{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:12:27Z","timestamp":1758089547943,"version":"3.44.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11133023","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Hydra: Harnessing Expert Popularity for Efficient Mixture-of-Expert Inference on Chiplet System"],"prefix":"10.1109","author":[{"given":"Siqi","family":"He","sequence":"first","affiliation":[{"name":"Shaoxin Laboratory,Shaoxing,Zhejiang,China"}]},{"given":"Haozhe","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shaoxin Laboratory,Shaoxing,Zhejiang,China"}]},{"given":"Jiapei","family":"Zheng","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Laboratory of Integrated Chips and Systems (SKLICS),Shanghai,China"}]},{"given":"Lizhou","family":"Wu","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Laboratory of Integrated Chips and Systems (SKLICS),Shanghai,China"}]},{"given":"Bo","family":"Jiao","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Laboratory of Integrated Chips and Systems (SKLICS),Shanghai,China"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Laboratory of Integrated Chips and Systems (SKLICS),Shanghai,China"}]},{"given":"Xiaoyang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Laboratory of Integrated Chips and Systems (SKLICS),Shanghai,China"}]},{"given":"Chixiao","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University,State Key Laboratory of Integrated Chips and Systems (SKLICS),Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"volume-title":"Mistral 7b","year":"2023","author":"Jiang","key":"ref3"},{"issue":"120","key":"ref4","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"JMLR"},{"key":"ref5","first-page":"7103","article-title":"Mixture-of-experts with expert choice routing","volume":"35","author":"Zhou","year":"2022","journal-title":"NIPS"},{"key":"ref6","first-page":"269","article-title":"Tutel: Adaptive mixture-of-experts at scale","volume":"5","author":"Hwang","year":"2023","journal-title":"MLS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9063103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2020.3036341"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549464"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"ref12","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614310"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624865"},{"key":"ref16","first-page":"731","article-title":"Evaluating chiplet-based Large-Scale interconnection networks via Cycle-Accurate Packet-Parallel simulation","author":"Feng","journal-title":"USENIX ATC, 2024"},{"key":"ref17","first-page":"945","article-title":"Accelerating distributed MoE training and inference with lina","author":"Li","journal-title":"USENIX ATC, 2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00086"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508418"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00078"},{"key":"ref21","first-page":"1","article-title":"Flame: Fully leveraging moe sparsity for transformer on fpga","author":"Xuanda","year":"2024","journal-title":"DAC"},{"key":"ref22","article-title":"Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2405.04434"},{"key":"ref23","first-page":"22 173","article-title":"Ta-moe: Topology-aware large scale mixture-of-expert training","volume":"35","author":"Chen","year":"2022","journal-title":"NIPS"},{"key":"ref24","article-title":"Hetumoe: An efficient trillion-scale mixture-of-expert distributed training system","author":"Nie","year":"2022","journal-title":"arXiv preprint arXiv:2203.14685"},{"key":"ref25","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2019","journal-title":"arXiv preprint arXiv:1910.10683"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2005.864128"},{"article-title":"The stress terminal ui: s-tui","year":"2019","author":"Manuskin","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2015.7245728"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","start":{"date-parts":[[2025,6,22]]},"location":"San Francisco, CA, USA","end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11133023.pdf?arnumber=11133023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:31:35Z","timestamp":1758000695000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11133023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11133023","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}