{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:01:55Z","timestamp":1773414115777,"version":"3.50.1"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T00:00:00Z","timestamp":1714435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["380524764"],"award-info":[{"award-number":["380524764"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Reconfigurable Technol. Syst."],"published-print":{"date-parts":[[2024,6,30]]},"abstract":"<jats:p>\n            With the increasing application of machine learning (ML) algorithms in embedded systems, there is a rising necessity to design low-cost computer arithmetic for these resource-constrained systems. As a result, emerging models of computation, such as approximate and stochastic computing, that leverage the inherent error-resilience of such algorithms are being actively explored for implementing ML inference on resource-constrained systems. Approximate computing (AxC) aims to provide disproportionate gains in the power, performance, and area (PPA) of an application by allowing some level of reduction in its behavioral accuracy (BEHAV). Using approximate operators (AxOs) for computer arithmetic forms one of the more prevalent methods of implementing AxC. AxOs provide the additional scope for finer granularity of optimization, compared to only precision scaling of computer arithmetic. To this end, the design of platform-specific and cost-efficient approximate operators forms an important research goal. Recently, multiple works have reported the use of AI\/ML-based approaches for synthesizing novel FPGA-based AxOs. However, most of such works limit the use of AI\/ML to designing ML-based surrogate functions that are used during iterative optimization processes. To this end, we propose a novel data analysis-driven mathematical programming-based approach to synthesizing approximate operators for FPGAs. Specifically, we formulate\n            <jats:italic>mixed integer quadratically constrained programs<\/jats:italic>\n            based on the results of correlation analysis of the characterization data and use the solutions to enable a more directed search approach for evolutionary optimization algorithms. Compared to traditional evolutionary algorithms-based optimization, we report up to 21% improvement in the hypervolume, for joint optimization of PPA and BEHAV, in the design of signed 8-bit multipliers. Further, we report up to 27% better hypervolume than other state-of-the-art approaches to DSE for FPGA-based application-specific AxOs.\n          <\/jats:p>","DOI":"10.1145\/3648694","type":"journal-article","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T12:20:30Z","timestamp":1708345230000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["<i>AxOMaP<\/i>\n            : Designing FPGA-based\n            <u>A<\/u>\n            ppro\n            <u>x<\/u>\n            imate Arithmetic\n            <u>O<\/u>\n            perators using\n            <u>Ma<\/u>\n            thematical\n            <u>P<\/u>\n            rogramming"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2243-5350","authenticated-orcid":false,"given":"Siva Satyendra","family":"Sahoo","sequence":"first","affiliation":[{"name":"Interuniversity Micro-Electronic Centre (IMEC), Leuven, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9774-9522","authenticated-orcid":false,"given":"Salim","family":"Ullah","sequence":"additional","affiliation":[{"name":"cfaed, Technische Universit\u00e4t Dresden, Dresden, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7125-1737","authenticated-orcid":false,"given":"Akash","family":"Kumar","sequence":"additional","affiliation":[{"name":"cfaed, Technische Universit\u00e4t Dresden, Dresden, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,4,30]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3107370"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2023.3292947"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","first-page":"2547","DOI":"10.1109\/IJCNN.2017.7966166","volume-title":"2017 International Joint Conference on Neural Networks (IJCNN\u201917)","author":"Alemdar Hande","year":"2017","unstructured":"Hande Alemdar, Vincent Leroy, Adrien Prost-Boucle, and Fr\u00e9d\u00e9ric P\u00e9trot. 2017. Ternary neural networks for resource-efficient AI applications. In 2017 International Joint Conference on Neural Networks (IJCNN\u201917). 2547\u20132554. 10.1109\/IJCNN.2017.7966166"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1973.223648"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02338"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1093\/qjmam\/4.2.236"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342073"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2018.8297390"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ReConFig48160.2019.8994777"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386263.3406907"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/2503308.2503311"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2015.7372600"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9181185"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2011.2148970"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSID.2011.51"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2016.2631630"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2017.35"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/1117201.1117205"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2893356"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317781"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7926993"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2020.3032495"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT47387.2019.00054"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2009.5272301"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2011.48"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2009.2033536"},{"key":"e_1_3_2_29_2","unstructured":"Aleksandra P\u0142o\u0144ska and Piotr P\u0142o\u0144ski. 2021. MLJAR: State-of-the-art Automated Machine Learning Framework for Tabular Data. Version 0.10.3. https:\/\/github.com\/mljar\/mljar-supervised"},{"key":"e_1_3_2_30_2","series-title":"DAC\u201920","volume-title":"Proceedings of the 57th ACM\/EDAC\/IEEE Design Automation Conference","author":"Prabakaran Bharath Srinivas","year":"2020","unstructured":"Bharath Srinivas Prabakaran, Vojtech Mrazek, Zdenek Vasicek, Lukas Sekanina, and Muhammad Shafique. 