{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:19:24Z","timestamp":1781972364532,"version":"3.54.5"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100017489","name":"Internship at Alibaba DAMO Academy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017489","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AI Chip Center for Emerging Smart Systems (ACCESS) and Research Grants Council of Hong Kong SAR","award":["CUHK14210723"],"award-info":[{"award-number":["CUHK14210723"]}]},{"name":"AI Chip Center for Emerging Smart Systems (ACCESS) and Research Grants Council of Hong Kong SAR","award":["CUHK14211824"],"award-info":[{"award-number":["CUHK14211824"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tcad.2024.3446858","type":"journal-article","created":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T23:29:23Z","timestamp":1724282963000},"page":"1045-1058","source":"Crossref","is-referenced-by-count":3,"title":["Klotski v2: Improved DNN Model Orchestration Framework for Dataflow Architecture Accelerators"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1742-0090","authenticated-orcid":false,"given":"Chen","family":"Bai","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuechao","family":"Wei","sequence":"additional","affiliation":[{"name":"Computing Technology Laboratory, Alibaba DAMO Academy, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1557-2613","authenticated-orcid":false,"given":"Youwei","family":"Zhuo","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Cai","sequence":"additional","affiliation":[{"name":"Computing Technology Laboratory, Alibaba DAMO Academy, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7696-9799","authenticated-orcid":false,"given":"Hongzhong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Computing Technology Laboratory, Alibaba DAMO Academy, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-4810","authenticated-orcid":false,"given":"Bei","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","year":"2023"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","volume":"33","author":"Brown"},{"key":"ref3","article-title":"LaMDA: Language models for dialog applications","author":"Thoppilan","year":"2022","journal-title":"arXiv:2201.08239"},{"key":"ref4","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"ref8","volume-title":"NVIDIA NVDLA deep learning accelerator","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001178"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080244"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527405"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061912"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3533040"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731633"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00100"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/641675.642111"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MC.1980.1653418"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3323923"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080221"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00042"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589048"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"ref26","article-title":"Scale-out first microarchitecture for efficient AI training","volume-title":"Linley Spring Process. Conf","author":"Ignjatovi\u0107"},{"key":"ref27","first-page":"2279","article-title":"Exploring hidden dimensions in parallelizing convolutional neural networks","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303953"},{"key":"ref29","first-page":"881","article-title":"Rammer: Enabling holistic deep learning compiler optimizations with rtasks","volume-title":"Proc. OSDI","author":"Ma"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","volume-title":"Gaussian Processes for Machine Learning","volume":"2","author":"Williams","year":"2006"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1966.tb01709.x"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00047"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/0117039"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01755-1"},{"key":"ref36","volume-title":"Space-filling curve","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_63468"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01607"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/69.908985"},{"key":"ref40","volume-title":"Hilbert curve","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0020-0190(97)00014-8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323893"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"ref44","volume-title":"nn_dataflow: A neural network dataflow scheduling tool","year":"2020"},{"key":"ref45","volume-title":"Gurobi Optimizer Reference Manual (2020)","year":"2020"},{"key":"ref46","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref49","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/10896910\/10643166.pdf?arnumber=10643166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T12:04:38Z","timestamp":1740139478000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10643166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":49,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2024.3446858","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}