{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:13:40Z","timestamp":1766268820552,"version":"build-2065373602"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2021ZD0110102"],"award-info":[{"award-number":["2021ZD0110102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF of China","doi-asserted-by":"publisher","award":["U22A2028","62302483","62372436","62102398","62222214"],"award-info":[{"award-number":["U22A2028","62302483","62372436","62102398","62222214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"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 CAS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tc.2024.3475575","type":"journal-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T13:36:08Z","timestamp":1728394568000},"page":"155-169","source":"Crossref","is-referenced-by-count":1,"title":["Efficient and Fast High-Performance Library Generation for Deep Learning Accelerators"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9956-7039","authenticated-orcid":false,"given":"Jun","family":"Bi","sequence":"first","affiliation":[{"name":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7775-2724","authenticated-orcid":false,"given":"Yuanbo","family":"Wen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7748-7967","authenticated-orcid":false,"given":"Xiaqing","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5503-4457","authenticated-orcid":false,"given":"Yongwei","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1462-8336","authenticated-orcid":false,"given":"Yuxuan","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6434-8602","authenticated-orcid":false,"given":"Enshuai","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9979-0561","authenticated-orcid":false,"given":"Xing","family":"Hu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7603-4210","authenticated-orcid":false,"given":"Zidong","family":"Du","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8877-9052","authenticated-orcid":false,"given":"Ling","family":"Li","sequence":"additional","affiliation":[{"name":"Intelligent Software Research Center, Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2058-7086","authenticated-orcid":false,"given":"Huaping","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7601-0753","authenticated-orcid":false,"given":"Tianshi","family":"Chen","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2530-5874","authenticated-orcid":false,"given":"Qi","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2996864"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694358"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173212"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00038"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref9","article-title":"Cambricon MLU"},{"key":"ref10","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation (OSDI)","author":"Chen","year":"2018"},{"key":"ref11","first-page":"1025","article-title":"Optimizing CNN model inference on CPUs","volume-title":"Proc. USENIX Conf. USENIX Annu. Tech. Conf. (ATC)","author":"Liu","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322967"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370330"},{"key":"ref14","first-page":"863","article-title":"ANSOR: Generating high-performance tensor programs for deep learning","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation (OSDI)","author":"Zheng","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527440"},{"key":"ref16","first-page":"3393","article-title":"Learning to optimize tensor programs","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen","year":"2018"},{"key":"ref17","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2014"},{"key":"ref18","first-page":"2023","article-title":"Heron: Automatically constrained high-performance library generation for deep learning accelerators","volume-title":"Proc. 28th ACM Int. Conf. Archit. Support Program. Lang. Operating Syst.","volume":"3","author":"Bi"},{"key":"ref19","article-title":"TenSet: A large-scale program performance dataset for learned tensor compilers","volume-title":"Proc. NeurIPS Datasets Benchmarks","author":"Zheng","year":"2021"},{"key":"ref20","first-page":"2022","article-title":"TLP: A deep learning-based cost model for tensor program tuning","volume-title":"Proc. 28th ACM Int. Conf. Archit. Support Program. Lang. Oper. Syst.","volume":"2","author":"Zhai"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2928962"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3576933"},{"issue":"102","key":"ref23","article-title":"Genetic algorithms in search, optimization, and machine learning","volume":"1989","author":"Golberg","year":"1989","journal-title":"Addion Wesley"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3533640"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.42"},{"year":"2023","key":"ref26","article-title":"Googles operations research tools"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1145\/3497776.3517774","article-title":"One-shot tuner for deep learning compilers","volume-title":"Proc. 31st ACM SIGPLAN Int. Conf. Compiler Construction","author":"Ryu","year":"2022"},{"year":"2023","key":"ref30","article-title":"NVIDIA V100 tensor core GPU"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref34","first-page":"9992","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Liu","year":"2021"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/4235.873238"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2007.4424570"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00619-7_7"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/10794426\/10707341.pdf?arnumber=10707341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T04:36:11Z","timestamp":1762317371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10707341\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":38,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tc.2024.3475575","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":[[2025,1]]}}}