{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:22:53Z","timestamp":1784643773388,"version":"3.55.0"},"reference-count":38,"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\/iccad57390.2023.10323725","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":49,"title":["SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference"],"prefix":"10.1109","author":[{"given":"Wenxun","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuchang","family":"Zhou","sequence":"additional","affiliation":[{"name":"MEGVII Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiqin","family":"Sun","sequence":"additional","affiliation":[{"name":"MEGVII Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongpan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1122"},{"key":"ref7","article-title":"End-to-end memory networks","volume":"28","author":"Sukhbaatar","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref8","volume-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref10","article-title":"Scaling vision transformers to 22 billion parameters","author":"Dehghani","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref21","first-page":"5506","article-title":"I-bert: Integer-only bert quantization","volume-title":"International conference on machine learning","author":"Kim","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/164"},{"key":"ref23","article-title":"Full stack optimization of transformer inference: a survey","author":"Kim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APCCAS.2018.8605654"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED52811.2021.9502473"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530505"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3291280.3291800"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.1962.5219391"},{"key":"ref29","article-title":"Online normalizer calculation for softmax","author":"Milakov","year":"2018","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"ref31","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref33","volume-title":"Training data-efficient image transformers distillation through attention","author":"Touvron","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref37","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref38","article-title":"Integer quantization for deep learning inference: Principles and empirical evaluation","author":"Wu","year":"2020","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD)","location":"San Francisco, CA, USA","start":{"date-parts":[[2023,10,28]]},"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\/10323725.pdf?arnumber=10323725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T22:06:08Z","timestamp":1709417168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10323725\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,28]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iccad57390.2023.10323725","relation":{},"subject":[],"published":{"date-parts":[[2023,10,28]]}}}