{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T20:48:53Z","timestamp":1782161333727,"version":"3.54.5"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB4501600"],"award-info":[{"award-number":["2022YFB4501600"]}]},{"name":"National Key Research and Development Program of China","award":["2022YFB4501603"],"award-info":[{"award-number":["2022YFB4501603"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172380"],"award-info":[{"award-number":["62172380"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20241818"],"award-info":[{"award-number":["BK20241818"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["Y2021121"],"award-info":[{"award-number":["Y2021121"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"University of Science and Technology of China (USTC) Research Funds of the Double First-Class Initiative","doi-asserted-by":"publisher","award":["YD2150002011"],"award-info":[{"award-number":["YD2150002011"]}],"id":[{"id":"10.13039\/501100002367","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":[[2026,7]]},"DOI":"10.1109\/tcad.2025.3629537","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:53:34Z","timestamp":1762455214000},"page":"3319-3332","source":"Crossref","is-referenced-by-count":1,"title":["LORA: A Latency-Oriented Recurrent Architecture for Large Language Model on Multi-FPGA Platform With Communication Optimization"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6486-3062","authenticated-orcid":false,"given":"Zhendong","family":"Zheng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8321-6920","authenticated-orcid":false,"given":"Qianyu","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7281-1203","authenticated-orcid":false,"given":"Teng","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2240-6672","authenticated-orcid":false,"given":"Wenqi","family":"Lou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8391-5526","authenticated-orcid":false,"given":"Lei","family":"Gong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglan","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9403-5575","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-3143","authenticated-orcid":false,"given":"Xuehai","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref2","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref3","article-title":"PaLM 2 technical report","volume-title":"arXiv:2305.10403","author":"Anil","year":"2023"},{"key":"ref4","article-title":"Bloom: A 176b-parameter open-access multilingual language model","author":"Le Scao","year":"2023","journal-title":"arXiv:2211.05100"},{"key":"ref5","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv:2206.07682"},{"key":"ref6","article-title":"One small step for generative AI, one giant leap for AGI: A complete survey on ChatGPT in AIGC era","author":"Zhang","year":"2023","journal-title":"arXiv:2304.06488"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1176"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.334"},{"key":"ref9","first-page":"1","article-title":"OPAL: Outlier-preserved microscaling quantization accelerator for generative large language models","volume-title":"Proc. 61st ACM\/IEEE Design Autom. Conf.","author":"Koo"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29237"},{"key":"ref11","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv:2210.17323"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3373592"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071081"},{"key":"ref15","article-title":"LUT-GEMM: Quantized matrix multiplication based on LUTs for efficient inference in large-scale generative language models","author":"Park","year":"2022","journal-title":"arXiv:2206.09557"},{"key":"ref16","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref17","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref18","article-title":"The falcon series of open language models","author":"Almazrouei","year":"2023","journal-title":"arXiv:2311.16867"},{"key":"ref19","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref20","first-page":"155","article-title":"InfiniGen: Efficient generative inference of large language models with dynamic KV cache management","volume-title":"Proc. 18th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Lee"},{"key":"ref21","volume-title":"NVIDIA DGX Platform","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.14778\/3626292.3626303"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00082"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2016.2587683"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197489"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3281714"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3391688"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2988209"},{"key":"ref30","first-page":"1","article-title":"DNNExplorer: A framework for modeling and exploring a novel paradigm of FPGA-based DNN accelerator","volume-title":"Proc. IEEE\/ACM Int. Conf. Comput. Aided Design (ICCAD)","author":"Zhang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439477"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474043"},{"key":"ref35","article-title":"Demystifying AI platform design for distributed inference of next-generation LLM models","author":"Bambhaniya","year":"2024","journal-title":"arXiv:2406.01698"},{"issue":"8","key":"ref36","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref37","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"issue":"120","key":"ref38","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"issue":"240","key":"ref39","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdher","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref41","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3397800"},{"issue":"2019","key":"ref43","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume":"1","author":"Jia","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref44","article-title":"OneFlow: Redesign the distributed deep learning framework from scratch","author":"Yuan","year":"2021","journal-title":"arXiv:2110.15032"},{"key":"ref45","first-page":"1","article-title":"Efficient large-scale language model training on GPU clusters using megatron-LM","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Narayanan"},{"key":"ref46","volume-title":"AMD Alveo V80 Compute Accelerator","year":"2025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651347"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3656177"},{"key":"ref50","volume-title":"Intel QuickPath Interconnect","year":"2025"},{"key":"ref51","volume-title":"Aurora 64B\/66B LogiCORE IP Product Guide","year":"2025"},{"key":"ref52","volume-title":"Alveo U280 Data Center Accelerator Card","year":"2025"},{"key":"ref53","volume-title":"HBM IP","year":"2025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3517751"},{"key":"ref55","volume-title":"HLS Math Library","year":"2025"},{"key":"ref56","volume-title":"Deep Learning With INT8 Optimization on Xilinx Devices","year":"2017"},{"key":"ref57","volume-title":"Convolutional Neural Network With INT4 Optimization on Xilinx Devices","year":"2020"},{"key":"ref58","volume-title":"Concrete Mathematics: A Foundation for Computer Science","author":"Graham","year":"1994"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1144"},{"key":"ref60","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv:1609.07843"},{"key":"ref61","volume-title":"ESC8000A-E11","year":"2025"},{"key":"ref62","volume-title":"AMD EPYC 7543","year":"2025"},{"key":"ref63","volume-title":"Vitis Unified Software Platform Documentation: Application Acceleration Development (UG1393)","year":"2022"},{"key":"ref64","volume-title":"Vivado Design Suite User Guide: Release Notes, Installation, and Licensing (UG973)","year":"2022"},{"key":"ref65","volume-title":"IEEE Standard for Floating-Point Arithmetic","year":"2025"},{"key":"ref66","volume-title":"NVIDIA V100 GPU","year":"2025"},{"key":"ref67","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019","journal-title":"arXiv:1909.08053"},{"key":"ref68","article-title":"Embracing data abundance: BookTest dataset for reading comprehension","author":"Bajgar","year":"2016","journal-title":"arXiv:1610.00956"},{"key":"ref69","volume-title":"AMD Versal\u2122 HBM Series VHK158 Evaluation Kit","year":"2025"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/11573128\/11230847.pdf?arnumber=11230847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T19:56:10Z","timestamp":1782158170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":69,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2025.3629537","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}