{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T04:39:49Z","timestamp":1767847189927,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ERDF Operational Program of Catalonia 2014-2020 (DRAC Project)","award":["001-P-001723"],"award-info":[{"award-number":["001-P-001723"]}]},{"name":"Spanish State Research Agency - Ministry of Science and Innovation","award":["PID2019-107255GB"],"award-info":[{"award-number":["PID2019-107255GB"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,2,28]]},"DOI":"10.1145\/3503222.3507746","type":"proceedings-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T20:49:01Z","timestamp":1645562941000},"page":"56-69","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["BiSon-e: a lightweight and high-performance accelerator for narrow integer linear algebra computing on the edge"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1385-7962","authenticated-orcid":false,"given":"Enrico","family":"Reggiani","sequence":"first","affiliation":[{"name":"Polytechnic University of Catalonia, Spain \/ Barcelona Supercomputing Center, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4945-7338","authenticated-orcid":false,"given":"Crist\u00f3bal Ram\u00edrez","family":"Lazo","sequence":"additional","affiliation":[{"name":"Polytechnic University of Catalonia, Spain \/ Barcelona Supercomputing Center, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2407-1228","authenticated-orcid":false,"given":"Roger Figueras","family":"Bagu\u00e9","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1277-9296","authenticated-orcid":false,"given":"Adri\u00e1n","family":"Cristal","sequence":"additional","affiliation":[{"name":"Polytechnic University of Catalonia, Spain \/ Barcelona Supercomputing Center, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0214-9904","authenticated-orcid":false,"given":"Mauro","family":"Olivieri","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome, Italy \/ Barcelona Supercomputing Center, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0544-9697","authenticated-orcid":false,"given":"Osman Sabri","family":"Unsal","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,2,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Kamel Abdelouahab Maxime Pelcat Jocelyn Serot and Fran\u00e7ois Berry. 2018. Accelerating CNN inference on FPGAs: A Survey. arXiv e-prints Article arXiv:1806.01683 May arXiv:1806.01683 pages. arxiv:1806.01683."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/DCIS51330.2020.9268664"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2019.00023"},{"key":"e_1_3_2_1_4_1","article-title":"A Survey of String Matching Algorithms","volume":"4","author":"Al-Khamaiseh Koloud","year":"2014","unstructured":"Koloud Al-Khamaiseh and Shadi ALShagarin. 2014. A Survey of String Matching Algorithms. International Journal of Engineering Research and Applications, 4 (2014), 08, 144\u2013156.","journal-title":"International Journal of Engineering Research and Applications"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics"},{"key":"e_1_3_2_1_7_1","volume-title":"The Practical Efficiency of Convolutions in Pattern Matching Algorithms. Fundam. Inf., 84, 1","author":"Amir Amihood","year":"2008","unstructured":"Amihood Amir, Avivit Levy, and Liron Reuveni. 2008. The Practical Efficiency of Convolutions in Pattern Matching Algorithms. Fundam. Inf., 84, 1 (2008), jan, 1\u201315. issn:0169-2968"},{"key":"e_1_3_2_1_8_1","unstructured":"Ron Banner Yury Nahshan Elad Hoffer and Daniel Soudry. 2018. Post-training 4-bit quantization of convolution networks for rapid-deployment. arXiv e-prints Article arXiv:1810.05723 Oct. arXiv:1810.05723 pages. arxiv:1810.05723."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Z\u00fclal Bing\u00f6l Mohammed Alser Onur Mutlu Ozcan Ozturk and Can Alkan. 2021. GateKeeper-GPU: Fast and Accurate Pre-Alignment Filtering in Short Read Mapping. 