{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T04:06:12Z","timestamp":1750824372539,"version":"3.41.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"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":[[2025,5,5]]},"DOI":"10.1109\/cscwd64889.2025.11033309","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:24:40Z","timestamp":1750699480000},"page":"2472-2477","source":"Crossref","is-referenced-by-count":0,"title":["HyperPipe: Bridging Heterogeneous GPUs for Accelerated Large-Scale Model Training"],"prefix":"10.1109","author":[{"given":"Fulai","family":"Liul","sequence":"first","affiliation":[{"name":"Shandong Fundamental Research Center for Computer Science,Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuantao","family":"Li","sequence":"additional","affiliation":[{"name":"Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunxiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jidong","family":"Huo","sequence":"additional","affiliation":[{"name":"Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Li","sequence":"additional","affiliation":[{"name":"Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianhui","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"ar Xiv preprint"},{"key":"ref2","article-title":"[Online]","volume-title":"Deepseek-rl: Incentivizing reasoning capability in llms via reinforcement learning","author":"DeepSeek-AI","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER51413.2022.00043"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607054"},{"key":"ref5","first-page":"945","article-title":"Mlaas in the wild: Workload analysis and scheduling in large-scale heterogeneous gpu clusters","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI22)","author":"Weng","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613175"},{"key":"ref7","first-page":"307","article-title":"{HetPipe}: Enabling large {DNN} training on (whimpy) heterogeneous {GPU} clusters through integration of pipelined model parallelism and data parallelism","volume-title":"2020 USENIX Annual Technical Conference (USENIX ATC 20)","author":"Park","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3386367.3432728"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17813"},{"key":"ref10","first-page":"673","article-title":"Whale: Efficient giant model training over heterogeneous {GPU s }","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Jia","year":"2022"},{"journal-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","year":"2019","author":"Shoeybi","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref14","first-page":"7937","article-title":"Memory-efficient pipeline-parallel dnn training","author":"Narayanan","year":"2021","journal-title":"International Con-ference on Machine Learning"},{"key":"ref15","article-title":"Large scale distributed deep networks","volume":"25","author":"Dean","year":"2012","journal-title":"vol"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.14778\/3598581.3598604"},{"key":"ref17","article-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism","volume":"32","author":"Huang","year":"2019","journal-title":"vol"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00036"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3458817.3476209","article-title":"Efficient large-scale language model training on gpu clusters using megatron-lm","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Narayanan","year":"2021"},{"article-title":"Language models are few-shot learners","volume-title":"Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Brown","key":"ref20"}],"event":{"name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","start":{"date-parts":[[2025,5,5]]},"location":"Compiegne, France","end":{"date-parts":[[2025,5,7]]}},"container-title":["2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11033175\/11033221\/11033309.pdf?arnumber=11033309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:41:17Z","timestamp":1750747277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11033309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/cscwd64889.2025.11033309","relation":{},"subject":[],"published":{"date-parts":[[2025,5,5]]}}}