[{"year":"2015","citation":{"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.","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.","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","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.","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."},"type":"conference","language":[{"iso":"eng"}],"date_updated":"2023-09-26T13:31:01Z","_id":"1773","doi":"10.1145/2675743.2771824","author":[{"last_name":"Schumacher","full_name":"Schumacher, Jörn","first_name":"Jörn"},{"first_name":"J.","full_name":"T. Anderson, J.","last_name":"T. Anderson"},{"last_name":"Borga","first_name":"A.","full_name":"Borga, A."},{"last_name":"Boterenbrood","first_name":"H.","full_name":"Boterenbrood, H."},{"last_name":"Chen","first_name":"H.","full_name":"Chen, H."},{"first_name":"K.","full_name":"Chen, K.","last_name":"Chen"},{"last_name":"Drake","full_name":"Drake, G.","first_name":"G."},{"last_name":"Francis","first_name":"D.","full_name":"Francis, D."},{"last_name":"Gorini","full_name":"Gorini, B.","first_name":"B."},{"first_name":"F.","full_name":"Lanni, F.","last_name":"Lanni"},{"last_name":"Lehmann-Miotto","first_name":"Giovanna","full_name":"Lehmann-Miotto, Giovanna"},{"last_name":"Levinson","full_name":"Levinson, L.","first_name":"L."},{"last_name":"Narevicius","first_name":"J.","full_name":"Narevicius, J."},{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"},{"last_name":"Roich","full_name":"Roich, A.","first_name":"A."},{"first_name":"S.","full_name":"Ryu, S.","last_name":"Ryu"},{"first_name":"F.","full_name":"P. Schreuder, F.","last_name":"P. Schreuder"},{"full_name":"Vandelli, Wainer","first_name":"Wainer","last_name":"Vandelli"},{"last_name":"Vermeulen","full_name":"Vermeulen, J.","first_name":"J."},{"last_name":"Zhang","first_name":"J.","full_name":"Zhang, J."}],"publisher":"ACM","quality_controlled":"1","publication":"Proc. Int. Conf. on Distributed Event-Based Systems (DEBS)","department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"status":"public","date_created":"2018-03-23T14:09:33Z","title":"Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm","user_id":"15278"},{"title":"Transparent offloading of computational hotspots from binary code to Xeon Phi","department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"project":[{"_id":"1","name":"SFB 901","grant_number":"160364472"},{"_id":"14","grant_number":"160364472","name":"SFB 901 - Subprojekt C2"},{"name":"SFB 901 - Project Area C","_id":"4"},{"_id":"34","grant_number":"610996","name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures"}],"date_updated":"2023-09-26T13:31:44Z","doi":"10.7873/DATE.2015.1124","language":[{"iso":"eng"}],"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."}],"user_id":"15278","ddc":["040"],"file":[{"file_name":"238-plessl15_date.pdf","date_created":"2018-03-21T10:29:49Z","access_level":"closed","creator":"florida","file_id":"1500","file_size":380552,"relation":"main_file","success":1,"content_type":"application/pdf","date_updated":"2018-03-21T10:29:49Z"}],"publication":"Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE)","file_date_updated":"2018-03-21T10:29:49Z","quality_controlled":"1","publisher":"EDA Consortium / IEEE","author":[{"full_name":"Damschen, Marvin","first_name":"Marvin","last_name":"Damschen"},{"id":"8961","last_name":"Riebler","full_name":"Riebler, Heinrich","first_name":"Heinrich"},{"last_name":"Vaz","id":"30332","first_name":"Gavin Francis","full_name":"Vaz, Gavin Francis"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"}],"date_created":"2017-10-17T12:41:38Z","has_accepted_license":"1","status":"public","_id":"238","page":"1078-1083","type":"conference","year":"2015","citation":{"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","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","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.","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} }","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.","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."}},{"date_updated":"2023-09-26T13:37:02Z","doi":"10.1109/ReConFig.2014.7032509","language":[{"iso":"eng"}],"title":"Deferring Accelerator Offloading Decisions to Application Runtime","department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"project":[{"grant_number":"160364472","name":"SFB 901","_id":"1"},{"_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"}],"_id":"439","page":"1-8","citation":{"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} }","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.","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.","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","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.","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."},"year":"2014","type":"conference","abstract":[{"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.","lang":"eng"}],"ddc":["040"],"user_id":"15278","publication":"Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)","file_date_updated":"2018-03-16T11:29:52Z","quality_controlled":"1","author":[{"first_name":"Gavin Francis","full_name":"Vaz, Gavin Francis","last_name":"Vaz","id":"30332"},{"last_name":"Riebler","id":"8961","first_name":"Heinrich","full_name":"Riebler, Heinrich"},{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"}],"publisher":"IEEE","file":[{"access_level":"closed","date_created":"2018-03-16T11:29:52Z","file_name":"439-plessl14a_reconfig.pdf","date_updated":"2018-03-16T11:29:52Z","content_type":"application/pdf","relation":"main_file","success":1,"file_size":557362,"creator":"florida","file_id":"1353"}],"date_created":"2017-10-17T12:42:17Z","status":"public","has_accepted_license":"1"},{"year":"2014","citation":{"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} }","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.","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","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.","short":"T. Kenter, H. Schmitz, C. Plessl, in: Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig), IEEE, 2014, pp. 1–8."