{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:25:31Z","timestamp":1755998731326,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"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":[[2019,9]]},"DOI":"10.1109\/hpec.2019.8916378","type":"proceedings-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T07:11:36Z","timestamp":1575011496000},"page":"1-7","source":"Crossref","is-referenced-by-count":13,"title":["Scalable Inference for Sparse Deep Neural Networks using Kokkos Kernels"],"prefix":"10.1109","author":[{"given":"J. Austin","family":"Ellis","sequence":"first","affiliation":[]},{"given":"Sivasankaran","family":"Rajamanickam","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Efficient sparse-winograd convolutional neural networks","author":"liu","year":"2018","journal-title":"arXiv 1802 06367"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref12","article-title":"One Weird Trick for Parallelizing Convolutional Neural Networks","author":"krizhevsky","year":"2014","journal-title":"arXiv 1404 5997"},{"key":"ref13","article-title":"Unifying Data, Model and Hybrid Parallelism in Deep Learning via Tensor Tiling","author":"wang","year":"2018","journal-title":"arXiv 1805 04170v1"},{"key":"ref14","article-title":"Exploring Hidden Dimensions in Parallelizing Convolutional Neural Networks","author":"jia","year":"2018","journal-title":"arXiv 1802 04924v2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/110848244"},{"key":"ref16","article-title":"RadiX-Net: Structured sparse matrices for deep neural networks","author":"robinett","year":"2019","journal-title":"IEEE IPDPS GrAPL Workshop 2"},{"key":"ref17","article-title":"Deep Expander Networks: Efficient deep networks from graph theory","author":"prabhu","year":"2017","journal-title":"CoRR abs\/1711 08757"},{"journal-title":"The MNIST Database of Handwritten Digits","year":"1998","author":"lecun","key":"ref18"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"3202","DOI":"10.1016\/j.jpdc.2014.07.003","article-title":"Kokkos: Enabling manycore performance portability through polymorphic memory access patterns","volume":"74","author":"edwards","year":"2014","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"ref4","first-page":"125","article-title":"WaveNet: a generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ISCA Workshop on Speech Synthesis"},{"key":"ref3","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in NIPS 30 Annual Conference"},{"key":"ref6","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Advances in NIPS"},{"key":"ref5","article-title":"The state of sparsity in deep neural networks","author":"gale","year":"2019","journal-title":"CoRR abs\/1902 09574"},{"key":"ref8","article-title":"Sparse networks from scratch: Faster training without losing performance","author":"dettmers","year":"2019","journal-title":"arXiv 1907 04840"},{"key":"ref7","article-title":"The Lottery Ticket Hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"2019","journal-title":"ICLRE"},{"key":"ref2","article-title":"BERT: pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"arXiv 1810 04805"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916336"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"journal-title":"Kokkos Kernels","year":"2017","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2018.06.009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.8"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1145\/3322125","article-title":"Algorithm 9xx: SuiteSparse:GraphBLAS: Graph algorithms in the language of sparse linear algebra","author":"davis","year":"2019","journal-title":"To appear in ACM Trans on Mathematical Software"},{"journal-title":"LAGraph","year":"2019","author":"davis","key":"ref23"},{"key":"ref25","article-title":"Graph algorithms via SuiteSparse:GraphBLAS: triangle counting and k-truss","author":"davis","year":"2018","journal-title":"IEEE HPEC"}],"event":{"name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2019,9,24]]},"location":"Waltham, MA, USA","end":{"date-parts":[[2019,9,26]]}},"container-title":["2019 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8910148\/8916214\/08916378.pdf?arnumber=8916378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:47:02Z","timestamp":1658141222000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8916378\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/hpec.2019.8916378","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}