209\u2013209. https:\/\/doi.org\/10.1109\/IPDPSW52791.2021.00039 10.1109\/IPDPSW52791.2021.00039","DOI":"10.1109\/IPDPSW52791.2021.00039"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/0885-064X(86)90001-4"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00014"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0747-7171(89)80004-5"},{"key":"e_1_3_2_1_13_1","volume-title":"High Performance Convolutional Neural Networks for Document Processing. In Tenth International Workshop on Frontiers in Handwriting Recognition, Guy Lorette (Ed.). Suvisoft","author":"Chellapilla Kumar","year":"2006","unstructured":"Kumar Chellapilla, Sidd Puri, and Patrice Simard. 2006. High Performance Convolutional Neural Networks for Document Processing. In Tenth International Workshop on Frontiers in Handwriting Recognition, Guy Lorette (Ed.). Suvisoft, La Baule (France). https:\/\/hal.inria.fr\/inria-00112631 http:\/\/www.suvisoft.com."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Yoni Choukroun Eli Kravchik Fan Yang and Pavel Kisilev. 2019. Low-bit Quantization of Neural Networks for Efficient Inference. 3009\u20133018. https:\/\/doi.org\/10.1109\/ICCVW.2019.00363 10.1109\/ICCVW.2019.00363","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"e_1_3_2_1_16_1","first-page":"113","article-title":"String matching and other products. In Complexity of Computation, RM Karp (editor)","volume":"7","author":"Fischer Michael J","year":"1974","unstructured":"Michael J Fischer and Michael S Paterson. 1974. String matching and other products. In Complexity of Computation, RM Karp (editor), SIAM-AMS Proceedings. 7, 113\u2013125.","journal-title":"SIAM-AMS Proceedings."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Kimmo Fredriksson and Szymon Grabowski. 2009. Fast Convolutions and Their Applications in Approximate String Matching. 254\u2013265. isbn:978-3-642-10216-5 https:\/\/doi.org\/10.1007\/978-3-642-10217-2_26 10.1007\/978-3-642-10217-2_26","DOI":"10.1007\/978-3-642-10217-2_26"},{"key":"e_1_3_2_1_18_1","unstructured":"Yao Fu Ephrem Wu Ashish Sirasao Sedny Attia Kamran Khan and Ralph Wittig. 2016. Deep learning with int8 optimization on xilinx devices. White Paper."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0155"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116529"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2017.2654506"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"e_1_3_2_1_23_1","unstructured":"Itay Hubara Matthieu Courbariaux Daniel Soudry Ran El-Yaniv and Yoshua Bengio. 2016. Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. arXiv e-prints Article arXiv:1609.07061 Sept. arXiv:1609.07061 pages. arxiv:1609.07061."},{"key":"e_1_3_2_1_24_1","unstructured":"Asifullah Khan Anabia Sohail Umme Zahoora and Aqsa Saeed Qureshi. 2019. A Survey of the Recent Architectures of Deep Convolutional Neural Networks. arXiv e-prints Article arXiv:1901.06032 Jan. arXiv:1901.06032 pages. arxiv:1901.06032."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.02.050"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_27_1","volume-title":"Xilinx ultrascale: The next-generation architecture for your next-generation architecture. Xilinx White Paper WP435, 143","author":"Leibson Steve","year":"2013","unstructured":"Steve Leibson and Nick Mehta. 2013. Xilinx ultrascale: The next-generation architecture for your next-generation architecture. Xilinx White Paper WP435, 143 (2013)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"},{"key":"e_1_3_2_1_29_1","volume-title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction. arXiv e-prints, Article arXiv:2102.05426, Feb., arXiv:2102.05426 pages. arxiv:2102.05426.","author":"Li Yuhang","year":"2021","unstructured":"Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, and Shi Gu. 2021. BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction. arXiv e-prints, Article arXiv:2102.05426, Feb., arXiv:2102.05426 pages. arxiv:2102.05426."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning -","volume":"48","author":"Lin Darryl D.","unstructured":"Darryl D. Lin, Sachin S. Talathi, and V. Sreekanth Annapureddy. 2016. Fixed Point Quantization of Deep Convolutional Networks. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 (ICML\u201916). JMLR.org, 2849\u20132858."