},"type":"conference","page":"1-8","_id":"406","file":[{"file_name":"406-ReConFig14.pdf","date_created":"2018-03-16T11:37:42Z","access_level":"closed","file_id":"1366","creator":"florida","file_size":932852,"relation":"main_file","success":1,"content_type":"application/pdf","date_updated":"2018-03-16T11:37:42Z"}],"quality_controlled":"1","author":[{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"last_name":"Schmitz","first_name":"Henning","full_name":"Schmitz, Henning"},{"orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian","id":"16153","last_name":"Plessl"}],"publisher":"IEEE","file_date_updated":"2018-03-16T11:37:42Z","publication":"Proceedings of the International Conference on ReConFigurable Computing and FPGAs (ReConFig)","has_accepted_license":"1","status":"public","date_created":"2017-10-17T12:42:11Z","abstract":[{"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.","lang":"eng"}],"user_id":"15278","ddc":["040"],"language":[{"iso":"eng"}],"date_updated":"2023-09-26T13:36:40Z","doi":"10.1109/ReConFig.2014.7032535","department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"project":[{"_id":"1","name":"SFB 901","grant_number":"160364472"},{"_id":"14","name":"SFB 901 - Subprojekt C2","grant_number":"160364472"},{"_id":"4","name":"SFB 901 - Project Area C"},{"grant_number":"610996","name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","_id":"34"}],"title":"Kernel-Centric Acceleration of High Accuracy Stereo-Matching"},{"doi":"10.1007/978-3-319-09063-4_19","date_updated":"2022-01-06T06:53:20Z","_id":"1781","citation":{"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.","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.","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} }","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.","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","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."},"type":"conference","year":"2014","page":"233-243","title":"Numerical Simulation of the Damping Behavior of Particle-Filled Hollow Spheres","user_id":"24135","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."}],"editor":[{"last_name":"Bock","first_name":"Hans Georg","full_name":"Bock, Hans Georg"},{"first_name":"Xuan Phu","full_name":"Hoang, Xuan Phu","last_name":"Hoang"},{"first_name":"Rolf","full_name":"Rannacher, Rolf","last_name":"Rannacher"},{"last_name":"Schlöder","first_name":"Johannes P.","full_name":"Schlöder, Johannes P."}],"publication_identifier":{"isbn":["978-3-319-09063-4"]},"status":"public","date_created":"2018-03-26T13:47:16Z","publisher":"Springer International Publishing","author":[{"last_name":"Steinle","full_name":"Steinle, Tobias","first_name":"Tobias"},{"full_name":"Vrabec, Jadran","first_name":"Jadran","last_name":"Vrabec"},{"first_name":"Andrea","full_name":"Walther, Andrea","last_name":"Walther"}],"publication":"Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC)","department":[{"_id":"27"},{"_id":"104"},{"_id":"155"}]},{"doi":"10.1007/978-3-319-09165-5_2","issue":"8427","date_updated":"2022-01-06T06:53:20Z","_id":"1782","page":"14-25","type":"conference","year":"2014","citation":{"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.","short":"T. Graf, L. Schaefers, M. Platzner, in: Proc. Conf. on Computers and Games (CG), Springer, Switzerland, 2014, pp. 14–25.","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} }","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.","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.","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","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"},"series_title":"Lecture Notes in Computer Science","title":"On Semeai Detection in Monte-Carlo Go","user_id":"24135","place":"Switzerland","date_created":"2018-03-26T13:50:37Z","status":"public","department":[{"_id":"27"},{"_id":"78"}],"publication":"Proc. Conf. on Computers and Games (CG)","author":[{"full_name":"Graf, Tobias","first_name":"Tobias","last_name":"Graf"},{"last_name":"Schaefers","first_name":"Lars","full_name":"Schaefers, Lars"},{"full_name":"Platzner, Marco","first_name":"Marco","id":"398","last_name":"Platzner"}],"publisher":"Springer"},{"year":"2014","citation":{"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)} }","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.","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.","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","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","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.","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."},"type":"conference","page":"144-155","intvolume":" 8405","_id":"388","file":[{"relation":"main_file","success":1,"content_type":"application/pdf","date_updated":"2018-03-20T07:02:02Z","creator":"florida","file_id":"1387","file_size":330193,"access_level":"closed","file_name":"388-plessl14_arc.pdf","date_created":"2018-03-20T07:02:02Z"}],"quality_controlled":"1","author":[{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"last_name":"Vaz","id":"30332","first_name":"Gavin Francis","full_name":"Vaz, Gavin Francis"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"publisher":"Springer International Publishing","file_date_updated":"2018-03-20T07:02:02Z","publication":"Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC)","has_accepted_license":"1","status":"public","date_created":"2017-10-17T12:42:07Z","volume":8405,"abstract":[{"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.","lang":"eng"}],"user_id":"15278","ddc":["040"],"series_title":"Lecture