[{"language":[{"iso":"eng"}],"doi":"10.1016/j.compeleceng.2016.04.021","date_updated":"2023-09-26T13:26:38Z","publication_identifier":{"issn":["0045-7906"]},"project":[{"name":"SFB 901","grant_number":"160364472","_id":"1"},{"_id":"14","grant_number":"160364472","name":"SFB 901 - Subprojekt C2"},{"_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"}],"department":[{"_id":"27"},{"_id":"518"}],"title":"Potential and Methods for Embedding Dynamic Offloading Decisions into Application Code","year":"2016","citation":{"bibtex":"@article{Vaz_Riebler_Kenter_Plessl_2016, title={Potential and Methods for Embedding Dynamic Offloading Decisions into Application Code}, volume={55}, DOI={10.1016/j.compeleceng.2016.04.021}, journal={Computers and Electrical Engineering}, publisher={Elsevier}, author={Vaz, Gavin Francis and Riebler, Heinrich and Kenter, Tobias and Plessl, Christian}, year={2016}, pages={91–111} }","mla":"Vaz, Gavin Francis, et al. “Potential and Methods for Embedding Dynamic Offloading Decisions into Application Code.” Computers and Electrical Engineering, vol. 55, Elsevier, 2016, pp. 91–111, doi:10.1016/j.compeleceng.2016.04.021.","chicago":"Vaz, Gavin Francis, Heinrich Riebler, Tobias Kenter, and Christian Plessl. “Potential and Methods for Embedding Dynamic Offloading Decisions into Application Code.” Computers and Electrical Engineering 55 (2016): 91–111. https://doi.org/10.1016/j.compeleceng.2016.04.021.","ama":"Vaz GF, Riebler H, Kenter T, Plessl C. Potential and Methods for Embedding Dynamic Offloading Decisions into Application Code. Computers and Electrical Engineering. 2016;55:91-111. doi:10.1016/j.compeleceng.2016.04.021","apa":"Vaz, G. F., Riebler, H., Kenter, T., & Plessl, C. (2016). Potential and Methods for Embedding Dynamic Offloading Decisions into Application Code. Computers and Electrical Engineering, 55, 91–111. https://doi.org/10.1016/j.compeleceng.2016.04.021","ieee":"G. F. Vaz, H. Riebler, T. Kenter, and C. Plessl, “Potential and Methods for Embedding Dynamic Offloading Decisions into Application Code,” Computers and Electrical Engineering, vol. 55, pp. 91–111, 2016, doi: 10.1016/j.compeleceng.2016.04.021.","short":"G.F. Vaz, H. Riebler, T. Kenter, C. Plessl, Computers and Electrical Engineering 55 (2016) 91–111."},"type":"journal_article","page":"91-111","_id":"165","intvolume":" 55","volume":55,"has_accepted_license":"1","status":"public","date_created":"2017-10-17T12:41:24Z","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"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"}],"publisher":"Elsevier","quality_controlled":"1","publication":"Computers and Electrical Engineering","file_date_updated":"2018-03-21T12:45:47Z","file":[{"file_name":"165-1-s2.0-S0045790616301021-main.pdf","date_created":"2018-03-21T12:45:47Z","access_level":"closed","file_id":"1544","creator":"florida","file_size":3037854,"relation":"main_file","success":1,"date_updated":"2018-03-21T12:45:47Z","content_type":"application/pdf"}],"ddc":["040"],"user_id":"15278","abstract":[{"lang":"eng","text":"A broad spectrum of applications can be accelerated by offloading computation intensive parts to reconfigurable hardware. However, to achieve speedups, the number of loop it- erations (trip count) needs to be sufficiently large to amortize offloading overheads. Trip counts are frequently not known at compile time, but only at runtime just before entering a loop. Therefore, we propose to generate code for both the CPU and the coprocessor, and defer the offloading decision to the application runtime. We demonstrate how a toolflow, based on the LLVM compiler framework, can automatically embed dynamic offloading de- cisions into the application code. We perform in-depth static and dynamic analysis of pop- ular benchmarks, which confirm the general potential of such an approach. We also pro- pose to optimize the offloading process by decoupling the runtime decision from the loop execution (decision slack). The feasibility of our approach is demonstrated by a toolflow that automatically identifies suitable data-parallel loops and generates code for the FPGA coprocessor of a Convey HC-1. We evaluate the integrated toolflow with representative loops executed for different input data sizes."}]},{"ddc":["040"],"user_id":"15278","abstract":[{"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.","lang":"eng"}],"date_created":"2017-10-17T12:41:24Z","status":"public","has_accepted_license":"1","publication":"Proceedings of the 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE)","file_date_updated":"2018-03-21T12:41:55Z","publisher":"EDA Consortium / IEEE","author":[{"first_name":"Achim","full_name":"Lösch, Achim","last_name":"Lösch","id":"43646"},{"last_name":"Beisel","first_name":"Tobias","full_name":"Beisel, Tobias"},{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian"},{"last_name":"Platzner","id":"398","first_name":"Marco","full_name":"Platzner, Marco"}],"quality_controlled":"1","file":[{"relation":"main_file","success":1,"content_type":"application/pdf","date_updated":"2018-03-21T12:41:55Z","creator":"florida","file_id":"1541","file_size":261356,"access_level":"closed","date_created":"2018-03-21T12:41:55Z","file_name":"168-07459438.pdf"}],"_id":"168","page":"912-917","type":"conference","citation":{"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.","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.","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.","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.","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.","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.","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} }"},"year":"2016","title":"Performance-centric scheduling with task migration for a heterogeneous compute node in the data center","project":[{"grant_number":"160364472","name":"SFB 901","_id":"1"},{"name":"SFB 901 - Subprojekt C2","grant_number":"160364472","_id":"14"},{"_id":"4","name":"SFB 901 - Project Area C"},{"grant_number":"01|H11004A","name":"Enabling Heterogeneous Hardware Acceleration using Novel Programming and Scheduling Models","_id":"30"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"date_updated":"2023-09-26T13:27:00Z","language":[{"iso":"eng"}]},{"type":"conference","citation":{"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.","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).","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.","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} }","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.","ieee":"T. Kenter, G. F. Vaz, H. Riebler, and C. Plessl, “Opportunities for deferring application partitioning and accelerator synthesis to runtime (extended abstract),” 2016."