{"date_updated":"2025-11-28T10:09:59Z","conference":{"location":"Naples, Italy ","start_date":"2025-06-23","end_date":"2025-06-26","name":"55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)"},"type":"conference","author":[{"id":"260919","full_name":"Jalil, Farjana","last_name":"Jalil","first_name":"Farjana"},{"full_name":"Awais, Muhammad","last_name":"Awais","first_name":"Muhammad"},{"full_name":"Ahmed, Qazi Arbab","id":"257333","orcid":"0000-0002-1837-2254","first_name":"Qazi Arbab","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0002-1837-2254/work/188568216","last_name":"Ahmed"},{"first_name":"Hassan Ghasemzadeh","last_name":"Mohammadi","full_name":"Mohammadi, Hassan Ghasemzadeh"},{"first_name":"Thorsten","last_name":"Jungeblut","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0001-7425-8766/work/188568217","orcid":"0000-0001-7425-8766","full_name":"Jungeblut, Thorsten","id":"242294"},{"first_name":"Marco","last_name":"Platzner","full_name":"Platzner, Marco"}],"status":"public","publication_identifier":{"eisbn":["979-8-3315-1205-7"]},"publisher":"IEEE","publication":"2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","page":"115-118","main_file_link":[{"open_access":"1"}],"department":[{"_id":"103"}],"year":"2025","_id":"6073","abstract":[{"lang":"eng","text":"Automatic synthesis of approximate accelerators remains a challenging problem owing to extremely large design space and high verification costs for evaluating intermediate design candidates. Existing frameworks typically employ searchbased strategies to explore the design space. While some frameworks aggressively prune candidate configurations to reduce runtime, leading to prematurely eliminating high-quality solutions, others use a learning based approach for design space exploration with an increased runtime cost. In this work, we propose an advanced Design Space Exploration (DSE) approach that incorporates a refined, cost-aware selection and expansion strategy to enable a more balanced and effective traversal of the search space. Our method builds upon an existing learning-based state-of-the-art technique to improve the accuracy and quality of tradeoffs, especially for large-scale accelerators. Experimental results demonstrate that our proposed approach achieves comparable area and power savings for small to medium-scale benchmarks while significantly outperforming the state-of-the-art approaches on larger circuits with up to 9% additional area savings with almost no runtime overhead."}],"title":"Deep&Wide: Achieving Area Efficiency in Scalable Approximate Accelerators","language":[{"iso":"eng"}],"project":[{"name":"Institut für Systemdynamik und Mechatronik","_id":"beb248c8-cd75-11ed-b77c-e432b4711f7b"}],"citation":{"alphadin":"<span style=\"font-variant:small-caps;\">Jalil, Farjana</span> ; <span style=\"font-variant:small-caps;\">Awais, Muhammad</span> ; <span style=\"font-variant:small-caps;\">Ahmed, Qazi Arbab</span> ; <span style=\"font-variant:small-caps;\">Mohammadi, Hassan Ghasemzadeh</span> ; <span style=\"font-variant:small-caps;\">Jungeblut, Thorsten</span> ; <span style=\"font-variant:small-caps;\">Platzner, Marco</span>: Deep&#38;Wide: Achieving Area Efficiency in Scalable Approximate Accelerators. In: <span style=\"font-variant:small-caps;\">Institute of Electrical and Electronics Engineers (IEEE)</span> (Hrsg.): <i>2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)</i> : IEEE, 2025, S. 115–118","apa":"Jalil, F., Awais, M., Ahmed, Q. A., Mohammadi, H. G., Jungeblut, T., &#38; Platzner, M. (2025). Deep&#38;Wide: Achieving Area Efficiency in Scalable Approximate Accelerators. In Institute of Electrical and Electronics Engineers (IEEE) (Ed.), <i>2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)</i> (pp. 115–118). Naples, Italy : IEEE. <a href=\"https://doi.org/10.1109/DSN-W65791.2025.00048\">https://doi.org/10.1109/DSN-W65791.2025.00048</a>","mla":"Jalil, Farjana, et al. “Deep&#38;Wide: Achieving Area Efficiency in Scalable Approximate Accelerators.” <i>2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)</i>, edited by Institute of Electrical and Electronics Engineers (IEEE), IEEE, 2025, pp. 115–18, doi:<a href=\"https://doi.org/10.1109/DSN-W65791.2025.00048\">10.1109/DSN-W65791.2025.00048</a>.","ieee":"F. Jalil, M. Awais, Q. A. Ahmed, H. G. Mohammadi, T. Jungeblut, and M. Platzner, “Deep&#38;Wide: Achieving Area Efficiency in Scalable Approximate Accelerators,” in <i>2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)</i>, Naples, Italy , 2025, pp. 115–118.","ama":"Jalil F, Awais M, Ahmed QA, Mohammadi HG, Jungeblut T, Platzner M. Deep&#38;Wide: Achieving Area Efficiency in Scalable Approximate Accelerators. In: Institute of Electrical and Electronics Engineers (IEEE), ed. <i>2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)</i>. IEEE; 2025:115-118. doi:<a href=\"https://doi.org/10.1109/DSN-W65791.2025.00048\">10.1109/DSN-W65791.2025.00048</a>","short":"F. Jalil, M. Awais, Q.A. Ahmed, H.G. Mohammadi, T. Jungeblut, M. Platzner, in: Institute of Electrical and Electronics Engineers (IEEE) (Ed.), 2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), IEEE, 2025, pp. 115–118.","bibtex":"@inproceedings{Jalil_Awais_Ahmed_Mohammadi_Jungeblut_Platzner_2025, title={Deep&#38;Wide: Achieving Area Efficiency in Scalable Approximate Accelerators}, DOI={<a href=\"https://doi.org/10.1109/DSN-W65791.2025.00048\">10.1109/DSN-W65791.2025.00048</a>}, booktitle={2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)}, publisher={IEEE}, author={Jalil, Farjana and Awais, Muhammad and Ahmed, Qazi Arbab and Mohammadi, Hassan Ghasemzadeh and Jungeblut, Thorsten and Platzner, Marco}, editor={Institute of Electrical and Electronics Engineers (IEEE)Editor}, year={2025}, pages={115–118} }","chicago":"Jalil, Farjana, Muhammad Awais, Qazi Arbab Ahmed, Hassan Ghasemzadeh Mohammadi, Thorsten Jungeblut, and Marco Platzner. “Deep&#38;Wide: Achieving Area Efficiency in Scalable Approximate Accelerators.” In <i>2025 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)</i>, edited by Institute of Electrical and Electronics Engineers (IEEE), 115–18. IEEE, 2025. <a href=\"https://doi.org/10.1109/DSN-W65791.2025.00048\">https://doi.org/10.1109/DSN-W65791.2025.00048</a>."},"user_id":"257333","publication_status":"published","doi":"10.1109/DSN-W65791.2025.00048","date_created":"2025-07-24T11:31:57Z","oa":"1","corporate_editor":["Institute of Electrical and Electronics Engineers (IEEE)"]}