{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T23:06:45Z","timestamp":1746313605194,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"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":[[2020,3]]},"DOI":"10.1109\/isqed48828.2020.9136967","type":"proceedings-article","created":{"date-parts":[[2020,7,9]],"date-time":"2020-07-09T20:46:45Z","timestamp":1594327605000},"page":"261-267","source":"Crossref","is-referenced-by-count":2,"title":["Alleviating Bottlenecks for DNN Execution on GPUs via Opportunistic Computing"],"prefix":"10.1109","author":[{"given":"Xianwei","family":"Cheng","sequence":"first","affiliation":[]},{"given":"Hui","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Mahmut","family":"Kandemir","sequence":"additional","affiliation":[]},{"given":"Saraju","family":"Mohanty","sequence":"additional","affiliation":[]},{"given":"Beilei","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref11","article-title":"Torch: A matlab-like environment for machine learning","author":"collobert","year":"0","journal-title":"BigLearn NIPS Workshop"},{"key":"ref12","article-title":"cudnn: Efficient primitives for deep learning","author":"sharan","year":"2014","journal-title":"ArXiv Preprint"},{"journal-title":"Fast convolutional nets with fbfft A GPU performance evaluation","year":"2015","author":"vasilache","key":"ref13"},{"key":"ref14","first-page":"3","article-title":"Theano: a cpu and gpu math expression compiler","volume":"4","author":"bergstra","year":"2010","journal-title":"SciPy"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2017.2777863"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7927141"},{"key":"ref18","article-title":"Leveraging the error resilience of machine-learning applications for designing highly energy efficient accelerators","author":"du","year":"2014","journal-title":"ASP-DAC"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062189"},{"key":"ref4","article-title":"Memory-Optimal Direct Convolutions for Maximizing Classification Accuracy in Embedded Applications","author":"gural","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref3","article-title":"High Performance Zero-Memory Overhead Direct Convolutions","author":"zhang","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2018.00049"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68612-7_3"},{"key":"ref8","article-title":"One weird trick for parallelizing convolutional neural networks","author":"krizhevsky","year":"2014","journal-title":"CoRR abs\/1404 5997"},{"key":"ref7","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123970"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"year":"0","key":"ref9"},{"key":"ref20","article-title":"An Efficient Kernel Transformation Architecture for Binary- and Ternary-weight Neural Network Inference","author":"zheng","year":"2018","journal-title":"DAC"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322212"}],"event":{"name":"2020 21st International Symposium on Quality Electronic Design (ISQED)","start":{"date-parts":[[2020,3,25]]},"location":"Santa Clara, CA, USA","end":{"date-parts":[[2020,3,26]]}},"container-title":["2020 21st International Symposium on Quality Electronic Design (ISQED)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9131689\/9136966\/09136967.pdf?arnumber=9136967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:56:43Z","timestamp":1656453403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9136967\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/isqed48828.2020.9136967","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}