},"year":"2016","language":[{"iso":"eng"}],"date_updated":"2023-09-26T13:27:21Z","_id":"171","quality_controlled":"1","author":[{"full_name":"Kenter, Tobias","first_name":"Tobias","id":"3145","last_name":"Kenter"},{"id":"30332","last_name":"Vaz","full_name":"Vaz, Gavin Francis","first_name":"Gavin Francis"},{"last_name":"Riebler","id":"8961","first_name":"Heinrich","full_name":"Riebler, Heinrich"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"}],"file_date_updated":"2018-03-21T12:39:46Z","department":[{"_id":"27"},{"_id":"518"}],"publication":"Workshop on Reconfigurable Computing (WRC)","file":[{"access_level":"closed","file_name":"171-plessl16_fpl_wrc.pdf","date_created":"2018-03-21T12:39:46Z","date_updated":"2018-03-21T12:39:46Z","content_type":"application/pdf","relation":"main_file","success":1,"file_size":54421,"file_id":"1538","creator":"florida"}],"has_accepted_license":"1","status":"public","date_created":"2017-10-17T12:41:25Z","project":[{"_id":"1","grant_number":"160364472","name":"SFB 901"},{"_id":"14","name":"SFB 901 - Subprojekt C2","grant_number":"160364472"},{"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"}],"ddc":["040"],"title":"Opportunities for deferring application partitioning and accelerator synthesis to runtime (extended abstract)","user_id":"15278"},{"department":[{"_id":"27"},{"_id":"104"}],"publication":"tm - Technisches Messen","publisher":"Walter de Gruyter","author":[{"last_name":"Hegler","first_name":"Sebastian","full_name":"Hegler, Sebastian"},{"full_name":"Statz, Christoph","first_name":"Christoph","last_name":"Statz"},{"last_name":"Mütze","first_name":"Marco","full_name":"Mütze, Marco"},{"last_name":"Mooshofer","first_name":"Hubert","full_name":"Mooshofer, Hubert"},{"last_name":"Goldammer","full_name":"Goldammer, Matthias","first_name":"Matthias"},{"last_name":"Fendt","first_name":"Karl","full_name":"Fendt, Karl"},{"first_name":"Stefan","full_name":"Schwarzer, Stefan","last_name":"Schwarzer"},{"full_name":"Feldhoff, Kim","first_name":"Kim","last_name":"Feldhoff"},{"last_name":"Flehmig","first_name":"Martin","full_name":"Flehmig, Martin"},{"last_name":"Markwardt","first_name":"Ulf","full_name":"Markwardt, Ulf"},{"last_name":"E. Nagel","full_name":"E. Nagel, Wolfgang","first_name":"Wolfgang"},{"last_name":"Schütte","full_name":"Schütte, Maria","first_name":"Maria"},{"full_name":"Walther, Andrea","first_name":"Andrea","last_name":"Walther"},{"last_name":"Meinel","first_name":"Michael","full_name":"Meinel, Michael"},{"first_name":"Achim","full_name":"Basermann, Achim","last_name":"Basermann"},{"first_name":"Dirk","full_name":"Plettemeier, Dirk","last_name":"Plettemeier"}],"date_created":"2018-03-23T14:01:39Z","status":"public","volume":82,"abstract":[{"text":"Große zylindrische Stahlprüflinge werden mittels der Methode der finiten Differenzen im Zeitbereich (engl. finite differences in time domain, FDTD) simulativ untersucht. Dabei werden Pitch-Catch-Messanordnungen verwendet. Es werden zwei Bildgebungsansätze vorgestellt: ersterer basiert auf dem Imaging Principle nach Claerbout, letzterer basiert auf gradientenbasierter Optimierung eines Zielfunktionals.","lang":"eng"}],"user_id":"24135","title":"Simulative Ultraschall-Untersuchung von Pitch-Catch-Messanordnungen für große zylindrische Stahl-Prüflinge und gradientenbasierte Bildgebung","page":"440-450","type":"journal_article","year":"2015","citation":{"ieee":"S. Hegler et al., “Simulative Ultraschall-Untersuchung von Pitch-Catch-Messanordnungen für große zylindrische Stahl-Prüflinge und gradientenbasierte Bildgebung,” tm - Technisches Messen, vol. 82, no. 9, pp. 440–450, 2015.","short":"S. Hegler, C. Statz, M. Mütze, H. Mooshofer, M. Goldammer, K. Fendt, S. Schwarzer, K. Feldhoff, M. Flehmig, U. Markwardt, W. E. Nagel, M. Schütte, A. Walther, M. Meinel, A. Basermann, D. Plettemeier, Tm - Technisches Messen 82 (2015) 440–450.","bibtex":"@article{Hegler_Statz_Mütze_Mooshofer_Goldammer_Fendt_Schwarzer_Feldhoff_Flehmig_Markwardt_et al._2015, title={Simulative Ultraschall-Untersuchung von Pitch-Catch-Messanordnungen für große zylindrische Stahl-Prüflinge und gradientenbasierte Bildgebung}, volume={82}, DOI={doi:10.1515/teme-2015-0031}, number={9}, journal={tm - Technisches Messen}, publisher={Walter de Gruyter}, author={Hegler, Sebastian and Statz, Christoph and Mütze, Marco and Mooshofer, Hubert and Goldammer, Matthias and Fendt, Karl and Schwarzer, Stefan and Feldhoff, Kim and Flehmig, Martin and Markwardt, Ulf and et al.}, year={2015}, pages={440–450} }","mla":"Hegler, Sebastian, et al. “Simulative Ultraschall-Untersuchung von Pitch-Catch-Messanordnungen Für Große Zylindrische Stahl-Prüflinge Und Gradientenbasierte Bildgebung.” Tm - Technisches Messen, vol. 82, no. 9, Walter de Gruyter, 2015, pp. 440–50, doi:doi:10.1515/teme-2015-0031.","ama":"Hegler S, Statz C, Mütze M, et al. Simulative Ultraschall-Untersuchung von Pitch-Catch-Messanordnungen für große zylindrische Stahl-Prüflinge und gradientenbasierte Bildgebung. tm - Technisches Messen. 2015;82(9):440-450. doi:doi:10.1515/teme-2015-0031","apa":"Hegler, S., Statz, C., Mütze, M., Mooshofer, H., Goldammer, M., Fendt, K., … Plettemeier, D. (2015). Simulative Ultraschall-Untersuchung von Pitch-Catch-Messanordnungen für große zylindrische Stahl-Prüflinge und gradientenbasierte Bildgebung. Tm - Technisches Messen, 82(9), 440–450. https://doi.org/doi:10.1515/teme-2015-0031","chicago":"Hegler, Sebastian, Christoph Statz, Marco Mütze, Hubert Mooshofer, Matthias Goldammer, Karl Fendt, Stefan Schwarzer, et al. “Simulative Ultraschall-Untersuchung von Pitch-Catch-Messanordnungen Für Große Zylindrische Stahl-Prüflinge Und Gradientenbasierte Bildgebung.” Tm - Technisches Messen 82, no. 9 (2015): 440–50. https://doi.org/doi:10.1515/teme-2015-0031."},"intvolume":" 82","_id":"1769","date_updated":"2022-01-06T06:53:17Z","issue":"9","doi":"doi:10.1515/teme-2015-0031"},{"language":[{"iso":"eng"}],"doi":"10.1109/MC.2015.205","date_updated":"2022-01-06T06:53:19Z","project":[{"_id":"1","name":"SFB 901"},{"_id":"4","name":"SFB 901 - Project Area C"},{"name":"SFB 901 - Subproject C2","_id":"14"},{"name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","grant_number":"610996","_id":"34"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"title":"Self-Aware and Self-Expressive Systems – Guest Editor's Introduction","page":"18-20","type":"journal_article","year":"2015","citation":{"ieee":"J. Torresen, C. Plessl, and X. Yao, “Self-Aware and Self-Expressive Systems – Guest Editor’s Introduction,” IEEE Computer, vol. 48, no. 7, pp. 18–20, 2015.","short":"J. Torresen, C. Plessl, X. Yao, IEEE Computer 48 (2015) 18–20.","bibtex":"@article{Torresen_Plessl_Yao_2015, title={Self-Aware and Self-Expressive Systems – Guest Editor’s Introduction}, volume={48}, DOI={10.1109/MC.2015.205}, number={7}, journal={IEEE Computer}, publisher={IEEE Computer Society}, author={Torresen, Jim and Plessl, Christian and Yao, Xin}, year={2015}, pages={18–20} }","mla":"Torresen, Jim, et al. “Self-Aware and Self-Expressive Systems – Guest Editor’s Introduction.” IEEE Computer, vol. 48, no. 7, IEEE Computer Society, 2015, pp. 18–20, doi:10.1109/MC.2015.205.","chicago":"Torresen, Jim, Christian Plessl, and Xin Yao. “Self-Aware and Self-Expressive Systems – Guest Editor’s Introduction.” IEEE Computer 48, no. 7 (2015): 18–20. https://doi.org/10.1109/MC.2015.205.","apa":"Torresen, J., Plessl, C., & Yao, X. (2015). Self-Aware and Self-Expressive Systems – Guest Editor’s Introduction. IEEE Computer, 48(7), 18–20. https://doi.org/10.1109/MC.2015.205","ama":"Torresen J, Plessl C, Yao X. Self-Aware and Self-Expressive Systems – Guest Editor’s Introduction. IEEE Computer. 