{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:19:35Z","timestamp":1774365575243,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"SmartMore"},{"name":"The Research Grants Council of Hong Kong, SAR","award":["CUHK24209017"],"award-info":[{"award-number":["CUHK24209017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tcad.2023.3317169","type":"journal-article","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T18:06:37Z","timestamp":1695146797000},"page":"586-599","source":"Crossref","is-referenced-by-count":7,"title":["GTCO: Graph and Tensor Co-Design for Transformer-Based Image Recognition on Tensor Cores"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5337-1783","authenticated-orcid":false,"given":"Yang","family":"Bai","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR"}]},{"given":"Xufeng","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5153-6698","authenticated-orcid":false,"given":"Qi","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9501-9254","authenticated-orcid":false,"given":"Wenqian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9401-0482","authenticated-orcid":false,"given":"Shixin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR"}]},{"given":"Zixiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR"}]},{"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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643487"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref3","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00188"},{"key":"ref6","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. NIPS","author":"Vaswani"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00681"},{"key":"ref11","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218700"},{"key":"ref13","first-page":"1","article-title":"ALCOP: Automatic load-compute pipelining in deep learning compiler for AI-GPUs","volume-title":"Proc. Mach. Learn. Syst.","author":"Huang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3241110"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530584"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26343"},{"key":"ref17","first-page":"874","article-title":"AMOS: Enabling automatic mapping for tensor computations on spatial accelerators with hardware abstraction","volume-title":"Proc. ISCA","author":"Zheng"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317829"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref21","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. OSDI","author":"Abadi"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref23","volume-title":"OneAPI deep neural network library","year":"2023"},{"key":"ref24","volume-title":"ARM-compute-library","year":"2023"},{"key":"ref25","article-title":"cuDNN: Efficient primitives for deep learning","author":"Chetlur","year":"2014","journal-title":"arXiv:1410.0759"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185528"},{"key":"ref27","first-page":"579","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. OSDI","author":"Chen"},{"key":"ref28","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. OSDI","author":"Zheng"},{"key":"ref29","volume-title":"NVIDIA TensorRT","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/17512786.2015.1058180"},{"key":"ref31","article-title":"Deep learning using rectified linear units (ReLU)","author":"Agarap","year":"2018","journal-title":"arXiv:1803.08375"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"ref33","first-page":"1","article-title":"IOS: Inter-operator scheduler for CNN acceleration","volume-title":"Proc. MLSys","volume":"3","author":"Ding"},{"key":"ref34","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref35","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"arXiv:1810.04805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref37","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref38","first-page":"1","article-title":"Post-training quantization for vision transformer","volume-title":"Proc. NIPS","author":"Liu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20222"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01064"},{"key":"ref41","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref42","first-page":"3393","article-title":"Learning to optimize tensor programs","volume-title":"Proc. NIPS","author":"Chen"},{"key":"ref43","article-title":"Data movement is all you need: A case study on optimizing transformers","author":"Ivanov","year":"2021","journal-title":"arXiv:2007.00072"},{"key":"ref44","volume-title":"SEgmentation TRansformers\u2014SETR","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1093\/oed\/7687604332"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/10410112\/10255251.pdf?arnumber=10255251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T19:14:58Z","timestamp":1734030898000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10255251\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":45,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2023.3317169","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}