{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T17:20:16Z","timestamp":1783790416032,"version":"3.55.0"},"reference-count":69,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tcad.2024.3524356","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T19:33:46Z","timestamp":1735673626000},"page":"2544-2557","source":"Crossref","is-referenced-by-count":3,"title":["Fine-Grained Structured Sparse Computing for FPGA-Based AI Inference"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2762-2726","authenticated-orcid":false,"given":"Chen","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2001-3763","authenticated-orcid":false,"given":"Shijie","family":"Cao","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8464-0130","authenticated-orcid":false,"given":"Guohao","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1719-5278","authenticated-orcid":false,"given":"Chenbo","family":"Geng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuliang","family":"Yao","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3043-522X","authenticated-orcid":false,"given":"Wencong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7352-8955","authenticated-orcid":false,"given":"Yunxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lintao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7315-6589","authenticated-orcid":false,"given":"Guangyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1138-804X","authenticated-orcid":false,"given":"Zhigang","family":"Ji","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7514-0767","authenticated-orcid":false,"given":"Runsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ru","family":"Huang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The history began from AlexNet: A comprehensive survey on deep learning approaches","author":"Alom","year":"2018","journal-title":"arXiv:1803.01164"},{"key":"ref2","article-title":"Convolutional networks for images, speech, and time series","volume-title":"Handbook of Brain Theory Neural Networks","author":"LeCun","year":"1995"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref4","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293898"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015676"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465842"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00367"},{"key":"ref11","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":"ref12","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Han"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref15","first-page":"21702","article-title":"Llm-pruner: On the structural pruning of large language models","volume":"36","author":"Ma","year":"2023","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445737"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080215"},{"key":"ref19","article-title":"Efficient sparse-winograd convolutional neural networks","author":"Liu","year":"2018","journal-title":"arXiv:1802.06367"},{"key":"ref20","article-title":"Exploring the regularity of sparse structure in convolutional neural networks","author":"Mao","year":"2017","journal-title":"arXiv:1705.08922"},{"key":"ref21","article-title":"Block-sparse recurrent neural networks","author":"Narang","year":"2017","journal-title":"arXiv:1711.02782"},{"key":"ref22","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01815-z"},{"key":"ref24","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":"ref25","article-title":"A simple and effective pruning approach for large language models","author":"Sun","year":"2023","journal-title":"arXiv:2306.11695"},{"key":"ref26","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2","author":"Solla"},{"key":"ref27","first-page":"1","article-title":"Net-Trim: Convex pruning of deep neural networks with performance guarantee","volume":"30","author":"Aghasi","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/72.317740"},{"key":"ref29","first-page":"1","article-title":"Runtime neural pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref31","article-title":"Sheared LLaMA: Accelerating language model pre-training via structured pruning","author":"Xia","year":"2023","journal-title":"arXiv:2310.06694"},{"key":"ref32","first-page":"1","article-title":"Structured Bayesian pruning via log-normal multiplicative noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Neklyudov"},{"key":"ref33","first-page":"1","article-title":"Learning structured sparsity in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Wen"},{"key":"ref34","article-title":"Learning intrinsic sparse structures within long short-term memory","author":"Wen","year":"2017","journal-title":"arXiv:1709.05027"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298681"},{"key":"ref36","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"Zhu","year":"2017","journal-title":"arXiv:1710.01878"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080254"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00011"},{"key":"ref40","first-page":"338","article-title":"RM-STC: Row-merge dataflow inspired GPU sparse tensor core for energy-efficient sparse acceleration","volume-title":"Proc. 56th Annu. IEEE\/ACM Int. Symp. Microarchit.","author":"Huang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/HPCSim.2014.6903755"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218732"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2019.00-42"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926299"},{"key":"ref48","first-page":"87","article-title":"AWQ: Activation-aware weight Quantization for on-device LLM compression and acceleration","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Lin"},{"key":"ref49","first-page":"30318","article-title":"Gpt3.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Dettmers"},{"key":"ref50","article-title":"Recurrent neural network regularization","author":"Zaremba","year":"2014","journal-title":"arXiv:1409.2329"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2401575"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530420"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3281715"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"ref57","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zaheer"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref59","volume-title":"PTB-XL, a large publicly available electrocardiography dataset (version 1.0.3)","author":"Wagner","year":"2022"},{"key":"ref60","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv:1609.07843"},{"key":"ref61","first-page":"213","article-title":"SparTA: Deep-learning model sparsity via tensor-with-sparsity-attribute","volume-title":"Proc. 16th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Zheng"},{"key":"ref62","article-title":"GPU kernels for block-sparse weights","author":"Gray","year":"2017","journal-title":"arXiv:1711.09224"},{"key":"ref63","volume-title":"CuSPARSELT: A high-performance CUDA library for sparse matrix-matrix multiplication","year":"2024"},{"key":"ref64","volume-title":"Alveo U200 and U250 data Center accelerator cards data sheet","year":"2020"},{"key":"ref65","volume-title":"U280 data Center accelerator card data sheet","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2785257"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070997"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/11044910\/10818746.pdf?arnumber=10818746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T07:06:10Z","timestamp":1750748770000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10818746\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":69,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2024.3524356","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}