{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:25:11Z","timestamp":1740101111545,"version":"3.37.3"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T00:00:00Z","timestamp":1665273600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T00:00:00Z","timestamp":1665273600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012632","name":"Nazarbayev University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012632","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,9]]},"DOI":"10.1109\/smc53654.2022.9945449","type":"proceedings-article","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T20:49:04Z","timestamp":1668804544000},"page":"486-491","source":"Crossref","is-referenced-by-count":0,"title":["A CNN Inference micro-benchmark for Performance Analysis and Optimization on GPUs"],"prefix":"10.1109","author":[{"given":"Jurn-Gyu","family":"Park","sequence":"first","affiliation":[{"name":"Nazarbayev University,School of Engineering and Digital Sciences,Nur-Sultan,Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhumakhan","family":"Nazir","sequence":"additional","affiliation":[{"name":"Nazarbayev University,School of Engineering and Digital Sciences,Nur-Sultan,Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beknur","family":"Kalmakhanbet","sequence":"additional","affiliation":[{"name":"Nazarbayev University,School of Engineering and Digital Sciences,Nur-Sultan,Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saidgaffor","family":"Sabyrov","sequence":"additional","affiliation":[{"name":"Nazarbayev University,School of Engineering and Digital Sciences,Nur-Sultan,Kazakhstan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3389","article-title":"Learning to optimize tensor programs","author":"chen","year":"2018","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1145\/3337821.3337839"},{"key":"ref12","article-title":"Optimizing cnn model inference on cpus","author":"liu","year":"2019","journal-title":"ATC"},{"key":"ref13","article-title":"Optimizing cnn model inference on cpus","author":"ahn","year":"2019","journal-title":"arXiv 1905 12799v1"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/DAC18072.2020.9218700"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/5.726791"},{"key":"ref16","article-title":"Imagenet classification with deep concovlutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"year":"2014","author":"krizhevsky","article-title":"cuda-convnet2","key":"ref17"},{"year":"2013","article-title":"NVIDIA CUDA Basic Linear Algebra Subroutines (cuBLAS) library","key":"ref18"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1145\/2647868.2654889"},{"year":"2014","author":"vasilache","journal-title":"Arxiv CoRR abs\/1412 7580","key":"ref4"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/RTAS.2019.00033"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ISPASS.2017.7975270"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CVPR.2016.435"},{"year":"2013","author":"mathieu","journal-title":"arXiv preprint arXiv 1312 5851","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1145\/3061639.3062297"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/SC.2016.53"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICPP.2016.15"},{"key":"ref9","first-page":"578","article-title":"Tvm: an auto- mated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"OSDI"},{"year":"2014","author":"chetlur","journal-title":"Arxiv 1410 0759","key":"ref1"},{"key":"ref20","article-title":"Torch: A matlab-like environment for machine learning","author":"collobert","year":"2011","journal-title":"BigLearn NIPS Workshop"},{"year":"0","article-title":"NVIDIA Profiler nvprof","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1137\/1.9781611970364"},{"key":"ref24","first-page":"4700","article-title":"Densely connected convolutional networks","author":"nd zhuang liu nd laurens van der maaten","year":"2017","journal-title":"CVPR"},{"key":"ref23","first-page":"7263","article-title":"Yolo9000: Better, faster, stronger","author":"redmon","year":"2017","journal-title":"CVPR"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1145\/3446382.3448606"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1145\/3470974"}],"event":{"name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2022,10,9]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2022,10,12]]}},"container-title":["2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9945068\/9945069\/09945449.pdf?arnumber=9945449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:55:56Z","timestamp":1670874956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9945449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,9]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/smc53654.2022.9945449","relation":{},"subject":[],"published":{"date-parts":[[2022,10,9]]}}}