{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T08:58:00Z","timestamp":1725613080394},"reference-count":12,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1109\/candarw51189.2020.00041","type":"proceedings-article","created":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T02:11:10Z","timestamp":1614046270000},"page":"164-167","source":"Crossref","is-referenced-by-count":0,"title":["An Efficient Skinny Matrix-Matrix Multiplication Method by Folding Input Matrices into Tensor Core Operations"],"prefix":"10.1109","author":[{"given":"Hao","family":"Tang","sequence":"first","affiliation":[]},{"given":"Kazuhiko","family":"Komatsu","sequence":"additional","affiliation":[]},{"given":"Masayuki","family":"Sato","sequence":"additional","affiliation":[]},{"given":"Hiroaki","family":"Kobayashi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.81"},{"year":"2018","key":"ref3","article-title":"Peak performance of over 2.7 TFLOPS to realize outstanding HPC and AI capabilities"},{"key":"ref10","article-title":"TSQR on TensorCores","author":"ootomo","year":"2019","journal-title":"SC19 research poster"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330355"},{"key":"ref11","article-title":"Mixed Precision Training","author":"micikevicius","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48311-X_158"},{"key":"ref12","article-title":"Mixed Precision Training of Convolutional Neural Networks using Integer Operations","author":"das","year":"2018","journal-title":"International Conference on Learning Representations"},{"year":"2020","key":"ref8","article-title":"CUDA C++ Programming Guide"},{"key":"ref7","first-page":"505","article-title":"Performance Engineering for a Tall & Skinny Matrix Multiplication Kernels on GPUs","author":"ernst","year":"2019","journal-title":"International Conference on Parallel Processing and Applied Mathematics"},{"year":"2019","key":"ref2","article-title":"Google Cloud TPU"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"year":"2019","key":"ref1","article-title":"NVIDIA Tensor Cores"}],"event":{"name":"2020 Eighth International Symposium on Computing and Networking Workshops (CANDARW)","start":{"date-parts":[[2020,11,24]]},"location":"Naha, Japan","end":{"date-parts":[[2020,11,27]]}},"container-title":["2020 Eighth International Symposium on Computing and Networking Workshops (CANDARW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9355832\/9355839\/09355859.pdf?arnumber=9355859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:45:24Z","timestamp":1656344724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9355859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/candarw51189.2020.00041","relation":{},"subject":[],"published":{"date-parts":[[2020,11]]}}}