2015;48(7):18-20. doi:10.1109/MC.2015.205"},"issue":"7","_id":"1772","intvolume":" 48","volume":48,"date_created":"2018-03-23T14:06:12Z","has_accepted_license":"1","status":"public","file_date_updated":"2018-11-02T15:47:45Z","publication":"IEEE Computer","keyword":["self-awareness","self-expression"],"author":[{"last_name":"Torresen","first_name":"Jim","full_name":"Torresen, Jim"},{"first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","last_name":"Plessl","id":"16153"},{"first_name":"Xin","full_name":"Yao, Xin","last_name":"Yao"}],"publisher":"IEEE Computer Society","file":[{"content_type":"application/pdf","date_updated":"2018-11-02T15:47:45Z","relation":"main_file","success":1,"file_size":5605009,"creator":"ups","file_id":"5313","access_level":"closed","date_created":"2018-11-02T15:47:45Z","file_name":"07163237.pdf"}],"ddc":["000"],"user_id":"16153"},{"publication":"PAMM","department":[{"_id":"27"},{"_id":"101"}],"author":[{"last_name":"Peitz","first_name":"Sebastian","full_name":"Peitz, Sebastian"},{"full_name":"Dellnitz, Michael","first_name":"Michael","last_name":"Dellnitz"}],"publisher":"WILEY-VCH Verlag","date_created":"2018-03-23T14:14:24Z","status":"public","publication_identifier":{"issn":["1617-7061"]},"volume":15,"abstract":[{"lang":"eng","text":"In this article an efficient numerical method to solve multiobjective optimization problems for fluid flow governed by the Navier Stokes equations is presented. In order to decrease the computational effort, a reduced order model is introduced using Proper Orthogonal Decomposition and a corresponding Galerkin Projection. A global, derivative free multiobjective optimization algorithm is applied to compute the Pareto set (i.e. the set of optimal compromises) for the concurrent objectives minimization of flow field fluctuations and control cost. The method is illustrated for a 2D flow around a cylinder at Re = 100."}],"user_id":"24135","title":"Multiobjective Optimization of the Flow Around a Cylinder Using Model Order Reduction","page":"613-614","type":"journal_article","year":"2015","citation":{"ieee":"S. Peitz and M. Dellnitz, “Multiobjective Optimization of the Flow Around a Cylinder Using Model Order Reduction,” PAMM, vol. 15, no. 1, pp. 613–614, 2015.","short":"S. Peitz, M. Dellnitz, PAMM 15 (2015) 613–614.","bibtex":"@article{Peitz_Dellnitz_2015, title={Multiobjective Optimization of the Flow Around a Cylinder Using Model Order Reduction}, volume={15}, DOI={10.1002/pamm.201510296}, number={1}, journal={PAMM}, publisher={WILEY-VCH Verlag}, author={Peitz, Sebastian and Dellnitz, Michael}, year={2015}, pages={613–614} }","mla":"Peitz, Sebastian, and Michael Dellnitz. “Multiobjective Optimization of the Flow Around a Cylinder Using Model Order Reduction.” PAMM, vol. 15, no. 1, WILEY-VCH Verlag, 2015, pp. 613–14, doi:10.1002/pamm.201510296.","ama":"Peitz S, Dellnitz M. Multiobjective Optimization of the Flow Around a Cylinder Using Model Order Reduction. PAMM. 2015;15(1):613-614. doi:10.1002/pamm.201510296","apa":"Peitz, S., & Dellnitz, M. (2015). Multiobjective Optimization of the Flow Around a Cylinder Using Model Order Reduction. PAMM, 15(1), 613–614. https://doi.org/10.1002/pamm.201510296","chicago":"Peitz, Sebastian, and Michael Dellnitz. “Multiobjective Optimization of the Flow Around a Cylinder Using Model Order Reduction.” PAMM 15, no. 1 (2015): 613–14. https://doi.org/10.1002/pamm.201510296."},"_id":"1774","intvolume":" 15","date_updated":"2022-01-06T06:53:19Z","issue":"1","doi":"10.1002/pamm.201510296"},{"abstract":[{"lang":"eng","text":"The use of heterogeneous computing resources, such as graphics processing units or other specialized co-processors, has become widespread in recent years because of their performance and energy efficiency advantages. Operating system approaches that are limited to optimizing CPU usage are no longer sufficient for the efficient utilization of systems that comprise diverse resource types.\r\n\r\nEnabling task preemption on these architectures and migration of tasks between different resource types at run-time is not only key to improving the performance and energy consumption but also to enabling automatic scheduling methods for heterogeneous compute nodes.\r\n\r\nThis thesis proposes novel techniques for run-time management of heterogeneous resources and enabling tasks to migrate between diverse hardware. It provides fundamental work towards future operating systems by discussing implications, limitations, and chances of the heterogeneity and introducing solutions for energy- and performance-efficient run-time systems. Scheduling methods to utilize heterogeneous systems by the use of a centralized scheduler are presented that show benefits over existing approaches in varying case studies."}],"place":"Berlin","title":"Management and Scheduling of Accelerators for Heterogeneous High-Performance Computing","user_id":"3118","department":[{"_id":"78"},{"_id":"27"},{"_id":"518"}],"publisher":"Logos Verlag Berlin GmbH","author":[{"last_name":"Beisel","full_name":"Beisel, Tobias","first_name":"Tobias"}],"publication_identifier":{"isbn":["978-3-8325-4155-2"]},"project":[{"name":"Enabling Heterogeneous Hardware Acceleration using Novel Programming and Scheduling Models","grant_number":"01|H11004","_id":"30"}],"date_created":"2019-07-10T09:36:58Z","status":"public","_id":"10624","date_updated":"2022-01-06T06:50:48Z","page":"183","citation":{"chicago":"Beisel, Tobias. Management and Scheduling of Accelerators for Heterogeneous High-Performance Computing. Berlin: Logos Verlag Berlin GmbH, 2015.","ama":"Beisel T. Management and Scheduling of Accelerators for Heterogeneous High-Performance Computing. Berlin: Logos Verlag Berlin GmbH; 2015.","apa":"Beisel, T. (2015). Management and Scheduling of Accelerators for Heterogeneous High-Performance Computing. Berlin: Logos Verlag Berlin GmbH.","mla":"Beisel, Tobias. Management and Scheduling of Accelerators for Heterogeneous High-Performance Computing. Logos Verlag Berlin GmbH, 2015.","bibtex":"@book{Beisel_2015, place={Berlin}, title={Management and Scheduling of Accelerators for Heterogeneous High-Performance Computing}, publisher={Logos Verlag Berlin GmbH}, author={Beisel, Tobias}, year={2015} }","short":"T. Beisel, Management and Scheduling of Accelerators for Heterogeneous High-Performance Computing, Logos Verlag Berlin GmbH, Berlin, 2015.","ieee":"T. Beisel, Management and Scheduling of Accelerators for Heterogeneous High-Performance Computing. Berlin: Logos Verlag Berlin GmbH, 2015."},"year":"2015","type":"dissertation","language":[{"iso":"eng"}],"supervisor":[{"last_name":"Plessl","id":"16153","first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian"}]},{"language":[{"iso":"eng"}],"doi":"10.1155/2015/859425","date_updated":"2023-09-26T13:29:08Z","project":[{"name":"SFB 901","grant_number":"160364472","_id":"1"},{"_id":"14","name":"SFB 901 - Subprojekt C2","grant_number":"160364472"},{"name":"SFB 901 - Project Area C","_id":"4"},{"_id":"34","name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","grant_number":"610996"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"title":"Exploring Tradeoffs between Specialized Kernels and a Reusable Overlay in a Stereo-Matching Case Study","year":"2015","type":"journal_article","citation":{"mla":"Kenter, Tobias, et al. “Exploring Tradeoffs between Specialized Kernels and a Reusable Overlay in a Stereo-Matching Case Study.” International Journal of Reconfigurable Computing (IJRC), vol. 2015, 859425, Hindawi, 2015, doi:10.1155/2015/859425.","bibtex":"@article{Kenter_Schmitz_Plessl_2015, title={Exploring Tradeoffs between Specialized Kernels and a Reusable Overlay in a Stereo-Matching Case Study}, volume={2015}, DOI={10.1155/2015/859425}, number={859425}, journal={International Journal of Reconfigurable Computing (IJRC)}, publisher={Hindawi}, author={Kenter, Tobias and Schmitz, Henning and Plessl, Christian}, year={2015} }","chicago":"Kenter, Tobias, Henning Schmitz, and Christian Plessl. “Exploring Tradeoffs between Specialized Kernels and a Reusable Overlay in a Stereo-Matching Case Study.” International Journal of Reconfigurable Computing (IJRC) 2015 (2015). https://doi.org/10.1155/2015/859425.","ama":"Kenter T, Schmitz H, Plessl C. Exploring Tradeoffs between Specialized Kernels and a Reusable Overlay in a Stereo-Matching Case Study. International Journal of Reconfigurable Computing (IJRC). 