{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:11:15Z","timestamp":1785604275767,"version":"3.56.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T00:00:00Z","timestamp":1744502400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T00:00:00Z","timestamp":1744502400000},"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":[[2025,4,13]]},"DOI":"10.1109\/cicc63670.2025.10982870","type":"proceedings-article","created":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T13:52:03Z","timestamp":1747662723000},"page":"1-3","source":"Crossref","is-referenced-by-count":2,"title":["A 52.03TOPS\/W DCIM-Based Accelerator with FlashAttention and Sparsity-Aware Alignment for LLMs"],"prefix":"10.1109","author":[{"given":"Bo","family":"Liu","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xilong","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingwen","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Si","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","author":"Frantar","year":"2023","journal-title":"ICML"},{"key":"ref3","article-title":"A simple and effective pruning approach for large language models","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","author":"Dao","year":"2022","journal-title":"NeurIPS"},{"key":"ref5","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42613.2021.9365958"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42615.2023.10067260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42614.2022.9731645"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42615.2023.10067360"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42614.2022.9731686"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/jssc.2024.3419808"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42613.2021.9365766"},{"key":"ref13","article-title":"A zonrn 16.3\u2013300 TOPS\/W computing-in-memory processor supporting floating-point NN inference\/training with intensive-CIM sparse-digital architecture","author":"Yue","year":"2023","journal-title":"ISSCC"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/hpca57654.2024.00062"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/isca.2016.30"}],"event":{"name":"2025 IEEE Custom Integrated Circuits Conference (CICC)","location":"Boston, MA, USA","start":{"date-parts":[[2025,4,13]]},"end":{"date-parts":[[2025,4,17]]}},"container-title":["2025 IEEE Custom Integrated Circuits Conference (CICC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10982532\/10982698\/10982870.pdf?arnumber=10982870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T18:02:01Z","timestamp":1753120921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10982870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,13]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/cicc63670.2025.10982870","relation":{},"subject":[],"published":{"date-parts":[[2025,4,13]]}}}