{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T23:14:45Z","timestamp":1776122085800,"version":"3.50.1"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"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":[[2023,2]]},"DOI":"10.1109\/hpca56546.2023.10071051","type":"proceedings-article","created":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T13:42:55Z","timestamp":1679665375000},"page":"638-650","source":"Crossref","is-referenced-by-count":5,"title":["MERCURY: Accelerating DNN Training By Exploiting Input Similarity"],"prefix":"10.1109","author":[{"given":"Vahid","family":"Janfaza","sequence":"first","affiliation":[{"name":"Texas A&M University,Computer Science and Engineering,College Station,TX,USA"}]},{"given":"Kevin","family":"Weston","sequence":"additional","affiliation":[{"name":"Texas A&M University,Computer Science and Engineering,College Station,TX,USA"}]},{"given":"Moein","family":"Razavi","sequence":"additional","affiliation":[{"name":"Texas A&M University,Computer Science and Engineering,College Station,TX,USA"}]},{"given":"Shantanu","family":"Mandal","sequence":"additional","affiliation":[{"name":"Texas A&M University,Computer Science and Engineering,College Station,TX,USA"}]},{"given":"Farabi","family":"Mahmud","sequence":"additional","affiliation":[{"name":"Texas A&M University,Computer Science and Engineering,College Station,TX,USA"}]},{"given":"Alex","family":"Hilty","sequence":"additional","affiliation":[{"name":"Texas A&M University,Computer Science and Engineering,College Station,TX,USA"}]},{"given":"Abdullah","family":"Muzahid","sequence":"additional","affiliation":[{"name":"Texas A&M University,Computer Science and Engineering,College Station,TX,USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00068"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0"},{"key":"ref15","article-title":"Energy efficient boosting of gemm accelerators for dnn via reuse","author":"cicek","year":"2021","journal-title":"ACM Trans Des Autom Electron Syst"},{"key":"ref59","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref14","first-page":"1","article-title":"General reuse-centric cnn accelerator","author":"cicek","year":"2021","journal-title":"IEEE Transactions on Computers"},{"key":"ref58","article-title":"An empirical study of example forgetting during deep neural network learning","author":"toneva","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1014192.802449"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.12"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3487025"},{"key":"ref17","article-title":"Binarynet: Training deep neural networks with weights and activations constrained to +1 or -1","author":"courbariaux","year":"2016","journal-title":"Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref16","article-title":"Selection via proxy: Efficient data selection for deep learning","author":"coleman","year":"2019"},{"key":"ref19","article-title":"Large scale distributed deep networks","volume":"25","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Mixed precision training of convolutional neural networks using integer operations","author":"das","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460375"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2013.6657019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00138"},{"key":"ref45","first-page":"6950","article-title":"Coresets for data-efficient training of machine learning models","author":"mirzasoleiman","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330384"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00069"},{"key":"ref41","article-title":"Dynamic sparse graph for efficient deep learning","author":"liu","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref44","article-title":"Scalable deep learning on distributed infrastructures: Challenges, techniques, and tools","volume":"53","author":"mayer","year":"2020","journal-title":"ACM Comput Surv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00020"},{"key":"ref49","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2006.13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref4","first-page":"1","article-title":"Scaling learning algorithms towards ai","volume":"34","author":"bengio","year":"2007","journal-title":"Large-Scale Kernel Machines"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/362686.362692"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/502512.502546"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694358"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16988"},{"key":"ref34","first-page":"5464","article-title":"Grad-match: Gradient matching based data subset selection for efficient deep model training","author":"killamsetty","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref37","article-title":"Self-paced learning for latent variable models","volume":"23","author":"kumar","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref36","first-page":"1740","article-title":"Flexpoint: An adaptive numerical format for efficient training of deep neural networks","author":"k\u00f6ster","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems ser NIPS’17"},{"key":"ref31","author":"hennessy","year":"2011","journal-title":"Computer Architecture Fifth Edition A Quantitative Approach"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00062"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00070"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00061"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TNNLS.2021.3132836","article-title":"A survey of convolutional neural networks: Analysis, applications, and prospects","author":"li","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173176"},{"key":"ref24","first-page":"23","author":"feldman","year":"2020","journal-title":"Core-Sets Updated Survey"},{"key":"ref23","article-title":"Learning what data to learn","author":"fan","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"ref25","article-title":"Learning the structure of manifolds using random projections","volume":"20","author":"freund","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304041"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322263"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00064"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00075"},{"key":"ref66","article-title":"Trained ternary quantization","author":"zhu","year":"2017","journal-title":"5th International Conference on Learning Representations ICLR 2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00092"},{"key":"ref28","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"ref60","article-title":"Virtex 7 fpga","year":"0"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3358331.3358387"},{"key":"ref61","article-title":"Vivado","year":"0"}],"event":{"name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2023,2,25]]},"end":{"date-parts":[[2023,3,1]]}},"container-title":["2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10070856\/10070923\/10071051.pdf?arnumber=10071051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,9]],"date-time":"2023-12-09T10:43:36Z","timestamp":1702118616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10071051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/hpca56546.2023.10071051","relation":{},"subject":[],"published":{"date-parts":[[2023,2]]}}}