{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T20:32:24Z","timestamp":1783715544078,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T00:00:00Z","timestamp":1708387200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,2]]},"DOI":"10.1145\/3627535.3638470","type":"proceedings-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T14:22:41Z","timestamp":1708438961000},"page":"377-389","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["A Row Decomposition-based Approach for Sparse Matrix Multiplication on GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5710-0285","authenticated-orcid":false,"given":"Meng","family":"Pang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9549-612X","authenticated-orcid":false,"given":"Xiang","family":"Fei","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1786-5372","authenticated-orcid":false,"given":"Peng","family":"Qu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2333-3580","authenticated-orcid":false,"given":"Youhui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1131-3024","authenticated-orcid":false,"given":"Zhaolin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,2,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.125"},{"key":"e_1_3_2_1_2_1","unstructured":"Hartwig Anzt Stanimire Tomov and Jack J Dongarra. 2015. Accelerating the LOBPCG method on GPUs using a blocked sparse matrix vector product.. In SpringSim (HPS). 75--82."},{"key":"e_1_3_2_1_3_1","first-page":"993","article-title":"Latent dirichlet allocation","author":"Blei David M","year":"2003","unstructured":"David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research 3, Jan (2003), 993--1022.","journal-title":"Journal of machine Learning research 3"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487677"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476182"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_7_1","first-page":"341","article-title":"Direct Methods for Sparse Matrices","volume":"1","author":"Duff Iain S.","year":"1984","unstructured":"Iain S. Duff, Alan M. Erisman, and John K. Reid. 1984. Direct Methods for Sparse Matrices. Numerical Methods for Partial Differential Equations 1, 4 (1984), 341--372.","journal-title":"Numerical Methods for Partial Differential Equations"},{"key":"e_1_3_2_1_8_1","volume-title":"The State of Sparsity in Deep Neural Networks. CoRR abs\/1902.09574","author":"Gale Trevor","year":"2019","unstructured":"Trevor Gale, Erich Elsen, and Sara Hooker. 2019. The State of Sparsity in Deep Neural Networks. CoRR abs\/1902.09574 (2019). arXiv:1902.09574 http:\/\/arxiv.org\/abs\/1902.09574"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433723"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208062"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"e_1_3_2_1_12_1","volume-title":"Dissecting the NVIDIA volta GPU architecture via microbench-marking. arXiv preprint arXiv:1804.06826","author":"Jia Zhe","year":"2018","unstructured":"Zhe Jia, Marco Maggioni, Benjamin Staiger, and Daniele P Scarpazza. 2018. Dissecting the NVIDIA volta GPU architecture via microbench-marking. arXiv preprint arXiv:1804.06826 (2018)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374546"},{"key":"e_1_3_2_1_14_1","unstructured":"Marcin Kalicinski Denny Lee and David Luebke. 2019. GPU Performance Analysis and Optimization. Morgan Kaufmann."},{"key":"e_1_3_2_1_15_1","volume-title":"Sparse convolutional networks using the permutohedral lattice. CoRR, abs\/1503.04949 2","author":"Kiefel Martin","year":"2015","unstructured":"Martin Kiefel, Varun Jampani, and Peter V Gehler. 2015. Sparse convolutional networks using the permutohedral lattice. CoRR, abs\/1503.04949 2 (2015)."},{"key":"e_1_3_2_1_16_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133901"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670314"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571934"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 806--814","author":"Liu Baoyuan","year":"2015","unstructured":"Baoyuan Liu, Min Wang, Hassan Foroosh, Marshall Tappen, and Marianna Pensky. 2015. Sparse convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 806--814."},{"key":"e_1_3_2_1_22_1","volume-title":"GPU Technology Conference.","author":"Naumov Maxim","year":"2010","unstructured":"Maxim Naumov, L Chien, Philippe Vandermersch, and Ujval Kapasi. 2010. Cusparse library. In GPU Technology Conference."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxt038"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3428226"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079086"},{"key":"e_1_3_2_1_26_1","volume-title":"The infinite gamma-Poisson feature model. Advances in Neural Information Processing Systems 20","author":"Titsias Michalis","year":"2007","unstructured":"Michalis Titsias. 2007. The infinite gamma-Poisson feature model. Advances in Neural Information Processing Systems 20 (2007)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/16\/1\/071"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591302"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362674"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96983-1_48"}],"event":{"name":"PPoPP '24: 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Edinburgh United Kingdom","acronym":"PPoPP '24","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627535.3638470","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627535.3638470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:26Z","timestamp":1750182566000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627535.3638470"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,20]]},"references-count":30,"alternative-id":["10.1145\/3627535.3638470","10.1145\/3627535"],"URL":"https:\/\/doi.org\/10.1145\/3627535.3638470","relation":{},"subject":[],"published":{"date-parts":[[2024,2,20]]},"assertion":[{"value":"2024-02-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}