{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T09:42:43Z","timestamp":1776332563743,"version":"3.50.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018550","name":"Scientific and Technological Innovation 2030-Major Projects","doi-asserted-by":"publisher","award":["2022ZD0210600"],"award-info":[{"award-number":["2022ZD0210600"]}],"id":[{"id":"10.13039\/501100018550","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92464102"],"award-info":[{"award-number":["92464102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62034007"],"award-info":[{"award-number":["62034007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023B1515020051"],"award-info":[{"award-number":["2023B1515020051"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20200109115210307"],"award-info":[{"award-number":["JCYJ20200109115210307"]}]},{"DOI":"10.13039\/501100019031","name":"Science and Technology Innovation Key Research and Development Program of Chongqing","doi-asserted-by":"publisher","award":["JCYJ20200109115210307"],"award-info":[{"award-number":["JCYJ20200109115210307"]}],"id":[{"id":"10.13039\/501100019031","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Key Research and Development Program of Chongqing"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. I"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tcsi.2025.3546256","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T18:55:10Z","timestamp":1741287310000},"page":"3352-3365","source":"Crossref","is-referenced-by-count":35,"title":["EdgeLLM: A Highly Efficient CPU-FPGA Heterogeneous Edge Accelerator for Large Language Models"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7794-3985","authenticated-orcid":false,"given":"Mingqiang","family":"Huang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4722-2367","authenticated-orcid":false,"given":"Ao","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3251-931X","authenticated-orcid":false,"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8154-8463","authenticated-orcid":false,"given":"Haoxiang","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9709-9673","authenticated-orcid":false,"given":"Boyu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0575-4038","authenticated-orcid":false,"given":"Yupeng","family":"Su","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2674-4118","authenticated-orcid":false,"given":"Hao","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Southern University of Science and Technology, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref6","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2009.5206848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref9","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"ref11","volume-title":"OpenAI","year":"2023"},{"key":"ref12","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv:2204.02311"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref14","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s44159-023-00241-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref17","article-title":"I-ViT: Integer-only quantization for efficient vision transformer inference","author":"Li","year":"2022","journal-title":"arXiv:2207.01405"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tcsi.2022.3178474"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tcsi.2023.3312775"},{"key":"ref21","article-title":"LLM-barber: Block-aware rebuilder for sparsity mask in one-shot for large language models","author":"Su","year":"2024","journal-title":"arXiv:2408.10631"},{"key":"ref22","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume-title":"Proc. Mach. Learn. Syst.","volume":"7","author":"Lin"},{"key":"ref23","first-page":"22137","article-title":"Deja Vu: Contextual sparsity for efficient LLMS at inference time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref24","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frantar"},{"key":"ref25","first-page":"52342","article-title":"Scissorhands: Exploiting the persistence of importance hypothesis for llm KVcache compression at test time","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"issue":"140","key":"ref26","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref27","article-title":"MT5: A massively multilingual pre-trained text-to-text transformer","author":"Xue","year":"2020","journal-title":"arXiv:2010.11934"},{"key":"ref28","article-title":"ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools","author":"Glm","year":"2024","journal-title":"arXiv:2406.12793"},{"key":"ref29","article-title":"PaLM 2 technical report","volume-title":"arXiv:2305.10403","author":"Anil","year":"2023"},{"key":"ref30","volume-title":"Sora: Creating Video from Text","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/isqed51717.2021.9424344"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2022.3197489"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/hpca53966.2022.00049"},{"key":"ref37","volume-title":"NVIDIA A100 Tensor Core GPU Architecture","year":"2021"}],"container-title":["IEEE Transactions on Circuits and Systems I: Regular Papers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8919\/11061257\/10916480.pdf?arnumber=10916480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T17:48:10Z","timestamp":1751478490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10916480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":37,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsi.2025.3546256","relation":{},"ISSN":["1549-8328","1558-0806"],"issn-type":[{"value":"1549-8328","type":"print"},{"value":"1558-0806","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}