{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:16:53Z","timestamp":1792790213982,"version":"4.5.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T00:00:00Z","timestamp":1688860800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T00:00:00Z","timestamp":1688860800000},"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":[[2023,7,9]]},"DOI":"10.1109\/dac56929.2023.10247730","type":"proceedings-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:31:31Z","timestamp":1694799091000},"page":"1-6","source":"Crossref","is-referenced-by-count":12,"title":["MixPipe: Efficient Bidirectional Pipeline Parallelism for Training Large-Scale Models"],"prefix":"10.1109","author":[{"given":"Weigang","family":"Zhang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuehai","family":"Tang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxing","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songlin","family":"Hu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476145"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00049"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref11","article-title":"Memory-efficient pipeline-parallel dnn training","author":"narayanan","year":"2021","journal-title":"PMLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref2","author":"devlin","year":"2018","journal-title":"BERT Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD46524.2019.00017"},{"key":"ref16","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref8","article-title":"On model parallelization and scheduling strategies for distributed machine learning","author":"lee","year":"2014","journal-title":"NIPS"},{"key":"ref7","article-title":"Communication efficient distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"NIPS"},{"key":"ref9","article-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism","author":"huang","year":"2019","journal-title":"NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"ref3","author":"dosovitskiy","year":"2020","journal-title":"An image is worth 16x16 words Transformers for image recognition at scale"},{"key":"ref6","article-title":"Zero-offload: Democratizing billion-scale model training","author":"ren","year":"2021","journal-title":"USENIX ATC"},{"key":"ref5","author":"chen","year":"2016","journal-title":"Training Deep Nets with Sublinear Memory Cost"}],"event":{"name":"2023 60th ACM\/IEEE Design Automation Conference (DAC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2023,7,9]]},"end":{"date-parts":[[2023,7,13]]}},"container-title":["2023 60th ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10247654\/10247655\/10247730.pdf?arnumber=10247730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T17:41:22Z","timestamp":1696268482000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10247730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,9]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/dac56929.2023.10247730","relation":{},"subject":[],"published":{"date-parts":[[2023,7,9]]}}}