{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:36:35Z","timestamp":1783035395041,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T00:00:00Z","timestamp":1740700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"This work was supported by the National Key Research and Development Program of China (2023YFB3002100) and the Chinese Academy of Sciences Strategic Priority Research Program (XDB0500103)."}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,2,28]]},"DOI":"10.1145\/3710848.3710888","type":"proceedings-article","created":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T06:20:57Z","timestamp":1740723657000},"page":"326-338","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Acc-SpMM: Accelerating General-purpose Sparse Matrix-Matrix Multiplication with GPU Tensor Cores"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5156-7456","authenticated-orcid":false,"given":"Haisha","family":"Zhao","sequence":"first","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8353-1242","authenticated-orcid":false,"given":"San","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5721-0303","authenticated-orcid":false,"given":"Jiaheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3812-5215","authenticated-orcid":false,"given":"Chunbao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5573-9986","authenticated-orcid":false,"given":"Jue","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3459-5105","authenticated-orcid":false,"given":"Zhikuang","family":"Xin","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6954-0035","authenticated-orcid":false,"given":"Shunde","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3803-7343","authenticated-orcid":false,"given":"Zhiqiang","family":"Liang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4199-3569","authenticated-orcid":false,"given":"Zhijie","family":"Pan","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9381-5928","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2026-417X","authenticated-orcid":false,"given":"Yan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5694-1617","authenticated-orcid":false,"given":"Yangang","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5353-3594","authenticated-orcid":false,"given":"Xuebin","family":"Chi","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,2,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A matrix approach to tomographic reconstruction and its implementation on gpus. Journal of structural biology, 170 1:146--51","author":"V\u00e1zquez Francisco","year":"2010","unstructured":"Francisco V\u00e1zquez, Ester M. Garz\u00f3n, and J. J. Fern\u00e1ndez. A matrix approach to tomographic reconstruction and its implementation on gpus. Journal of structural biology, 170 1:146--51, 2010."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.125"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2016.7761646"},{"key":"e_1_3_2_1_4_1","volume-title":"Software, environments, tools","author":"Demmel James","year":"2000","unstructured":"James Demmel, Jack J. Dongarra, Axel Ruhe, Henk A. van der Vorst, and Zhaojun Bai. Templates for the solution of algebraic eigenvalue problems. In Software, environments, tools, 2000."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","author":"Kannan Ramakrishnan","year":"2015","unstructured":"Ramakrishnan Kannan, Grey Ballard, and Haesun Park. A high-performance parallel algorithm for nonnegative matrix factorization. Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, 2015."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403227"},{"issue":"1","key":"e_1_3_2_1_7_1","first-page":"20","article-title":"Exploring data layout for sparse tensor times dense matrix on gpus","volume":"21","author":"Ahmad Khalid","year":"2023","unstructured":"Khalid Ahmad, Cris Cecka, Michael Garland, and Mary Hall. Exploring data layout for sparse tensor times dense matrix on gpus. ACM Transactions on Architecture and Code Optimization, 21:1 - 20, 2023.","journal-title":"ACM Transactions on Architecture and Code Optimization"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1515\/9781400830329"},{"key":"e_1_3_2_1_9_1","volume-title":"Multi-scale spectral decomposition of massive graphs","author":"Si Si","year":"2014","unstructured":"Si Si, D. Shin, Inderjit S. Dhillon, and Beresford N. Parlett. Multi-scale spectral decomposition of massive graphs. 2014."