{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:16:37Z","timestamp":1772907397256,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tc.2020.3022318","type":"journal-article","created":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T21:48:13Z","timestamp":1599515293000},"page":"1-1","source":"Crossref","is-referenced-by-count":11,"title":["Evaluation of Optimized CNNs on Heterogeneous Accelerators using a Novel Benchmarking Approach"],"prefix":"10.1109","author":[{"given":"Michaela","family":"Blott","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Fraser","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giulio","family":"Gambardella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lisa","family":"Halder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes","family":"Kath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zachary","family":"Neveu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaman","family":"Umuroglu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alina","family":"Vasilciuc","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miriam","family":"Leeser","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linda","family":"Doyle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581275"},{"key":"ref38","article-title":"Dissecting the NVidia turing T4 GPU via microbenchmarking","author":"jia","year":"2019"},{"key":"ref33","article-title":"gemmlowp: A small self-contained low-precision GEMM library","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00059"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021740"},{"key":"ref37","year":"2018"},{"key":"ref36","article-title":"Box and whiskers","year":"2019"},{"key":"ref35","article-title":"QuTiBench: Benchmarking neural networks on heterogeneous hardware","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref10","first-page":"525","article-title":"XNOR-Net: ImageNet classification using binary convolutional neural networks","author":"rastegari","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref40","article-title":"Active TPC benchmarks","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3029580.3029586"},{"key":"ref12","article-title":"Resiliency of deep neural networks under quantization","author":"sung","year":"2015"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.5244\/C.30.87","article-title":"Wide residual networks","author":"zagoruyko","year":"2016"},{"key":"ref14","article-title":"WRPN: Wide reduced-precision networks","author":"mishra","year":"2017"},{"key":"ref15","article-title":"Bitwise neural networks","author":"kim","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref17","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","author":"mishra","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00826"},{"key":"ref19","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3242897"},{"key":"ref27","article-title":"Tearing apart Google’s TPU 3.0 AI coprocessor","author":"teich","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3358700"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342167"},{"key":"ref29","article-title":"Binarized neural network (BNN) accelerator IP","year":"2018"},{"key":"ref5","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015"},{"key":"ref8","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1","author":"courbariaux","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342176"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref9","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"zhou","year":"2016"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2017.73"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-78890-6_3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3352020.3352024"},{"key":"ref22","article-title":"Inside volta: The world’s most advanced data center GPU","author":"durant","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref42","article-title":"MLPerf: A broad ML benchmark suite for measuring performance of ML software frameworks, ML hardware accelerators, and ML cloud platforms","year":"2018"},{"key":"ref24","article-title":"AMD’s radeon vega GPU is headed everywhere, even to machine learning","author":"hardawar","year":"2018"},{"key":"ref41","article-title":"Benchmarking TPU, GPU, and CPU platforms for deep learning","author":"wang","year":"2019"},{"key":"ref23","article-title":"Taking a deeper look at the AMD radeon instinct GPUs for deep learning","year":"2017"},{"key":"ref44","year":"2018","journal-title":"Proceedings of the 1st on Reproducible Quality-Efficient Systems Tournament on Co-designing Pareto-efficient Deep Learning"},{"key":"ref26","article-title":"An in-depth look at Google’s first tensor processing unit (TPU)","author":"sato","year":"2017"},{"key":"ref43","article-title":"Collective knowledge","year":"2017"},{"key":"ref25","article-title":"NVIDIA jetson TX2 delivers twice the intelligence to the edge","author":"franklin","year":"2017"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/4358213\/09187576.pdf?arnumber=9187576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:05:01Z","timestamp":1642003501000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9187576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tc.2020.3022318","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}