2015;2015. doi:10.1155/2015/859425","apa":"Kenter, T., Schmitz, H., & Plessl, C. (2015). Exploring Tradeoffs between Specialized Kernels and a Reusable Overlay in a Stereo-Matching Case Study. International Journal of Reconfigurable Computing (IJRC), 2015, Article 859425. https://doi.org/10.1155/2015/859425","ieee":"T. Kenter, H. Schmitz, and C. Plessl, “Exploring Tradeoffs between Specialized Kernels and a Reusable Overlay in a Stereo-Matching Case Study,” International Journal of Reconfigurable Computing (IJRC), vol. 2015, Art. no. 859425, 2015, doi: 10.1155/2015/859425.","short":"T. Kenter, H. Schmitz, C. Plessl, International Journal of Reconfigurable Computing (IJRC) 2015 (2015)."},"article_number":"859425","intvolume":" 2015","_id":"296","status":"public","has_accepted_license":"1","date_created":"2017-10-17T12:41:49Z","volume":2015,"file":[{"date_created":"2018-03-20T07:47:56Z","file_name":"296-859425.pdf","access_level":"closed","creator":"florida","file_id":"1444","file_size":2993898,"success":1,"relation":"main_file","content_type":"application/pdf","date_updated":"2018-03-20T07:47:56Z"}],"publisher":"Hindawi","author":[{"id":"3145","last_name":"Kenter","full_name":"Kenter, Tobias","first_name":"Tobias"},{"full_name":"Schmitz, Henning","first_name":"Henning","last_name":"Schmitz"},{"id":"16153","last_name":"Plessl","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"quality_controlled":"1","file_date_updated":"2018-03-20T07:47:56Z","publication":"International Journal of Reconfigurable Computing (IJRC)","user_id":"15278","ddc":["040"],"abstract":[{"lang":"eng","text":"FPGAs are known to permit huge gains in performance and efficiency for suitable applications but still require reduced design efforts and shorter development cycles for wider adoption. In this work, we compare the resulting performance of two design concepts that in different ways promise such increased productivity. As common starting point, we employ a kernel-centric design approach, where computational hotspots in an application are identified and individually accelerated on FPGA. By means of a complex stereo matching application, we evaluate two fundamentally different design philosophies and approaches for implementing the required kernels on FPGAs. In the first implementation approach, we designed individually specialized data flow kernels in a spatial programming language for a Maxeler FPGA platform; in the alternative design approach, we target a vector coprocessor with large vector lengths, which is implemented as a form of programmable overlay on the application FPGAs of a Convey HC-1. We assess both approaches in terms of overall system performance, raw kernel performance, and performance relative to invested resources. After compensating for the effects of the underlying hardware platforms, the specialized dataflow kernels on the Maxeler platform are around 3x faster than kernels executing on the Convey vector coprocessor. In our concrete scenario, due to trade-offs between reconfiguration overheads and exposed parallelism, the advantage of specialized dataflow kernels is reduced to around 2.5x."}]},{"_id":"303","citation":{"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.","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).","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.","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.","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} }","short":"M. Damschen, C. Plessl, 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."},"year":"2015","type":"conference","abstract":[{"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.","lang":"eng"}],"user_id":"15278","ddc":["040"],"file":[{"date_created":"2018-03-20T07:46:46Z","file_name":"303-plessl15_adapt.pdf","access_level":"open_access","file_size":1176620,"creator":"florida","file_id":"1442","date_updated":"2019-08-01T09:10:44Z","content_type":"application/pdf","relation":"main_file"}],"author":[{"last_name":"Damschen","first_name":"Marvin","full_name":"Damschen, Marvin"},{"last_name":"Plessl","id":"16153","first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982"}],"quality_controlled":"1","publication":"Proceedings of the 5th International Workshop on Adaptive Self-tuning Computing Systems (ADAPT)","file_date_updated":"2019-08-01T09:10:44Z","status":"public","has_accepted_license":"1","date_created":"2017-10-17T12:41:51Z","date_updated":"2023-09-26T13:29:59Z","oa":"1","language":[{"iso":"eng"}],"external_id":{"arxiv":["1412.3906"]},"title":"Easy-to-Use On-The-Fly Binary Program Acceleration on Many-Cores","department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"project":[{"grant_number":"160364472","name":"SFB 901","_id":"1"},{"name":"SFB 901 - Subprojekt C2","grant_number":"160364472","_id":"14"},{"name":"SFB 901 - Project Area C","_id":"4"},{"grant_number":"610996","name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","_id":"34"}]},{"language":[{"iso":"eng"}],"type":"conference","year":"2015","citation":{"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.","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} }","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.","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.","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","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"},"doi":"10.1145/2675743.2771824","_id":"1773","date_updated":"2023-09-26T13:31:01Z","status":"public","date_created":"2018-03-23T14:09:33Z","author":[{"full_name":"Schumacher, Jörn","first_name":"Jörn","last_name":"Schumacher"},{"last_name":"T. Anderson","full_name":"T. Anderson, J.","first_name":"J."},{"last_name":"Borga","first_name":"A.","full_name":"Borga, A."},{"last_name":"Boterenbrood","first_name":"H.","full_name":"Boterenbrood, H."},{"first_name":"H.","full_name":"Chen, H.","last_name":"Chen"},{"last_name":"Chen","first_name":"K.","full_name":"Chen, K."},{"first_name":"G.","full_name":"Drake, G.","last_name":"Drake"},{"full_name":"Francis, D.","first_name":"D.","last_name":"Francis"},{"last_name":"Gorini","full_name":"Gorini, B.","first_name":"B."},{"last_name":"Lanni","full_name":"Lanni, F.","first_name":"F."},{"last_name":"Lehmann-Miotto","full_name":"Lehmann-Miotto, Giovanna","first_name":"Giovanna"},{"last_name":"Levinson","full_name":"Levinson, L.","first_name":"L."},{"last_name":"Narevicius","full_name":"Narevicius, J.","first_name":"J."},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian"},{"full_name":"Roich, A.","first_name":"A.","last_name":"Roich"},{"last_name":"Ryu","first_name":"S.","full_name":"Ryu, S."},{"first_name":"F.","full_name":"P. Schreuder, F.","last_name":"P. Schreuder"},{"last_name":"Vandelli","first_name":"Wainer","full_name":"Vandelli, Wainer"},{"full_name":"Vermeulen, J.","first_name":"J.","last_name":"Vermeulen"},{"first_name":"J.","full_name":"Zhang, J.","last_name":"Zhang"}],"publisher":"ACM","quality_controlled":"1","department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"publication":"Proc. Int. Conf. on Distributed Event-Based Systems (DEBS)","user_id":"15278","title":"Improving Packet Processing Performance in the ATLAS FELIX Project – Analysis and Optimization of a Memory-Bounded Algorithm"},{"date_created":"2018-03-23T13:58:34Z","status":"public","keyword":["approximate computing","survey"],"department":[{"_id":"27"},{"_id":"518"},{"_id":"263"},{"_id":"78"}],"publication":"Informatik Spektrum","author":[{"orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian","id":"16153","last_name":"Plessl"},{"full_name":"Platzner, Marco","first_name":"Marco","id":"398","last_name":"Platzner"},{"last_name":"Schreier","first_name":"Peter J.","full_name":"Schreier, Peter J."