{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:19:46Z","timestamp":1730269186439,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/USG.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/ipdps.2019.00022","type":"proceedings-article","created":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T01:19:46Z","timestamp":1567473586000},"page":"111-122","source":"Crossref","is-referenced-by-count":23,"title":["Fast Batched Matrix Multiplication for Small Sizes Using Half-Precision Arithmetic on GPUs"],"prefix":"10.1109","author":[{"given":"Ahmad","family":"Abdelfattah","sequence":"first","affiliation":[]},{"given":"Stanimire","family":"Tomov","sequence":"additional","affiliation":[]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","article-title":"Variable-size batched GaussJordan elimination for block-Jacobi preconditioning on graphics processors","author":"anzt","year":"2018","journal-title":"Parallel Computing"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/IPDPS.2018.00102"},{"key":"ref10","article-title":"Faster, Cheaper, Better – a Hybridization Methodology to Develop Linear Algebra Software for GPUs","volume":"2","author":"agullo","year":"2010","journal-title":"GPU Computing Gems"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/978-3-642-01970-8_89"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/TPDS.2011.311"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1145\/2063384.2063431"},{"key":"ref14","first-page":"1","article-title":"Performance Upper Bound Analysis and Optimization of SGEMM on Fermi and Kepler GPUs","author":"lai","year":"2013","journal-title":"Proceedings of the 2013 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO) CGO"},{"year":"2015","author":"gray","journal-title":"A full walk through of the SGEMM implementation","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1177\/1094342014567546"},{"key":"ref17","article-title":"A GEMM interface and implementation on NVIDIA GPUs for multiple small matrices","volume":"abs 1304 7053","author":"jhurani","year":"2013","journal-title":"CoRR"},{"key":"ref18","article-title":"cuDNN: Efficient Primitives for Deep Learning","author":"chetlur","year":"2014","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1007\/978-3-319-41321-1_2"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1145\/3126908.3126941"},{"key":"ref4","first-page":"1737","article-title":"Deep Learning with Limited Numerical Precision","author":"gupta","year":"2015","journal-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37 ser ICML’15 JMLR org"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/SC.2018.00050"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1016\/j.procs.2016.05.302"},{"key":"ref6","first-page":"31","article-title":"Benchmarking GPUs to tune dense linear algebra","author":"volkov","year":"2008","journal-title":"Proceedings of the ACM\/IEEE Conference on High Performance Computing SC 2008"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1007\/978-3-319-43659-3_48"},{"key":"ref5","first-page":"1","article-title":"IEEE Standard for Floating-Point Arithmetic","year":"2008","journal-title":"IEEE Std 754-2008"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1016\/j.parco.2009.12.005"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1177\/1094342010385729"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1145\/3065870"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1137\/15M1026419"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1145\/1498765.1498785","article-title":"Roofline: An Insightful Visual Performance Model for Multicore Architectures","volume":"52","author":"williams","year":"2009","journal-title":"Commun ACM"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/2647868.2654889"},{"key":"ref22","article-title":"High Performance Convolutional Neural Networks for Document Processing","author":"chellapilla","year":"0","journal-title":"IRISA Université de Rennes 1"},{"key":"ref21","article-title":"MagmaDNN High-Performance Data Analytics for Manycore GPUs and CPUs","author":"ng","year":"2017","journal-title":"magma-DNN 2017 Summer Research Experiences for Undergraduate (REU)"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1137\/1.9781611970364"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2016.435"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1007\/978-3-319-93698-7_45"},{"key":"ref25","article-title":"On deep neural networks for detecting heart disease","volume":"abs 1808 7168","author":"tomov","year":"2018","journal-title":"CoRR"}],"event":{"name":"2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","start":{"date-parts":[[2019,5,20]]},"location":"Rio de Janeiro, Brazil","end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8804711\/8820774\/08821034.pdf?arnumber=8821034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:19:35Z","timestamp":1657855175000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8821034\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ipdps.2019.00022","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}