{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:03:36Z","timestamp":1789081416067,"version":"build-2803163510"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["92464302"],"award-info":[{"award-number":["92464302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tc.2025.3549621","type":"journal-article","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T17:36:16Z","timestamp":1741628176000},"page":"2058-2072","source":"Crossref","is-referenced-by-count":4,"title":["DESA: Dataflow Efficient Systolic Array for Acceleration of Transformers"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6051-9486","authenticated-orcid":false,"given":"Zhican","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Micro-Nano Engineering Science, and the School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2387-5611","authenticated-orcid":false,"given":"Hongxiang","family":"Fan","sequence":"additional","affiliation":[{"name":"Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0486-6421","authenticated-orcid":false,"given":"Guanghui","family":"He","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Micro-Nano Engineering Science, and the School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Efficient 8-bit quantization of transformer neural machine language translation model","author":"Bhandare","year":"2019"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref3","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023"},{"key":"ref4","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"35","author":"Dao","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474255"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071047"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISEDA62518.2024.10617499"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575747"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439477"},{"key":"ref20","first-page":"5506","article-title":"I-bert: Integer-only bert quantization","volume-title":"Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref21","article-title":"Full stack optimization of transformer inference: A survey","author":"Kim","year":"2023"},{"key":"ref22","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00799"},{"key":"ref25","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref27","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume-title":"Adv. Neur. Inf. Process. Syst.","volume":"34","author":"Liu","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"ref30","article-title":"Online normalizer calculation for softmax","author":"Milakov","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3655955"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"ref36","article-title":"Long range arena: A benchmark for efficient transformers","author":"Tay"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/dac56929.2023.10247678"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071027"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref43","volume-title":"Dive into deep learning","author":"Zhang","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3477002"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3170848"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/10994769\/10918723.pdf?arnumber=10918723","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T17:43:43Z","timestamp":1747071823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10918723\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":45,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tc.2025.3549621","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}