{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:34:07Z","timestamp":1781886847412,"version":"3.54.5"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20301,62102433"],"award-info":[{"award-number":["U23A20301,62102433"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.23919\/date64628.2025.10992780","type":"proceedings-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:36:35Z","timestamp":1747848995000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["WinAcc: Window-based Acceleration of Neural Networks Using Block Floating Point"],"prefix":"10.23919","author":[{"given":"Xin","family":"Ju","sequence":"first","affiliation":[{"name":"School of Computer, National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasong","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junzhong","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoyun","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref3","article-title":"Vs-quant: Per-vector scaled quantization for accurate low-precision neural network inference","volume-title":"Proceedings of the Fourth Conference on Machine Learning and Systems, MLSys 2021","author":"Dai","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00067"},{"key":"ref5","first-page":"1002","article-title":"Bucket getter: A bucket-based processing engine for low-bit block floating point (BFP) dnns","volume-title":"Proceedings of the 56th Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO 2023","author":"Lo","year":"2023"},{"key":"ref6","article-title":"Pushing the limits of narrow precision inferencing at cloud scale with microsoft floating point","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Rouhani","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589351"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2023.3234893"},{"key":"ref9","article-title":"Block and subword-scaling floating-point (BSFP): An efficient non-uniform quantization for low precision inference","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Lo","year":"2023"},{"key":"ref10","first-page":"1742","article-title":"Flexpoint: An adaptive numerical format for efficient training of deep neural networks","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"K\u00f6ster","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00095"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ieeestd.1985.82928"},{"key":"ref13","article-title":"Winning both the accuracy of floating point activation and the simplicity of integer arithmetic","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Kim","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3543622.3573210"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00082"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3655986"},{"key":"ref17","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020","author":"Zheng","year":"2020"},{"key":"ref18","article-title":"AWQ: activation-aware weight quantization for on-device LLM compression and acceleration","volume-title":"Proceedings of the Seventh Annual Conference on Machine Learning and Systems, MLSys 2024","author":"Lin","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"3rd International Conference on Learning Representations, ICLR 2015","author":"Simonyan","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref22","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy","year":"2021"},{"key":"ref23","first-page":"4171","article-title":"BERT: pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolo-gies, NAACL-HLT 2019","author":"Devlin","year":"2019"},{"key":"ref24","article-title":"Llama 2: Open foundation and fine-tuned chat models","volume":"abs\/2307.09288","author":"Touvron","year":"2023","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref27","article-title":"Measuring massive multitask language understanding","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Hendrycks","year":"2021"},{"key":"ref28","first-page":"12322","article-title":"A study of BFLOAT16 for deep learning training","volume":"abs\/1905","author":"Kalamkar","year":"2019","journal-title":"CoRR"},{"key":"ref29","article-title":"Tensorfloat-32 in the a100 gpu accelerates ai training, hpc up to 20x","author":"Kharya","year":"2020","journal-title":"NVIDIA Corporation, Tech. Rep"}],"event":{"name":"2025 Design, Automation & Test in Europe Conference (DATE)","location":"Lyon, France","start":{"date-parts":[[2025,3,31]]},"end":{"date-parts":[[2025,4,2]]}},"container-title":["2025 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10992638\/10992588\/10992780.pdf?arnumber=10992780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:32:11Z","timestamp":1747891931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10992780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":29,"URL":"https:\/\/doi.org\/10.23919\/date64628.2025.10992780","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}