{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T16:26:33Z","timestamp":1754151993694,"version":"3.41.2"},"publisher-location":"New York, NY, USA","reference-count":9,"publisher":"ACM","funder":[{"name":"the Young Elite Scientists Sponsorship Program"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,28]]},"DOI":"10.1145\/3719276.3725188","type":"proceedings-article","created":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:00:46Z","timestamp":1751605246000},"page":"76-79","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Flex8: A Flexible Precision Co-design for 8-bit Neural Network"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7883-1131","authenticated-orcid":false,"given":"Xiaoning","family":"Li","sequence":"first","affiliation":[{"name":"Defense Innovation Institution, Academy of Military Science, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2548-9087","authenticated-orcid":false,"given":"Lu","family":"Wang","sequence":"additional","affiliation":[{"name":"Defense Innovation Institution, Academy of Military Science, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4732-9674","authenticated-orcid":false,"given":"Guangda","family":"Zhang","sequence":"additional","affiliation":[{"name":"Defense Innovation Institution, Academy of Military Science, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6479-9200","authenticated-orcid":false,"given":"Xia","family":"Zhao","sequence":"additional","affiliation":[{"name":"Defense Innovation Institution, Academy of Military Science, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6690-3718","authenticated-orcid":false,"given":"Shiqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Defense Innovation Institution, Academy of Military Science, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,4]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Gupta R. R. & Ranga V. (2021). Comparative study of different reduced precision techniques in deep neural network. Lecture Notes in Networks and Systems 123\u2013136.","DOI":"10.1007\/978-981-15-8377-3_11"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Tortorella Y. Bertaccini L. Benini L. et al. (2023). RedMule: A mixed-precision matrix-matrix operation engine for flexible and energy-efficient on-chip linear algebra and TinyML training acceleration. Future Generation Computer Systems 122\u2013135.","DOI":"10.1016\/j.future.2023.07.002"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Li H. Lu H. & Li X. (2024). Mortar-FP8: Morphing the Existing FP32 Infrastructure for High-Performance Deep Learning Acceleration. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems No.3 878\u2013891.","DOI":"10.1109\/TCAD.2023.3329778"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Dong Z. Yao Z. Cai Y. Arfeen D. Gholami A. Mahoney M. W. & Keutzer K. (2019). HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks. Journal.","DOI":"10.1109\/ICCV.2019.00038"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Li Z. Ni B. Yang X. Zhang W. & Gao W. (2023). Residual Quantization for Low Bit-Width Neural Networks. IEEE Transactions on Multimedia 214\u2013227.","DOI":"10.1109\/TMM.2021.3124095"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Mach S. Schuiki F. Zaruba F. & Benini L. (2021). FPnew: An Open-Source Multiformat Floating-Point Unit Architecture for Energy-Proportional Transprecision Computing. IEEE Transactions on Very Large Scale Integration (VLSI) Systems No.4 774\u2013787.","DOI":"10.1109\/TVLSI.2020.3044752"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Croci M. Fasi M. Higham N. J. Mary T. & Mikaitis M. (2022). Stochastic rounding: implementation error analysis and applications. Royal Society Open Science No.3 211631.","DOI":"10.1098\/rsos.211631"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Zhang T. Lin Z. Yang G. & De Sa C. (2019). QPyTorch: A Low-Precision Arithmetic Simulation Framework. In Proceedings of the 2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing - NeurIPS Edition (EMC2-NIPS).","DOI":"10.1109\/EMC2-NIPS53020.2019.00010"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"He K. Zhang X. Ren S. & Sun J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 770-778.","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"CF '25: 22nd ACM International Conference on Computing Frontiers","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"],"location":"Cagliari Italy","acronym":"CF '25"},"container-title":["Proceedings of the 22nd ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3719276.3725188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T09:49:09Z","timestamp":1753091349000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3719276.3725188"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":9,"alternative-id":["10.1145\/3719276.3725188","10.1145\/3719276"],"URL":"https:\/\/doi.org\/10.1145\/3719276.3725188","relation":{},"subject":[],"published":{"date-parts":[[2025,5,28]]},"assertion":[{"value":"2025-07-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}