}],"quality_controlled":"1","publisher":"Springer","title":"Aktuelles Schlagwort: Approximate Computing","user_id":"15278","page":"396-399","year":"2015","citation":{"chicago":"Plessl, Christian, Marco Platzner, and Peter J. Schreier. “Aktuelles Schlagwort: Approximate Computing.” Informatik Spektrum, no. 5 (2015): 396–99. https://doi.org/10.1007/s00287-015-0911-z.","apa":"Plessl, C., Platzner, M., & Schreier, P. J. (2015). Aktuelles Schlagwort: Approximate Computing. Informatik Spektrum, 5, 396–399. https://doi.org/10.1007/s00287-015-0911-z","ama":"Plessl C, Platzner M, Schreier PJ. Aktuelles Schlagwort: Approximate Computing. Informatik Spektrum. 2015;(5):396-399. doi:10.1007/s00287-015-0911-z","mla":"Plessl, Christian, et al. “Aktuelles Schlagwort: Approximate Computing.” Informatik Spektrum, no. 5, Springer, 2015, pp. 396–99, doi:10.1007/s00287-015-0911-z.","bibtex":"@article{Plessl_Platzner_Schreier_2015, title={Aktuelles Schlagwort: Approximate Computing}, DOI={10.1007/s00287-015-0911-z}, number={5}, journal={Informatik Spektrum}, publisher={Springer}, author={Plessl, Christian and Platzner, Marco and Schreier, Peter J.}, year={2015}, pages={396–399} }","short":"C. Plessl, M. Platzner, P.J. Schreier, Informatik Spektrum (2015) 396–399.","ieee":"C. Plessl, M. Platzner, and P. J. Schreier, “Aktuelles Schlagwort: Approximate Computing,” Informatik Spektrum, no. 5, pp. 396–399, 2015, doi: 10.1007/s00287-015-0911-z."},"type":"journal_article","language":[{"iso":"eng"}],"doi":"10.1007/s00287-015-0911-z","issue":"5","date_updated":"2023-09-26T13:30:22Z","_id":"1768"},{"_id":"238","type":"conference","year":"2015","citation":{"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.","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.","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.","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} }","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."},"page":"1078-1083","user_id":"15278","ddc":["040"],"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."}],"has_accepted_license":"1","status":"public","date_created":"2017-10-17T12:41:38Z","file":[{"file_size":380552,"file_id":"1500","creator":"florida","content_type":"application/pdf","date_updated":"2018-03-21T10:29:49Z","success":1,"relation":"main_file","date_created":"2018-03-21T10:29:49Z","file_name":"238-plessl15_date.pdf","access_level":"closed"}],"author":[{"full_name":"Damschen, Marvin","first_name":"Marvin","last_name":"Damschen"},{"full_name":"Riebler, Heinrich","first_name":"Heinrich","id":"8961","last_name":"Riebler"},{"first_name":"Gavin Francis","full_name":"Vaz, Gavin Francis","last_name":"Vaz","id":"30332"},{"last_name":"Plessl","id":"16153","first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982"}],"publisher":"EDA Consortium / IEEE","quality_controlled":"1","publication":"Proceedings of the 2015 Conference on Design, Automation and Test in Europe (DATE)","file_date_updated":"2018-03-21T10:29:49Z","doi":"10.7873/DATE.2015.1124","date_updated":"2023-09-26T13:31:44Z","language":[{"iso":"eng"}],"title":"Transparent offloading of computational hotspots from binary code to Xeon Phi","project":[{"name":"SFB 901","grant_number":"160364472","_id":"1"},{"_id":"14","grant_number":"160364472","name":"SFB 901 - Subprojekt C2"},{"name":"SFB 901 - Project Area C","_id":"4"},{"name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","grant_number":"610996","_id":"34"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}]},{"volume":664,"date_created":"2018-03-23T14:19:27Z","status":"public","department":[{"_id":"27"},{"_id":"518"}],"publication":"Journal of Physics: Conference Series","quality_controlled":"1","author":[{"first_name":"J","full_name":"Anderson, J","last_name":"Anderson"},{"last_name":"Borga","full_name":"Borga, A","first_name":"A"},{"last_name":"Boterenbrood","first_name":"H","full_name":"Boterenbrood, H"},{"last_name":"Chen","first_name":"H","full_name":"Chen, H"},{"full_name":"Chen, K","first_name":"K","last_name":"Chen"},{"full_name":"Drake, G","first_name":"G","last_name":"Drake"},{"first_name":"D","full_name":"Francis, D","last_name":"Francis"},{"last_name":"Gorini","full_name":"Gorini, B","first_name":"B"},{"last_name":"Lanni","first_name":"F","full_name":"Lanni, F"},{"first_name":"G","full_name":"Lehmann Miotto, G","last_name":"Lehmann Miotto"},{"last_name":"Levinson","full_name":"Levinson, L","first_name":"L"},{"last_name":"Narevicius","full_name":"Narevicius, J","first_name":"J"},{"first_name":"Christian","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","last_name":"Plessl","id":"16153"},{"last_name":"Roich","first_name":"A","full_name":"Roich, A"},{"last_name":"Ryu","first_name":"S","full_name":"Ryu, S"},{"first_name":"F","full_name":"Schreuder, F","last_name":"Schreuder"},{"full_name":"Schumacher, Jörn","first_name":"Jörn","last_name":"Schumacher"},{"last_name":"Vandelli","full_name":"Vandelli, Wainer","first_name":"Wainer"},{"first_name":"J","full_name":"Vermeulen, J","last_name":"Vermeulen"},{"full_name":"Zhang, J","first_name":"J","last_name":"Zhang"}],"publisher":"IOP Publishing","title":"FELIX: a High-Throughput Network Approach for Interfacing to Front End Electronics for ATLAS Upgrades","user_id":"15278","abstract":[{"lang":"eng","text":"The ATLAS experiment at CERN is planning full deployment of a new unified optical link technology for connecting detector front end electronics on the timescale of the LHC Run 4 (2025). It is estimated that roughly 8000 GBT (GigaBit Transceiver) links, with transfer rates up to 10.24 Gbps, will replace existing links used for readout, detector control and distribution of timing and trigger information. A new class of devices will be needed to interface many GBT links to the rest of the trigger, data-acquisition and detector control systems. In this paper FELIX (Front End LInk eXchange) is presented, a PC-based device to route data from and to multiple GBT links via a high-performance general purpose network capable of a total throughput up to O(20 Tbps). FELIX implies architectural changes to the ATLAS data acquisition system, such as the use of industry standard COTS components early in the DAQ chain. Additionally the design and implementation of a FELIX demonstration platform is presented and hardware and software aspects will be discussed."}],"type":"journal_article","year":"2015","citation":{"ieee":"J. Anderson et al., “FELIX: a High-Throughput Network Approach for Interfacing to Front End Electronics for ATLAS Upgrades,” Journal of Physics: Conference Series, vol. 664, Art. no. 082050, 2015, doi: 10.1088/1742-6596/664/8/082050.","short":"J. 