{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T04:01:57Z","timestamp":1746331317815,"version":"3.40.4"},"reference-count":7,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2025,5,1]]},"DOI":"10.1587\/transinf.2024edl8061","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T22:12:56Z","timestamp":1731535976000},"page":"436-439","source":"Crossref","is-referenced-by-count":0,"title":["APW: Asymmetric Padded Winograd to Reduce Thread Divergence for Computational Efficiency on SIMT Architecture"],"prefix":"10.1587","volume":"E108.D","author":[{"given":"Wonho","family":"LEE","sequence":"first","affiliation":[{"name":"Yeungnam University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jong Wook","family":"KWAK","sequence":"additional","affiliation":[{"name":"Yeungnam University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] M.M. Taye, \u201cTheoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions,\u201d Computation, vol.11, no.3, p.52, 2023. 10.3390\/computation11030052","DOI":"10.3390\/computation11030052"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] B. Barabasz, A. Anderson, K.M. Soodhalter, and D. Gregg, \u201cError analysis and improving the accuracy of winograd convolution for deep neural networks,\u201d ACM Transactions on Mathematical Software (TOMS), vol.46, no.4, pp.1-33, 2020. 10.1145\/3412380","DOI":"10.1145\/3412380"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] D. Huang, R. Zhang, X. Zhang, F. Wu, X. Wang, P. Jin, S. Liu, L. Li, and Y. Chen, \u201cA decomposable winograd method for n-d convolution acceleration in video analysis,\u201d International Journal of Computer Vision, vol.129, no.10, pp.2806-2826, 2021. 10.1007\/s11263-021-01500-9","DOI":"10.1007\/s11263-021-01500-9"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] P. Mori, L. Frickenstein, S.B. Sampath, M. Thoma, N. Fasfous, M.R. Vemparala, A. Frickenstein, C. Unger, W. Stechele, D. Mueller-Gritschneder, and C. Passerone, \u201cWino vidi vici: Conquering numerical instability of 8-bit winograd convolution for accurate inference acceleration on edge,\u201d Proc. IEEE\/CVF Winter Conference on Applications of Computer Vision, pp.53-62, 2024. 10.1109\/wacv57701.2024.00013","DOI":"10.1109\/WACV57701.2024.00013"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] C. Li, P. Jiang, H. Zhou, X. Wang, and X. Zhao, \u201cHaw: Hardware-aware point selection for efficient winograd convolution,\u201d IEEE Signal Process. Lett., vol.30, pp.269-273, 2023. 10.1109\/lsp.2023.3258863","DOI":"10.1109\/LSP.2023.3258863"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] C. Saumya, K. Sundararajah, and M. Kulkarni, \u201cDarm: control-flow melding for simt thread divergence reduction,\u201d 2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), pp.1-13, IEEE, 2022. 10.1109\/cgo53902.2022.9741285","DOI":"10.1109\/CGO53902.2022.9741285"},{"key":"7","unstructured":"[7] NVIDIA, \u201cNVIDIA H100 Tensor Core GPU Architecture,\u201d https:\/\/resources.nvidia.com\/en-us-tensor-core, 2023."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/5\/E108.D_2024EDL8061\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T03:46:27Z","timestamp":1746243987000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/5\/E108.D_2024EDL8061\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,1]]},"references-count":7,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024edl8061","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2025,5,1]]},"article-number":"2024EDL8061"}}