{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T11:30:04Z","timestamp":1763724604106,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,10]],"date-time":"2022-07-10T00:00:00Z","timestamp":1657411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-1901378"],"award-info":[{"award-number":["CCF-1901378"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,10]]},"DOI":"10.1145\/3489517.3530618","type":"proceedings-article","created":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T23:19:29Z","timestamp":1661296769000},"page":"1394-1395","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["FPGA-aware automatic acceleration framework for vision transformer with mixed-scheme quantization"],"prefix":"10.1145","author":[{"given":"Mengshu","family":"Sun","sequence":"first","affiliation":[{"name":"Northeastern University"}]},{"given":"Zhengang","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Alec","family":"Lu","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}]},{"given":"Haoyu","family":"Ma","sequence":"additional","affiliation":[{"name":"University of California"}]},{"given":"Geng","family":"Yuan","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Yanyue","family":"Xie","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"ETH Zurich"}]},{"given":"Yanyu","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Miriam","family":"Leeser","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Zhangyang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}]},{"given":"Xue","family":"Lin","sequence":"additional","affiliation":[{"name":"Northeastern University"}]},{"given":"Zhenman","family":"Fang","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}]}],"member":"320","published-online":{"date-parts":[[2022,8,23]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Binarybert: Pushing the limit of bert quantization. In ACL\/IJCNLP (1).","author":"Haoli Bai","year":"2021","unstructured":"Haoli Bai et al. 2021. Binarybert: Pushing the limit of bert quantization. In ACL\/IJCNLP (1)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Sung-En Chang et al. 2021. Mix and Match: A novel FPGA-centric deep neural network quantization framework. In HPCA.","DOI":"10.1109\/HPCA51647.2021.00027"},{"key":"e_1_3_2_1_3_1","volume-title":"Words: Transformers for Image Recognition at Scale. In ICLR.","author":"Alexey Dosovitskiy","year":"2021","unstructured":"Alexey Dosovitskiy et al. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR."},{"key":"e_1_3_2_1_4_1","unstructured":"Bingbing Li et al. 2020. Ftrans: energy-efficient acceleration of transformers using fpga. In ISLPED."},{"key":"e_1_3_2_1_5_1","unstructured":"Zhenhua Liu et al. 2021. Post-Training Quantization for Vision Transformer. In NeurIPS. https:\/\/openreview.net\/forum?id=9TX5OsKJvm"},{"key":"e_1_3_2_1_6_1","volume-title":"FPGA: Coupling the Balanced Model Compression and FPGA-Implementation Optimization. In GLSVLSI.","author":"Panjie Qi","year":"2021","unstructured":"Panjie Qi et al. 2021. Accommodating Transformer onto FPGA: Coupling the Balanced Model Compression and FPGA-Implementation Optimization. In GLSVLSI."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Hugo Touvron et al. 2021. Training data-efficient image transformers & distillation through attention. In ICML.","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"e_1_3_2_1_8_1","unstructured":"Ashish Vaswani et al. 2017. Attention is all you need. In NeurIPS."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Li Yuan et al. 2021. Tokens-to-Token ViT: Training Vision Transformers From Scratch on ImageNet. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Ofir Zafrir et al. 2019. Q8bert: Quantized 8bit bert. NeurIPS EMC2 Workshop (2019).","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"e_1_3_2_1_11_1","volume-title":"Ternarybert: Distillation-aware ultra-low bit bert. In EMNLP.","author":"Wei Zhang","year":"2020","unstructured":"Wei Zhang et al. 2020. Ternarybert: Distillation-aware ultra-low bit bert. In EMNLP."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Xinyi Zhang et al. 2021. Algorithm-hardware Co-design of Attention Mechanism on FPGA Devices. TECS (2021).","DOI":"10.1145\/3477002"}],"event":{"name":"DAC '22: 59th ACM\/IEEE Design Automation Conference","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA"],"location":"San Francisco California","acronym":"DAC '22"},"container-title":["Proceedings of the 59th ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489517.3530618","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3489517.3530618","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3489517.3530618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:23Z","timestamp":1750186943000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489517.3530618"}},"subtitle":["late breaking results"],"short-title":[],"issued":{"date-parts":[[2022,7,10]]},"references-count":12,"alternative-id":["10.1145\/3489517.3530618","10.1145\/3489517"],"URL":"https:\/\/doi.org\/10.1145\/3489517.3530618","relation":{},"subject":[],"published":{"date-parts":[[2022,7,10]]},"assertion":[{"value":"2022-08-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}