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. Schreuder, J. Schumacher, W. Vandelli, J. Vermeulen, J. Zhang, Journal of Physics: Conference Series 664 (2015).","mla":"Anderson, J., et al. “FELIX: A High-Throughput Network Approach for Interfacing to Front End Electronics for ATLAS Upgrades.” Journal of Physics: Conference Series, vol. 664, 082050, IOP Publishing, 2015, doi:10.1088/1742-6596/664/8/082050.","bibtex":"@article{Anderson_Borga_Boterenbrood_Chen_Chen_Drake_Francis_Gorini_Lanni_Lehmann Miotto_et al._2015, title={FELIX: a High-Throughput Network Approach for Interfacing to Front End Electronics for ATLAS Upgrades}, volume={664}, DOI={10.1088/1742-6596/664/8/082050}, number={082050}, journal={Journal of Physics: Conference Series}, publisher={IOP Publishing}, author={Anderson, J and Borga, A and Boterenbrood, H and Chen, H and Chen, K and Drake, G and Francis, D and Gorini, B and Lanni, F and Lehmann Miotto, G and et al.}, year={2015} }","chicago":"Anderson, J, A Borga, H Boterenbrood, H Chen, K Chen, G Drake, D Francis, et al. “FELIX: A High-Throughput Network Approach for Interfacing to Front End Electronics for ATLAS Upgrades.” Journal of Physics: Conference Series 664 (2015). https://doi.org/10.1088/1742-6596/664/8/082050.","ama":"Anderson J, Borga A, Boterenbrood H, et al. FELIX: a High-Throughput Network Approach for Interfacing to Front End Electronics for ATLAS Upgrades. Journal of Physics: Conference Series. 2015;664. doi:10.1088/1742-6596/664/8/082050","apa":"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., Schreuder, F., Schumacher, J., Vandelli, W., Vermeulen, J., & Zhang, J. (2015). FELIX: a High-Throughput Network Approach for Interfacing to Front End Electronics for ATLAS Upgrades. Journal of Physics: Conference Series, 664, Article 082050. https://doi.org/10.1088/1742-6596/664/8/082050"},"language":[{"iso":"eng"}],"doi":"10.1088/1742-6596/664/8/082050","article_number":"082050","_id":"1775","intvolume":" 664","date_updated":"2023-09-26T13:31:23Z"},{"user_id":"24135","title":"Numerical Simulation of the Damping Behavior of Particle-Filled Hollow Spheres","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."}],"date_created":"2018-03-26T13:47:16Z","status":"public","publication_identifier":{"isbn":["978-3-319-09063-4"]},"editor":[{"full_name":"Bock, Hans Georg","first_name":"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"},{"last_name":"Schlöder","first_name":"Johannes P.","full_name":"Schlöder, Johannes P."}],"department":[{"_id":"27"},{"_id":"104"},{"_id":"155"}],"publication":"Proc. Modeling, Simulation and Optimization of Complex Processes (HPSC)","publisher":"Springer International Publishing","author":[{"first_name":"Tobias","full_name":"Steinle, Tobias","last_name":"Steinle"},{"last_name":"Vrabec","full_name":"Vrabec, Jadran","first_name":"Jadran"},{"last_name":"Walther","first_name":"Andrea","full_name":"Walther, Andrea"}],"doi":"10.1007/978-3-319-09063-4_19","_id":"1781","date_updated":"2022-01-06T06:53:20Z","page":"233-243","type":"conference","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.","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.","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} }","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."},"year":"2014"},{"page":"14-25","type":"conference","citation":{"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","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."},"year":"2014","series_title":"Lecture Notes in Computer Science","issue":"8427","doi":"10.1007/978-3-319-09165-5_2","_id":"1782","date_updated":"2022-01-06T06:53:20Z","date_created":"2018-03-26T13:50:37Z","status":"public","publication":"Proc. Conf. on Computers and Games (CG)","department":[{"_id":"27"},{"_id":"78"}],"publisher":"Springer","author":[{"last_name":"Graf","full_name":"Graf, Tobias","first_name":"Tobias"},{"first_name":"Lars","full_name":"Schaefers, Lars","last_name":"Schaefers"},{"first_name":"Marco","full_name":"Platzner, Marco","last_name":"Platzner","id":"398"}],"user_id":"24135","title":"On Semeai Detection in Monte-Carlo Go","place":"Switzerland"},{"_id":"335","page":"123-144","type":"book_chapter","year":"2014","citation":{"mla":"Platzner, Marco, and Christian Plessl. “Verschiebungen an der Grenze zwischen Hardware und Software.” Logiken strukturbildender Prozesse: Automatismen, edited by Jörn Künsemöller et al., Wilhelm Fink, 2014, pp. 123–44.","bibtex":"@inbook{Platzner_Plessl_2014, place={Paderborn}, series={Schriftenreihe des Graduiertenkollegs “Automatismen”}, title={Verschiebungen an der Grenze zwischen Hardware und Software}, booktitle={Logiken strukturbildender Prozesse: Automatismen}, publisher={Wilhelm Fink}, author={Platzner, Marco and Plessl, Christian}, editor={Künsemöller, Jörn and Eke, Norber Otto and Foit, Lioba and Kaerlein, Timo}, year={2014}, pages={123–144}, collection={Schriftenreihe des Graduiertenkollegs “Automatismen”} }","apa":"Platzner, M., & Plessl, C. (2014). Verschiebungen an der Grenze zwischen Hardware und Software. In J. Künsemöller, N. O. Eke, L. Foit, & T. Kaerlein (Eds.), Logiken strukturbildender Prozesse: Automatismen (pp. 123–144). Wilhelm Fink.","ama":"Platzner M, Plessl C. Verschiebungen an der Grenze zwischen Hardware und Software. In: Künsemöller J, Eke NO, Foit L, Kaerlein T, eds. Logiken strukturbildender Prozesse: Automatismen. Schriftenreihe des Graduiertenkollegs “Automatismen.” Wilhelm Fink; 2014:123-144.","chicago":"Platzner, Marco, and Christian Plessl. “Verschiebungen an der Grenze zwischen Hardware und Software.” In Logiken strukturbildender Prozesse: Automatismen, edited by Jörn Künsemöller, Norber Otto Eke, Lioba Foit, and Timo Kaerlein, 123–44. Schriftenreihe des Graduiertenkollegs “Automatismen.” Paderborn: Wilhelm Fink, 2014.","ieee":"M. Platzner and C. Plessl, “Verschiebungen an der Grenze zwischen Hardware und Software,” in Logiken strukturbildender Prozesse: Automatismen, J. Künsemöller, N. O. Eke, L. Foit, and T. Kaerlein, Eds. Paderborn: Wilhelm Fink, 2014, pp. 123–144.","short":"M. Platzner, C. Plessl, in: J. Künsemöller, N.O. Eke, L. Foit, T. Kaerlein (Eds.), Logiken strukturbildender Prozesse: Automatismen, Wilhelm Fink, Paderborn, 2014, pp. 123–144."},"user_id":"15278","ddc":["040"],"abstract":[{"lang":"eng","text":"Im Bereich der Computersysteme ist die Festlegung der Grenze zwischen Hardware und Software eine zentrale Problemstellung. Diese Grenze hat in den letzten Jahrzehnten nicht nur die Entwicklung von Computersystemen bestimmt, sondern auch die Strukturierung der Ausbildung in den Computerwissenschaften beeinflusst und sogar zur Entstehung von neuen Forschungsrichtungen gef{\\\"u}hrt. In diesem Beitrag besch{\\\"a}ftigen wir uns mit Verschiebungen an der Grenze zwischen Hardware und Software und diskutieren insgesamt drei qualitativ unterschiedliche Formen solcher Verschiebungen. Wir beginnen mit der Entwicklung von Computersystemen im letzten Jahrhundert und der Entstehung dieser Grenze, die Hardware und Software erst als eigenst{\\\"a}ndige Produkte differenziert. Dann widmen wir uns der Frage, welche Funktionen in einem Computersystem besser in Hardware und welche besser in Software realisiert werden sollten, eine Fragestellung die zu Beginn der 90er-Jahre zur Bildung einer eigenen Forschungsrichtung, dem sogenannten Hardware/Software Co-design, gef{\\\"u}hrt hat. Im Hardware/Software Co-design findet eine Verschiebung von Funktionen an der Grenze zwischen Hardware und Software w{\\\"a}hrend der Entwicklung eines Produktes statt, um Produkteigenschaften zu optimieren. Im fertig entwickelten und eingesetzten Produkt hingegen k{\\\"o}nnen wir dann eine feste Grenze zwischen Hardware und Software beobachten. Im dritten Teil dieses Beitrags stellen wir mit selbst-adaptiven Systemen eine hochaktuelle Forschungsrichtung vor. In unserem Kontext bedeutet Selbstadaption, dass ein System Verschiebungen von Funktionen an der Grenze zwischen Hardware und Software autonom w{\\\"a}hrend der Betriebszeit vornimmt. Solche Systeme beruhen auf rekonfigurierbarer Hardware, einer relativ neuen Technologie mit der die Hardware eines Computers w{\\\"a}hrend der Laufzeit ver{\\\"a}ndert werden kann. Diese Technologie f{\\\"u}hrt zu einer durchl{\\\"a}ssigen Grenze zwischen Hardware und Software bzw. l{\\\"o}st sie die herk{\\\"o}mmliche Vorstellung einer festen Hardware und einer flexiblen Software damit auf."