},{"key":"e_1_3_2_1_10_1","volume-title":"Graphblast: A high-performance linear algebra-based graph framework on the gpu. ACM Transactions on Mathematical Software (TOMS), 48:1 - 51","author":"Yang Carl","year":"2019","unstructured":"Carl Yang, Aydin Bulu\u00e7, and John Douglas Owens. Graphblast: A high-performance linear algebra-based graph framework on the gpu. ACM Transactions on Mathematical Software (TOMS), 48:1 - 51, 2019."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/b97861"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","volume":"2","author":"Peng Hongwu","year":"2023","unstructured":"Hongwu Peng, Xi Xie, Kaustubh Shivdikar, Md Amit Hasan, Jiahui Zhao, Shaoyi Huang, Omer Khan, David Kaeli, and Caiwen Ding. Maxk-gnn: Extremely fast gpu kernel design for accelerating graph neural networks training. Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, 2023."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3281714"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599805"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651528"},{"key":"e_1_3_2_1_16_1","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. Language models are few-shot learners. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 1877--1901. Curran Associates, Inc., 2020."},{"key":"e_1_3_2_1_17_1","first-page":"241","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler Torsten","year":"2021","unstructured":"Torsten Hoefler, Dan Alistarh, Tal Ben-Nun, Nikoli Dryden, and Alexandra Peste. Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks. J. Mach. Learn. Res., 22:241:1--241:124, 2021.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_18_1","volume-title":"Generating long sequences with sparse transformers. ArXiv, abs\/1904.10509","author":"Child Rewon","year":"2019","unstructured":"Rewon Child, Scott Gray, Alec Radford, and Ilya Sutskever. Generating long sequences with sparse transformers. ArXiv, abs\/1904.10509, 2019."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530508"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433723"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374546"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651378"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571934"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476182"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569691"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxt038"},{"key":"e_1_3_2_1_29_1","unstructured":"NVIDIA. Accelerating matrix multiplication with block sparsity. Technical Report 2021."},{"key":"e_1_3_2_1_30_1","volume-title":"Spring Simulation Multiconference","author":"Anzt Hartwig","year":"2015","unstructured":"Hartwig Anzt, Stanimire Tomov, and Jack J. Dongarra. Accelerating the lobpcg method on gpus using a blocked sparse matrix vector product. In Spring Simulation Multiconference, 2015."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3210259.3210263"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.110"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433816"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00071"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00086"},{"key":"e_1_3_2_1_36_1","volume-title":"Exposing memory access patterns to improve instruction and memory efficiency in gpus. ACM Transactions on Architecture and Code Optimization (TACO), 15:1 - 23","author":"Crago Neal Clayton","year":"2018","unstructured":"Neal Clayton Crago, Mark W. Stephenson, and Stephen W. Keckler. Exposing memory access patterns to improve instruction and memory efficiency in gpus. ACM Transactions on Architecture and Code Optimization (TACO), 15:1 - 23, 2018."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_38_1","volume-title":"Tc-gnn: Bridging sparse gnn computation and dense tensor cores on gpus","author":"Wang Yuke","year":"2021","unstructured":"Yuke Wang, Boyuan Feng, Zheng Wang, Guyue Huang, and Yufei Ding. Tc-gnn: Bridging sparse gnn computation and dense tensor cores on gpus. 2021."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","volume":"3","author":"Ye Zihao","year":"2022","unstructured":"Zihao Ye, Ruihang Lai, Junru Shao, Tianqi Chen, and Luis Ceze. Sparsetir: Composable abstractions for sparse compilation in deep learning. Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3, 2022."},{"key":"e_1_3_2_1_40_1","volume-title":"GPU Technology Conference","author":"Naumov Maxim","year":"2010","unstructured":"Maxim Naumov, L. Chien, Philippe Vandermersch, and Ujval Kapasi. Cusparse library. In GPU Technology Conference, 2010."},{"key":"e_1_3_2_1_41_1","unstructured":"NVIDIA rtx 4090 architecture. https:\/\/developer.nvidia.com\/rtx-4090-graphics-cards. Accessed: 2023-04-01."