{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T06:58:48Z","timestamp":1771657128085,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T00:00:00Z","timestamp":1673827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of the Ministry of science and technology","award":["2021YFE0204000"],"award-info":[{"award-number":["2021YFE0204000"]}]},{"name":"National Natural Science Foundation of China (NSFC) Key Program","award":["62034007"],"award-info":[{"award-number":["62034007"]}]},{"name":"Guangdong Provincial Key Laboratory Program","award":["2021B1212040001"],"award-info":[{"award-number":["2021B1212040001"]}]},{"name":"Shenzhen Science and Technology Program","award":["KQTD20200820113051096"],"award-info":[{"award-number":["KQTD20200820113051096"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,1,16]]},"DOI":"10.1145\/3566097.3567871","type":"proceedings-article","created":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T18:40:49Z","timestamp":1675190449000},"page":"490-495","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Agile Hardware and Software Co-Design for RISC-V-Based Multi-Precision Deep Learning Microprocessor"],"prefix":"10.1145","author":[{"given":"Zicheng","family":"He","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology and University of California, Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ao","family":"Shen","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiufeng","family":"Li","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Yu","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,1,31]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Mixed quantization of convnets via differentiable neural architecture search,\" ArXiv preprint arXiv:1812.00090","author":"Wu B.","year":"2018","unstructured":"B. Wu et al., \"Mixed quantization of convnets via differentiable neural architecture search,\" ArXiv preprint arXiv:1812.00090, 2018."},{"key":"e_1_3_2_1_2_1","first-page":"242","article-title":"14.3 a 28nm soc with a 1.2ghz 568nj\/prediction sparse deep-neural-network engine with >0.1 timing error rate tolerance for iot applications","author":"Whatmough P. N.","year":"2017","unstructured":"P. N. Whatmough et al., \"14.3 a 28nm soc with a 1.2ghz 568nj\/prediction sparse deep-neural-network engine with >0.1 timing error rate tolerance for iot applications,\" ISSCC, pp. 242--243, 2017.","journal-title":"ISSCC"},{"key":"e_1_3_2_1_3_1","first-page":"21","article-title":"Integrating nvidia deep learning accelerator (nvdla) with risc-v soc on firesim","author":"Farshchi F.","year":"2019","unstructured":"F. Farshchi et al., \"Integrating nvidia deep learning accelerator (nvdla) with risc-v soc on firesim,\" EMC2, pp. 21--25, 2019.","journal-title":"EMC2"},{"key":"e_1_3_2_1_4_1","volume-title":"others, \"Ansor : Generating high-performance tensor programs for deep learning,\" in OSDI","author":"L.","year":"2020","unstructured":"L. Z. others, \"Ansor : Generating high-performance tensor programs for deep learning,\" in OSDI, 2020."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"e_1_3_2_1_7_1","volume-title":"Tvm: An automated end-to-end optimizing compiler for deep learning,\" in OSDI","author":"Chen T.","year":"2018","unstructured":"T. Chen et al., \"Tvm: An automated end-to-end optimizing compiler for deep learning,\" in OSDI, 2018."},{"key":"e_1_3_2_1_8_1","volume-title":"An energy-efficient bit-split-and-combination systolic accelerator for nas-based multi-precision convolution neural networks,\" in ASP-DAC","author":"Dai L.","year":"2022","unstructured":"L. Dai et al., \"An energy-efficient bit-split-and-combination systolic accelerator for nas-based multi-precision convolution neural networks,\" in ASP-DAC, 2022."},{"key":"e_1_3_2_1_9_1","volume-title":"An energy-efficient bit-split-and-combination systolic accelerator for nas-based multi-precision convolution neural networks,\" in FPGA","author":"Huang M.","year":"2022","unstructured":"M. Huang et al., \"An energy-efficient bit-split-and-combination systolic accelerator for nas-based multi-precision convolution neural networks,\" in FPGA, 2022."},{"key":"e_1_3_2_1_10_1","first-page":"764","volume-title":"Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network,\" in ISCA","author":"Sharma H.","year":"2018","unstructured":"H. Sharma et al., \"Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network,\" in ISCA, pp. 764--775, 2018."},{"key":"e_1_3_2_1_11_1","first-page":"08368","article-title":"Relay: A high-level ir for deep learning","author":"Roesch J.","year":"1904","unstructured":"J. Roesch et al., \"Relay: A high-level ir for deep learning,\" ArXiv preprint arXiv:1904.08368, 2019.","journal-title":"ArXiv preprint arXiv"},{"key":"e_1_3_2_1_12_1","first-page":"24","article-title":"Angel-eye: A complete design flow for mapping cnn onto customized hardware","author":"Guo K.","year":"2016","unstructured":"K. Guo et al., \"Angel-eye: A complete design flow for mapping cnn onto customized hardware,\" in ISVLSI, pp. 24--29, 2016.","journal-title":"ISVLSI"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2934644"},{"key":"e_1_3_2_1_15_1","volume-title":"Optimizing loop operation and dataflow in fpga acceleration of deep convolutional neural networks,\" FPGA '17, (New York","author":"Ma Y.","year":"2017","unstructured":"Y. Ma et al., \"Optimizing loop operation and dataflow in fpga acceleration of deep convolutional neural networks,\" FPGA '17, (New York, NY, USA), p. 45--54, 2017."},{"issue":"11","key":"e_1_3_2_1_16_1","first-page":"2072","article-title":"Caffeine: Toward uniformed representation and acceleration for deep convolutional neural networks","volume":"38","author":"Zhang C.","year":"2019","unstructured":"C. Zhang et al., \"Caffeine: Toward uniformed representation and acceleration for deep convolutional neural networks,\" TCAD, vol. 38, no. 11, pp. 2072--2085, 2019.","journal-title":"TCAD"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_18_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications,\" ArXiv preprint arXiv:1704.04861","author":"Howard A. G.","year":"2017","unstructured":"A. G. Howard et al., \"Mobilenets: Efficient convolutional neural networks for mobile vision applications,\" ArXiv preprint arXiv:1704.04861, 2017."},{"key":"e_1_3_2_1_19_1","first-page":"770","article-title":"Deep residual learning for image recognition","volume":"16","author":"He K.","year":"2016","unstructured":"K. He et al., \"Deep residual learning for image recognition,\" CVPR' 16, pp. 770--778, 2016.","journal-title":"CVPR'"}],"event":{"name":"ASPDAC '23: 28th Asia and South Pacific Design Automation Conference","location":"Tokyo Japan","acronym":"ASPDAC '23","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA","IEICE","IEEE CAS","IPSJ"]},"container-title":["Proceedings of the 28th Asia and South Pacific Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3566097.3567871","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3566097.3567871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T17:35:14Z","timestamp":1767807314000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3566097.3567871"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,16]]},"references-count":19,"alternative-id":["10.1145\/3566097.3567871","10.1145\/3566097"],"URL":"https:\/\/doi.org\/10.1145\/3566097.3567871","relation":{},"subject":[],"published":{"date-parts":[[2023,1,16]]},"assertion":[{"value":"2023-01-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}