}],"date_created":"2017-10-17T12:41:57Z","has_accepted_license":"1","status":"public","file":[{"file_size":2848154,"creator":"florida","file_id":"1424","date_updated":"2018-03-20T07:29:58Z","content_type":"application/pdf","success":1,"relation":"main_file","date_created":"2018-03-20T07:29:58Z","file_name":"335-2014_plessl_automatismen.pdf","access_level":"closed"}],"file_date_updated":"2018-03-20T07:29:58Z","publication":"Logiken strukturbildender Prozesse: Automatismen","publisher":"Wilhelm Fink","author":[{"last_name":"Platzner","id":"398","first_name":"Marco","full_name":"Platzner, Marco"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian"}],"quality_controlled":"1","date_updated":"2023-09-26T13:32:49Z","language":[{"iso":"ger"}],"series_title":"Schriftenreihe des Graduiertenkollegs \"Automatismen\"","title":"Verschiebungen an der Grenze zwischen Hardware und Software","place":"Paderborn","project":[{"_id":"1","grant_number":"160364472","name":"SFB 901"},{"grant_number":"160364472","name":"SFB 901 - Subprojekt C2","_id":"14"},{"_id":"4","name":"SFB 901 - Project Area C"}],"publication_identifier":{"isbn":["978-3-7705-5730-1"]},"publication_status":"published","editor":[{"last_name":"Künsemöller","full_name":"Künsemöller, Jörn","first_name":"Jörn"},{"last_name":"Eke","full_name":"Eke, Norber Otto","first_name":"Norber Otto"},{"last_name":"Foit","first_name":"Lioba","full_name":"Foit, Lioba"},{"full_name":"Kaerlein, Timo","first_name":"Timo","last_name":"Kaerlein"}],"department":[{"_id":"518"},{"_id":"27"},{"_id":"78"}]},{"ddc":["040"],"user_id":"15278","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"}],"volume":8405,"has_accepted_license":"1","status":"public","date_created":"2017-10-17T12:42:07Z","publisher":"Springer International Publishing","quality_controlled":"1","author":[{"first_name":"Tobias","full_name":"Kenter, Tobias","last_name":"Kenter","id":"3145"},{"last_name":"Vaz","id":"30332","first_name":"Gavin Francis","full_name":"Vaz, Gavin Francis"},{"last_name":"Plessl","id":"16153","first_name":"Christian","full_name":"Plessl, Christian","orcid":"0000-0001-5728-9982"}],"file_date_updated":"2018-03-20T07:02:02Z","publication":"Proceedings of the International Symposium on Reconfigurable Computing: Architectures, Tools, and Applications (ARC)","file":[{"file_size":330193,"file_id":"1387","creator":"florida","date_updated":"2018-03-20T07:02:02Z","content_type":"application/pdf","success":1,"relation":"main_file","file_name":"388-plessl14_arc.pdf","date_created":"2018-03-20T07:02:02Z","access_level":"closed"}],"_id":"388","intvolume":" 8405","type":"conference","citation":{"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.","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","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.","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)} }","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.","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."},"year":"2014","page":"144-155","title":"Partitioning and Vectorizing Binary Applications for a Reconfigurable Vector Computer","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"},{"grant_number":"610996","name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","_id":"34"}],"department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"doi":"10.1007/978-3-319-05960-0_13","date_updated":"2023-09-26T13:34:08Z","language":[{"iso":"eng"}],"series_title":"Lecture Notes in Computer Science (LNCS)"},{"department":[{"_id":"27"},{"_id":"518"},{"_id":"78"}],"project":[{"_id":"1","grant_number":"160364472","name":"SFB 901"},{"name":"SFB 901 - Subprojekt C2","grant_number":"160364472","_id":"14"},{"_id":"4","name":"SFB 901 - Project Area C"},{"grant_number":"257906","name":"Engineering Proprioception in Computing Systems","_id":"31"}],"title":"Seven Recipes for Setting Your FPGA on Fire – A Cookbook on Heat Generators","language":[{"iso":"eng"}],"date_updated":"2023-09-26T13:33:06Z","doi":"10.1016/j.micpro.2013.12.001","file":[{"date_created":"2018-03-20T07:20:31Z","file_name":"363-plessl13_micpro.pdf","access_level":"closed","file_size":1499996,"file_id":"1408","creator":"florida","date_updated":"2018-03-20T07:20:31Z","content_type":"application/pdf","relation":"main_file","success":1}],"file_date_updated":"2018-03-20T07:20:31Z","publication":"Microprocessors and Microsystems","quality_controlled":"1","publisher":"Elsevier","author":[{"full_name":"Agne, Andreas","first_name":"Andreas","last_name":"Agne"},{"first_name":"Hendrik","full_name":"Hangmann, Hendrik","last_name":"Hangmann"},{"last_name":"Happe","full_name":"Happe, Markus","first_name":"Markus"},{"last_name":"Platzner","id":"398","first_name":"Marco","full_name":"Platzner, Marco"},{"orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian","id":"16153","last_name":"Plessl"}],"date_created":"2017-10-17T12:42:02Z","status":"public","has_accepted_license":"1","volume":38,"abstract":[{"text":"Due to the continuously shrinking device structures and increasing densities of FPGAs, thermal aspects have become the new focus for many research projects over the last years. Most researchers rely on temperature simulations to evaluate their novel thermal management techniques. However, these temperature simulations require a high computational effort if a detailed thermal model is used and their accuracies are often unclear. In contrast to simulations, the use of synthetic heat sources allows for experimental evaluation of temperature management methods. In this paper we investigate the creation of significant rises in temperature on modern FPGAs to enable future evaluation of thermal management techniques based on experiments. To that end, we have developed seven different heat-generating cores that use different subsets of FPGA resources. Our experimental results show that, according to external temperature probes connected to the FPGA’s heat sink, we can increase the temperature by an average of 81 !C. This corresponds to an average increase of 156.3 !C as measured by the built-in thermal diodes of our Virtex-5 FPGAs in less than 30 min by only utilizing about 21 percent of the slices.","lang":"eng"}],"user_id":"15278","ddc":["040"],"page":"911-919","year":"2014","type":"journal_article","citation":{"mla":"Agne, Andreas, et al. “Seven Recipes for Setting Your FPGA on Fire – A Cookbook on Heat Generators.” Microprocessors and Microsystems, vol. 38, no. 8, Part B, Elsevier, 2014, pp. 911–19, doi:10.1016/j.micpro.2013.12.001.","bibtex":"@article{Agne_Hangmann_Happe_Platzner_Plessl_2014, title={Seven Recipes for Setting Your FPGA on Fire – A Cookbook on Heat Generators}, volume={38}, DOI={10.1016/j.micpro.2013.12.001}, number={8, Part B}, journal={Microprocessors and Microsystems}, publisher={Elsevier}, author={Agne, Andreas and Hangmann, Hendrik and Happe, Markus and Platzner, Marco and Plessl, Christian}, year={2014}, pages={911–919} }","ama":"Agne A, Hangmann H, Happe M, Platzner M, Plessl C. Seven Recipes for Setting Your FPGA on Fire – A Cookbook on Heat Generators. Microprocessors and Microsystems. 