},{"issue":"2","key":"e_1_3_2_1_42_1","first-page":"1","article-title":"A 16-trump tensor core gpu architecture","volume":"56","author":"NVIDIA.","year":"2020","unstructured":"NVIDIA. Nvidia a100: A 16-trump tensor core gpu architecture. Journal of Supercomputing, 56(2):1--1, 2020.","journal-title":"Journal of Supercomputing"},{"key":"e_1_3_2_1_43_1","volume-title":"https:\/\/developer.nvidia.com\/h100-technology-deep-dive","author":"NVIDIA","year":"2020","unstructured":"NVIDIA h100 tensor core gpu architecture. https:\/\/developer.nvidia.com\/h100-technology-deep-dive, 2020."},{"key":"e_1_3_2_1_44_1","volume-title":"Nvidia cuda c programming guide","author":"NVIDIA Corporation","year":"2024","unstructured":"NVIDIA Corporation. Nvidia cuda c programming guide, 2024."},{"key":"e_1_3_2_1_45_1","volume-title":"The Volta Architecture Whitepaper","author":"NVIDIA.","year":"2018","unstructured":"NVIDIA. The Volta Architecture Whitepaper. 2018. [Online; accessed 1. April 2023]."},{"key":"e_1_3_2_1_46_1","unstructured":"NVIDIA. PTX ISA. NVIDIA Corporation USA 2024. [Online; accessed 1st June 2024]."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/829576"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971538"},{"key":"e_1_3_2_1_49_1","volume-title":"Finding and evaluating community structurein networks. Physical review E, 69(26113):1--16","author":"Newman Mark EJ","year":"2004","unstructured":"Mark EJ Newman. Finding and evaluating community structurein networks. Physical review E, 69(26113):1--16, 2004."},{"key":"e_1_3_2_1_50_1","volume-title":"Flashsparse: Minimizing computation redundancy for fast sparse matrix multiplications on tensor cores. arXiv preprint arXiv:2412.11007","author":"Shi Jinliang","year":"2024","unstructured":"Jinliang Shi, Shigang Li, Youxuan Xu, Rongtian Fu, Xueying Wang, and Tong Wu. Flashsparse: Minimizing computation redundancy for fast sparse matrix multiplications on tensor cores. arXiv preprint arXiv:2412.11007, 2024."},{"key":"e_1_3_2_1_51_1","volume-title":"Snap: A general-purpose network analysis and graph-mining library. ACM Transactions on Intelligent Systems and Technology (TIST), 8(1):1--20","author":"Leskovec Jure","year":"2016","unstructured":"Jure Leskovec and Rok Sosi\u010d. Snap: A general-purpose network analysis and graph-mining library. ACM Transactions on Intelligent Systems and Technology (TIST), 8(1):1--20, 2016."},{"key":"e_1_3_2_1_52_1","volume-title":"Yu Gai, Zihao Ye, Mufei Li, Jinjing Zhou, Qi Huang, Chao Ma, Ziyue Huang, et al. Deep graph library: towards efficient and scalable deep learning on graphs. corr abs\/1909.01315","author":"Wang Minjie","year":"2019","unstructured":"Minjie Wang, Lingfan Yu, Quan Gan Da Zheng, Yu Gai, Zihao Ye, Mufei Li, Jinjing Zhou, Qi Huang, Chao Ma, Ziyue Huang, et al. Deep graph library: towards efficient and scalable deep learning on graphs. corr abs\/1909.01315 (2019). arXiv preprint arXiv:1909.01315, 2019."},{"key":"e_1_3_2_1_53_1","volume-title":"Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems, 33:22118--22133","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems, 33:22118--22133, 2020."},{"key":"e_1_3_2_1_54_1","volume-title":"A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices version 5.0","author":"Karypis George","year":"1998","unstructured":"George Karypis. A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices version 5.0. 1998."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.59"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441585"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208062"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638470"},{"key":"e_1_3_2_1_59_1","unstructured":"NVIDIA. Exploiting nvidia ampere structured sparsity with cusparselt. NVIDIA Technical Report 2020--002 2020."}],"event":{"name":"PPoPP '25: The 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Las Vegas NV USA","acronym":"PPoPP '25","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3710848.3710888","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3710848.3710888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:14:32Z","timestamp":1755875672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3710848.3710888"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,28]]},"references-count":59,"alternative-id":["10.1145\/3710848.3710888","10.1145\/3710848"],"URL":"https:\/\/doi.org\/10.1145\/3710848.3710888","relation":{},"subject":[],"published":{"date-parts":[[2025,2,28]]},"assertion":[{"value":"2025-02-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}