{"quality_controlled":"1","abstract":[{"lang":"eng","text":"Branch and bound (B&B) algorithms structure the search space as a tree and eliminate infeasible solutions early by pruning subtrees that cannot lead to a valid or optimal solution. Custom hardware designs significantly accelerate the execution of these algorithms. In this article, we demonstrate a high-performance B&B implementation on FPGAs. First, we identify general elements of B&B algorithms and describe their implementation as a finite state machine. Then, we introduce workers that autonomously cooperate using work stealing to allow parallel execution and full utilization of the target FPGA. Finally, we explore advantages of instance-specific designs that target a specific problem instance to improve performance.\r\n\r\nWe evaluate our concepts by applying them to a branch and bound problem, the reconstruction of corrupted AES keys obtained from cold-boot attacks. The evaluation shows that our work stealing approach is scalable with the available resources and provides speedups proportional to the number of workers. Instance-specific designs allow us to achieve an overall speedup of 47 × compared to the fastest implementation of AES key reconstruction so far. Finally, we demonstrate how instance-specific designs can be generated just-in-time such that the provided speedups outweigh the additional time required for design synthesis."}],"has_accepted_license":"1","project":[{"grant_number":"160364472","_id":"1","name":"SFB 901"},{"name":"SFB 901 - Project Area C","_id":"4"},{"name":"SFB 901 - Subproject C2","_id":"14","grant_number":"160364472"},{"name":"Self-Adaptive Virtualisation-Aware High-Performance/Low-Energy Heterogeneous System Architectures","_id":"34","grant_number":"610996"},{"name":"Computing Resources Provided by the Paderborn Center for Parallel Computing","_id":"52"}],"date_created":"2017-07-25T14:17:32Z","file_date_updated":"2018-11-02T16:04:14Z","keyword":["coldboot"],"issue":"3","publication_status":"published","ddc":["000"],"page":"24:1-24:23","file":[{"access_level":"closed","content_type":"application/pdf","relation":"main_file","date_created":"2018-11-02T16:04:14Z","date_updated":"2018-11-02T16:04:14Z","creator":"ups","file_size":2131617,"success":1,"file_id":"5322","file_name":"a24-riebler.pdf"}],"doi":"10.1145/3053687","author":[{"first_name":"Heinrich","full_name":"Riebler, Heinrich","id":"8961","last_name":"Riebler"},{"orcid":"0000-0002-5708-7632","first_name":"Michael","full_name":"Lass, Michael","id":"24135","last_name":"Lass"},{"first_name":"Robert","full_name":"Mittendorf, Robert","last_name":"Mittendorf"},{"last_name":"Löcke","full_name":"Löcke, Thomas","first_name":"Thomas"},{"full_name":"Plessl, Christian","last_name":"Plessl","id":"16153","orcid":"0000-0001-5728-9982","first_name":"Christian"}],"publisher":"Association for Computing Machinery (ACM)","intvolume":"        10","status":"public","year":"2017","citation":{"bibtex":"@article{Riebler_Lass_Mittendorf_Löcke_Plessl_2017, title={Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs}, volume={10}, DOI={<a href=\"https://doi.org/10.1145/3053687\">10.1145/3053687</a>}, number={3}, journal={ACM Transactions on Reconfigurable Technology and Systems (TRETS)}, publisher={Association for Computing Machinery (ACM)}, author={Riebler, Heinrich and Lass, Michael and Mittendorf, Robert and Löcke, Thomas and Plessl, Christian}, year={2017}, pages={24:1-24:23} }","ama":"Riebler H, Lass M, Mittendorf R, Löcke T, Plessl C. Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs. <i>ACM Transactions on Reconfigurable Technology and Systems (TRETS)</i>. 2017;10(3):24:1-24:23. doi:<a href=\"https://doi.org/10.1145/3053687\">10.1145/3053687</a>","mla":"Riebler, Heinrich, et al. “Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs.” <i>ACM Transactions on Reconfigurable Technology and Systems (TRETS)</i>, vol. 10, no. 3, Association for Computing Machinery (ACM), 2017, p. 24:1-24:23, doi:<a href=\"https://doi.org/10.1145/3053687\">10.1145/3053687</a>.","ieee":"H. Riebler, M. Lass, R. Mittendorf, T. Löcke, and C. Plessl, “Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs,” <i>ACM Transactions on Reconfigurable Technology and Systems (TRETS)</i>, vol. 10, no. 3, p. 24:1-24:23, 2017, doi: <a href=\"https://doi.org/10.1145/3053687\">10.1145/3053687</a>.","chicago":"Riebler, Heinrich, Michael Lass, Robert Mittendorf, Thomas Löcke, and Christian Plessl. “Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs.” <i>ACM Transactions on Reconfigurable Technology and Systems (TRETS)</i> 10, no. 3 (2017): 24:1-24:23. <a href=\"https://doi.org/10.1145/3053687\">https://doi.org/10.1145/3053687</a>.","short":"H. Riebler, M. Lass, R. Mittendorf, T. Löcke, C. Plessl, ACM Transactions on Reconfigurable Technology and Systems (TRETS) 10 (2017) 24:1-24:23.","apa":"Riebler, H., Lass, M., Mittendorf, R., Löcke, T., &#38; Plessl, C. (2017). Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs. <i>ACM Transactions on Reconfigurable Technology and Systems (TRETS)</i>, <i>10</i>(3), 24:1-24:23. <a href=\"https://doi.org/10.1145/3053687\">https://doi.org/10.1145/3053687</a>"},"user_id":"15278","publication_identifier":{"issn":["1936-7406"]},"department":[{"_id":"27"},{"_id":"518"}],"_id":"18","title":"Efficient Branch and Bound on FPGAs Using Work Stealing and Instance-Specific Designs","volume":10,"language":[{"iso":"eng"}],"publication":"ACM Transactions on Reconfigurable Technology and Systems (TRETS)","date_updated":"2023-09-26T13:23:58Z","type":"journal_article"}