{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T22:58:12Z","timestamp":1768085892800,"version":"3.49.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","award":["2021R1A2C1095162"],"award-info":[{"award-number":["2021R1A2C1095162"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tpds.2023.3247808","type":"journal-article","created":{"date-parts":[[2023,3,17]],"date-time":"2023-03-17T17:25:29Z","timestamp":1679073929000},"page":"1479-1494","source":"Crossref","is-referenced-by-count":12,"title":["LAS: Locality-Aware Scheduling for GEMM-Accelerated Convolutions in GPUs"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5671-1870","authenticated-orcid":false,"given":"Hyeonjin","family":"Kim","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9170-5986","authenticated-orcid":false,"given":"William J.","family":"Song","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Asynchronous shaders: Unlocking the full potential of the GPU","year":"2015","journal-title":"AMD White Paper"},{"key":"ref2","first-page":"1","article-title":"AMD CNDA2 architecture","year":"2022","journal-title":"AMD White Paper"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01309"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref5","first-page":"815","article-title":"MEC: Memory-efficient convolution for deep neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cho"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"5951","article-title":"Constructing fast network through deconstruction of convolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jeon"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2013.6618813"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00086"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00065"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2017.7975270"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/355841.355847"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835937"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037709"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643535"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00041"},{"key":"ref22","first-page":"1","article-title":"Fast training of convolutional networks through FFTs","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Mathieu"},{"key":"ref23","first-page":"1","article-title":"NVIDIAs next generation CUDA compute architecture: Kepler GK110\/210","year":"2014","journal-title":"NVIDIA White Paper"},{"key":"ref24","first-page":"1","article-title":"NVIDIA Tesla V100 GPU architecture","year":"2017","journal-title":"NVIDIA White Paper"},{"key":"ref25","article-title":"NVIDIA cuda C programing guide","year":"2019"},{"key":"ref26","first-page":"1","article-title":"NVIDIA deep learning SDK documentation","year":"2019"},{"key":"ref27","first-page":"1","article-title":"NVIDIA A100 tensor core GPU architecture","year":"2020","journal-title":"NVIDIA White Paper"},{"key":"ref28","article-title":"Deep learning performance documentation","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2018.2813379"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503219"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00017"},{"key":"ref35","first-page":"1","article-title":"Very deep convolutional networks for layer-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00012"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00088"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00071"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10075651\/10050129.pdf?arnumber=10050129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T18:19:31Z","timestamp":1707848371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10050129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":42,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3247808","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}