{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T10:49:35Z","timestamp":1775558975113,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819583980","type":"print"},{"value":"9789819583997","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-8399-7_3","type":"book-chapter","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T09:52:47Z","timestamp":1775555567000},"page":"37-57","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VPFU: A Bit-Serial Architecture for\u00a0Energy-Efficient Acceleration of\u00a0Ultra-low Precision DNNs"],"prefix":"10.1007","author":[{"given":"Cheng","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibai","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"issue":"8081","key":"3_CR1","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","volume":"645","author":"D Guo","year":"2025","unstructured":"Guo, D., Zhang, H., et al.: DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645(8081), 633\u2013638 (2025)","journal-title":"Nature"},{"issue":"5","key":"3_CR2","doi-asserted-by":"publisher","first-page":"16681","DOI":"10.1109\/JIOT.2025.3536526","volume":"12","author":"M Nurul Achmadiah","year":"2025","unstructured":"Nurul Achmadiah, M., Ahamad, A., et al.: Energy-efficient fast object detection on edge devices for IoT systems. IEEE Internet Things J. 12(5), 16681\u201316694 (2025)","journal-title":"IEEE Internet Things J."},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, S., Ma, L.: Tiny transducer: a highly-efficient speech recognition model on edge devices. In: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6024\u20136028. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413854"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Dupuis, T., et al.: Sparq: a custom RISC-v vector processor for efficient sub-byte quantized inference. In: 2023 21st IEEE Interregional NEWCAS Conference (NEWCAS), pp. 1\u20135 (2023)","DOI":"10.1109\/NEWCAS57931.2023.10198172"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Gholami, A., Kim, S., Dong, Z., et al.: A survey of quantization methods for efficient neural network inference. Low-Power Comput. Vis., 291\u2013326 (2022)","DOI":"10.1201\/9781003162810-13"},{"issue":"07","key":"3_CR6","first-page":"160","volume":"67","author":"K Yao","year":"2024","unstructured":"Yao, K., Li, W.: Re-quantization based binary graph neural networks. Sci. China (Inf. Sci.) 67(07), 160\u2013171 (2024)","journal-title":"Sci. China (Inf. Sci.)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Xu, Y., Han, X., Yang, Z., et al.: Onebit: towards extremely low-bit large language models. In: Proceedings of the 38th International Conference on Neural Information Processing Systems, pp. 66357\u201366382 (2024)","DOI":"10.52202\/079017-2122"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wen, J., Wang, Y., et al.: VPTQ: extreme low-bit vector post-training quantization for large language models. In: 2024 Conference on Empirical Methods in Natural Language Processing, pp. 8181\u20138196 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.467"},{"key":"3_CR9","unstructured":"Kim, H., Kim, Y., Ryu, S., et al.: BitSplit-Net: multi-bit deep neural network with bitwise activation function. arXiv preprint arXiv:1903.09807 (2019)"},{"key":"3_CR10","unstructured":"Zhang, H., et al.: BitNet: scaling 1-bit transformers for large language models. arXiv preprint arXiv:2310.11453 (2023)"},{"key":"3_CR11","unstructured":"Jouppi, N.P., Young, C., Patil, N., et al.: In-datacenter performance analysis of a tensor processing unit. In: 2017 ACM\/IEEE 44th Annual International Symposium on Computer Architecture (ISCA), pp. 1\u201312 (2017)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: DaDianNao: a machine-learning supercomputer. In: 2014 47th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 609\u2013622 (2014)","DOI":"10.1109\/MICRO.2014.58"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Judd, P., Albericio, J., Hetherington, T., Aamodt, T.M., Moshovos, A.: Stripes: bit-serial deep neural network computing. In: 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 1\u201312 (2016)","DOI":"10.1109\/MICRO.2016.7783722"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: BitMoD: bit-serial mixture-of-datatype LLM acceleration. In: 2025 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 1082\u20131097 (2025)","DOI":"10.1109\/HPCA61900.2025.00084"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Sharma, H., et al.: Bit fusion: bit-level dynamically composable architecture for accelerating deep neural network. In: 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), pp. 764\u2013775 (2018)","DOI":"10.1109\/ISCA.2018.00069"},{"key":"3_CR16","first-page":"154","volume":"8","author":"I Hubara","year":"2018","unstructured":"Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Quantized neural networks: training neural networks with low precision weights and activations. J. Mach. Learn. Res. 8, 154\u2013234 (2018)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR17","unstructured":"Howard, A.G.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013780 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR21","unstructured":"Samajdar, A., et al.: SCALE-sim: systolic CNN accelerator simulator. arXiv preprint arXiv:1811.02883 (2019)"},{"key":"3_CR22","first-page":"52","volume":"4","author":"J Won","year":"2022","unstructured":"Won, J., et al.: ULPPACK: fast sub-8-bit matrix multiply on commodity SIMD hardware. Proc. Mach. Learn. Syst. 4, 52\u201363 (2022)","journal-title":"Proc. Mach. Learn. Syst."}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8399-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T09:52:55Z","timestamp":1775555575000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8399-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819583980","9789819583997"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8399-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"8 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}