2014;38(8, Part B):911-919. doi:10.1016/j.micpro.2013.12.001","apa":"Agne, A., Hangmann, H., Happe, M., Platzner, M., & Plessl, C. (2014). Seven Recipes for Setting Your FPGA on Fire – A Cookbook on Heat Generators. Microprocessors and Microsystems, 38(8, Part B), 911–919. https://doi.org/10.1016/j.micpro.2013.12.001","chicago":"Agne, Andreas, Hendrik Hangmann, Markus Happe, Marco Platzner, and Christian Plessl. “Seven Recipes for Setting Your FPGA on Fire – A Cookbook on Heat Generators.” Microprocessors and Microsystems 38, no. 8, Part B (2014): 911–19. https://doi.org/10.1016/j.micpro.2013.12.001.","ieee":"A. Agne, H. Hangmann, M. Happe, M. Platzner, and C. Plessl, “Seven Recipes for Setting Your FPGA on Fire – A Cookbook on Heat Generators,” Microprocessors and Microsystems, vol. 38, no. 8, Part B, pp. 911–919, 2014, doi: 10.1016/j.micpro.2013.12.001.","short":"A. Agne, H. Hangmann, M. Happe, M. Platzner, C. Plessl, Microprocessors and Microsystems 38 (2014) 911–919."},"_id":"363","intvolume":" 38","issue":"8, Part B"},{"status":"public","has_accepted_license":"1","date_created":"2017-10-17T12:42:05Z","author":[{"full_name":"Riebler, Heinrich","first_name":"Heinrich","id":"8961","last_name":"Riebler"},{"first_name":"Tobias","full_name":"Kenter, Tobias","last_name":"Kenter","id":"3145"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian"},{"last_name":"Sorge","full_name":"Sorge, Christoph","first_name":"Christoph"}],"quality_controlled":"1","publisher":"IEEE","publication":"Proceedings of Field-Programmable Custom Computing Machines (FCCM)","keyword":["coldboot"],"file_date_updated":"2018-03-20T07:14:20Z","file":[{"access_level":"closed","file_name":"377-FCCM14.pdf","date_created":"2018-03-20T07:14:20Z","relation":"main_file","success":1,"date_updated":"2018-03-20T07:14:20Z","content_type":"application/pdf","file_id":"1397","creator":"florida","file_size":1003907}],"ddc":["040"],"user_id":"15278","abstract":[{"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.","lang":"eng"}],"citation":{"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.","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.","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","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","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.","short":"H. Riebler, T. Kenter, C. Plessl, C. Sorge, in: Proceedings of Field-Programmable Custom Computing Machines (FCCM), IEEE, 2014, pp. 222–229."},"type":"conference","year":"2014","page":"222-229","_id":"377","project":[{"_id":"1","name":"SFB 901","grant_number":"160364472"},{"_id":"14","name":"SFB 901 - Subprojekt C2","grant_number":"160364472"},{"name":"SFB 901 - Project Area C","_id":"4"},{"_id":"34","name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","grant_number":"610996"}],"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"},{"language":[{"iso":"eng"}],"doi":"10.1145/2617596","date_updated":"2023-09-26T13:33:31Z","project":[{"_id":"1","name":"SFB 901","grant_number":"160364472"},{"grant_number":"160364472","name":"SFB 901 - Subprojekt C2","_id":"14"},{"_id":"4","name":"SFB 901 - Project Area C"},{"grant_number":"257906","name":"Engineering Proprioception in Computing Systems","_id":"31"}],"department":[{"_id":"27"},{"_id":"78"},{"_id":"518"}],"title":"Self-awareness as a Model for Designing and Operating Heterogeneous Multicores","year":"2014","type":"journal_article","citation":{"ieee":"A. Agne, M. Happe, A. Lösch, C. Plessl, and M. Platzner, “Self-awareness as a Model for Designing and Operating Heterogeneous Multicores,” ACM Transactions on Reconfigurable Technology and Systems (TRETS), vol. 7, no. 2, Art. no. 13, 2014, doi: 10.1145/2617596.","short":"A. Agne, M. Happe, A. Lösch, C. Plessl, M. Platzner, ACM Transactions on Reconfigurable Technology and Systems (TRETS) 7 (2014).","mla":"Agne, Andreas, et al. “Self-Awareness as a Model for Designing and Operating Heterogeneous Multicores.” ACM Transactions on Reconfigurable Technology and Systems (TRETS), vol. 7, no. 2, 13, ACM, 2014, doi:10.1145/2617596.","bibtex":"@article{Agne_Happe_Lösch_Plessl_Platzner_2014, title={Self-awareness as a Model for Designing and Operating Heterogeneous Multicores}, volume={7}, DOI={10.1145/2617596}, number={213}, journal={ACM Transactions on Reconfigurable Technology and Systems (TRETS)}, publisher={ACM}, author={Agne, Andreas and Happe, Markus and Lösch, Achim and Plessl, Christian and Platzner, Marco}, year={2014} }","ama":"Agne A, Happe M, Lösch A, Plessl C, Platzner M. Self-awareness as a Model for Designing and Operating Heterogeneous Multicores. ACM Transactions on Reconfigurable Technology and Systems (TRETS). 2014;7(2). doi:10.1145/2617596","apa":"Agne, A., Happe, M., Lösch, A., Plessl, C., & Platzner, M. (2014). Self-awareness as a Model for Designing and Operating Heterogeneous Multicores. ACM Transactions on Reconfigurable Technology and Systems (TRETS), 7(2), Article 13. https://doi.org/10.1145/2617596","chicago":"Agne, Andreas, Markus Happe, Achim Lösch, Christian Plessl, and Marco Platzner. “Self-Awareness as a Model for Designing and Operating Heterogeneous Multicores.” ACM Transactions on Reconfigurable Technology and Systems (TRETS) 7, no. 2 (2014). https://doi.org/10.1145/2617596."},"article_number":"13","issue":"2","_id":"365","intvolume":" 7","volume":7,"date_created":"2017-10-17T12:42:03Z","has_accepted_license":"1","status":"public","publication":"ACM Transactions on Reconfigurable Technology and Systems (TRETS)","file_date_updated":"2018-03-20T07:19:19Z","publisher":"ACM","author":[{"first_name":"Andreas","full_name":"Agne, Andreas","last_name":"Agne"},{"last_name":"Happe","full_name":"Happe, Markus","first_name":"Markus"},{"last_name":"Lösch","id":"43646","first_name":"Achim","full_name":"Lösch, Achim"},{"id":"16153","last_name":"Plessl","orcid":"0000-0001-5728-9982","full_name":"Plessl, Christian","first_name":"Christian"},{"id":"398","last_name":"Platzner","full_name":"Platzner, Marco","first_name":"Marco"}],"quality_controlled":"1","file":[{"success":1,"relation":"main_file","content_type":"application/pdf","date_updated":"2018-03-20T07:19:19Z","creator":"florida","file_id":"1406","file_size":916052,"access_level":"closed","date_created":"2018-03-20T07:19:19Z","file_name":"365-plessl14_trets_01.pdf"}],"ddc":["040"],"user_id":"15278","abstract":[{"text":"Self-aware computing is a paradigm for structuring and simplifying the design and operation of computing systems that face unprecedented levels of system dynamics and thus require novel forms of adaptivity. The generality of the paradigm makes it applicable to many types of computing systems and, previously, researchers started to introduce concepts of self-awareness to multicore architectures. In our work we build on a recent reference architectural framework as a model for self-aware computing and instantiate it for an FPGA-based heterogeneous multicore running the ReconOS reconfigurable architecture and operating system. After presenting the model for self-aware computing and ReconOS, we demonstrate with a case study how a multicore application built on the principle of self-awareness, autonomously adapts to changes in the workload and system state. Our work shows that the reference architectural framework as a model for self-aware computing can be practically applied and allows us to structure and simplify the design process, which is essential for designing complex future computing systems.","lang":"eng"}]}]