{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T06:10:10Z","timestamp":1749881410387,"version":"3.41.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["2022ZD0161902"],"award-info":[{"award-number":["2022ZD0161902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["92373110","U22A2028","62341411","U23B2020","62322201","62032023","62072018"],"award-info":[{"award-number":["92373110","U22A2028","62341411","U23B2020","62322201","62032023","62072018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tc.2025.3551937","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T17:33:14Z","timestamp":1742232794000},"page":"2101-2113","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning Operators Performance Tuning for Changeable Sized Input Data on Tensor Accelerate Hardware"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4847-8148","authenticated-orcid":false,"given":"Pengyu","family":"Mu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1829-2817","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2741-6033","authenticated-orcid":false,"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6163-2074","authenticated-orcid":false,"given":"Guoxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8932-1297","authenticated-orcid":false,"given":"Hangcheng","family":"An","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1379-0576","authenticated-orcid":false,"given":"Qianhe","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1101-7927","authenticated-orcid":false,"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1399-0352","authenticated-orcid":false,"given":"Chenhao","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7186-0556","authenticated-orcid":false,"given":"Zhongzhi","family":"Luan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0349-1100","authenticated-orcid":false,"given":"Chunye","family":"Gong","sequence":"additional","affiliation":[{"name":"National Supercomputer Center, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-1473","authenticated-orcid":false,"given":"Depei","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3389507"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3208206"},{"year":"2017","key":"ref3","article-title":"Intel math kernel library for deep learning networks"},{"article-title":"cuDNN: Efficient primitives for deep learning","year":"2014","author":"Chetlur","key":"ref4"},{"key":"ref5","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operat. Syst. Des. Implement. (OSDI)","author":"Chen","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3275094"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3321938"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3325625"},{"year":"2024","key":"ref11","article-title":"Cuda [eb\/ol]"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3222955"},{"key":"ref13","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. 14th USENIX Symp. Operat. Syst. Des. Implement. (OSDI)","author":"Zheng","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454106"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370330"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527440"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3576933"},{"key":"ref18","first-page":"35783","article-title":"Tensor program optimization with probabilistic programs","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 35: Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Shao","year":"2022"},{"key":"ref19","first-page":"289","article-title":"Enabling tensor language model to assist in generating high-performance tensor programs for deep learning","volume-title":"Proc. 18th USENIX Symp. Operat. Syst. Des. Implement. (OSDI)","author":"Zhai","year":"2024"},{"key":"ref20","first-page":"848","article-title":"DietCode: Automatic optimization for dynamic tensor programs","volume-title":"Proc. Mach. Learn. Syst. (MLSys)","author":"Zheng","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3288758"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640390"},{"key":"ref23","first-page":"233","article-title":"ROLLER: Fast and efficient tensor compilation for deep learning","volume-title":"Proc. 16th USENIX Symp. Operat. Syst. Des. Implement. (OSDI)","author":"Zhu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582061"},{"article-title":"ONNX: Open neural network exchange","year":"2019","author":"Bai","key":"ref25"},{"author":"Roesch","key":"ref26","article-title":"Relay: A high-level IR for deep learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322967"},{"year":"2021","key":"ref28","article-title":"cuBLAS: CUDA basic linear algebra subroutine library"},{"year":"2022","key":"ref29","article-title":"CUTLASS: CUDA templates for linear algebra subroutines"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"issue":"8","key":"ref31","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume-title":"OpenAI blog","volume":"1","author":"Radford","year":"2019"},{"year":"2022","key":"ref32","article-title":"The nested tensor package prototype"},{"year":"2021","key":"ref33","article-title":"OpenBLAS: An optimized blas library"},{"article-title":"XLA: Tensorflow, compiled. tensorflow dev summit","year":"2017","author":"Leary","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3385269"},{"year":"2023","key":"ref37","article-title":"Blazerml"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3570641"},{"article-title":"Slective tuning","year":"2019","author":"Yu","key":"ref39"},{"key":"ref40","first-page":"208","article-title":"Nimble: Efficiently compiling dynamic neural networks for model inference","volume-title":"Proc. Mach. Learn. Syst. (MLSys)","author":"Shen","year":"2021"},{"year":"2024.","key":"ref41","article-title":"Dlight"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3437984.3458838"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/10994769\/10929012.pdf?arnumber=10929012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T05:29:36Z","timestamp":1749878976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10929012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":42,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tc.2025.3551937","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":[[2025,6]]}}}