{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:03:50Z","timestamp":1740099830407,"version":"3.37.3"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,9,22]],"date-time":"2020-09-22T00:00:00Z","timestamp":1600732800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,22]],"date-time":"2020-09-22T00:00:00Z","timestamp":1600732800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,22]],"date-time":"2020-09-22T00:00:00Z","timestamp":1600732800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-1725657"],"award-info":[{"award-number":["CCF-1725657"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,9,22]]},"DOI":"10.1109\/hpec43674.2020.9286195","type":"proceedings-article","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T21:07:15Z","timestamp":1608671235000},"page":"1-7","source":"Crossref","is-referenced-by-count":6,"title":["Studying the Effects of Hashing of Sparse Deep Neural Networks on Data and Model Parallelisms"],"prefix":"10.1109","author":[{"given":"Mohammad Hasanzadeh","family":"Mofrad","sequence":"first","affiliation":[]},{"given":"Rami","family":"Melhem","sequence":"additional","affiliation":[]},{"given":"Yousuf","family":"Ahmad","sequence":"additional","affiliation":[]},{"given":"Mohammad","family":"Hammoud","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/110848244"},{"journal-title":"Linear Algebraic Primitives for Parallel Computing on Large Graphs","year":"2010","author":"buluc","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536313"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/0613024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/355705.355707"},{"key":"ref30","first-page":"103","article-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism","author":"huang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/355791.355796"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3229710.3229720"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2019.8891008"},{"journal-title":"Tensorflow machine learning platform","year":"0","key":"ref10"},{"journal-title":"Pytorch machine learning framework","year":"0","key":"ref11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.8"},{"journal-title":"Caffe Deep learning framework","year":"0","key":"ref12"},{"journal-title":"A cellular computer to implement the Kalman filter algorithm","year":"1969","author":"cannon","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719918"},{"journal-title":"Google's neural machine translation system Bridging the gap between human and machine translation","year":"2016","author":"wu","key":"ref15"},{"key":"ref16","first-page":"13265","article-title":"Extreme classification in log memory using count-min sketch: A case study of amazon search with 50m products","author":"medini","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"journal-title":"NVIDIA DGX-2","year":"0","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"journal-title":"To prune or not to prune exploring the efficacy of pruning for model compression","year":"2017","author":"zhu","key":"ref4"},{"journal-title":"Pipedream Fast and efficient pipeline parallel dnn training","year":"2018","author":"harlap","key":"ref28"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"journal-title":"Exploring sparsity in recurrent neural networks","year":"2017","author":"narang","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04316-3"},{"journal-title":"Megatron-lm Training multi-billion parameter language models using model parallelism","year":"2019","author":"shoeybi","key":"ref29"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s17112556"},{"key":"ref2","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"journal-title":"YOLOv3 An Incremental Improvement","year":"2018","author":"redmon","key":"ref1"},{"journal-title":"An overview of gradient descent optimization algorithms","year":"2016","author":"ruder","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.14778\/3204028.3204035"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3210377.3210394"},{"key":"ref45","article-title":"Radix-net: Structured sparse matrices for deep neural networks","author":"robinett","year":"2019","journal-title":"2019 IEEE International Parallel and Distributed Processing Symposium Workshop (IPDPSW)"},{"journal-title":"The MNIST Database of Handwritten Digits","year":"0","author":"lecun","key":"ref48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2020373.2020375"},{"journal-title":"Posix thread (pthread) library","year":"0","key":"ref47"},{"journal-title":"Intel MPI Library","year":"0","key":"ref21"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref24","first-page":"1509","article-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Advances in neural information processing systems"},{"journal-title":"Nvidia nccl","year":"0","key":"ref23"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2012.6507483"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916494"},{"journal-title":"Zero Memory optimization towards training a trillion parameter models","year":"2019","author":"rajbhandari","key":"ref26"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916336"},{"key":"ref25","first-page":"10414","article-title":"Mesh-tensorflow: Deep learning for supercomputers","author":"shazeer","year":"2018","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2020,9,22]]},"location":"Waltham, MA, USA","end":{"date-parts":[[2020,9,24]]}},"container-title":["2020 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9285977\/9286137\/09286195.pdf?arnumber=9286195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:54:47Z","timestamp":1656345287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9286195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,22]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/hpec43674.2020.9286195","relation":{},"subject":[],"published":{"date-parts":[[2020,9,22]]}}}