},{"key":"e_1_3_2_1_31_1","volume-title":"Optimizing CNN Model Inference on CPUs. In 2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Liu Yizhi","year":"2019","unstructured":"Yizhi Liu, Yao Wang, Ruofei Yu, Mu Li, Vin Sharma, and Yida Wang. 2019. Optimizing CNN Model Inference on CPUs. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). USENIX Association, Renton, WA. 1025\u20131040. isbn:978-1-939133-03-8 https:\/\/www.usenix.org\/conference\/atc19\/presentation\/liu-yizhi"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2017.8335699"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Machine Learning. 7197\u20137206","author":"Nagel Markus","year":"2020","unstructured":"Markus Nagel, Rana Ali Amjad, Mart Van Baalen, Christos Louizos, and Tijmen Blankevoort. 2020. Up or down? adaptive rounding for post-training quantization. In International Conference on Machine Learning. 7197\u20137206."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI49217.2020.000-5"},{"key":"e_1_3_2_1_36_1","volume-title":"How to Multiply Matrices Faster","author":"Pan Victor","unstructured":"Victor Pan. 1984. How to Multiply Matrices Faster. Springer-Verlag, Berlin, Heidelberg. isbn:3387138668"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/0898-1221(93)90144-K"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107281"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422667"},{"key":"e_1_3_2_1_40_1","unstructured":"[n.d.]. RISC-V GNU Compiler Toolchain. https:\/\/github.com\/riscv\/riscv-gnu-toolchain"},{"key":"e_1_3_2_1_41_1","unstructured":"[n.d.]. RISC-V \"V\" Vector Extension. https:\/\/github.com\/riscv\/riscv-v-spec\/releases"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","unstructured":"Arnold Sch\u00f6nhage. 2006. Asymptotically fast algorithms for the numerical muitiplication and division of polynomials with complex coefficients. 3\u201315. isbn:978-3-540-11607-3 https:\/\/doi.org\/10.1007\/3-540-11607-9_1 10.1007\/3-540-11607-9_1","DOI":"10.1007\/3-540-11607-9_1"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"e_1_3_2_1_44_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"e_1_3_2_1_45_1","volume-title":"Automation Test in Europe Conference Exhibition (DATE).","author":"Sol\u00e9-Bonet Marc","year":"2022","unstructured":"Marc Sol\u00e9-Bonet and Leonidas Kosmidis. 2022. SPARROW: A Low-Cost Hardware\/Software Co-designed SIMD Microarchitecture for AI Operations in Space Processors. 2022 Design, Automation Test in Europe Conference Exhibition (DATE)."},{"key":"e_1_3_2_1_46_1","unstructured":"Aravind Vasudevan Andrew Anderson and David Gregg. 2017. Parallel Multi Channel Convolution using General Matrix Multiplication. arXiv e-prints Article arXiv:1704.04428 April arXiv:1704.04428 pages. arxiv:1704.04428."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2017.7995254"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00021"},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning. 9847\u20139856","author":"Wang Peisong","year":"2020","unstructured":"Peisong Wang, Qiang Chen, Xiangyu He, and Jian Cheng. 2020. Towards accurate post-training network quantization via bit-split and stitching. In International Conference on Machine Learning. 9847\u20139856."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.038"}],"event":{"name":"ASPLOS '22: 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Lausanne Switzerland","acronym":"ASPLOS '22","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503222.3507746","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503222.3507746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:40Z","timestamp":1750191100000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503222.3507746"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,22]]},"references-count":50,"alternative-id":["10.1145\/3503222.3507746","10.1145\/3503222"],"URL":"https:\/\/doi.org\/10.1145\/3503222.3507746","relation":{},"subject":[],"published":{"date-parts":[[2022,2,22]]},"assertion":[{"value":"2022-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}