... --- _id: '168' abstract: - lang: eng text: 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: - first_name: Achim full_name: Lösch, Achim id: '43646' last_name: Lösch - first_name: Tobias full_name: Beisel, Tobias last_name: Beisel - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: Marco full_name: Platzner, Marco id: '398' last_name: Platzner citation: ama: 'Lösch A, Beisel T, Kenter T, Plessl C, Platzner M. Performance-centric scheduling with task migration for a heterogeneous compute node in the data center. In: Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE). EDA Consortium / IEEE; 2016:912-917.' apa: Lösch, A., Beisel, T., Kenter, T., Plessl, C., & Platzner, M. (2016). Performance-centric scheduling with task migration for a heterogeneous compute node in the data center. Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE), 912–917. bibtex: '@inproceedings{Lösch_Beisel_Kenter_Plessl_Platzner_2016, title={Performance-centric scheduling with task migration for a heterogeneous compute node in the data center}, booktitle={Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE)}, publisher={EDA Consortium / IEEE}, author={Lösch, Achim and Beisel, Tobias and Kenter, Tobias and Plessl, Christian and Platzner, Marco}, year={2016}, pages={912–917} }' chicago: Lösch, Achim, Tobias Beisel, Tobias Kenter, Christian Plessl, and Marco Platzner. “Performance-Centric Scheduling with Task Migration for a Heterogeneous Compute Node in the Data Center.” In Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE), 912–17. EDA Consortium / IEEE, 2016. ieee: A. Lösch, T. Beisel, T. Kenter, C. Plessl, and M. Platzner, “Performance-centric scheduling with task migration for a heterogeneous compute node in the data center,” in Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2016, pp. 912–917. mla: Lösch, Achim, et al. “Performance-Centric Scheduling with Task Migration for a Heterogeneous Compute Node in the Data Center.” Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE), EDA Consortium / IEEE, 2016, pp. 912–17. short: 'A. Lösch, T. Beisel, T. Kenter, C. Plessl, M. Platzner, in: Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE), EDA Consortium / IEEE, 2016, pp. 912–917.' date_created: 2017-10-17T12:41:24Z date_updated: 2023-09-26T13:27:00Z ddc: - '040' department: - _id: '27' - _id: '518' - _id: '78' file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-21T12:41:55Z date_updated: 2018-03-21T12:41:55Z file_id: '1541' file_name: 168-07459438.pdf file_size: 261356 relation: main_file success: 1 file_date_updated: 2018-03-21T12:41:55Z has_accepted_license: '1' language: - iso: eng page: 912-917 project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '4' name: SFB 901 - Project Area C - _id: '30' grant_number: 01|H11004A name: Enabling Heterogeneous Hardware Acceleration using Novel Programming and Scheduling Models publication: Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE) publisher: EDA Consortium / IEEE quality_controlled: '1' status: public title: Performance-centric scheduling with task migration for a heterogeneous compute node in the data center type: conference user_id: '15278' year: '2016' ... --- _id: '171' author: - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Gavin Francis full_name: Vaz, Gavin Francis id: '30332' last_name: Vaz - first_name: Heinrich full_name: Riebler, Heinrich id: '8961' last_name: Riebler - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Kenter T, Vaz GF, Riebler H, Plessl C. Opportunities for deferring application partitioning and accelerator synthesis to runtime (extended abstract). In: Workshop on Reconfigurable Computing (WRC). ; 2016.' apa: Kenter, T., Vaz, G. F., Riebler, H., & Plessl, C. (2016). Opportunities for deferring application partitioning and accelerator synthesis to runtime (extended abstract). Workshop on Reconfigurable Computing (WRC). bibtex: '@inproceedings{Kenter_Vaz_Riebler_Plessl_2016, title={Opportunities for deferring application partitioning and accelerator synthesis to runtime (extended abstract)}, booktitle={Workshop on Reconfigurable Computing (WRC)}, author={Kenter, Tobias and Vaz, Gavin Francis and Riebler, Heinrich and Plessl, Christian}, year={2016} }' chicago: Kenter, Tobias, Gavin Francis Vaz, Heinrich Riebler, and Christian Plessl. “Opportunities for Deferring Application Partitioning and Accelerator Synthesis to Runtime (Extended Abstract).” In Workshop on Reconfigurable Computing (WRC), 2016. ieee: T. Kenter, G. F. Vaz, H. Riebler, and C. Plessl, “Opportunities for deferring application partitioning and accelerator synthesis to runtime (extended abstract),” 2016. mla: Kenter, Tobias, et al. “Opportunities for Deferring Application Partitioning and Accelerator Synthesis to Runtime (Extended Abstract).” Workshop on Reconfigurable Computing (WRC), 2016. short: 'T. Kenter, G.F. Vaz, H. Riebler, C. Plessl, in: Workshop on Reconfigurable Computing (WRC), 2016.' date_created: 2017-10-17T12:41:25Z date_updated: 2023-09-26T13:27:21Z ddc: - '040' department: - _id: '27' - _id: '518' file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-21T12:39:46Z date_updated: 2018-03-21T12:39:46Z file_id: '1538' file_name: 171-plessl16_fpl_wrc.pdf file_size: 54421 relation: main_file success: 1 file_date_updated: 2018-03-21T12:39:46Z has_accepted_license: '1' language: - iso: eng project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '4' name: SFB 901 - Project Area C - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: Workshop on Reconfigurable Computing (WRC) quality_controlled: '1' status: public title: Opportunities for deferring application partitioning and accelerator synthesis to runtime (extended abstract) type: conference user_id: '15278' year: '2016' ... --- _id: '303' abstract: - lang: eng text: 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: - first_name: Marvin full_name: Damschen, Marvin last_name: Damschen - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Damschen M, Plessl C. Easy-to-Use On-The-Fly Binary Program Acceleration on Many-Cores. In: Proceedings of the 5th International Workshop on Adaptive Self-Tuning Computing Systems (ADAPT). ; 2015.' apa: Damschen, M., & Plessl, C. (2015). Easy-to-Use On-The-Fly Binary Program Acceleration on Many-Cores. Proceedings of the 5th International Workshop on Adaptive Self-Tuning Computing Systems (ADAPT). bibtex: '@inproceedings{Damschen_Plessl_2015, title={Easy-to-Use On-The-Fly Binary Program Acceleration on Many-Cores}, booktitle={Proceedings of the 5th International Workshop on Adaptive Self-tuning Computing Systems (ADAPT)}, author={Damschen, Marvin and Plessl, Christian}, year={2015} }' chicago: Damschen, Marvin, and Christian Plessl. “Easy-to-Use On-The-Fly Binary Program Acceleration on Many-Cores.” In Proceedings of the 5th International Workshop on Adaptive Self-Tuning Computing Systems (ADAPT), 2015. ieee: M. Damschen and C. Plessl, “Easy-to-Use On-The-Fly Binary Program Acceleration on Many-Cores,” 2015. mla: Damschen, Marvin, and Christian Plessl. “Easy-to-Use On-The-Fly Binary Program Acceleration on Many-Cores.” Proceedings of the 5th International Workshop on Adaptive Self-Tuning Computing Systems (ADAPT), 2015. short: 'M. Damschen, C. Plessl, in: Proceedings of the 5th International Workshop on Adaptive Self-Tuning Computing Systems (ADAPT), 2015.' date_created: 2017-10-17T12:41:51Z date_updated: 2023-09-26T13:29:59Z ddc: - '040' department: - _id: '27' - _id: '518' - _id: '78' external_id: arxiv: - '1412.3906' file: - access_level: open_access content_type: application/pdf creator: florida date_created: 2018-03-20T07:46:46Z date_updated: 2019-08-01T09:10:44Z file_id: '1442' file_name: 303-plessl15_adapt.pdf file_size: 1176620 relation: main_file file_date_updated: 2019-08-01T09:10:44Z has_accepted_license: '1' language: - iso: eng oa: '1' project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '4' name: SFB 901 - Project Area C - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: Proceedings of the 5th International Workshop on Adaptive Self-tuning Computing Systems (ADAPT) quality_controlled: '1' status: public title: Easy-to-Use On-The-Fly Binary Program Acceleration on Many-Cores type: conference user_id: '15278' year: '2015' ... --- _id: '1773' author: - first_name: Jörn full_name: Schumacher, Jörn last_name: Schumacher - first_name: J. full_name: T. Anderson, J. last_name: T. Anderson - first_name: A. full_name: Borga, A. last_name: Borga - first_name: H. full_name: Boterenbrood, H. last_name: Boterenbrood - first_name: H. full_name: Chen, H. last_name: Chen - first_name: K. full_name: Chen, K. last_name: Chen - first_name: G. full_name: Drake, G. last_name: Drake - first_name: D. full_name: Francis, D. last_name: Francis - first_name: B. full_name: Gorini, B. last_name: Gorini - first_name: F. full_name: Lanni, F. last_name: Lanni - first_name: Giovanna full_name: Lehmann-Miotto, Giovanna last_name: Lehmann-Miotto - first_name: L. full_name: Levinson, L. last_name: Levinson - first_name: J. full_name: Narevicius, J. last_name: Narevicius - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: A. full_name: Roich, A. last_name: Roich - first_name: S. full_name: Ryu, S. last_name: Ryu - first_name: F. full_name: P. Schreuder, F. last_name: P. Schreuder - first_name: Wainer full_name: Vandelli, Wainer last_name: Vandelli - first_name: J. full_name: Vermeulen, J. last_name: Vermeulen - first_name: J. full_name: Zhang, J. last_name: Zhang citation: ama: 'Schumacher J, T. Anderson J, Borga A, et al. Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm. In: Proc. Int. Conf. on Distributed Event-Based Systems (DEBS). ACM; 2015. doi:10.1145/2675743.2771824' apa: Schumacher, J., T. Anderson, J., Borga, A., Boterenbrood, H., Chen, H., Chen, K., Drake, G., Francis, D., Gorini, B., Lanni, F., Lehmann-Miotto, G., Levinson, L., Narevicius, J., Plessl, C., Roich, A., Ryu, S., P. Schreuder, F., Vandelli, W., Vermeulen, J., & Zhang, J. (2015). Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm. Proc. Int. Conf. on Distributed Event-Based Systems (DEBS). https://doi.org/10.1145/2675743.2771824 bibtex: '@inproceedings{Schumacher_T. Anderson_Borga_Boterenbrood_Chen_Chen_Drake_Francis_Gorini_Lanni_et al._2015, title={Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm}, DOI={10.1145/2675743.2771824}, booktitle={Proc. Int. Conf. on Distributed Event-Based Systems (DEBS)}, publisher={ACM}, 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 et al.