{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T08:31:47Z","timestamp":1777105907986,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFA1003602"],"award-info":[{"award-number":["2021YFA1003602"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3656507","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["FLAME: Fully Leveraging MoE Sparsity for Transformer on FPGA"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6355-2439","authenticated-orcid":false,"given":"Xuanda","family":"Lin","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3887-6852","authenticated-orcid":false,"given":"Huinan","family":"Tian","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1394-9149","authenticated-orcid":false,"given":"Wenxiao","family":"Xue","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9697-4442","authenticated-orcid":false,"given":"Lanqi","family":"Ma","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9054-5500","authenticated-orcid":false,"given":"Jialin","family":"Cao","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7437-6587","authenticated-orcid":false,"given":"Manting","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4286-9292","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7288-1789","authenticated-orcid":false,"given":"Kun","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5409"},{"key":"e_1_3_2_1_2_1","first-page":"1573","article-title":"An algorithm-hardware co-optimized framework for accelerating N: M sparse transformers","volume":"30","author":"Chao Fang","year":"2022","unstructured":"Chao Fang et.al. 2022. An algorithm-hardware co-optimized framework for accelerating N: M sparse transformers. VLSI 30, 11 (2022), 1573--1586.","journal-title":"VLSI"},{"key":"e_1_3_2_1_3_1","unstructured":"Dmitry Lepikhin et.al. 2020. GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. arXiv:2006.16668 [cs.CL]"},{"key":"e_1_3_2_1_4_1","volume-title":"Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference. arXiv preprint arXiv:2303.06182","author":"Haiyang Huang","year":"2023","unstructured":"Haiyang Huang et.al. 2023. Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference. arXiv preprint arXiv:2303.06182 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Hongwu Peng et.al. 2021. Accelerating Transformer-based Deep Learning Models on FPGAs using Column Balanced Block Pruning. In ISQED. 142--148. 10.1109\/ISQED51717.2021.9424344","DOI":"10.1109\/ISQED51717.2021.9424344"},{"key":"e_1_3_2_1_6_1","unstructured":"Nan Du et.al. 2022. GLaM: Efficient Scaling of Language Models with Mixture-of-Experts. arXiv:2112.06905 [cs.CL]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_2_1_8_1","volume-title":"Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference. arXiv preprint arXiv:2308.12066","author":"Ranggi Hwang","year":"2023","unstructured":"Ranggi Hwang et.al. 2023. Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference. arXiv preprint arXiv:2308.12066 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Edgemoe: Fast on-device inference of moe-based large language models. arXiv preprint arXiv:2308.14352","author":"Rongjie Yi","year":"2023","unstructured":"Rongjie Yi et.al. 2023. Edgemoe: Fast on-device inference of moe-based large language models. arXiv preprint arXiv:2308.14352 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Learning both weights and connections for efficient neural network. Advances in neural information processing systems 28","author":"Song Han","year":"2015","unstructured":"Song Han et.al. 2015. Learning both weights and connections for efficient neural network. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_11_1","volume-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538","author":"Shazeer Noam","year":"2017","unstructured":"Shazeer Noam et.al. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)."},{"key":"e_1_3_2_1_12_1","volume-title":"Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts. arXiv preprint arXiv:2305.18691","author":"Sarkar Rishov","year":"2023","unstructured":"Sarkar Rishov et.al. 2023. Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts. arXiv preprint arXiv:2305.18691 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. arXiv:2101.03961 [cs.LG]","author":"William Fedus","year":"2022","unstructured":"William Fedus et.al. 2022. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. arXiv:2101.03961 [cs.LG]"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Yueyin Bai et.al. 2023. LTrans-OPU: A Low-Latency FPGA-Based Overlay Processor for Transformer Networks. In FPL. 283--287. 10.1109\/FPL60245.2023.00048","DOI":"10.1109\/FPL60245.2023.00048"}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","location":"San Francisco CA USA","acronym":"DAC '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656507","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3656507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:55Z","timestamp":1750295875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656507"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":14,"alternative-id":["10.1145\/3649329.3656507","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3656507","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}