{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T13:03:43Z","timestamp":1773320623834,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"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":[[2026,1,19]]},"DOI":"10.1109\/asp-dac66049.2026.11420607","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:51:15Z","timestamp":1773172275000},"page":"865-871","source":"Crossref","is-referenced-by-count":0,"title":["SnipSnap: A Joint Compression Format and Dataflow Co-Optimization Framework for Efficient Sparse LLM Accelerator Design"],"prefix":"10.1109","author":[{"given":"Junyi","family":"Wu","sequence":"first","affiliation":[{"name":"Nanjing University"}]},{"given":"Chao","family":"Fang","sequence":"additional","affiliation":[{"name":"Nanjing University"}]},{"given":"Zhongfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref2","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2205.01068"},{"key":"ref3","journal-title":"GitHub. Copilot"},{"key":"ref4","article-title":"ReLU Strikes Back: Exploiting activation sparsity in large language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Mirzadeh"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1468"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2022.3197282"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tc.2024.3475814"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS48785.2022.9937659"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00062"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067360"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3172600"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3317789"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00064"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/isscc49661.2025.10904499"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3059962"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00082"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC53511.2021.00028"},{"key":"ref23","first-page":"1","article-title":"TeAAL: A Declarative Framework for Modeling Sparse Tensor Accelerators","volume-title":"56th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Nayak"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546866"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00096"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2025.3549709"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942127"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3358198"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC62300.2024.10737844"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582069"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE59016.2024.10444348"},{"issue":"241","key":"ref36","first-page":"1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref38","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"International Conference on Machine Learning (ICML).","author":"Leviathan"},{"key":"ref39","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs\/1409.1556","author":"Simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00049"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2020.3043870"}],"event":{"name":"2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)","location":"Lantau, Hong Kong","start":{"date-parts":[[2026,1,19]]},"end":{"date-parts":[[2026,1,22]]}},"container-title":["2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11420221\/11420229\/11420607.pdf?arnumber=11420607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T19:35:58Z","timestamp":1773257758000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11420607\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/asp-dac66049.2026.11420607","relation":{},"subject":[],"published":{"date-parts":[[2026,1,19]]}}}