{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T18:00:20Z","timestamp":1785952820224,"version":"3.56.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,9,8]],"date-time":"2020-09-08T00:00:00Z","timestamp":1599523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,8]],"date-time":"2020-09-08T00:00:00Z","timestamp":1599523200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,8]],"date-time":"2020-09-08T00:00:00Z","timestamp":1599523200000},"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":["61604068"],"award-info":[{"award-number":["61604068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,9,8]]},"DOI":"10.1109\/socc49529.2020.9524802","type":"proceedings-article","created":{"date-parts":[[2021,9,6]],"date-time":"2021-09-06T21:38:32Z","timestamp":1630964312000},"page":"84-89","source":"Crossref","is-referenced-by-count":129,"title":["Hardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer"],"prefix":"10.1109","author":[{"given":"Siyuan","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meiqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.29007\/21r5"},{"key":"ref11","first-page":"6000","article-title":"Attention is all you need","author":"ashish","year":"0","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref13","first-page":"223","article-title":"A high-speed and low-complexity architecture for softmax function in deep learning","author":"siyuan","year":"0","journal-title":"2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)"},{"key":"ref14","article-title":"Structbert: Incorporating language structures into pre-training for deep language understanding","author":"wang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC.2016.7905501"},{"key":"ref4","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"0","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref3","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"NIPS 2014 Deep Learning Workshop"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref5","article-title":"Compressing large-scale transformer-based models: A case study on bert","author":"ganesh","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"lan","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref2","article-title":"Efficient 8-bit quantization of transformer neural machine language translation model","author":"bhandare","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref9","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2019","journal-title":"ArXiv Preprint"}],"event":{"name":"2020 IEEE 33rd International System-on-Chip Conference (SOCC)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,9,8]]},"end":{"date-parts":[[2020,9,11]]}},"container-title":["2020 IEEE 33rd International System-on-Chip Conference (SOCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9524739\/9524720\/09524802.pdf?arnumber=9524802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:16:22Z","timestamp":1656602182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9524802\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,8]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/socc49529.2020.9524802","relation":{},"subject":[],"published":{"date-parts":[[2020,9,8]]}}}