{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:20:27Z","timestamp":1787012427050,"version":"3.56.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,21]],"date-time":"2023-05-21T00:00:00Z","timestamp":1684627200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,21]],"date-time":"2023-05-21T00:00:00Z","timestamp":1684627200000},"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":[[2023,5,21]]},"DOI":"10.1109\/iscas46773.2023.10181465","type":"proceedings-article","created":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T13:19:44Z","timestamp":1689945584000},"page":"1-5","source":"Crossref","is-referenced-by-count":28,"title":["Hardware-efficient Softmax Approximation for Self-Attention Networks"],"prefix":"10.1109","author":[{"given":"Nazim Altar","family":"Koca","sequence":"first","affiliation":[{"name":"Institute of Microelectronics, A*STAR (Agency for Science, Technology and Research),Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anh Tuan","family":"Do","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics, A*STAR (Agency for Science, Technology and Research),Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chip-Hong","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"I-bert: Integer-only bert quantization","author":"kim","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref12","article-title":"Towards fully 8-bit integer inference for the transformer model","author":"lin","year":"2021","journal-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ser IJCAI'20"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICSICT.2018.8565706"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774692"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530585"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref2","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"abs 1810 4805","author":"devlin","year":"2018","journal-title":"CoRR"},{"key":"ref1","article-title":"Attention is all you need","volume":"abs 1706 3762","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.3002564"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9180870"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3175534"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC.2016.7905501"},{"key":"ref24","article-title":"Magic pyramid: Accelerating inference with early exiting and token pruning","volume":"abs 2111 230","author":"he","year":"2021","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP49362.2020.00017"},{"key":"ref25","article-title":"Huggingface's transformers: State-of-the-art natural language processing","volume":"abs 1910 3771","author":"wolf","year":"2019","journal-title":"CoRR"},{"key":"ref20","article-title":"Efficient softmax approximation for deep neural networks with attention mechanism","volume":"abs 2111 10770","author":"vasyltsov","year":"2021","journal-title":"CoRR"},{"key":"ref22","article-title":"Reduced softmax unit for deep neural network accelerators","volume":"abs 2201 4562","author":"s","year":"2022","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2021.3120495"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref4","article-title":"Language models are few-shot learners","volume":"abs 2005 14165","author":"brown","year":"2020","journal-title":"CoRR"},{"key":"ref3","article-title":"Roberta: A robustly optimized BERT pretraining approach","volume":"abs 1907 11692","author":"liu","year":"2019","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"}],"event":{"name":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"Monterey, CA, USA","start":{"date-parts":[[2023,5,21]]},"end":{"date-parts":[[2023,5,25]]}},"container-title":["2023 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10181241\/10181318\/10181465.pdf?arnumber=10181465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T13:48:34Z","timestamp":1691416114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10181465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,21]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iscas46773.2023.10181465","relation":{},"subject":[],"published":{"date-parts":[[2023,5,21]]}}}