2020. ApproxFPGAs: Embracing ASIC-based approximate arithmetic components for FPGA-based systems. In Proceedings of the 57th ACM\/EDAC\/IEEE Design Automation Conference (Virtual Event, USA) (DAC\u201920). IEEE Press, Article 118, 6 pages."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323678"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342140"},{"key":"e_1_3_2_33_2","article-title":"CFU playground: Full-stack open-source framework for tiny machine learning (tinyML) acceleration on FPGAs","author":"Prakash Shvetank","year":"2022","unstructured":"Shvetank Prakash, Tim Callahan, Joseph Bushagour, Colby Banbury, Alan V. Green, Pete Warden, Tim Ansell, and Vijay Janapa Reddi. 2022. CFU playground: Full-stack open-source framework for tiny machine learning (tinyML) acceleration on FPGAs. arXiv preprint arXiv:2201.01863 (2022).","journal-title":"arXiv preprint arXiv:2201.01863"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3566097.3567891"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2967005"},{"key":"e_1_3_2_36_2","unstructured":"Siva Satyendra Sahoo Salim Ullah Soumyo Bhattacharjee and Akash Kumar. 2023. AxOCS: Scaling FPGA-based Approximate Operators using Configuration Supersampling. arxiv:2309.12830 [cs.AR]."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3609096"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744778"},{"key":"e_1_3_2_39_2","volume-title":"DAC","author":"Shafique Muhammad","year":"2016","unstructured":"Muhammad Shafique, Rehan Hafiz, Semeen Rehman, Walaa El-Harouni, and J\u00f6rg Henkel. 2016. Cross-layer approximate computing: From logic to architectures. In DAC."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465845"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3056337"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3513262"},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1109\/DAC18074.2021.9586260","volume-title":"2021 58th ACM\/IEEE Design Automation Conference (DAC\u201921)","author":"Ullah Salim","year":"2021","unstructured":"Salim Ullah, Siva Satyendra Sahoo, and Akash Kumar. 2021. CLAppED: A design framework for implementing cross-layer approximation in FPGA-based embedded systems. In 2021 58th ACM\/IEEE Design Automation Conference (DAC\u201921). 475\u2013480. 10.1109\/DAC18074.2021.9586260"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2988404"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2970968"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2751163"},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1109\/ACSSC.2014.7094659","volume-title":"2014 48th Asilomar Conference on Signals, Systems and Computers","author":"Walters E. George","year":"2014","unstructured":"E. George Walters. 2014. Partial-product generation and addition for multiplication in FPGAs with 6-input LUTs. In 2014 48th Asilomar Conference on Signals, Systems and Computers. 1247\u20131251. 10.1109\/ACSSC.2014.7094659"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.3390\/computers5040020"},{"key":"e_1_3_2_49_2","article-title":"BFloat16: The secret to high performance on Cloud TPUs","author":"Wang Shibo","year":"2019","unstructured":"Shibo Wang and Pankaj Kanwar. 2019. BFloat16: The secret to high performance on Cloud TPUs. Google Cloud Blog (2019).","journal-title":"Google Cloud Blog"},{"key":"e_1_3_2_50_2","article-title":"Xilinx UltraScale Architecture DSP Slice User Guide","year":"2021","unstructured":"Xilinx. 2021. Xilinx UltraScale Architecture DSP Slice User Guide. https:\/\/docs.xilinx.com\/v\/u\/en-US\/ug579-ultrascale-dspAccessed: 2023-10-04.","journal-title":"https:\/\/docs.xilinx.com\/v\/u\/en-US\/ug579-ultrascale-dsp"},{"key":"e_1_3_2_51_2","article-title":"Xilinx Versal ACAP DSP Engine Architecture Manual","year":"2022","unstructured":"Xilinx. 2022. Xilinx Versal ACAP DSP Engine Architecture Manual. https:\/\/docs.xilinx.com\/r\/en-US\/am004-versal-dsp-engine\/Device-ResourcesAccessed: 2023-10-04.","journal-title":"https:\/\/docs.xilinx.com\/r\/en-US\/am004-versal-dsp-engine\/Device-Resources"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2013.6691096"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"}],"container-title":["ACM Transactions on Reconfigurable Technology and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3648694","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3648694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:20Z","timestamp":1750287020000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3648694"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,30]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,6,30]]}},"alternative-id":["10.1145\/3648694"],"URL":"https:\/\/doi.org\/10.1145\/3648694","relation":{},"ISSN":["1936-7406","1936-7414"],"issn-type":[{"value":"1936-7406","type":"print"},{"value":"1936-7414","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,30]]},"assertion":[{"value":"2023-07-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-15","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}