{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T07:42:59Z","timestamp":1774942979547,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T00:00:00Z","timestamp":1617753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T00:00:00Z","timestamp":1617753600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T00:00:00Z","timestamp":1617753600000},"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":[],"published-print":{"date-parts":[[2021,4,7]]},"DOI":"10.1109\/isqed51717.2021.9424344","type":"proceedings-article","created":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T00:09:51Z","timestamp":1620691791000},"page":"142-148","source":"Crossref","is-referenced-by-count":94,"title":["Accelerating Transformer-based Deep Learning Models on FPGAs using Column Balanced Block Pruning"],"prefix":"10.1109","author":[{"given":"Hongwu","family":"Peng","sequence":"first","affiliation":[]},{"given":"Shaoyi","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Tong","family":"Geng","sequence":"additional","affiliation":[]},{"given":"Ang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Weiwen","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Hang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Shusen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Caiwen","family":"Ding","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2017.7858394"},{"key":"ref11","article-title":"Accelerating sparse dnn models without hardwaresupport via tile-wise sparsity","author":"guo","year":"2020","journal-title":"arXiv preprint arXiv 2008 13253"},{"key":"ref12","article-title":"Accelerated large batch optimization of bert pretraining in 54 minutes","author":"zheng","year":"2020","journal-title":"arXiv preprint arXiv 2006 13823"},{"key":"ref13","article-title":"Deebert: Dynamic early exiting for accelerating bert inference","author":"xin","year":"2020","journal-title":"arXiv preprint arXiv 2004 10491"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref15","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019","journal-title":"arXiv preprint arXiv 1907 11634"},{"key":"ref16","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"sanh","year":"2019","journal-title":"arXiv preprint arXiv 1910 01108"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv 2010 10042"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015676"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2016.7577314"},{"key":"ref3","article-title":"Recurrent neural networks hardware implementation on fpga","author":"chang","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref6","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2015","journal-title":"arXiv preprint arXiv 1510 00149"},{"key":"ref5","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5954"},{"key":"ref7","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref9","article-title":"Structured pruning of large language models","author":"wang","year":"2019","journal-title":"arXiv preprint arXiv 1910 12731"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293898"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174253"},{"key":"ref23","article-title":"Transformations of highlevel synthesis codes for high-performance computing","author":"de fine licht","year":"2018","journal-title":"arXiv preprint arXiv 1805 08288"},{"key":"ref26","first-page":"184","article-title":"A systematic dnn weight pruning framework using alternating direction method of multipliers","author":"zhang","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref25","article-title":"Pointer sentinel mixture models","author":"merity","year":"2017","journal-title":"5th International Conference on Learning RepresentationsICLR"}],"event":{"name":"2021 22nd International Symposium on Quality Electronic Design (ISQED)","location":"Santa Clara, CA, USA","start":{"date-parts":[[2021,4,7]]},"end":{"date-parts":[[2021,4,9]]}},"container-title":["2021 22nd International Symposium on Quality Electronic Design (ISQED)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424228\/9424248\/09424344.pdf?arnumber=9424344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:24Z","timestamp":1652197284000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9424344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/isqed51717.2021.9424344","relation":{},"subject":[],"published":{"date-parts":[[2021,4,7]]}}}