{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:53:54Z","timestamp":1781794434506,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"German Federal Ministry of Research, Technology and Space","award":["03ZU2106CA (NeuroSys II)"],"award-info":[{"award-number":["03ZU2106CA (NeuroSys II)"]}]},{"name":"German Federal Ministry of Research, Technology and Space","award":["16ME0399 (NEUROTEC II)"],"award-info":[{"award-number":["16ME0399 (NEUROTEC II)"]}]},{"name":"German Federal Ministry for the Environment, Climate Action, Nature Conservation and Nuclear Safety","award":["67KI32006A (RESCALE)"],"award-info":[{"award-number":["67KI32006A (RESCALE)"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3787109.3815213","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:17:19Z","timestamp":1781792239000},"page":"876-882","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GUPrecision: Group-Wise Uniform Precision Accelerator for Depthwise Separable Convolution using Hardware-Algorithm Co-Design"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2101-5235","authenticated-orcid":false,"given":"Yi","family":"Chen","sequence":"first","affiliation":[{"name":"RWTH Aachen University, Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0380-8585","authenticated-orcid":false,"given":"Jie","family":"Lou","sequence":"additional","affiliation":[{"name":"RWTH Aachen University, Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9122-3610","authenticated-orcid":false,"given":"Malte","family":"Wabnitz","sequence":"additional","affiliation":[{"name":"RWTH Aachen University, Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1583-3411","authenticated-orcid":false,"given":"Tobias","family":"Gemmeke","sequence":"additional","affiliation":[{"name":"RWTH Aachen University, Aachen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSI-SoC57769.2023.10321918"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC62300.2024.10737823"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/COOLCHIPS65488.2025.11018601"},{"key":"e_1_3_3_1_5_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Han Song","year":"2015","unstructured":"Song Han et\u00a0al. 2015. Learning both Weights and Connections for Efficient Neural Network. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_3_1_7_2","volume-title":"arXiv\n                  CoRR","author":"Howard Andrew\u00a0G.","year":"2017","unstructured":"Andrew\u00a0G. Howard et\u00a0al. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, In arXiv. CoRR abs\/1704.04861. arXiv:https:\/\/arXiv.org\/abs\/1704.04861"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Jueun Jung et\u00a0al. 2024. An Energy-Efficient Unified CNN Accelerator for Real-Time Multi-Object Semantic Segmentation for Autonomous Vehicle. IEEE Transactions on Circuits and Systems I: Regular Papers (2024) 1\u201312. doi:10.1109\/TCSI.2024.3349588","DOI":"10.1109\/TCSI.2024.3349588"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Ben Keller et\u00a0al. 2023. A 95.6-TOPS\/W Deep Learning Inference Accelerator With Per-Vector Scaled 4-bit Quantization in 5 nm. IEEE Journal of Solid-State Circuits 58 4 (2023) 1129\u20131141. doi:10.1109\/JSSC.2023.3234893","DOI":"10.1109\/JSSC.2023.3234893"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49661.2025.10904594"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49661.2025.10904761"},{"key":"e_1_3_3_1_12_2","unstructured":"Raghuraman Krishnamoorthi. 2018. Quantizing deep convolutional networks for efficient inference: A whitepaper. arxiv:https:\/\/arXiv.org\/abs\/1806.08342\u00a0[cs.LG]"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Bo Liu et\u00a0al. 2024. Layer-Wise Mixed-Modes CNN Processing Architecture With Double-Stationary Dataflow and Dimension-Reshape Strategy. IEEE Transactions on Circuits and Systems I: Regular Papers 71 10 (2024) 4652\u20134664. doi:10.1109\/TCSI.2024.3434706","DOI":"10.1109\/TCSI.2024.3434706"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Jie Lou et\u00a0al. 2024. An Energy Efficient All-Digital Time-Domain Compute-in-Memory Macro Optimized for Binary Neural Networks. IEEE Transactions on Circuits and Systems I: Regular Papers 71 1 (2024) 287\u2013298. doi:10.1109\/TCSI.2023.3323205","DOI":"10.1109\/TCSI.2023.3323205"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3716368.3735161"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS56072.2025.11043778"},{"key":"e_1_3_3_1_17_2","first-page":"21","volume-title":"IEEE International Solid-State Circuits Conference (ISSCC)","author":"Moon Seunghyun","year":"2023","unstructured":"Seunghyun Moon et\u00a0al. 2023. A 127.8 TOPS\/W Arbitrarily Quantized 1-to-8b Scalable-Precision Accelerator for General-Purpose Deep Learning with Reduction of Storage, Logic and Latency Waste. In IEEE International Solid-State Circuits Conference (ISSCC). 21\u201323. doi:10.1109\/ISSCC42615.2023.10067615"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Beatrice\u00a0Alessandra Motetti et\u00a0al. 2024. Joint Pruning and Channel-Wise Mixed-Precision Quantization for Efficient Deep Neural Networks. IEEE Trans. Comput. 73 11 (2024) 2619\u20132633. doi:10.1109\/TC.2024.3449084","DOI":"10.1109\/TC.2024.3449084"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3268562"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CICC60959.2024.10529086"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Malte Wabnitz et\u00a0al. 2023. Toolflow for the algorithm-hardware co-design of memristive ANN accelerators. Memories - Materials Devices Circuits and Systems 5 (2023) 100066. doi:10.1016\/j.memori.2023.100066","DOI":"10.1016\/j.memori.2023.100066"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC66049.2026.11420567"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062207"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00225"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Zhe Yuan et\u00a0al. 2020. STICKER: An Energy-Efficient Multi-Sparsity Compatible Accelerator for Convolutional Neural Networks in 65-nm CMOS. IEEE Journal of Solid-State Circuits 55 2 (2020) 465\u2013477. doi:10.1109\/JSSC.2019.2946771","DOI":"10.1109\/JSSC.2019.2946771"},{"key":"e_1_3_3_1_28_2","volume-title":"International Conference on Machine Learning (ICML)","author":"Zhou Aojun","year":"2021","unstructured":"Aojun Zhou et\u00a0al. 2021. Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch. In International Conference on Machine Learning (ICML). doi:10.48550\/arXiv.2102.04010"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3658617.3697682"}],"event":{"name":"GLSVLSI '26: Great Lakes Symposium on VLSI 2026","location":"Canandaigua , NY , USA","acronym":"GLSVLSI '26","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA"]},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2026"],"original-title":[],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:20:05Z","timestamp":1781792405000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787109.3815213"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":28,"alternative-id":["10.1145\/3787109.3815213","10.1145\/3787109"],"URL":"https:\/\/doi.org\/10.1145\/3787109.3815213","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}