{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:02:04Z","timestamp":1776978124812,"version":"3.51.4"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["92470202"],"award-info":[{"award-number":["92470202"]}],"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":["62272475"],"award-info":[{"award-number":["62272475"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fund of National Key Laboratory of Multispectral Information Intelligent Processing Technology","award":["202410487201"],"award-info":[{"award-number":["202410487201"]}]},{"DOI":"10.13039\/501100001321","name":"Guangzhou Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["SL2024A04J0183"],"award-info":[{"award-number":["SL2024A04J0183"]}],"id":[{"id":"10.13039\/501100001321","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":[[2026,5]]},"DOI":"10.1109\/tcad.2025.3616078","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:36:52Z","timestamp":1759772212000},"page":"2446-2459","source":"Crossref","is-referenced-by-count":1,"title":["Terafly: A Multinode FPGA-Based Accelerator Design for Efficient Cooperative Inference in LLMs"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5037-4848","authenticated-orcid":false,"given":"Jianing","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4234-1359","authenticated-orcid":false,"given":"Gang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7878-3998","authenticated-orcid":false,"given":"Libo","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7196-9861","authenticated-orcid":false,"given":"Xin","family":"Lou","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The price of prompting: Profiling energy use in large language models inference","author":"Johannes Husom","year":"2024","journal-title":"arXiv:2407.16893"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474043"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3047371"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3564606"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref7","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref8","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3656177"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439477"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10993087"},{"key":"ref13","article-title":"EDGE-LLM: Enabling efficient large language model adaptation on edge devices via layerwise unified compression and adaptive layer tuning and voting","author":"Yu","year":"2024","journal-title":"arXiv:2406.15758"},{"key":"ref14","article-title":"LLM.int8(): 8-bit matrix multiplication for transformers at scale","author":"Dettmers","year":"2022","journal-title":"arXiv:2208.07339"},{"key":"ref15","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Xiao"},{"key":"ref16","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv:2210.17323"},{"key":"ref17","article-title":"BitNet: Scaling 1-bit transformers for large language models","author":"Wang","year":"2023","journal-title":"arXiv:2310.11453"},{"key":"ref18","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Frantar"},{"key":"ref19","article-title":"LLM-pruner: On the structural pruning of large language models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Ma"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293910"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00060"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3123465"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240850"},{"key":"ref24","article-title":"Hls4ml: An open-source codesign workflow to empower scientific low-power machine learning devices","author":"Fahim","year":"2021","journal-title":"arXiv:2103.05579"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3482854"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","article-title":"Language models are few-shot learners","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Brown"},{"key":"ref30","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3698590"},{"key":"ref32","first-page":"33","article-title":"Towards high-bandwidth-utilization SpMV on FPGAs via partial vector duplication","volume-title":"Proc. 28th Asia South Pacific Design Autom. Conf. (ASP-DAC)","author":"Liu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3716392"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3201494"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2815085"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1144"},{"key":"ref39","article-title":"ZeroQuant: Efficient and affordable post-training quantization for large-scale transformers","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Yao"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/11493579\/11185144.pdf?arnumber=11185144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T19:59:26Z","timestamp":1776974366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11185144\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":39,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2025.3616078","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}