}, year={2015} }' chicago: Schumacher, Jörn, J. T. Anderson, A. Borga, H. Boterenbrood, H. Chen, K. Chen, G. Drake, et al. “Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm.” In Proc. Int. Conf. on Distributed Event-Based Systems (DEBS). ACM, 2015. https://doi.org/10.1145/2675743.2771824. ieee: 'J. Schumacher et al., “Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm,” 2015, doi: 10.1145/2675743.2771824.' mla: Schumacher, Jörn, et al. “Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm.” Proc. Int. Conf. on Distributed Event-Based Systems (DEBS), ACM, 2015, doi:10.1145/2675743.2771824. short: 'J. Schumacher, J. T. Anderson, A. Borga, H. Boterenbrood, H. Chen, K. Chen, G. Drake, D. Francis, B. Gorini, F. Lanni, G. Lehmann-Miotto, L. Levinson, J. Narevicius, C. Plessl, A. Roich, S. Ryu, F. P. Schreuder, W. Vandelli, J. Vermeulen, J. Zhang, in: Proc. Int. Conf. on Distributed Event-Based Systems (DEBS), ACM, 2015.' date_created: 2018-03-23T14:09:33Z date_updated: 2023-09-26T13:31:01Z department: - _id: '27' - _id: '518' - _id: '78' doi: 10.1145/2675743.2771824 language: - iso: eng publication: Proc. Int. Conf. on Distributed Event-Based Systems (DEBS) publisher: ACM quality_controlled: '1' status: public title: Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm type: conference user_id: '15278' year: '2015' ... --- _id: '238' abstract: - lang: eng text: 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: - first_name: Marvin full_name: Damschen, Marvin last_name: Damschen - first_name: Heinrich full_name: Riebler, Heinrich id: '8961' last_name: Riebler - first_name: Gavin Francis full_name: Vaz, Gavin Francis id: '30332' last_name: Vaz - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Damschen M, Riebler H, Vaz GF, Plessl C. Transparent offloading of computational hotspots from binary code to Xeon Phi. In: Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE). EDA Consortium / IEEE; 2015:1078-1083. doi:10.7873/DATE.2015.1124' apa: Damschen, M., Riebler, H., Vaz, G. F., & Plessl, C. (2015). Transparent offloading of computational hotspots from binary code to Xeon Phi. Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE), 1078–1083. https://doi.org/10.7873/DATE.2015.1124 bibtex: '@inproceedings{Damschen_Riebler_Vaz_Plessl_2015, title={Transparent offloading of computational hotspots from binary code to Xeon Phi}, DOI={10.7873/DATE.2015.1124}, booktitle={Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE)}, publisher={EDA Consortium / IEEE}, author={Damschen, Marvin and Riebler, Heinrich and Vaz, Gavin Francis and Plessl, Christian}, year={2015}, pages={1078–1083} }' chicago: Damschen, Marvin, Heinrich Riebler, Gavin Francis Vaz, and Christian Plessl. “Transparent Offloading of Computational Hotspots from Binary Code to Xeon Phi.” In Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE), 1078–83. EDA Consortium / IEEE, 2015. https://doi.org/10.7873/DATE.2015.1124. ieee: 'M. Damschen, H. Riebler, G. F. Vaz, and C. Plessl, “Transparent offloading of computational hotspots from binary code to Xeon Phi,” in Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE), 2015, pp. 1078–1083, doi: 10.7873/DATE.2015.1124.' mla: Damschen, Marvin, et al. “Transparent Offloading of Computational Hotspots from Binary Code to Xeon Phi.” Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE), EDA Consortium / IEEE, 2015, pp. 1078–83, doi:10.7873/DATE.2015.1124. short: 'M. Damschen, H. Riebler, G.F. Vaz, C. Plessl, in: Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE), EDA Consortium / IEEE, 2015, pp. 1078–1083.' date_created: 2017-10-17T12:41:38Z date_updated: 2023-09-26T13:31:44Z ddc: - '040' department: - _id: '27' - _id: '518' - _id: '78' doi: 10.7873/DATE.2015.1124 file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-21T10:29:49Z date_updated: 2018-03-21T10:29:49Z file_id: '1500' file_name: 238-plessl15_date.pdf file_size: 380552 relation: main_file success: 1 file_date_updated: 2018-03-21T10:29:49Z has_accepted_license: '1' language: - iso: eng page: 1078-1083 project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '4' name: SFB 901 - Project Area C - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE) publisher: EDA Consortium / IEEE quality_controlled: '1' status: public title: Transparent offloading of computational hotspots from binary code to Xeon Phi type: conference user_id: '15278' year: '2015' ... --- _id: '1781' abstract: - lang: eng text: 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: - first_name: Tobias full_name: Steinle, Tobias last_name: Steinle - first_name: Jadran full_name: Vrabec, Jadran last_name: Vrabec - first_name: Andrea full_name: Walther, Andrea last_name: Walther citation: ama: 'Steinle T, Vrabec J, Walther A. Numerical Simulation of the Damping Behavior of Particle-Filled Hollow Spheres. In: Bock HG, Hoang XP, Rannacher R, Schlöder JP, eds. Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC). Springer International Publishing; 2014:233-243. doi:10.1007/978-3-319-09063-4_19' apa: Steinle, T., Vrabec, J., & Walther, A. (2014). Numerical Simulation of the Damping Behavior of Particle-Filled Hollow Spheres. In H. G. Bock, X. P. Hoang, R. Rannacher, & J. P. Schlöder (Eds.), Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC) (pp. 233–243). Springer International Publishing. https://doi.org/10.1007/978-3-319-09063-4_19 bibtex: '@inproceedings{Steinle_Vrabec_Walther_2014, title={Numerical Simulation of the Damping Behavior of Particle-Filled Hollow Spheres}, DOI={10.1007/978-3-319-09063-4_19}, booktitle={Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC)}, publisher={Springer International Publishing}, author={Steinle, Tobias and Vrabec, Jadran and Walther, Andrea}, editor={Bock, Hans Georg and Hoang, Xuan Phu and Rannacher, Rolf and Schlöder, Johannes P.Editors}, year={2014}, pages={233–243} }' chicago: Steinle, Tobias, Jadran Vrabec, and Andrea Walther. “Numerical Simulation of the Damping Behavior of Particle-Filled Hollow Spheres.” In Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC), edited by Hans Georg Bock, Xuan Phu Hoang, Rolf Rannacher, and Johannes P. Schlöder, 233–43. Springer International Publishing, 2014. https://doi.org/10.1007/978-3-319-09063-4_19. ieee: T. Steinle, J. Vrabec, and A. Walther, “Numerical Simulation of the Damping Behavior of Particle-Filled Hollow Spheres,” in Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC), 2014, pp. 233–243. mla: Steinle, Tobias, et al. “Numerical Simulation of the Damping Behavior of Particle-Filled Hollow Spheres.” Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC), edited by Hans Georg Bock et al., Springer International Publishing, 2014, pp. 233–43, doi:10.1007/978-3-319-09063-4_19. short: 'T. Steinle, J. Vrabec, A. Walther, in: H.G. Bock, X.P. Hoang, R. Rannacher, J.P. Schlöder (Eds.), Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC), Springer International Publishing, 2014, pp. 233–243.' date_created: 2018-03-26T13:47:16Z date_updated: 2022-01-06T06:53:20Z department: - _id: '27' - _id: '104' - _id: '155' doi: 10.1007/978-3-319-09063-4_19 editor: - first_name: Hans Georg full_name: Bock, Hans Georg last_name: Bock - first_name: Xuan Phu full_name: Hoang, Xuan Phu last_name: Hoang - first_name: Rolf full_name: Rannacher, Rolf last_name: Rannacher - first_name: Johannes P. full_name: Schlöder, Johannes P. last_name: Schlöder page: 233-243 publication: Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC) publication_identifier: isbn: - 978-3-319-09063-4 publisher: Springer International Publishing status: public title: Numerical Simulation of the Damping Behavior of Particle-Filled Hollow Spheres type: conference user_id: '24135' year: '2014' ... --- _id: '1782' author: - first_name: Tobias full_name: Graf, Tobias last_name: Graf - first_name: Lars full_name: Schaefers, Lars last_name: Schaefers - first_name: Marco full_name: Platzner, Marco id: '398' last_name: Platzner citation: ama: 'Graf T, Schaefers L, Platzner M. On Semeai Detection in Monte-Carlo Go. In: Proc. Conf. on Computers and Games (CG). Lecture Notes in Computer Science. Switzerland: Springer; 2014:14-25. doi:10.1007/978-3-319-09165-5_2' apa: 'Graf, T., Schaefers, L., & Platzner, M. (2014). On Semeai Detection in Monte-Carlo Go. In Proc. Conf. on Computers and Games (CG) (pp. 14–25). Switzerland: Springer. https://doi.org/10.1007/978-3-319-09165-5_2' bibtex: '@inproceedings{Graf_Schaefers_Platzner_2014, place={Switzerland}, series={Lecture Notes in Computer Science}, title={On Semeai Detection in Monte-Carlo Go}, DOI={10.1007/978-3-319-09165-5_2}, number={8427}, booktitle={Proc. Conf. on Computers and Games (CG)}, publisher={Springer}, author={Graf, Tobias and Schaefers, Lars and Platzner, Marco}, year={2014}, pages={14–25}, collection={Lecture Notes in Computer Science} }' chicago: 'Graf, Tobias, Lars Schaefers, and Marco Platzner. “On Semeai Detection in Monte-Carlo Go.” In Proc. Conf. on Computers and Games (CG), 14–25. Lecture Notes in Computer Science. Switzerland: Springer, 2014. https://doi.org/10.1007/978-3-319-09165-5_2.' ieee: T. Graf, L. Schaefers, and M. Platzner, “On Semeai Detection in Monte-Carlo Go,” in Proc. Conf. on Computers and Games (CG), 2014, no. 8427, pp. 14–25. mla: Graf, Tobias, et al. “On Semeai Detection in Monte-Carlo Go.” Proc. Conf. on Computers and Games (CG), no. 8427, Springer, 2014, pp. 14–25, doi:10.1007/978-3-319-09165-5_2. short: 'T. Graf, L. Schaefers, M. Platzner, in: Proc. Conf. on Computers and Games (CG), Springer, Switzerland, 2014, pp. 14–25.' date_created: 2018-03-26T13:50:37Z date_updated: 2022-01-06T06:53:20Z department: - _id: '27' - _id: '78' doi: 10.1007/978-3-319-09165-5_2 issue: '8427' page: 14-25 place: Switzerland publication: Proc. Conf. on Computers and Games (CG) publisher: Springer series_title: Lecture Notes in Computer Science status: public title: On Semeai Detection in Monte-Carlo Go type: conference user_id: '24135' year: '2014' ... --- _id: '388' abstract: - lang: eng text: 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: - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Gavin Francis full_name: Vaz, Gavin Francis id: '30332' last_name: Vaz - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Kenter T, Vaz GF, Plessl C. Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer. In: Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC). Vol 8405. Lecture Notes in Computer Science (LNCS). Springer International Publishing; 2014:144-155. doi:10.1007/978-3-319-05960-0_13' apa: 'Kenter, T., Vaz, G. F., & Plessl, C. (2014). Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer. Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC), 8405, 144–155. https://doi.org/10.1007/978-3-319-05960-0_13' bibtex: '@inproceedings{Kenter_Vaz_Plessl_2014, place={Cham}, series={Lecture Notes in Computer Science (LNCS)}, title={Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer}, volume={8405}, DOI={10.1007/978-3-319-05960-0_13}, booktitle={Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC)}, publisher={Springer International Publishing}, author={Kenter, Tobias and Vaz, Gavin Francis and Plessl, Christian}, year={2014}, pages={144–155}, collection={Lecture Notes in Computer Science (LNCS)} }' chicago: 'Kenter, Tobias, Gavin Francis Vaz, and Christian Plessl. “Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer.” In Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC), 8405:144–55. Lecture Notes in Computer Science (LNCS). Cham: Springer International Publishing, 2014. https://doi.org/10.1007/978-3-319-05960-0_13.' ieee: 'T. Kenter, G. F. Vaz, and C. Plessl, “Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer,” in Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC), 2014, vol. 8405, pp. 144–155, doi: 10.1007/978-3-319-05960-0_13.' mla: 'Kenter, Tobias, et al. “Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer.” Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC), vol. 8405, Springer International Publishing, 2014, pp. 144–55, doi:10.1007/978-3-319-05960-0_13.' short: 'T. Kenter, G.F. Vaz, C. Plessl, in: Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC), Springer International Publishing, Cham, 2014, pp. 144–155.' date_created: 2017-10-17T12:42:07Z date_updated: 2023-09-26T13:34:08Z ddc: - '040' department: - _id: '27' - _id: '518' - _id: '78' doi: 10.1007/978-3-319-05960-0_13 file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-20T07:02:02Z date_updated: 2018-03-20T07:02:02Z file_id: '1387' file_name: 388-plessl14_arc.pdf file_size: 330193 relation: main_file success: 1 file_date_updated: 2018-03-20T07:02:02Z has_accepted_license: '1' intvolume: ' 8405' language: - iso: eng page: 144-155 place: Cham project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '4' name: SFB 901 - Project Area C - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: 'Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC)' publisher: Springer International Publishing quality_controlled: '1' series_title: Lecture Notes in Computer Science (LNCS) status: public title: Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer type: conference user_id: '15278' volume: 8405 year: '2014' ... --- _id: '377' abstract: - lang: eng text: 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: - first_name: Heinrich full_name: Riebler, Heinrich id: '8961' last_name: Riebler - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: Christoph full_name: Sorge, Christoph last_name: Sorge citation: ama: 'Riebler H, Kenter T, Plessl C, Sorge C. Reconstructing AES Key Schedules from Decayed Memory with FPGAs. In: Proceedings of Field-Programmable Custom Computing Machines (FCCM). IEEE; 2014:222-229. doi:10.1109/FCCM.2014.67' apa: Riebler, H., Kenter, T., Plessl, C., & Sorge, C. (2014). Reconstructing AES Key Schedules from Decayed Memory with FPGAs. Proceedings of Field-Programmable Custom Computing Machines (FCCM), 222–229. https://doi.org/10.1109/FCCM.2014.67 bibtex: '@inproceedings{Riebler_Kenter_Plessl_Sorge_2014, title={Reconstructing AES Key Schedules from Decayed Memory with FPGAs}, DOI={10.1109/FCCM.2014.67}, booktitle={Proceedings of Field-Programmable Custom Computing Machines (FCCM)}, publisher={IEEE}, author={Riebler, Heinrich and Kenter, Tobias and Plessl, Christian and Sorge, Christoph}, year={2014}, pages={222–229} }' chicago: Riebler, Heinrich, Tobias Kenter, Christian Plessl, and Christoph Sorge. “Reconstructing AES Key Schedules from Decayed Memory with FPGAs.” In Proceedings of Field-Programmable Custom Computing Machines (FCCM), 222–29. IEEE, 2014. https://doi.org/10.1109/FCCM.2014.67. ieee: 'H. Riebler, T. Kenter, C. Plessl, and C. Sorge, “Reconstructing AES Key Schedules from Decayed Memory with FPGAs,” in Proceedings of Field-Programmable Custom Computing Machines (FCCM), 2014, pp. 222–229, doi: 10.1109/FCCM.2014.67.' mla: Riebler, Heinrich, et al. “Reconstructing AES Key Schedules from Decayed Memory with FPGAs.” Proceedings of Field-Programmable Custom Computing Machines (FCCM), IEEE, 2014, pp. 222–29, doi:10.1109/FCCM.2014.67. short: 'H. Riebler, T. Kenter, C. Plessl, C. Sorge, in: Proceedings of Field-Programmable Custom Computing Machines (FCCM), IEEE, 2014, pp. 222–229.' date_created: 2017-10-17T12:42:05Z date_updated: 2023-09-26T13:33:50Z ddc: - '040' department: - _id: '27' - _id: '518' - _id: '78' doi: 10.1109/FCCM.2014.67 file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-20T07:14:20Z date_updated: 2018-03-20T07:14:20Z file_id: '1397' file_name: 377-FCCM14.pdf file_size: 1003907 relation: main_file success: 1 file_date_updated: 2018-03-20T07:14:20Z has_accepted_license: '1' keyword: - coldboot language: - iso: eng page: 222-229 project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '4' name: SFB 901 - Project Area C - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: Proceedings of Field-Programmable Custom Computing Machines (FCCM) publisher: IEEE quality_controlled: '1' status: public title: Reconstructing AES Key Schedules from Decayed Memory with FPGAs type: conference user_id: '15278' year: '2014' ... --- _id: '1778' author: - first_name: Gianluca full_name: C. Durelli, Gianluca last_name: C. Durelli - first_name: Marcello full_name: Pogliani, Marcello last_name: Pogliani - first_name: Antonio full_name: Miele, Antonio last_name: Miele - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: Heinrich full_name: Riebler, Heinrich id: '8961' last_name: Riebler - first_name: Gavin Francis full_name: Vaz, Gavin Francis id: '30332' last_name: Vaz - first_name: Marco full_name: D. Santambrogio, Marco last_name: D. Santambrogio - first_name: Cristiana full_name: Bolchini, Cristiana last_name: Bolchini citation: ama: 'C. Durelli G, Pogliani M, Miele A, et al. Runtime Resource Management in Heterogeneous System Architectures: The SAVE Approach. In: Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA). IEEE; 2014:142-149. doi:10.1109/ISPA.2014.27' apa: 'C. Durelli, G., Pogliani, M., Miele, A., Plessl, C., Riebler, H., Vaz, G. F., D. Santambrogio, M., & Bolchini, C. (2014). Runtime Resource Management in Heterogeneous System Architectures: The SAVE Approach. Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA), 142–149. https://doi.org/10.1109/ISPA.2014.27' bibtex: '@inproceedings{C. Durelli_Pogliani_Miele_Plessl_Riebler_Vaz_D. Santambrogio_Bolchini_2014, title={Runtime Resource Management in Heterogeneous System Architectures: The SAVE Approach}, DOI={10.1109/ISPA.2014.27}, booktitle={Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA)}, publisher={IEEE}, 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}, year={2014}, pages={142–149} }' chicago: 'C. Durelli, Gianluca, Marcello Pogliani, Antonio Miele, Christian Plessl, Heinrich Riebler, Gavin Francis Vaz, Marco D. Santambrogio, and Cristiana Bolchini. “Runtime Resource Management in Heterogeneous System Architectures: The SAVE Approach.” In Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA), 142–49. IEEE, 2014. https://doi.org/10.1109/ISPA.2014.27.' ieee: 'G. C. Durelli et al., “Runtime Resource Management in Heterogeneous System Architectures: The SAVE Approach,” in Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA), 2014, pp. 142–149, doi: 10.1109/ISPA.2014.27.' mla: 'C. Durelli, Gianluca, et al. “Runtime Resource Management in Heterogeneous System Architectures: The SAVE Approach.” Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA), IEEE, 2014, pp. 142–49, doi:10.1109/ISPA.2014.27.' short: 'G. C. Durelli, M. Pogliani, A. Miele, C. Plessl, H. Riebler, G.F. Vaz, M. D. Santambrogio, C. Bolchini, in: Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA), IEEE, 2014, pp. 142–149.' date_created: 2018-03-26T13:40:14Z date_updated: 2023-09-26T13:35:40Z department: - _id: '27' - _id: '518' - _id: '78' doi: 10.1109/ISPA.2014.27 language: - iso: eng page: 142-149 project: - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA) publisher: IEEE quality_controlled: '1' status: public title: 'Runtime Resource Management in Heterogeneous System Architectures: The SAVE Approach' type: conference user_id: '15278' year: '2014' ... --- _id: '439' abstract: - lang: eng text: 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: - first_name: Gavin Francis full_name: Vaz, Gavin Francis id: '30332' last_name: Vaz - first_name: Heinrich full_name: Riebler, Heinrich id: '8961' last_name: Riebler - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Vaz GF, Riebler H, Kenter T, Plessl C. Deferring Accelerator Offloading Decisions to Application Runtime. In: Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig). IEEE; 2014:1-8. doi:10.1109/ReConFig.2014.7032509' apa: Vaz, G. F., Riebler, H., Kenter, T., & Plessl, C. (2014). Deferring Accelerator Offloading Decisions to Application Runtime. Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), 1–8. https://doi.org/10.1109/ReConFig.2014.7032509 bibtex: '@inproceedings{Vaz_Riebler_Kenter_Plessl_2014, title={Deferring Accelerator Offloading Decisions to Application Runtime}, DOI={10.1109/ReConFig.2014.7032509}, booktitle={Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)}, publisher={IEEE}, author={Vaz, Gavin Francis and Riebler, Heinrich and Kenter, Tobias and Plessl, Christian}, year={2014}, pages={1–8} }' chicago: Vaz, Gavin Francis, Heinrich Riebler, Tobias Kenter, and Christian Plessl. “Deferring Accelerator Offloading Decisions to Application Runtime.” In Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), 1–8. IEEE, 2014. https://doi.org/10.1109/ReConFig.2014.7032509. ieee: 'G. F. Vaz, H. Riebler, T. Kenter, and C. Plessl, “Deferring Accelerator Offloading Decisions to Application Runtime,” in Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), 2014, pp. 1–8, doi: 10.1109/ReConFig.2014.7032509.' mla: Vaz, Gavin Francis, et al. “Deferring Accelerator Offloading Decisions to Application Runtime.” Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), IEEE, 2014, pp. 1–8, doi:10.1109/ReConFig.2014.7032509. short: 'G.F. Vaz, H. Riebler, T. Kenter, C. Plessl, in: Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), IEEE, 2014, pp. 1–8.' date_created: 2017-10-17T12:42:17Z date_updated: 2023-09-26T13:37:02Z ddc: - '040' department: - _id: '27' - _id: '518' - _id: '78' doi: 10.1109/ReConFig.2014.7032509 file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-16T11:29:52Z date_updated: 2018-03-16T11:29:52Z file_id: '1353' file_name: 439-plessl14a_reconfig.pdf file_size: 557362 relation: main_file success: 1 file_date_updated: 2018-03-16T11:29:52Z has_accepted_license: '1' language: - iso: eng page: 1-8 project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '4' name: SFB 901 - Project Area C - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig) publisher: IEEE quality_controlled: '1' status: public title: Deferring Accelerator Offloading Decisions to Application Runtime type: conference user_id: '15278' year: '2014' ... --- _id: '406' abstract: - lang: eng text: 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: - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Henning full_name: Schmitz, Henning last_name: Schmitz - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Kenter T, Schmitz H, Plessl C. Kernel-Centric Acceleration of High Accuracy Stereo-Matching. In: Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig). IEEE; 2014:1-8. doi:10.1109/ReConFig.2014.7032535' apa: Kenter, T., Schmitz, H., & Plessl, C. (2014). Kernel-Centric Acceleration of High Accuracy Stereo-Matching. Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), 1–8. https://doi.org/10.1109/ReConFig.2014.7032535 bibtex: '@inproceedings{Kenter_Schmitz_Plessl_2014, title={Kernel-Centric Acceleration of High Accuracy Stereo-Matching}, DOI={10.1109/ReConFig.2014.7032535}, booktitle={Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)}, publisher={IEEE}, author={Kenter, Tobias and Schmitz, Henning and Plessl, Christian}, year={2014}, pages={1–8} }' chicago: Kenter, Tobias, Henning Schmitz, and Christian Plessl. “Kernel-Centric Acceleration of High Accuracy Stereo-Matching.” In Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), 1–8. IEEE, 2014. https://doi.org/10.1109/ReConFig.2014.7032535. ieee: 'T. Kenter, H. Schmitz, and C. Plessl, “Kernel-Centric Acceleration of High Accuracy Stereo-Matching,” in Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), 2014, pp. 1–8, doi: 10.1109/ReConFig.2014.7032535.' mla: Kenter, Tobias, et al. “Kernel-Centric Acceleration of High Accuracy Stereo-Matching.” Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), IEEE, 2014, pp. 1–8, doi:10.1109/ReConFig.2014.7032535. short: 'T. Kenter, H. Schmitz, C. Plessl, in: Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), IEEE, 2014, pp. 1–8.' date_created: 2017-10-17T12:42:11Z date_updated: 2023-09-26T13:36:40Z ddc: - '040' department: - _id: '27' - _id: '518' - _id: '78' doi: 10.1109/ReConFig.2014.7032535 file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-16T11:37:42Z date_updated: 2018-03-16T11:37:42Z file_id: '1366' file_name: 406-ReConFig14.pdf file_size: 932852 relation: main_file success: 1 file_date_updated: 2018-03-16T11:37:42Z has_accepted_license: '1' language: - iso: eng page: 1-8 project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '4' name: SFB 901 - Project Area C - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig) publisher: IEEE quality_controlled: '1' status: public title: Kernel-Centric Acceleration of High Accuracy Stereo-Matching type: conference user_id: '15278' year: '2014' ... --- _id: '1780' author: - first_name: Gianluca full_name: C. Durelli, Gianluca last_name: C. Durelli - first_name: Marcello full_name: Copolla, Marcello last_name: Copolla - first_name: Karim full_name: Djafarian, Karim last_name: Djafarian - first_name: George full_name: Koranaros, George last_name: Koranaros - first_name: Antonio full_name: Miele, Antonio last_name: Miele - first_name: Michele full_name: Paolino, Michele last_name: Paolino - first_name: Oliver full_name: Pell, Oliver last_name: Pell - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: Marco full_name: D. Santambrogio, Marco last_name: D. Santambrogio - first_name: Cristiana full_name: Bolchini, Cristiana last_name: Bolchini citation: ama: 'C. Durelli G, Copolla M, Djafarian K, et al. SAVE: Towards efficient resource management in heterogeneous system architectures. In: Proc. Int. Conf. on Reconfigurable Computing: Architectures, Tools and Applications (ARC). Springer; 2014. doi:10.1007/978-3-319-05960-0_38' apa: 'C. Durelli, G., Copolla, M., Djafarian, K., Koranaros, G., Miele, A., Paolino, M., Pell, O., Plessl, C., D. Santambrogio, M., & Bolchini, C. (2014). SAVE: Towards efficient resource management in heterogeneous system architectures. Proc. Int. Conf. on Reconfigurable Computing: Architectures, Tools and Applications (ARC). https://doi.org/10.1007/978-3-319-05960-0_38' bibtex: '@inproceedings{C. Durelli_Copolla_Djafarian_Koranaros_Miele_Paolino_Pell_Plessl_D. Santambrogio_Bolchini_2014, title={SAVE: Towards efficient resource management in heterogeneous system architectures}, DOI={10.1007/978-3-319-05960-0_38}, booktitle={Proc. Int. Conf. on Reconfigurable Computing: Architectures, Tools and Applications (ARC)}, publisher={Springer}, 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}, year={2014} }' chicago: 'C. Durelli, Gianluca, Marcello Copolla, Karim Djafarian, George Koranaros, Antonio Miele, Michele Paolino, Oliver Pell, Christian Plessl, Marco D. Santambrogio, and Cristiana Bolchini. “SAVE: Towards Efficient Resource Management in Heterogeneous System Architectures.” In Proc. Int. Conf. on Reconfigurable Computing: Architectures, Tools and Applications (ARC). Springer, 2014. https://doi.org/10.1007/978-3-319-05960-0_38.' ieee: 'G. C. Durelli et al., “SAVE: Towards efficient resource management in heterogeneous system architectures,” 2014, doi: 10.1007/978-3-319-05960-0_38.' mla: 'C. Durelli, Gianluca, et al. “SAVE: Towards Efficient Resource Management in Heterogeneous System Architectures.” Proc. Int. Conf. on Reconfigurable Computing: Architectures, Tools and Applications (ARC), Springer, 2014, doi:10.1007/978-3-319-05960-0_38.' short: 'G. C. Durelli, M. Copolla, K. Djafarian, G. Koranaros, A. Miele, M. Paolino, O. Pell, C. Plessl, M. D. Santambrogio, C. Bolchini, in: Proc. Int. Conf. on Reconfigurable Computing: Architectures, Tools and Applications (ARC), Springer, 2014.' date_created: 2018-03-26T13:45:35Z date_updated: 2023-09-26T13:36:20Z department: - _id: '27' - _id: '518' - _id: '78' doi: 10.1007/978-3-319-05960-0_38 language: - iso: eng project: - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: 'Proc. Int. Conf. on Reconfigurable Computing: Architectures, Tools and Applications (ARC)' publisher: Springer quality_controlled: '1' status: public title: 'SAVE: Towards efficient resource management in heterogeneous system architectures' type: conference user_id: '15278' year: '2014' ... --- _id: '1784' author: - first_name: Jürgen full_name: Kaiser, Jürgen last_name: Kaiser - first_name: Dirk full_name: Meister, Dirk last_name: Meister - first_name: Viktor full_name: Gottfried, Viktor last_name: Gottfried - first_name: André full_name: Brinkmann, André last_name: Brinkmann citation: ama: 'Kaiser J, Meister D, Gottfried V, Brinkmann A. MCD: Overcoming the Data Download Bottleneck in Data Centers. In: Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS). Washington DC, USA: IEEE Computer Society; 2013:88-97. doi:10.1109/NAS.2013.18' apa: 'Kaiser, J., Meister, D., Gottfried, V., & Brinkmann, A. (2013). MCD: Overcoming the Data Download Bottleneck in Data Centers. In Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS) (pp. 88–97). Washington DC, USA: IEEE Computer Society. https://doi.org/10.1109/NAS.2013.18' bibtex: '@inproceedings{Kaiser_Meister_Gottfried_Brinkmann_2013, place={Washington DC, USA}, title={MCD: Overcoming the Data Download Bottleneck in Data Centers}, DOI={10.1109/NAS.2013.18}, booktitle={Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS)}, publisher={IEEE Computer Society}, author={Kaiser, Jürgen and Meister, Dirk and Gottfried, Viktor and Brinkmann, André}, year={2013}, pages={88–97} }' chicago: 'Kaiser, Jürgen, Dirk Meister, Viktor Gottfried, and André Brinkmann. “MCD: Overcoming the Data Download Bottleneck in Data Centers.” In Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS), 88–97. Washington DC, USA: IEEE Computer Society, 2013. https://doi.org/10.1109/NAS.2013.18.' ieee: 'J. Kaiser, D. Meister, V. Gottfried, and A. Brinkmann, “MCD: Overcoming the Data Download Bottleneck in Data Centers,” in Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS), 2013, pp. 88–97.' mla: 'Kaiser, Jürgen, et al. “MCD: Overcoming the Data Download Bottleneck in Data Centers.” Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS), IEEE Computer Society, 2013, pp. 88–97, doi:10.1109/NAS.2013.18.' short: 'J. Kaiser, D. Meister, V. Gottfried, A. Brinkmann, in: Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS), IEEE Computer Society, Washington DC, USA, 2013, pp. 88–97.' date_created: 2018-03-26T14:43:38Z date_updated: 2022-01-06T06:53:20Z department: - _id: '27' doi: 10.1109/NAS.2013.18 page: 88-97 place: Washington DC, USA publication: Proc. IEEE Int. Conf. on Networking, Architecture and Storage (NAS) publisher: IEEE Computer Society status: public title: 'MCD: Overcoming the Data Download Bottleneck in Data Centers' type: conference user_id: '24135' year: '2013' ... --- _id: '1786' author: - first_name: Server full_name: Kasap, Server last_name: Kasap - first_name: Soydan full_name: Redif, Soydan last_name: Redif citation: ama: 'Kasap S, Redif S. FPGA Implementation of a Second-Order Convolutive Blind Signal Separation Algorithm. In: Proc. IEEE Signal Processing and Communications Conf. (SUI). IEEE; 2013. doi:10.1109/SIU.2013.6531530' apa: Kasap, S., & Redif, S. (2013). FPGA Implementation of a Second-Order Convolutive Blind Signal Separation Algorithm. In Proc. IEEE Signal Processing and Communications Conf. (SUI). IEEE. https://doi.org/10.1109/SIU.2013.6531530 bibtex: '@inproceedings{Kasap_Redif_2013, title={FPGA Implementation of a Second-Order Convolutive Blind Signal Separation Algorithm}, DOI={10.1109/SIU.2013.6531530}, booktitle={Proc. IEEE Signal Processing and Communications Conf. (SUI)}, publisher={IEEE}, author={Kasap, Server and Redif, Soydan}, year={2013} }' chicago: Kasap, Server, and Soydan Redif. “FPGA Implementation of a Second-Order Convolutive Blind Signal Separation Algorithm.” In Proc. IEEE Signal Processing and Communications Conf. (SUI). IEEE, 2013. https://doi.org/10.1109/SIU.2013.6531530. ieee: S. Kasap and S. Redif, “FPGA Implementation of a Second-Order Convolutive Blind Signal Separation Algorithm,” in Proc. IEEE Signal Processing and Communications Conf. (SUI), 2013. mla: Kasap, Server, and Soydan Redif. “FPGA Implementation of a Second-Order Convolutive Blind Signal Separation Algorithm.” Proc. IEEE Signal Processing and Communications Conf. (SUI), IEEE, 2013, doi:10.1109/SIU.2013.6531530. short: 'S. Kasap, S. Redif, in: Proc. IEEE Signal Processing and Communications Conf. (SUI), IEEE, 2013.' date_created: 2018-03-26T14:48:53Z date_updated: 2022-01-06T06:53:20Z department: - _id: '27' - _id: '78' doi: 10.1109/SIU.2013.6531530 publication: Proc. IEEE Signal Processing and Communications Conf. (SUI) publisher: IEEE status: public title: FPGA Implementation of a Second-Order Convolutive Blind Signal Separation Algorithm type: conference user_id: '24135' year: '2013' ... --- _id: '1788' author: - first_name: Petra full_name: Berenbrink, Petra last_name: Berenbrink - first_name: André full_name: Brinkmann, André last_name: Brinkmann - first_name: Tom full_name: Friedetzky, Tom last_name: Friedetzky - first_name: Dirk full_name: Meister, Dirk last_name: Meister - first_name: Lars full_name: Nagel, Lars last_name: Nagel citation: ama: 'Berenbrink P, Brinkmann A, Friedetzky T, Meister D, Nagel L. Distributing Storage in Cloud Environments. In: Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW). IEEE; 2013. doi:10.1109/IPDPSW.2013.148' apa: Berenbrink, P., Brinkmann, A., Friedetzky, T., Meister, D., & Nagel, L. (2013). Distributing Storage in Cloud Environments. In Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW). IEEE. https://doi.org/10.1109/IPDPSW.2013.148 bibtex: '@inproceedings{Berenbrink_Brinkmann_Friedetzky_Meister_Nagel_2013, title={Distributing Storage in Cloud Environments}, DOI={10.1109/IPDPSW.2013.148}, booktitle={Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW)}, publisher={IEEE}, author={Berenbrink, Petra and Brinkmann, André and Friedetzky, Tom and Meister, Dirk and Nagel, Lars}, year={2013} }' chicago: Berenbrink, Petra, André Brinkmann, Tom Friedetzky, Dirk Meister, and Lars Nagel. “Distributing Storage in Cloud Environments.” In Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW). IEEE, 2013. https://doi.org/10.1109/IPDPSW.2013.148. ieee: P. Berenbrink, A. Brinkmann, T. Friedetzky, D. Meister, and L. Nagel, “Distributing Storage in Cloud Environments,” in Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW), 2013. mla: Berenbrink, Petra, et al. “Distributing Storage in Cloud Environments.” Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW), IEEE, 2013, doi:10.1109/IPDPSW.2013.148. short: 'P. Berenbrink, A. Brinkmann, T. Friedetzky, D. Meister, L. Nagel, in: Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW), IEEE, 2013.' date_created: 2018-03-26T14:52:56Z date_updated: 2022-01-06T06:53:22Z department: - _id: '27' doi: 10.1109/IPDPSW.2013.148 publication: Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW) publisher: IEEE status: public title: Distributing Storage in Cloud Environments type: conference user_id: '24135' year: '2013' ... --- _id: '1793' author: - first_name: Dirk full_name: Meister, Dirk last_name: Meister - first_name: André full_name: Brinkmann, André last_name: Brinkmann - first_name: Tim full_name: Süß, Tim last_name: Süß citation: ama: 'Meister D, Brinkmann A, Süß T. File Recipe Compression in Data Deduplication Systems. In: Proc. USENIX Conference on File and Storage Technologies (FAST). USENIX Association; 2013:175-182.' apa: Meister, D., Brinkmann, A., & Süß, T. (2013). File Recipe Compression in Data Deduplication Systems. In Proc. USENIX Conference on File and Storage Technologies (FAST) (pp. 175–182). USENIX Association. bibtex: '@inproceedings{Meister_Brinkmann_Süß_2013, title={File Recipe Compression in Data Deduplication Systems}, booktitle={Proc. USENIX Conference on File and Storage Technologies (FAST)}, publisher={USENIX Association}, author={Meister, Dirk and Brinkmann, André and Süß, Tim}, year={2013}, pages={175–182} }' chicago: Meister, Dirk, André Brinkmann, and Tim Süß. “File Recipe Compression in Data Deduplication Systems.” In Proc. USENIX Conference on File and Storage Technologies (FAST), 175–82. USENIX Association, 2013. ieee: D. Meister, A. Brinkmann, and T. Süß, “File Recipe Compression in Data Deduplication Systems,” in Proc. USENIX Conference on File and Storage Technologies (FAST), 2013, pp. 175–182. mla: Meister, Dirk, et al. “File Recipe Compression in Data Deduplication Systems.” Proc. USENIX Conference on File and Storage Technologies (FAST), USENIX Association, 2013, pp. 175–82. short: 'D. Meister, A. Brinkmann, T. Süß, in: Proc. USENIX Conference on File and Storage Technologies (FAST), USENIX Association, 2013, pp. 175–182.' date_created: 2018-03-26T15:16:03Z date_updated: 2022-01-06T06:53:23Z department: - _id: '27' page: 175-182 publication: Proc. USENIX Conference on File and Storage Technologies (FAST) publisher: USENIX Association status: public title: File Recipe Compression in Data Deduplication Systems type: conference user_id: '24135' year: '2013' ... --- _id: '528' abstract: - lang: eng text: 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: - first_name: Heinrich full_name: Riebler, Heinrich id: '8961' last_name: Riebler - first_name: Tobias full_name: Kenter, Tobias id: '3145' last_name: Kenter - first_name: Christoph full_name: Sorge, Christoph last_name: Sorge - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Riebler H, Kenter T, Sorge C, Plessl C. FPGA-accelerated Key Search for Cold-Boot Attacks against AES. In: Proceedings of the International Conference on Field-Programmable Technology (FPT). IEEE; 2013:386-389. doi:10.1109/FPT.2013.6718394' apa: Riebler, H., Kenter, T., Sorge, C., & Plessl, C. (2013). FPGA-accelerated Key Search for Cold-Boot Attacks against AES. Proceedings of the International Conference on Field-Programmable Technology (FPT), 386–389. https://doi.org/10.1109/FPT.2013.6718394 bibtex: '@inproceedings{Riebler_Kenter_Sorge_Plessl_2013, title={FPGA-accelerated Key Search for Cold-Boot Attacks against AES}, DOI={10.1109/FPT.2013.6718394}, booktitle={Proceedings of the International Conference on Field-Programmable Technology (FPT)}, publisher={IEEE}, author={Riebler, Heinrich and Kenter, Tobias and Sorge, Christoph and Plessl, Christian}, year={2013}, pages={386–389} }' chicago: Riebler, Heinrich, Tobias Kenter, Christoph Sorge, and Christian Plessl. “FPGA-Accelerated Key Search for Cold-Boot Attacks against AES.” In Proceedings of the International Conference on Field-Programmable Technology (FPT), 386–89. IEEE, 2013. https://doi.org/10.1109/FPT.2013.6718394. ieee: 'H. Riebler, T. Kenter, C. Sorge, and C. Plessl, “FPGA-accelerated Key Search for Cold-Boot Attacks against AES,” in Proceedings of the International Conference on Field-Programmable Technology (FPT), 2013, pp. 386–389, doi: 10.1109/FPT.2013.6718394.' mla: Riebler, Heinrich, et al. “FPGA-Accelerated Key Search for Cold-Boot Attacks against AES.” Proceedings of the International Conference on Field-Programmable Technology (FPT), IEEE, 2013, pp. 386–89, doi:10.1109/FPT.2013.6718394. short: 'H. Riebler, T. Kenter, C. Sorge, C. Plessl, in: Proceedings of the International Conference on Field-Programmable Technology (FPT), IEEE, 2013, pp. 386–389.' date_created: 2017-10-17T12:42:35Z date_updated: 2023-09-26T13:37:35Z ddc: - '040' department: - _id: '27' - _id: '518' - _id: '78' doi: 10.1109/FPT.2013.6718394 file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-15T10:36:08Z date_updated: 2018-03-15T10:36:08Z file_id: '1294' file_name: 528-plessl13_fpt.pdf file_size: 822680 relation: main_file success: 1 file_date_updated: 2018-03-15T10:36:08Z has_accepted_license: '1' keyword: - coldboot language: - iso: eng page: 386-389 project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '13' name: SFB 901 - Subproject C1 - _id: '4' name: SFB 901 - Project Area C - _id: '34' grant_number: '610996' name: Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures publication: Proceedings of the International Conference on Field-Programmable Technology (FPT) publisher: IEEE quality_controlled: '1' status: public title: FPGA-accelerated Key Search for Cold-Boot Attacks against AES type: conference user_id: '15278' year: '2013' ... --- _id: '505' abstract: - lang: eng text: 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: - first_name: Markus full_name: Happe, Markus last_name: Happe - first_name: Peter full_name: Kling, Peter last_name: Kling - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: Marco full_name: Platzner, Marco id: '398' last_name: Platzner - first_name: Friedhelm full_name: Meyer auf der Heide, Friedhelm id: '15523' last_name: Meyer auf der Heide citation: ama: 'Happe M, Kling P, Plessl C, Platzner M, Meyer auf der Heide F. On-The-Fly Computing: A Novel Paradigm for Individualized IT Services. In: Proceedings of the 9th IEEE Workshop on Software Technology for Future Embedded and Ubiquitous Systems (SEUS). IEEE; 2013. doi:10.1109/ISORC.2013.6913232' apa: 'Happe, M., Kling, P., Plessl, C., Platzner, M., & Meyer auf der Heide, F. (2013). On-The-Fly Computing: A Novel Paradigm for Individualized IT Services. Proceedings of the 9th IEEE Workshop on Software Technology for Future Embedded and Ubiquitous Systems (SEUS). https://doi.org/10.1109/ISORC.2013.6913232' bibtex: '@inproceedings{Happe_Kling_Plessl_Platzner_Meyer auf der Heide_2013, title={On-The-Fly Computing: A Novel Paradigm for Individualized IT Services}, DOI={10.1109/ISORC.2013.6913232}, booktitle={Proceedings of the 9th IEEE Workshop on Software Technology for Future embedded and Ubiquitous Systems (SEUS)}, publisher={IEEE}, author={Happe, Markus and Kling, Peter and Plessl, Christian and Platzner, Marco and Meyer auf der Heide, Friedhelm}, year={2013} }' chicago: 'Happe, Markus, Peter Kling, Christian Plessl, Marco Platzner, and Friedhelm Meyer auf der Heide. “On-The-Fly Computing: A Novel Paradigm for Individualized IT Services.” In Proceedings of the 9th IEEE Workshop on Software Technology for Future Embedded and Ubiquitous Systems (SEUS). IEEE, 2013. https://doi.org/10.1109/ISORC.2013.6913232.' ieee: 'M. Happe, P. Kling, C. Plessl, M. Platzner, and F. Meyer auf der Heide, “On-The-Fly Computing: A Novel Paradigm for Individualized IT Services,” 2013, doi: 10.1109/ISORC.2013.6913232.' mla: 'Happe, Markus, et al. “On-The-Fly Computing: A Novel Paradigm for Individualized IT Services.” Proceedings of the 9th IEEE Workshop on Software Technology for Future Embedded and Ubiquitous Systems (SEUS), IEEE, 2013, doi:10.1109/ISORC.2013.6913232.' short: 'M. Happe, P. Kling, C. Plessl, M. Platzner, F. Meyer auf der Heide, in: Proceedings of the 9th IEEE Workshop on Software Technology for Future Embedded and Ubiquitous Systems (SEUS), IEEE, 2013.' date_created: 2017-10-17T12:42:30Z date_updated: 2023-09-26T13:38:20Z ddc: - '040' department: - _id: '63' - _id: '27' - _id: '518' - _id: '78' doi: 10.1109/ISORC.2013.6913232 file: - access_level: closed content_type: application/pdf creator: florida date_created: 2018-03-15T13:38:56Z date_updated: 2018-03-15T13:38:56Z file_id: '1308' file_name: 505-Plessl13_seus.pdf file_size: 1040834 relation: main_file success: 1 file_date_updated: 2018-03-15T13:38:56Z has_accepted_license: '1' language: - iso: eng project: - _id: '1' grant_number: '160364472' name: SFB 901 - _id: '14' grant_number: '160364472' name: SFB 901 - Subprojekt C2 - _id: '4' name: SFB 901 - Project Area C publication: Proceedings of the 9th IEEE Workshop on Software Technology for Future embedded and Ubiquitous Systems (SEUS) publisher: IEEE quality_controlled: '1' status: public title: 'On-The-Fly Computing: A Novel Paradigm for Individualized IT Services' type: conference user_id: '15278' year: '2013' ... --- _id: '1787' author: - first_name: Tim full_name: Suess, Tim last_name: Suess - first_name: Andrew full_name: Schoenrock, Andrew last_name: Schoenrock - first_name: Sebastian full_name: Meisner, Sebastian last_name: Meisner - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 citation: ama: 'Suess T, Schoenrock A, Meisner S, Plessl C. Parallel Macro Pipelining on the Intel SCC Many-Core Computer. In: Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW). IEEE Computer Society; 2013:64-73. doi:10.1109/IPDPSW.2013.136' apa: Suess, T., Schoenrock, A., Meisner, S., & Plessl, C. (2013). Parallel Macro Pipelining on the Intel SCC Many-Core Computer. Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW), 64–73. https://doi.org/10.1109/IPDPSW.2013.136 bibtex: '@inproceedings{Suess_Schoenrock_Meisner_Plessl_2013, place={Washington, DC, USA}, title={Parallel Macro Pipelining on the Intel SCC Many-Core Computer}, DOI={10.1109/IPDPSW.2013.136}, booktitle={Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW)}, publisher={IEEE Computer Society}, author={Suess, Tim and Schoenrock, Andrew and Meisner, Sebastian and Plessl, Christian}, year={2013}, pages={64–73} }' chicago: 'Suess, Tim, Andrew Schoenrock, Sebastian Meisner, and Christian Plessl. “Parallel Macro Pipelining on the Intel SCC Many-Core Computer.” In Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW), 64–73. Washington, DC, USA: IEEE Computer Society, 2013. https://doi.org/10.1109/IPDPSW.2013.136.' ieee: 'T. Suess, A. Schoenrock, S. Meisner, and C. Plessl, “Parallel Macro Pipelining on the Intel SCC Many-Core Computer,” in Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW), 2013, pp. 64–73, doi: 10.1109/IPDPSW.2013.136.' mla: Suess, Tim, et al. “Parallel Macro Pipelining on the Intel SCC Many-Core Computer.” Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW), IEEE Computer Society, 2013, pp. 64–73, doi:10.1109/IPDPSW.2013.136. short: 'T. Suess, A. Schoenrock, S. Meisner, C. Plessl, in: Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW), IEEE Computer Society, Washington, DC, USA, 2013, pp. 64–73.' date_created: 2018-03-26T14:51:05Z date_updated: 2023-09-26T13:38:05Z department: - _id: '27' - _id: '518' - _id: '78' - _id: '63' doi: 10.1109/IPDPSW.2013.136 language: - iso: eng page: 64-73 place: Washington, DC, USA project: - _id: '30' grant_number: 01|H11004A name: Enabling Heterogeneous Hardware Acceleration using Novel Programming and Scheduling Models publication: Proc. Int. Symp. on Parallel and Distributed Processing Workshops (IPDPSW) publication_identifier: isbn: - 978-0-7695-4979-8 publisher: IEEE Computer Society quality_controlled: '1' status: public title: Parallel Macro Pipelining on the Intel SCC Many-Core Computer type: conference user_id: '15278' year: '2013' ... --- _id: '2097' author: - first_name: Server full_name: Kasap, Server last_name: Kasap - first_name: Soydan full_name: Redif, Soydan last_name: Redif citation: ama: 'Kasap S, Redif S. FPGA-based design and implementation of an approximate polynomial matrix EVD algorithm. In: Proc. Int. Conf. on Field Programmable Technology (ICFPT). IEEE Computer Society; 2012:135-140. doi:10.1109/FPT.2012.6412125' apa: Kasap, S., & Redif, S. (2012). FPGA-based design and implementation of an approximate polynomial matrix EVD algorithm. In Proc. Int. Conf. on Field Programmable Technology (ICFPT) (pp. 135–140). IEEE Computer Society. https://doi.org/10.1109/FPT.2012.6412125 bibtex: '@inproceedings{Kasap_Redif_2012, title={FPGA-based design and implementation of an approximate polynomial matrix EVD algorithm}, DOI={10.1109/FPT.2012.6412125}, booktitle={Proc. Int. Conf. on Field Programmable Technology (ICFPT)}, publisher={IEEE Computer Society}, author={Kasap, Server and Redif, Soydan}, year={2012}, pages={135–140} }' chicago: Kasap, Server, and Soydan Redif. “FPGA-Based Design and Implementation of an Approximate Polynomial Matrix EVD Algorithm.” In Proc. Int. Conf. on Field Programmable Technology (ICFPT), 135–40. IEEE Computer Society, 2012. https://doi.org/10.1109/FPT.2012.6412125. ieee: S. Kasap and S. Redif, “FPGA-based design and implementation of an approximate polynomial matrix EVD algorithm,” in Proc. Int. Conf. on Field Programmable Technology (ICFPT), 2012, pp. 135–140. mla: Kasap, Server, and Soydan Redif. “FPGA-Based Design and Implementation of an Approximate Polynomial Matrix EVD Algorithm.” Proc. Int. Conf. on Field Programmable Technology (ICFPT), IEEE Computer Society, 2012, pp. 135–40, doi:10.1109/FPT.2012.6412125. short: 'S. Kasap, S. Redif, in: Proc. Int. Conf. on Field Programmable Technology (ICFPT), IEEE Computer Society, 2012, pp. 135–140.' date_created: 2018-03-29T14:34:48Z date_updated: 2022-01-06T06:54:42Z department: - _id: '27' - _id: '78' doi: 10.1109/FPT.2012.6412125 page: 135-140 publication: Proc. Int. Conf. on Field Programmable Technology (ICFPT) publisher: IEEE Computer Society status: public title: FPGA-based design and implementation of an approximate polynomial matrix EVD algorithm type: conference user_id: '24135' year: '2012' ... --- _id: '2098' author: - first_name: Jürgen full_name: Kaiser, Jürgen last_name: Kaiser - first_name: Dirk full_name: Meister, Dirk last_name: Meister - first_name: Tim full_name: Hartung, Tim last_name: Hartung - first_name: André full_name: Brinkmann, André last_name: Brinkmann citation: ama: 'Kaiser J, Meister D, Hartung T, Brinkmann A. ESB: Ext2 Split Block Device. In: Proc. IEEE Int. Conf. on Parallel and Distributed Systems (ICPADS). IEEE; 2012:181-188. doi:10.1109/ICPADS.2012.34' apa: 'Kaiser, J., Meister, D., Hartung, T., & Brinkmann, A. (2012). ESB: Ext2 Split Block Device. In Proc. IEEE Int. Conf. on Parallel and Distributed Systems (ICPADS) (pp. 181–188). IEEE. https://doi.org/10.1109/ICPADS.2012.34' bibtex: '@inproceedings{Kaiser_Meister_Hartung_Brinkmann_2012, title={ESB: Ext2 Split Block Device}, DOI={10.1109/ICPADS.2012.34}, booktitle={Proc. IEEE Int. Conf. on Parallel and Distributed Systems (ICPADS)}, publisher={IEEE}, author={Kaiser, Jürgen and Meister, Dirk and Hartung, Tim and Brinkmann, André}, year={2012}, pages={181–188} }' chicago: 'Kaiser, Jürgen, Dirk Meister, Tim Hartung, and André Brinkmann. “ESB: Ext2 Split Block Device.” In Proc. IEEE Int. Conf. on Parallel and Distributed Systems (ICPADS), 181–88. IEEE, 2012. https://doi.org/10.1109/ICPADS.2012.34.' ieee: 'J. Kaiser, D. Meister, T. Hartung, and A. Brinkmann, “ESB: Ext2 Split Block Device,” in Proc. IEEE Int. Conf. on Parallel and Distributed Systems (ICPADS), 2012, pp. 181–188.' mla: 'Kaiser, Jürgen, et al. “ESB: Ext2 Split Block Device.” Proc. IEEE Int. Conf. on Parallel and Distributed Systems (ICPADS), IEEE, 2012, pp. 181–88, doi:10.1109/ICPADS.2012.34.' short: 'J. Kaiser, D. Meister, T. Hartung, A. Brinkmann, in: Proc. IEEE Int. Conf. on Parallel and Distributed Systems (ICPADS), IEEE, 2012, pp. 181–188.' date_created: 2018-03-29T14:40:04Z date_updated: 2022-01-06T06:54:42Z department: - _id: '27' doi: 10.1109/ICPADS.2012.34 page: 181-188 publication: Proc. IEEE Int. Conf. on Parallel and Distributed Systems (ICPADS) publisher: IEEE status: public title: 'ESB: Ext2 Split Block Device' type: conference user_id: '24135' year: '2012' ... --- _id: '2099' author: - first_name: Dirk full_name: Meister, Dirk last_name: Meister - first_name: Jürgen full_name: Kaiser, Jürgen last_name: Kaiser - first_name: André full_name: Brinkmann, André last_name: Brinkmann - first_name: Michael full_name: Kuhn, Michael last_name: Kuhn - first_name: Julian full_name: Kunkel, Julian last_name: Kunkel - first_name: Toni full_name: Cortes, Toni last_name: Cortes citation: ama: 'Meister D, Kaiser J, Brinkmann A, Kuhn M, Kunkel J, Cortes T. A Study on Data Deduplication in HPC Storage Systems. In: Proc. Int. Conf. on Supercomputing (SC). Los Alamitos, CA, USA: IEEE Computer Society; 2012:7:1-7:11. doi:10.1109/SC.2012.14' apa: 'Meister, D., Kaiser, J., Brinkmann, A., Kuhn, M., Kunkel, J., & Cortes, T. (2012). A Study on Data Deduplication in HPC Storage Systems. In Proc. Int. Conf. on Supercomputing (SC) (pp. 7:1-7:11). Los Alamitos, CA, USA: IEEE Computer Society. https://doi.org/10.1109/SC.2012.14' bibtex: '@inproceedings{Meister_Kaiser_Brinkmann_Kuhn_Kunkel_Cortes_2012, place={Los Alamitos, CA, USA}, title={A Study on Data Deduplication in HPC Storage Systems}, DOI={10.1109/SC.2012.14}, booktitle={Proc. Int. Conf. on Supercomputing (SC)}, publisher={IEEE Computer Society}, author={Meister, Dirk and Kaiser, Jürgen and Brinkmann, André and Kuhn, Michael and Kunkel, Julian and Cortes, Toni}, year={2012}, pages={7:1-7:11} }' chicago: 'Meister, Dirk, Jürgen Kaiser, André Brinkmann, Michael Kuhn, Julian Kunkel, and Toni Cortes. “A Study on Data Deduplication in HPC Storage Systems.” In Proc. Int. Conf. on Supercomputing (SC), 7:1-7:11. Los Alamitos, CA, USA: IEEE Computer Society, 2012. https://doi.org/10.1109/SC.2012.14.' ieee: D. Meister, J. Kaiser, A. Brinkmann, M. Kuhn, J. Kunkel, and T. Cortes, “A Study on Data Deduplication in HPC Storage Systems,” in Proc. Int. Conf. on Supercomputing (SC), 2012, pp. 7:1-7:11. mla: Meister, Dirk, et al. “A Study on Data Deduplication in HPC Storage Systems.” Proc. Int. Conf. on Supercomputing (SC), IEEE Computer Society, 2012, pp. 7:1-7:11, doi:10.1109/SC.2012.14. short: 'D. Meister, J. Kaiser, A. Brinkmann, M. Kuhn, J. Kunkel, T. Cortes, in: Proc. Int. Conf. on Supercomputing (SC), IEEE Computer Society, Los Alamitos, CA, USA, 2012, pp. 7:1-7:11.' date_created: 2018-03-29T14:41:55Z date_updated: 2022-01-06T06:54:42Z department: - _id: '27' doi: 10.1109/SC.2012.14 page: 7:1-7:11 place: Los Alamitos, CA, USA publication: Proc. Int. Conf. on Supercomputing (SC) publisher: IEEE Computer Society status: public title: A Study on Data Deduplication in HPC Storage Systems type: conference user_id: '24135' year: '2012' ... --- _id: '2100' author: - first_name: Server full_name: Kasap, Server last_name: Kasap - first_name: Soydan full_name: Redif, Soydan last_name: Redif citation: ama: 'Kasap S, Redif S. FPGA implementation of a second-order convolutive blind signal separation algorithm. In: Int. Architecture and Engineering Symp. (ARCHENG). ; 2012.' apa: Kasap, S., & Redif, S. (2012). FPGA implementation of a second-order convolutive blind signal separation algorithm. In Int. Architecture and Engineering Symp. (ARCHENG). bibtex: '@inproceedings{Kasap_Redif_2012, title={FPGA implementation of a second-order convolutive blind signal separation algorithm}, booktitle={Int. Architecture and Engineering Symp. (ARCHENG)}, author={Kasap, Server and Redif, Soydan}, year={2012} }' chicago: Kasap, Server, and Soydan Redif. “FPGA Implementation of a Second-Order Convolutive Blind Signal Separation Algorithm.” In Int. Architecture and Engineering Symp. (ARCHENG), 2012. ieee: S. Kasap and S. Redif, “FPGA implementation of a second-order convolutive blind signal separation algorithm,” in Int. Architecture and Engineering Symp. (ARCHENG), 2012. mla: Kasap, Server, and Soydan Redif. “FPGA Implementation of a Second-Order Convolutive Blind Signal Separation Algorithm.” Int. Architecture and Engineering Symp. (ARCHENG), 2012. short: 'S. Kasap, S. Redif, in: Int. Architecture and Engineering Symp. (ARCHENG), 2012.' date_created: 2018-03-29T14:43:18Z date_updated: 2022-01-06T06:54:42Z department: - _id: '27' - _id: '78' publication: Int. Architecture and Engineering Symp. (ARCHENG) status: public title: FPGA implementation of a second-order convolutive blind signal separation algorithm type: conference user_id: '24135' year: '2012' ... --- _id: '2101' author: - first_name: Matthias full_name: Grawinkel, Matthias last_name: Grawinkel - first_name: Tim full_name: Süß, Tim last_name: Süß - first_name: Georg full_name: Best, Georg last_name: Best - first_name: Ivan full_name: Popov, Ivan last_name: Popov - first_name: André full_name: Brinkmann, André last_name: Brinkmann citation: ama: 'Grawinkel M, Süß T, Best G, Popov I, Brinkmann A. Towards Dynamic Scripted pNFS Layouts. In: Proc. Parallel Data Storage Workshop (PDSW). IEEE; 2012:13-17. doi:10.1109/SC.Companion.2012.13' apa: Grawinkel, M., Süß, T., Best, G., Popov, I., & Brinkmann, A. (2012). Towards Dynamic Scripted pNFS Layouts. In Proc. Parallel Data Storage Workshop (PDSW) (pp. 13–17). IEEE. https://doi.org/10.1109/SC.Companion.2012.13 bibtex: '@inproceedings{Grawinkel_Süß_Best_Popov_Brinkmann_2012, title={Towards Dynamic Scripted pNFS Layouts}, DOI={10.1109/SC.Companion.2012.13}, booktitle={Proc. Parallel Data Storage Workshop (PDSW)}, publisher={IEEE}, author={Grawinkel, Matthias and Süß, Tim and Best, Georg and Popov, Ivan and Brinkmann, André}, year={2012}, pages={13–17} }' chicago: Grawinkel, Matthias, Tim Süß, Georg Best, Ivan Popov, and André Brinkmann. “Towards Dynamic Scripted PNFS Layouts.” In Proc. Parallel Data Storage Workshop (PDSW), 13–17. IEEE, 2012. https://doi.org/10.1109/SC.Companion.2012.13. ieee: M. Grawinkel, T. Süß, G. Best, I. Popov, and A. Brinkmann, “Towards Dynamic Scripted pNFS Layouts,” in Proc. Parallel Data Storage Workshop (PDSW), 2012, pp. 13–17. mla: Grawinkel, Matthias, et al. “Towards Dynamic Scripted PNFS Layouts.” Proc. Parallel Data Storage Workshop (PDSW), IEEE, 2012, pp. 13–17, doi:10.1109/SC.Companion.2012.13. short: 'M. Grawinkel, T. Süß, G. Best, I. Popov, A. Brinkmann, in: Proc. Parallel Data Storage Workshop (PDSW), IEEE, 2012, pp. 13–17.' date_created: 2018-03-29T14:44:24Z date_updated: 2022-01-06T06:54:42Z department: - _id: '27' doi: 10.1109/SC.Companion.2012.13 page: 13-17 publication: Proc. Parallel Data Storage Workshop (PDSW) publisher: IEEE status: public title: Towards Dynamic Scripted pNFS Layouts type: conference user_id: '24135' year: '2012' ... --- _id: '2103' author: - first_name: Martin full_name: Wistuba, Martin last_name: Wistuba - first_name: Lars full_name: Schaefers, Lars last_name: Schaefers - first_name: Marco full_name: Platzner, Marco id: '398' last_name: Platzner citation: ama: 'Wistuba M, Schaefers L, Platzner M. Comparison of Bayesian Move Prediction Systems for Computer Go. In: Proc. IEEE Conf. on Computational Intelligence and Games (CIG). IEEE; 2012:91-99. doi:10.1109/CIG.2012.6374143' apa: Wistuba, M., Schaefers, L., & Platzner, M. (2012). Comparison of Bayesian Move Prediction Systems for Computer Go. In Proc. IEEE Conf. on Computational Intelligence and Games (CIG) (pp. 91–99). IEEE. https://doi.org/10.1109/CIG.2012.6374143 bibtex: '@inproceedings{Wistuba_Schaefers_Platzner_2012, title={Comparison of Bayesian Move Prediction Systems for Computer Go}, DOI={10.1109/CIG.2012.6374143}, booktitle={Proc. IEEE Conf. on Computational Intelligence and Games (CIG)}, publisher={IEEE}, author={Wistuba, Martin and Schaefers, Lars and Platzner, Marco}, year={2012}, pages={91–99} }' chicago: Wistuba, Martin, Lars Schaefers, and Marco Platzner. “Comparison of Bayesian Move Prediction Systems for Computer Go.” In Proc. IEEE Conf. on Computational Intelligence and Games (CIG), 91–99. IEEE, 2012. https://doi.org/10.1109/CIG.2012.6374143. ieee: M. Wistuba, L. Schaefers, and M. Platzner, “Comparison of Bayesian Move Prediction Systems for Computer Go,” in Proc. IEEE Conf. on Computational Intelligence and Games (CIG), 2012, pp. 91–99. mla: Wistuba, Martin, et al. “Comparison of Bayesian Move Prediction Systems for Computer Go.” Proc. IEEE Conf. on Computational Intelligence and Games (CIG), IEEE, 2012, pp. 91–99, doi:10.1109/CIG.2012.6374143. short: 'M. Wistuba, L. Schaefers, M. Platzner, in: Proc. IEEE Conf. on Computational Intelligence and Games (CIG), IEEE, 2012, pp. 91–99.' date_created: 2018-03-29T14:59:35Z date_updated: 2022-01-06T06:54:42Z department: - _id: '27' - _id: '78' doi: 10.1109/CIG.2012.6374143 page: 91-99 publication: Proc. IEEE Conf. on Computational Intelligence and Games (CIG) publisher: IEEE status: public title: Comparison of Bayesian Move Prediction Systems for Computer Go type: conference user_id: '24135' year: '2012' ... --- _id: '2104' author: - first_name: Tobias full_name: Schlemmer, Tobias last_name: Schlemmer - first_name: Richard full_name: Grunzke, Richard last_name: Grunzke - first_name: Sandra full_name: Gesing, Sandra last_name: Gesing - first_name: Jens full_name: Krüger, Jens last_name: Krüger - first_name: Georg full_name: Birkenheuer, Georg last_name: Birkenheuer - first_name: Ralph full_name: Müller-Pfefferkorn, Ralph last_name: Müller-Pfefferkorn - first_name: Oliver full_name: Kohlbacher, Oliver last_name: Kohlbacher citation: ama: 'Schlemmer T, Grunzke R, Gesing S, et al. Generic User Management for Science Gateways via Virtual Organizations. In: Proc. EGI Technical Forum. ; 2012.' apa: Schlemmer, T., Grunzke, R., Gesing, S., Krüger, J., Birkenheuer, G., Müller-Pfefferkorn, R., & Kohlbacher, O. (2012). Generic User Management for Science Gateways via Virtual Organizations. In Proc. EGI Technical Forum. bibtex: '@inproceedings{Schlemmer_Grunzke_Gesing_Krüger_Birkenheuer_Müller-Pfefferkorn_Kohlbacher_2012, title={Generic User Management for Science Gateways via Virtual Organizations}, booktitle={Proc. EGI Technical Forum}, author={Schlemmer, Tobias and Grunzke, Richard and Gesing, Sandra and Krüger, Jens and Birkenheuer, Georg and Müller-Pfefferkorn, Ralph and Kohlbacher, Oliver}, year={2012} }' chicago: Schlemmer, Tobias, Richard Grunzke, Sandra Gesing, Jens Krüger, Georg Birkenheuer, Ralph Müller-Pfefferkorn, and Oliver Kohlbacher. “Generic User Management for Science Gateways via Virtual Organizations.” In Proc. EGI Technical Forum, 2012. ieee: T. Schlemmer et al., “Generic User Management for Science Gateways via Virtual Organizations,” in Proc. EGI Technical Forum, 2012. mla: Schlemmer, Tobias, et al. “Generic User Management for Science Gateways via Virtual Organizations.” Proc. EGI Technical Forum, 2012. short: 'T. Schlemmer, R. Grunzke, S. Gesing, J. Krüger, G. Birkenheuer, R. Müller-Pfefferkorn, O. Kohlbacher, in: Proc. EGI Technical Forum, 2012.' date_created: 2018-03-29T15:00:48Z date_updated: 2022-01-06T06:54:42Z department: - _id: '27' publication: Proc. EGI Technical Forum status: public title: Generic User Management for Science Gateways via Virtual Organizations type: conference user_id: '24135' year: '2012' ... --- _id: '2105' author: - first_name: Giuseppe full_name: Congiu, Giuseppe last_name: Congiu - first_name: Matthias full_name: Grawinkel, Matthias last_name: Grawinkel - first_name: Sai full_name: Narasimhamurthy, Sai last_name: Narasimhamurthy - first_name: André full_name: Brinkmann, André last_name: Brinkmann citation: ama: 'Congiu G, Grawinkel M, Narasimhamurthy S, Brinkmann A. One Phase Commit: A Low Overhead Atomic Commitment Protocol for Scalable Metadata Services. In: Proc. Workshop on Interfaces and Architectures for Scientific Data Storage (IASDS). IEEE; 2012:16-24. doi:10.1109/ClusterW.2012.16' apa: 'Congiu, G., Grawinkel, M., Narasimhamurthy, S., & Brinkmann, A. (2012). One Phase Commit: A Low Overhead Atomic Commitment Protocol for Scalable Metadata Services. In Proc. Workshop on Interfaces and Architectures for Scientific Data Storage (IASDS) (pp. 16–24). IEEE. https://doi.org/10.1109/ClusterW.2012.16' bibtex: '@inproceedings{Congiu_Grawinkel_Narasimhamurthy_Brinkmann_2012, title={One Phase Commit: A Low Overhead Atomic Commitment Protocol for Scalable Metadata Services}, DOI={10.1109/ClusterW.2012.16}, booktitle={Proc. Workshop on Interfaces and Architectures for Scientific Data Storage (IASDS)}, publisher={IEEE}, author={Congiu, Giuseppe and Grawinkel, Matthias and Narasimhamurthy, Sai and Brinkmann, André}, year={2012}, pages={16–24} }' chicago: 'Congiu, Giuseppe, Matthias Grawinkel, Sai Narasimhamurthy, and André Brinkmann. “One Phase Commit: A Low Overhead Atomic Commitment Protocol for Scalable Metadata Services.” In Proc. Workshop on Interfaces and Architectures for Scientific Data Storage (IASDS), 16–24. IEEE, 2012. https://doi.org/10.1109/ClusterW.2012.16.' ieee: 'G. Congiu, M. Grawinkel, S. Narasimhamurthy, and A. Brinkmann, “One Phase Commit: A Low Overhead Atomic Commitment Protocol for Scalable Metadata Services,” in Proc. Workshop on Interfaces and Architectures for Scientific Data Storage (IASDS), 2012, pp. 16–24.' mla: 'Congiu, Giuseppe, et al. “One Phase Commit: A Low Overhead Atomic Commitment Protocol for Scalable Metadata Services.” Proc. Workshop on Interfaces and Architectures for Scientific Data Storage (IASDS), IEEE, 2012, pp. 16–24, doi:10.1109/ClusterW.2012.16.' short: 'G. Congiu, M. Grawinkel, S. Narasimhamurthy, A. Brinkmann, in: Proc. Workshop on Interfaces and Architectures for Scientific Data Storage (IASDS), IEEE, 2012, pp. 16–24.' date_created: 2018-03-29T15:02:15Z date_updated: 2022-01-06T06:54:42Z department: - _id: '27' doi: 10.1109/ClusterW.2012.16 page: 16-24 publication: Proc. Workshop on Interfaces and Architectures for Scientific Data Storage (IASDS) publisher: IEEE status: public title: 'One Phase Commit: A Low Overhead Atomic Commitment Protocol for Scalable Metadata Services' type: conference user_id: '24135' year: '2012' ... --- _id: '2107' author: - first_name: Richard full_name: Grunzke, Richard last_name: Grunzke - first_name: Georg full_name: Birkenheuer, Georg last_name: Birkenheuer - first_name: Dirk full_name: Blunk, Dirk last_name: Blunk - first_name: Sebastian full_name: Breuers, Sebastian last_name: Breuers - first_name: André full_name: Brinkmann, André last_name: Brinkmann - first_name: Sandra full_name: Gesing, Sandra last_name: Gesing - first_name: Sonja full_name: Herres-Pawlis, Sonja last_name: Herres-Pawlis - first_name: Oliver full_name: Kohlbacher, Oliver last_name: Kohlbacher - first_name: Jens full_name: Krüger, Jens last_name: Krüger - first_name: Martin full_name: Kruse, Martin last_name: Kruse - first_name: Ralph full_name: Müller-Pfefferkorn, Ralph last_name: Müller-Pfefferkorn - first_name: Patrick full_name: Schäfer, Patrick last_name: Schäfer - first_name: Bernd full_name: Schuller, Bernd last_name: Schuller - first_name: Thomas full_name: Steinke, Thomas last_name: Steinke - first_name: Andreas full_name: Zink, Andreas last_name: Zink citation: ama: 'Grunzke R, Birkenheuer G, Blunk D, et al. A Data Driven Science Gateway for Computational Workflows. In: Proc. UNICORE Summit. ; 2012.' apa: Grunzke, R., Birkenheuer, G., Blunk, D., Breuers, S., Brinkmann, A., Gesing, S., … Zink, A. (2012). A Data Driven Science Gateway for Computational Workflows. In Proc. UNICORE Summit. bibtex: '@inproceedings{Grunzke_Birkenheuer_Blunk_Breuers_Brinkmann_Gesing_Herres-Pawlis_Kohlbacher_Krüger_Kruse_et al._2012, title={A Data Driven Science Gateway for Computational Workflows}, booktitle={Proc. UNICORE Summit}, 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 et al.