{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:18:56Z","timestamp":1792786736548,"version":"4.5.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U25B2057"],"award-info":[{"award-number":["U25B2057"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tc.2026.3715379","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T19:01:21Z","timestamp":1784833281000},"page":"3653-3668","source":"Crossref","is-referenced-by-count":0,"title":["SD-Acc: Accelerating Stable Diffusion through Phase-Aware Sampling and Hardware Co-Optimizations"],"prefix":"10.1109","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6051-9486","authenticated-orcid":false,"given":"Zhican","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"],"department":["State Key Laboratory of Micro-Nano Engineering Science and the School of Integrated Circuits"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0486-6421","authenticated-orcid":false,"given":"Guanghui","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"],"department":["State Key Laboratory of Micro-Nano Engineering Science and the School of Integrated Circuits"]}],"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","place":["London, U.K."],"department":["Department of Computing"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10558026"},{"key":"ref4","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/N19-1423","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0731"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0580"},{"key":"ref10","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575747"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref15","article-title":"BK-SDM: Architecturally compressed stable diffusion for efficient text-to-image generation","author":"Kim","year":"2023","journal-title":"Proc. Workshop Efficient Syst. Found. Models@ ICML"},{"key":"ref16","article-title":"I-BERT: Integer-only BERT quantization","author":"Kim","year":"2021"},{"key":"ref17","article-title":"Full stack optimization of transformer inference: A survey","author":"Kim","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00070"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1117201.1117205"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173176"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0907"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875654"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","first-page":"2022","article-title":"Pseudo numerical methods for diffusion models on manifolds","author":"Liu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref29","article-title":"Online normalizer calculation for softmax","author":"Milakov","year":"2018"},{"key":"ref30","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114820"},{"key":"ref32","article-title":"NVIDIA deep learning accelerator","author":"Nvidia","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00346"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2011.7477494"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref36","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Ramesh","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3532863"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2017.7995254"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2025.3549621"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"ref46","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022"},{"key":"ref47","article-title":"NN-LUT: Neural approximation of non-linear operations for efficient transformer inference","author":"Yu","year":"2021"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/11684918\/11621966.pdf?arnumber=11621966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:20:33Z","timestamp":1790263233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11621966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":47,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tc.2026.3715379","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":[[2026,10]]}}}