{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:50:50Z","timestamp":1763751050529,"version":"3.45.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["62374101"],"award-info":[{"award-number":["62374101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tcad.2025.3561719","type":"journal-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T13:51:19Z","timestamp":1744811479000},"page":"4290-4303","source":"Crossref","is-referenced-by-count":0,"title":["SASDenSebLE: A Compact Vision Transformer Inference Architecture With Saturation-Approximate Softmax Dataflow Enabling Sequence-Parallelism Boosted Layer-Fusion Execution"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1928-8801","authenticated-orcid":false,"given":"Liu","family":"He","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0974-0463","authenticated-orcid":false,"given":"Yujin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4557-3163","authenticated-orcid":false,"given":"Zongle","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5314-3002","authenticated-orcid":false,"given":"Shupei","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3411-0078","authenticated-orcid":false,"given":"Chen","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0424-5868","authenticated-orcid":false,"given":"Shuyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1293-7891","authenticated-orcid":false,"given":"Luchang","family":"Lei","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2421-353X","authenticated-orcid":false,"given":"Huazhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4892-2309","authenticated-orcid":false,"given":"Yongpan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8692-1860","authenticated-orcid":false,"given":"Hongyang","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref2","first-page":"10421","article-title":"BEVFusion: A simple and robust LiDAR-camera fusion framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liang"},{"key":"ref3","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref4","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref7","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rao"},{"key":"ref8","article-title":"FQ-ViT: Post-training quantization for fully quantized vision transformer","author":"Lin","year":"2021","journal-title":"arXiv:2111.13824"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42615.2023.10067817"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2023.3234893"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9180870"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323725"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323651"},{"key":"ref18","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Dao"},{"volume-title":"NVIDIA Jetson Orin AGX","year":"2021","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071027"},{"key":"ref22","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref27","first-page":"5506","article-title":"I-BERT: Integer-only BERT quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.vlsi.2017.02.002","article-title":"Scaling equations for the accurate prediction of CMOS device performance from 180 nm to 7 nm","volume":"58","author":"Stillmaker","year":"2017","journal-title":"Integration"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247913"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3222059"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454323"},{"volume-title":"FasterTransformer","year":"2022","key":"ref33"},{"key":"ref34","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","author":"Xiao","year":"2024","journal-title":"arXiv:2211.10438"},{"key":"ref35","article-title":"Flashdecoding++: Faster large language model inference on GPUs","author":"Hong","year":"2023","journal-title":"arXiv:2311.01282"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/hpca47549.2020.00035"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731686"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46769.2022.9830277"},{"key":"ref39","first-page":"1","article-title":"Exploring approximation and dataflow co-optimization for scalable transformer inference architecture on the edge","volume-title":"Proc. IEEE 37th Int. Syst. Chip Conf. (SOCC)","author":"He"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/11211509\/10966444.pdf?arnumber=10966444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:43:19Z","timestamp":1763750599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10966444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":39,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2025.3561719","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"type":"print","value":"0278-0070"},{"type":"electronic","value":"1937-4151"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}