{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:17:23Z","timestamp":1767183443460,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,28]]},"DOI":"10.1109\/iccad57390.2023.10323752","type":"proceedings-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T18:58:45Z","timestamp":1701370725000},"page":"1-9","source":"Crossref","is-referenced-by-count":17,"title":["FET-OPU: A Flexible and Efficient FPGA-Based Overlay Processor for Transformer Networks"],"prefix":"10.1109","author":[{"given":"Yueyin","family":"Bai","sequence":"first","affiliation":[{"name":"Fudan University,State Key Lab of ASIC & System,Shanghai,China"}]},{"given":"Hao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Lab of ASIC & System,Shanghai,China"}]},{"given":"Keqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Lab of ASIC & System,Shanghai,China"}]},{"given":"Hongji","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Lab of ASIC & System,Shanghai,China"}]},{"given":"Jianli","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Lab of ASIC & System,Shanghai,China"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Lab of ASIC & System,Shanghai,China"}]},{"given":"Kun","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Lab of ASIC & System,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474043"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213521"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439477"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2019.2939726"},{"key":"ref9","article-title":"AMMUS: A Survey of Transformer-based Pretrained Models in Natural Language Processing","author":"Kalyan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"volume-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref12"},{"issue":"8","key":"ref13","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3121264"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375311"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.2995741"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3543622.3573152"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/FPL53798.2021.00014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM57271.2023.00049"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7927113"},{"key":"ref23","article-title":"Efficient 8-bit quantization of transformer neural machine language translation model","author":"Bhandare","year":"2019","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530505"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.3004602"},{"key":"ref26","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","author":"Chen","year":"2018","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Glow: Graph lowering compiler techniques for neural networks","author":"Rotem","year":"2018","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD)","start":{"date-parts":[[2023,10,28]]},"location":"San Francisco, CA, USA","end":{"date-parts":[[2023,11,2]]}},"container-title":["2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10323590\/10323543\/10323752.pdf?arnumber=10323752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T17:49:49Z","timestamp":1726681789000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10323752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,28]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iccad57390.2023.10323752","relation":{},"subject":[],"published":{"date-parts":[[2023,10,28]]}}}