{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:17:02Z","timestamp":1777655822144,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"PKU-Sensetime Joint Lab"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61520106004"],"award-info":[{"award-number":["61520106004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672048"],"award-info":[{"award-number":["61672048"]}],"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":[[2020]]},"DOI":"10.1109\/tc.2020.2973144","type":"journal-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T21:11:25Z","timestamp":1582319485000},"page":"1-1","source":"Crossref","is-referenced-by-count":13,"title":["Enabling Efficient Fast Convolution Algorithms on GPUs via MegaKernels"],"prefix":"10.1109","author":[{"given":"Liancheng","family":"Jia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiuhong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqiang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengen","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751213"},{"key":"ref38","first-page":"1","article-title":"Inter-block GPU communication via fast barrier synchronization","author":"xiao","year":"2010","journal-title":"Proc 24th IEEE Int Symp Parallel Distrib Process"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2016.15"},{"key":"ref30","first-page":"815","article-title":"MEC: Memory-efficient convolution for deep neural network","author":"cho","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2012.255"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.300"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661187"},{"key":"ref34","article-title":"Tensor comprehensions: Framework-agnostic high-performance machine learning abstractions","author":"vasilache","year":"2018","journal-title":"CoRR"},{"key":"ref10","article-title":"cuDNN: Efficient primitives for deep learning","author":"chetlur","year":"2014","journal-title":"CoRR"},{"key":"ref40","first-page":"413","article-title":"Locality-aware software throttling for sparse matrix operation on GPUs","author":"chen","year":"2018","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339596"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123978"},{"key":"ref13","year":"0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2017.00017"},{"key":"ref15","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref16","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref18","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"Proc 12th USENIX Symp Operating Syst Des Implementation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295734"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00037"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41321-1_2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.53"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref7","first-page":"951","article-title":"DeepCPU: Serving RNN-based deep learning models 10x faster","author":"zhang","year":"2018","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref2","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref9","article-title":"Fast convolutional nets with fbfft: A GPU performance evaluation","author":"vasilache","year":"2015"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref20","article-title":"Neon","year":"0"},{"key":"ref22","article-title":"CUTLASS: Fast linear algebra in CUDA C++","year":"0"},{"key":"ref21","article-title":"Fast training of convolutional networks through FFTs","author":"mathieu","year":"2014"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830813"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062244"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178496"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3146347.3146356"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2313342"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2018.00024"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/4358213\/09006949.pdf?arnumber=9006949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:28:53Z","timestamp":1642004933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9006949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/tc.2020.2973144","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}