{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T16:03:05Z","timestamp":1784995385592,"version":"3.55.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191521","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-9","source":"Crossref","is-referenced-by-count":37,"title":["SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers"],"prefix":"10.1109","author":[{"given":"Alberto","family":"Marchisio","sequence":"first","affiliation":[{"name":"Technische Universität Wien,Vienna,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davide","family":"Dura","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Turin,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maurizio","family":"Capra","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Turin,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maurizio","family":"Martina","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Turin,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guido","family":"Masera","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Turin,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Shafique","sequence":"additional","affiliation":[{"name":"New York University,Abu Dhabi,UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML)"},{"key":"ref35","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","author":"wang","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref12","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30 (Ne u rIPS)"},{"key":"ref34","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"CoRR vol abs\/1907 11692"},{"key":"ref15","article-title":"Universal transformers","author":"dehghani","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref37","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25 (Ne u rIPS)"},{"key":"ref14","article-title":"Bridging nonlinearities and stochastic regularizers with gaussian error linear units","author":"hendrycks","year":"2016","journal-title":"CoRR vol abs\/1606 08415"},{"key":"ref36","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474043"},{"key":"ref11","first-page":"5506","article-title":"1-BERT: integer-only BERT quantization","author":"kim","year":"2021","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref33","volume":"182","author":"richard crandall","year":"2006","journal-title":"Prime Numbers A Computational Perspective"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCDCS.2004.1393405"},{"key":"ref32","first-page":"11875","article-title":"HAWQ-V3: dyadic neural network quantization","author":"yao","year":"2021","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2019.00105"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342120"},{"key":"ref17","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 (Ne u rIPS)"},{"key":"ref16","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies (NAACL-HLT)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref18","article-title":"Linformer: Self-attention with linear complexity","author":"wang","year":"2020","journal-title":"CoRR vol abs\/2006 04768"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3039858"},{"key":"ref26","author":"wang","year":"2020","journal-title":"Efficient algorithms and hardware for natural language processing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"ref20","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","author":"fedus","year":"2021","journal-title":"CoRR vol abs\/2101 03961"},{"key":"ref22","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref21","article-title":"I-vit: Integer-only quantization for efficient vision transformer inference","author":"li","year":"2022","journal-title":"CoRR vol abs\/2207 01405"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.1"},{"key":"ref27","article-title":"Efficient 8-bit quantization of transformer neural machine language translation model","author":"bhandare","year":"2019","journal-title":"CoRR vol abs\/1906 00532"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11213550"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/520"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref9","year":"0","journal-title":"Nvidia h100 tensor core gpu architecture whitepaper"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643539"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"113","DOI":"10.3390\/fi12070113","article-title":"An updated survey of efficient hardware architectures for accelerating deep convolutional neural networks","volume":"12","author":"capra","year":"2020","journal-title":"Future Internet"},{"key":"ref6","article-title":"OPTIMUS: optimized matrix multiplication structure for transformer neural network accelerator","author":"park","year":"2020","journal-title":"Proceedings of Machine Learning and Systems 2020 (MLSys)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/VTS52500.2021.9794253"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","location":"Gold Coast, Australia","start":{"date-parts":[[2023,6,18]]},"end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191521.pdf?arnumber=10191521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:43:38Z","timestamp":1692639818000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191521\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191521","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}