{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:03:12Z","timestamp":1771923792422,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/cgo68049.2026.11395201","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:46:32Z","timestamp":1771879592000},"page":"453-465","source":"Crossref","is-referenced-by-count":0,"title":["SparseX: Synergizing GPU Libraries for Sparse Matrix Multiplication on Heterogeneous Processors"],"prefix":"10.1109","author":[{"given":"Ruifeng","family":"Zhang","sequence":"first","affiliation":[{"name":"North Carolina State University,Department of Computer Science,Raleigh,NC,USA"}]},{"given":"Xiangwei","family":"Wang","sequence":"additional","affiliation":[{"name":"North Carolina State University,Department of Computer Science,Raleigh,NC,USA"}]},{"given":"Ang","family":"Li","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory and University of Washington,Seattle,WA,USA"}]},{"given":"Xipeng","family":"Shen","sequence":"additional","affiliation":[{"name":"North Carolina State University,Department of Computer Science,Raleigh,NC,USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Parallel breadth-first search on distributed memory systems","volume-title":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Buluc"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809983"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"ref4","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","volume-title":"ICLR workshop on representation learning on graphs and manifolds","author":"Wang"},{"key":"ref5","first-page":"2498","article-title":"Variational dropout sparsifies deep neural networks","volume-title":"International conference on machine learning","author":"Molchanov"},{"key":"ref6","article-title":"Learning sparse neural networks through l_0 regularization","author":"Louizos","year":"2017"},{"key":"ref7","first-page":"213","article-title":"{SparTA}:{Deep-Learning} model sparsity via {Tensor-with-Sparsity-Attribute}","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zheng"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569691"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607087"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673108"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622791"},{"key":"ref14","first-page":"149","article-title":"{TC-GNN}: Bridging sparse {GNN} computation and dense tensor cores on {GPUs}","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Wang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651378"},{"key":"ref16","article-title":"Cusparse library","volume":"12","author":"Naumov","year":"2010","journal-title":"GPU Technology Conference"},{"key":"ref17","article-title":"Efficient llm inference using dynamic input pruning and cache-aware masking","author":"Federici","year":"2024"},{"key":"ref18","article-title":"Relu strikes back: Exploiting activation sparsity in large language models","author":"Mirzadeh","year":"2023"},{"key":"ref19","first-page":"5533","article-title":"Inducing and exploiting activation sparsity for fast inference on deep neural networks","volume-title":"International Conference on Machine Learning","author":"Kurtz"},{"key":"ref20","article-title":"Nvidia a100 tensor core gpu architecture","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS51385.2021.00016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD58817.2023.00076"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605632"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577506"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CGO57630.2024.10444812"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178495"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2932931"},{"key":"ref28","article-title":"Megablocks: Efficient sparse training with mixture-of-experts","author":"Gale","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3322125"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3685277"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref32","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref33","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref34","article-title":"The falcon series of open language models","author":"Almazrouei","year":"2023"},{"key":"ref35","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref36","article-title":"Performance metrics (error measures) in machine learning regression, forecasting and prognostics: Properties and typology","author":"Botchkarev","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3133901"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC49654.2021.9622791"},{"key":"ref40","volume-title":"SparseX: Synergizing GPU Libraries for Sparse Matrix Multiplication on Heterogeneous Processors - Research Paper Artifact"}],"event":{"name":"2026 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11395173\/11394837\/11395201.pdf?arnumber=11395201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:02:57Z","timestamp":1771920177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11395201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/cgo68049.2026.11395201","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}