Notes in Computer Science (LNCS)","language":[{"iso":"eng"}],"date_updated":"2023-09-26T13:34:08Z","doi":"10.1007/978-3-319-05960-0_13","department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"project":[{"name":"SFB 901","grant_number":"160364472","_id":"1"},{"name":"SFB 901 - Subprojekt C2","grant_number":"160364472","_id":"14"},{"_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"}],"place":"Cham","title":"Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer"},{"project":[{"name":"SFB 901","grant_number":"160364472","_id":"1"},{"grant_number":"160364472","name":"SFB 901 - Subprojekt C2","_id":"14"},{"name":"SFB 901 - Project Area C","_id":"4"},{"_id":"34","grant_number":"610996","name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"title":"Reconstructing AES Key Schedules from Decayed Memory with FPGAs","language":[{"iso":"eng"}],"doi":"10.1109/FCCM.2014.67","date_updated":"2023-09-26T13:33:50Z","date_created":"2017-10-17T12:42:05Z","status":"public","has_accepted_license":"1","file":[{"date_updated":"2018-03-20T07:14:20Z","content_type":"application/pdf","relation":"main_file","success":1,"file_size":1003907,"file_id":"1397","creator":"florida","access_level":"closed","date_created":"2018-03-20T07:14:20Z","file_name":"377-FCCM14.pdf"}],"keyword":["coldboot"],"publication":"Proceedings of Field-Programmable Custom Computing Machines (FCCM)","file_date_updated":"2018-03-20T07:14:20Z","author":[{"first_name":"Heinrich","full_name":"Riebler, Heinrich","last_name":"Riebler","id":"8961"},{"first_name":"Tobias","full_name":"Kenter, Tobias","last_name":"Kenter","id":"3145"},{"last_name":"Plessl","id":"16153","first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982"},{"last_name":"Sorge","first_name":"Christoph","full_name":"Sorge, Christoph"}],"quality_controlled":"1","publisher":"IEEE","user_id":"15278","ddc":["040"],"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."}],"page":"222-229","citation":{"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.","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} }","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.","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."},"year":"2014","type":"conference","_id":"377"},{"quality_controlled":"1","author":[{"last_name":"C. Durelli","first_name":"Gianluca","full_name":"C. Durelli, Gianluca"},{"first_name":"Marcello","full_name":"Pogliani, Marcello","last_name":"Pogliani"},{"last_name":"Miele","full_name":"Miele, Antonio","first_name":"Antonio"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"},{"id":"8961","last_name":"Riebler","full_name":"Riebler, Heinrich","first_name":"Heinrich"},{"id":"30332","last_name":"Vaz","full_name":"Vaz, Gavin Francis","first_name":"Gavin Francis"},{"first_name":"Marco","full_name":"D. Santambrogio, Marco","last_name":"D. Santambrogio"},{"last_name":"Bolchini","first_name":"Cristiana","full_name":"Bolchini, Cristiana"}],"publisher":"IEEE","publication":"Proc. Int. Symp. on Parallel and Distributed Processing with Applications (ISPA)","department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"status":"public","project":[{"name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","grant_number":"610996","_id":"34"}],"date_created":"2018-03-26T13:40:14Z","user_id":"15278","title":"Runtime Resource Management in Heterogeneous System Architectures: The SAVE Approach","language":[{"iso":"eng"}],"type":"conference","year":"2014","citation":{"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","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","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.","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.","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} }","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.","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."},"page":"142-149","date_updated":"2023-09-26T13:35:40Z","_id":"1778","doi":"10.1109/ISPA.2014.27"},{"doi":"10.1007/978-3-319-05960-0_38","_id":"1780","date_updated":"2023-09-26T13:36:20Z","type":"conference","year":"2014","citation":{"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.","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.","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} }","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.","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","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","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."},"language":[{"iso":"eng"}],"title":"SAVE: Towards efficient resource management in heterogeneous system architectures","user_id":"15278","project":[{"grant_number":"610996","name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","_id":"34"}],"date_created":"2018-03-26T13:45:35Z","status":"public","department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"publication":"Proc. Int. Conf. on Reconfigurable Computing: Architectures, Tools and Applications (ARC)","quality_controlled":"1","publisher":"Springer","author":[{"first_name":"Gianluca","full_name":"C. Durelli, Gianluca","last_name":"C. Durelli"},{"full_name":"Copolla, Marcello","first_name":"Marcello","last_name":"Copolla"},{"last_name":"Djafarian","full_name":"Djafarian, Karim","first_name":"Karim"},{"last_name":"Koranaros","full_name":"Koranaros, George","first_name":"George"},{"last_name":"Miele","full_name":"Miele, Antonio","first_name":"Antonio"},{"first_name":"Michele","full_name":"Paolino, Michele","last_name":"Paolino"},{"last_name":"Pell","full_name":"Pell, Oliver","first_name":"Oliver"},{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"},{"last_name":"D. Santambrogio","first_name":"Marco","full_name":"D. Santambrogio, Marco"},{"last_name":"Bolchini","full_name":"Bolchini, Cristiana","first_name":"Cristiana"}]}]