{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T09:58:29Z","timestamp":1740131909612,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"CAS Project for Young Scientists in Basic Research","award":["YSBR-029"],"award-info":[{"award-number":["YSBR-029"]}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61732002","61906179","61925208","62002338","U19B2019","U20A20227"],"award-info":[{"award-number":["61732002","61906179","61925208","62002338","U19B2019","U20A20227"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Nova Program of Science and Technology","award":["Z191100001119093"],"award-info":[{"award-number":["Z191100001119093"]}]},{"name":"National Key Research and Development Program of China","award":["2018AAA0103300"],"award-info":[{"award-number":["2018AAA0103300"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tc.2021.3128266","type":"journal-article","created":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T20:33:05Z","timestamp":1637094785000},"page":"1-1","source":"Crossref","is-referenced-by-count":2,"title":["Enabling One-size-fits-all Compilation Optimization across Machine Learning Computers for Inference"],"prefix":"10.1109","author":[{"given":"Yuanbo","family":"Wen","sequence":"first","affiliation":[]},{"given":"Qi","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Zidong","family":"Du","sequence":"additional","affiliation":[]},{"given":"Jianxing","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Zhenxing","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xing","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhou","family":"Xuehai","sequence":"additional","affiliation":[]},{"given":"Tianshi","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref2","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proc. 33rd Int. Conf. Int. Conf. Mach. Learn.","author":"Amodei"},{"key":"ref3","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139361"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref6","first-page":"609","article-title":"Dadiannao: A machine-learning supercomputer","volume-title":"Proc. 47th Annu. IEEE\/ACM Int. Symp. Microarchit.","author":"Y."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2996864"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2928962"},{"key":"ref11","article-title":"NVIDIA Tensor Core"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref13","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Oper. Syst. Des. Implementation","author":"Abadi"},{"key":"ref14","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Oper. Syst. Des. Implementation","author":"Chen"},{"key":"ref15","article-title":"NVIDIA TensorRT"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/1674-4926\/41\/2\/021403"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"ref19","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. 14th USENIX Symp. Oper. Syst. Des. Implementation","author":"Zheng"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3211346.3211348"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"ref22","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"CoRR","volume":"abs\/1810.04805","author":"Devlin","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694358"},{"key":"ref25","first-page":"3393","article-title":"Learning to optimize tensor programs","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"author":"Simonyan","key":"ref28","article-title":"Very deep convolutional networks for large-scale image recognition"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref31","article-title":"Yolov3: An incremental improvement","volume":"abs\/1804.02767","author":"Redmon","year":"2018","journal-title":"CoRR"},{"key":"ref32","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016","journal-title":"arXiv:1611.01578"},{"key":"ref33","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080244"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.12"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304048"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"ref39","article-title":"XLA: Optimizing compiler for machine learning"},{"key":"ref40","article-title":"Glow: Graph lowering compiler techniques for neural networks","author":"Rotem","year":"2018","journal-title":"arXiv: 1805.00907"},{"key":"ref41","article-title":"Intel NGraph: An intermediate representation, compiler, and executor for deep learning","author":"Cyphers","year":"2018","journal-title":"arXiv: 1801.08058"},{"key":"ref42","article-title":"MLIR: A compiler infrastructure for the end of moore\u2019s law","volume":"abs\/2002.11054","author":"Lattner","year":"2020","journal-title":"ArXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3227-1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3234-0"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/4358213\/09616441.pdf?arnumber=9616441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:50:49Z","timestamp":1705020649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9616441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tc.2021.3128266","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"type":"print","value":"0018-9340"},{"type":"electronic","value":"1557-9956"},{"type":"electronic","value":"2326-3814"}],"subject":[],"published":{"date-parts":[[2021]]}}}