}, year={2012} }' chicago: Grunzke, Richard, Georg Birkenheuer, Dirk Blunk, Sebastian Breuers, André Brinkmann, Sandra Gesing, Sonja Herres-Pawlis, et al. “A Data Driven Science Gateway for Computational Workflows.” In Proc. UNICORE Summit, 2012. ieee: R. Grunzke et al., “A Data Driven Science Gateway for Computational Workflows,” in Proc. UNICORE Summit, 2012. mla: Grunzke, Richard, et al. “A Data Driven Science Gateway for Computational Workflows.” Proc. UNICORE Summit, 2012. short: 'R. Grunzke, G. Birkenheuer, D. Blunk, S. Breuers, A. Brinkmann, S. Gesing, S. Herres-Pawlis, O. Kohlbacher, J. Krüger, M. Kruse, R. Müller-Pfefferkorn, P. Schäfer, B. Schuller, T. Steinke, A. Zink, in: Proc. UNICORE Summit, 2012.' date_created: 2018-03-29T15:06:46Z date_updated: 2022-01-06T06:54:44Z department: - _id: '27' - _id: '518' publication: Proc. UNICORE Summit status: public title: A Data Driven Science Gateway for Computational Workflows type: conference user_id: '24135' year: '2012' ... --- _id: '1789' author: - first_name: Jürgen full_name: Kaiser, Jürgen last_name: Kaiser - first_name: Dirk full_name: Meister, Dirk last_name: Meister - first_name: André full_name: Brinkmann, André last_name: Brinkmann - first_name: Sascha full_name: Effert, Sascha last_name: Effert citation: ama: 'Kaiser J, Meister D, Brinkmann A, Effert S. Design of an exact data deduplication cluster. In: Proc. Symp. on Mass Storage Systems and Technologies (MSST). IEEE; 2012:1-12. doi:10.1109/MSST.2012.6232380' apa: Kaiser, J., Meister, D., Brinkmann, A., & Effert, S. (2012). Design of an exact data deduplication cluster. In Proc. Symp. on Mass Storage Systems and Technologies (MSST) (pp. 1–12). IEEE. https://doi.org/10.1109/MSST.2012.6232380 bibtex: '@inproceedings{Kaiser_Meister_Brinkmann_Effert_2012, title={Design of an exact data deduplication cluster}, DOI={10.1109/MSST.2012.6232380}, booktitle={Proc. Symp. on Mass Storage Systems and Technologies (MSST)}, publisher={IEEE}, author={Kaiser, Jürgen and Meister, Dirk and Brinkmann, André and Effert, Sascha}, year={2012}, pages={1–12} }' chicago: Kaiser, Jürgen, Dirk Meister, André Brinkmann, and Sascha Effert. “Design of an Exact Data Deduplication Cluster.” In Proc. Symp. on Mass Storage Systems and Technologies (MSST), 1–12. IEEE, 2012. https://doi.org/10.1109/MSST.2012.6232380. ieee: J. Kaiser, D. Meister, A. Brinkmann, and S. Effert, “Design of an exact data deduplication cluster,” in Proc. Symp. on Mass Storage Systems and Technologies (MSST), 2012, pp. 1–12. mla: Kaiser, Jürgen, et al. “Design of an Exact Data Deduplication Cluster.” Proc. Symp. on Mass Storage Systems and Technologies (MSST), IEEE, 2012, pp. 1–12, doi:10.1109/MSST.2012.6232380. short: 'J. Kaiser, D. Meister, A. Brinkmann, S. Effert, in: Proc. Symp. on Mass Storage Systems and Technologies (MSST), IEEE, 2012, pp. 1–12.' date_created: 2018-03-26T15:12:01Z date_updated: 2022-01-06T06:53:22Z department: - _id: '27' doi: 10.1109/MSST.2012.6232380 page: 1-12 publication: Proc. Symp. on Mass Storage Systems and Technologies (MSST) publisher: IEEE status: public title: Design of an exact data deduplication cluster type: conference user_id: '24135' year: '2012' ... --- _id: '2171' author: - first_name: Sandra full_name: Gesing, Sandra last_name: Gesing - first_name: Sonja full_name: Herres-Pawlis, Sonja last_name: Herres-Pawlis - first_name: Georg full_name: Birkenheuer, Georg last_name: Birkenheuer - first_name: André full_name: Brinkmann, André last_name: Brinkmann - first_name: Richard full_name: Grunzke, Richard last_name: Grunzke - first_name: Peter full_name: Kacsuk, Peter last_name: Kacsuk - first_name: Oliver full_name: Kohlbacher, Oliver last_name: Kohlbacher - first_name: Miklos full_name: Kozlovszky, Miklos last_name: Kozlovszky - first_name: Jens full_name: Krüger, Jens last_name: Krüger - first_name: Ralph full_name: Müller-Pfefferkorn, Ralph last_name: Müller-Pfefferkorn - first_name: Patrick full_name: Schäfer, Patrick last_name: Schäfer - first_name: Thomas full_name: Steinke, Thomas last_name: Steinke citation: ama: 'Gesing S, Herres-Pawlis S, Birkenheuer G, et al. The MoSGrid Community From National to International Scale. In: Proc. EGI Community Forum. ; 2012.' apa: Gesing, S., Herres-Pawlis, S., Birkenheuer, G., Brinkmann, A., Grunzke, R., Kacsuk, P., … Steinke, T. (2012). The MoSGrid Community From National to International Scale. In Proc. EGI Community Forum. bibtex: '@inproceedings{Gesing_Herres-Pawlis_Birkenheuer_Brinkmann_Grunzke_Kacsuk_Kohlbacher_Kozlovszky_Krüger_Müller-Pfefferkorn_et al._2012, title={The MoSGrid Community From National to International Scale}, booktitle={Proc. EGI Community Forum}, 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 et al.}, year={2012} }' chicago: Gesing, Sandra, Sonja Herres-Pawlis, Georg Birkenheuer, André Brinkmann, Richard Grunzke, Peter Kacsuk, Oliver Kohlbacher, et al. “The MoSGrid Community From National to International Scale.” In Proc. EGI Community Forum, 2012. ieee: S. Gesing et al., “The MoSGrid Community From National to International Scale,” in Proc. EGI Community Forum, 2012. mla: Gesing, Sandra, et al. “The MoSGrid Community From National to International Scale.” Proc. EGI Community Forum, 2012. short: 'S. Gesing, S. Herres-Pawlis, G. Birkenheuer, A. Brinkmann, R. Grunzke, P. Kacsuk, O. Kohlbacher, M. Kozlovszky, J. Krüger, R. Müller-Pfefferkorn, P. Schäfer, T. Steinke, in: Proc. EGI Community Forum, 2012.' date_created: 2018-04-03T09:01:19Z date_updated: 2022-01-06T06:55:11Z department: - _id: '27' publication: Proc. EGI Community Forum status: public title: The MoSGrid Community From National to International Scale type: conference user_id: '24135' year: '2012' ... --- _id: '2178' author: - first_name: Sandra full_name: Gesing, Sandra last_name: Gesing - first_name: Sonja full_name: Herres-Pawlis, Sonja last_name: Herres-Pawlis - first_name: Georg full_name: Birkenheuer, Georg last_name: Birkenheuer - first_name: André full_name: Brinkmann, André last_name: Brinkmann - first_name: Richard full_name: Grunzke, Richard last_name: Grunzke - first_name: Peter full_name: Kacsuk, Peter last_name: Kacsuk - first_name: Oliver full_name: Kohlbacher, Oliver last_name: Kohlbacher - first_name: Miklos full_name: Kozlovszky, Miklos last_name: Kozlovszky - first_name: Jens full_name: Krüger, Jens last_name: Krüger - first_name: Ralph full_name: Müller-Pfefferkorn, Ralph last_name: Müller-Pfefferkorn - first_name: Patrick full_name: Schäfer, Patrick last_name: Schäfer - first_name: Thomas full_name: Steinke, Thomas last_name: Steinke citation: ama: 'Gesing S, Herres-Pawlis S, Birkenheuer G, et al. A Science Gateway Getting Ready for Serving the International Molecular Simulation Community. In: Proceedings of Science. Vol PoS(EGICF12-EMITC2)050. ; 2012.' apa: Gesing, S., Herres-Pawlis, S., Birkenheuer, G., Brinkmann, A., Grunzke, R., Kacsuk, P., … Steinke, T. (2012). A Science Gateway Getting Ready for Serving the International Molecular Simulation Community. In Proceedings of Science (Vol. PoS(EGICF12-EMITC2)050). bibtex: '@inproceedings{Gesing_Herres-Pawlis_Birkenheuer_Brinkmann_Grunzke_Kacsuk_Kohlbacher_Kozlovszky_Krüger_Müller-Pfefferkorn_et al._2012, title={A Science Gateway Getting Ready for Serving the International Molecular Simulation Community}, volume={PoS(EGICF12-EMITC2)050}, booktitle={Proceedings of Science}, 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 et al.}, year={2012} }' chicago: Gesing, Sandra, Sonja Herres-Pawlis, Georg Birkenheuer, André Brinkmann, Richard Grunzke, Peter Kacsuk, Oliver Kohlbacher, et al. “A Science Gateway Getting Ready for Serving the International Molecular Simulation Community.” In Proceedings of Science, Vol. PoS(EGICF12-EMITC2)050, 2012. ieee: S. Gesing et al., “A Science Gateway Getting Ready for Serving the International Molecular Simulation Community,” in Proceedings of Science, 2012, vol. PoS(EGICF12-EMITC2)050. mla: Gesing, Sandra, et al. “A Science Gateway Getting Ready for Serving the International Molecular Simulation Community.” Proceedings of Science, vol. PoS(EGICF12-EMITC2)050, 2012. short: 'S. Gesing, S. Herres-Pawlis, G. Birkenheuer, A. Brinkmann, R. Grunzke, P. Kacsuk, O. Kohlbacher, M. Kozlovszky, J. Krüger, R. Müller-Pfefferkorn, P. Schäfer, T. Steinke, in: Proceedings of Science, 2012.' date_created: 2018-04-03T09:15:35Z date_updated: 2022-01-06T06:55:13Z department: - _id: '27' publication: Proceedings of Science status: public title: A Science Gateway Getting Ready for Serving the International Molecular Simulation Community type: conference user_id: '24135' volume: PoS(EGICF12-EMITC2)050 year: '2012' ... --- _id: '2106' abstract: - lang: eng text: "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.\r\nIn this work we study whether the promise of effective FPGA acceleration with an OpenMP-like programming effort\r\ncan actually be held. Our target system is the Convey HC-1 reconfigurable computer for which an OpenMP-like\r\nprogramming environment exists. As case study we use an application from computational nanophotonics. Our results\r\nshow 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: - first_name: Björn full_name: Meyer, Björn last_name: Meyer - first_name: Jörn full_name: Schumacher, Jörn last_name: Schumacher - first_name: Christian full_name: Plessl, Christian id: '16153' last_name: Plessl orcid: 0000-0001-5728-9982 - first_name: Jens full_name: Förstner, Jens id: '158' last_name: Förstner orcid: 0000-0001-7059-9862 citation: ama: 'Meyer B, Schumacher J, Plessl C, Förstner J. Convey Vector Personalities – FPGA Acceleration with an OpenMP-like Effort? In: Proc. Int. Conf. on Field Programmable Logic and Applications (FPL). IEEE; 2012:189-196. doi:10.1109/FPL.2012.6339370' apa: Meyer, B., Schumacher, J., Plessl, C., & Förstner, J. (2012). Convey Vector Personalities – FPGA Acceleration with an OpenMP-like Effort? Proc. Int. Conf. on Field Programmable Logic and Applications (FPL), 189–196. https://doi.org/10.1109/FPL.2012.6339370 bibtex: '@inproceedings{Meyer_Schumacher_Plessl_Förstner_2012, title={Convey Vector Personalities – FPGA Acceleration with an OpenMP-like Effort?}, DOI={10.1109/FPL.2012.6339370}, booktitle={Proc. Int. Conf. on Field Programmable Logic and Applications (FPL)}, publisher={IEEE}, author={Meyer, Björn and Schumacher, Jörn and Plessl, Christian and Förstner, Jens}, year={2012}, pages={189–196} }' chicago: Meyer, Björn, Jörn Schumacher, Christian Plessl, and Jens Förstner. “Convey Vector Personalities – FPGA Acceleration with an OpenMP-like Effort?” In Proc. Int. Conf. on Field Programmable Logic and Applications (FPL), 189–96. IEEE, 2012. https://doi.org/10.1109/FPL.2012.6339370. ieee: 'B. Meyer, J. Schumacher, C. Plessl, and J. Förstner, “Convey Vector Personalities – FPGA Acceleration with an OpenMP-like Effort?,” in Proc. Int. Conf. on Field Programmable Logic and Applications (FPL), 2012, pp. 189–196, doi: 10.1109/FPL.2012.6339370.' mla: Meyer, Björn, et al. “Convey Vector Personalities – FPGA Acceleration with an OpenMP-like Effort?” Proc. Int. Conf. on Field Programmable Logic and Applications (FPL), IEEE, 2012, pp. 189–96, doi:10.1109/FPL.2012.6339370. short: 'B. Meyer, J. Schumacher, C. Plessl, J. Förstner, in: Proc. Int. Conf. on Field Programmable Logic and Applications (FPL), IEEE, 2012, pp. 189–196.' conference: name: 22nd International Conference on Field Programmable Logic and Applicaitons (FPL) date_created: 2018-03-29T15:04:25Z date_updated: 2023-09-26T13:39:13Z ddc: - '000' department: - _id: '27' - _id: '518' - _id: '15' - _id: '78' doi: 10.1109/FPL.2012.6339370 file: - access_level: closed content_type: application/pdf creator: fossie date_created: 2019-02-13T09:04:46Z date_updated: 2019-02-13T09:04:46Z file_id: '7638' file_name: 2012-11 Meyer,Schumacher,Plessl,Förstner_Convey vector personalities-FPGA acceleratin with an openmp-like programming effort.pdf file_size: 2148787 relation: main_file success: 1 file_date_updated: 2019-02-13T09:04:46Z has_accepted_license: '1' keyword: - funding-upb-forschungspreis - funding-maxup - tet_topic_hpc language: - iso: eng page: 189-196 publication: Proc. Int. Conf. on Field Programmable Logic and Applications (FPL) publisher: IEEE quality_controlled: '1' status: public title: Convey Vector Personalities – FPGA Acceleration with an OpenMP-like Effort? type: conference user_id: '15278' year: '2012' ...