{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:36:48Z","timestamp":1783035408688,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":46,"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":[{"DOI":"10.13039\/501100006374","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2023ZD0120502"],"award-info":[{"award-number":["2023ZD0120502"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372055"],"award-info":[{"award-number":["62372055"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,2,28]]},"DOI":"10.1145\/3710848.3710858","type":"proceedings-article","created":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T06:20:57Z","timestamp":1740723657000},"page":"312-325","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["FlashSparse: Minimizing Computation Redundancy for Fast Sparse Matrix Multiplications on Tensor Cores"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5420-906X","authenticated-orcid":false,"given":"Jinliang","family":"Shi","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0022-7865","authenticated-orcid":false,"given":"Shigang","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1698-3565","authenticated-orcid":false,"given":"Youxuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7636-3082","authenticated-orcid":false,"given":"Rongtian","family":"Fu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7835-113X","authenticated-orcid":false,"given":"Xueying","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0472-5178","authenticated-orcid":false,"given":"Tong","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, 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","unstructured":"2023. Tensor Core.. https:\/\/www.nvidia.cn\/data-center\/tensor-cores\/."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2022.09.029"},{"key":"e_1_3_2_1_3_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_4_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_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02587-w"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476182"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3331057"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_9_1","unstructured":"dgl. 2018. DGL. https:\/\/docs.dgl.ai."},{"key":"e_1_3_2_1_10_1","first-page":"253","article-title":"DTC-SpMM: Bridging the Gap in Accelerating General Sparse Matrix Multiplication with Tensor Cores. In ASPLOS24","volume":"3","author":"Fan Ruibo","year":"2024","unstructured":"Ruibo Fan, Wei Wang, and Xiaowen Chu. 2024. DTC-SpMM: Bridging the Gap in Accelerating General Sparse Matrix Multiplication with Tensor Cores. In ASPLOS24: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3. 253--267.","journal-title":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems"},{"key":"e_1_3_2_1_11_1","volume-title":"Xin Fu, Anton Lukashchuk, Arslan Sajid Raja, et al.","author":"Feldmann Johannes","year":"2021","unstructured":"Johannes Feldmann, Nathan Youngblood, Maxim Karpov, Helge Gehring, Xuan Li, Maik Stappers, Manuel Le Gallo, Xin Fu, Anton Lukashchuk, Arslan Sajid Raja, et al. 2021. Parallel convolutional processing using an integrated photonic tensor core. Nature 589, 7840 (2021), 52--58."},{"key":"e_1_3_2_1_12_1","volume-title":"Fast graph representation learning with PyTorch Geometric. arXiv preprint arXiv:1903.02428","author":"Fey Matthias","year":"2019","unstructured":"Matthias Fey and Jan Eric Lenssen. 2019. Fast graph representation learning with PyTorch Geometric. arXiv preprint arXiv:1903.02428 (2019)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433723"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.01.009"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374546"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117921"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599843"},{"key":"e_1_3_2_1_20_1","volume-title":"Natural language processing: State of the art, current trends and challenges. Multimedia tools and applications 82, 3","author":"Khurana Diksha","year":"2023","unstructured":"Diksha Khurana, Aditya Koli, Kiran Khatter, and Sukhdev Singh. 2023. Natural language processing: State of the art, current trends and challenges. Multimedia tools and applications 82, 3 (2023), 3713--3744."},{"key":"e_1_3_2_1_21_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_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.06.075"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553447"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670314"},{"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":"10.1109\/ICPECA53709.2022.9718847"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607051"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508431"},{"key":"e_1_3_2_1_29_1","unstructured":"NVIDIA. [n. d.]. cuSPARSE.. https:\/\/developer.nvidia.cn\/cusparse."},{"key":"e_1_3_2_1_30_1","unstructured":"Nvidia. [n. d.]. Warp level matrix multiply-accumulate instructions. https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/index.html#matrix-shape."},{"key":"e_1_3_2_1_31_1","unstructured":"NVIDIA. 2020. Exploiting NVIDIA Ampere Structured Sparsity with cuSPARSELt. https:\/\/developer.nvidia.com\/blog\/exploiting-ampere-structured-sparsity-with-cusparselt\/."},{"key":"e_1_3_2_1_32_1","unstructured":"NVIDIA. 2023. Matrix Fragments for mma.m16n8k8. https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/index.html#matrix-fragments-for-mma-m16n8k8."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638470"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640426"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21366"},{"key":"e_1_3_2_1_36_1","unstructured":"Jeff Pool Abhishek Sawarkar and Jay Rodge. 2021. Accelerating Inference with Sparsity Using the NVIDIA Ampere Architecture and NVIDIA TensorRT."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835698.1835791"},{"key":"e_1_3_2_1_38_1","volume-title":"Markus Hagenbuchner, and Gabriele Monfardini.","author":"Scarselli Franco","year":"2008","unstructured":"Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2008. The graph neural network model. IEEE transactions on neural networks 20, 1 (2008), 61--80."},{"key":"e_1_3_2_1_39_1","volume-title":"Attention-based graph neural network for semi-supervised learning. arXiv preprint arXiv:1803.03735","author":"Thekumparampil Kiran K","year":"2018","unstructured":"Kiran K Thekumparampil, Chong Wang, Sewoong Oh, and Li-Jia Li. 2018. Attention-based graph neural network for semi-supervised learning. arXiv preprint arXiv:1803.03735 (2018)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1731011.1731020"},{"key":"e_1_3_2_1_41_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Veli\u010dkovi\u0107 Petar","year":"2017","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_3_2_1_42_1","unstructured":"Minjie Wang Da Zheng Zihao Ye Quan Gan Mufei Li Xiang Song Jinjing Zhou Chao Ma Lingfan Yu Yu Gai et al. 2019. Deep graph library: A graph-centric highly-performant package for graph neural networks. arXiv preprint arXiv:1909.01315 (2019)."},{"key":"e_1_3_2_1_43_1","volume-title":"15th USENIX symposium on operating systems design and implementation (OSDI).","author":"Wang Yuke","year":"2021","unstructured":"Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, Yuan Xie, and Yufei Ding. 2021. {GNNAdvisor}: An adaptive and efficient runtime system for {GNN} acceleration on {GPUs}. In 15th USENIX symposium on operating systems design and implementation (OSDI)."},{"key":"e_1_3_2_1_44_1","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC).","author":"Wang Yuke","year":"2023","unstructured":"Yuke Wang, Boyuan Feng, Zheng Wang, Guyue Huang, and Yufei Ding. 2023. {TC-GNN}: Bridging Sparse {GNN} Computation and Dense Tensor Cores on {GPUs}. In 2023 USENIX Annual Technical Conference (USENIX ATC)."},{"key":"e_1_3_2_1_45_1","volume-title":"TurboMGNN: Improving Concurrent GNN Training Tasks on GPU With Fine-Grained Kernel Fusion","author":"Wu Wenchao","year":"2023","unstructured":"Wenchao Wu, Xuanhua Shi, Ligang He, and Hai Jin. 2023. TurboMGNN: Improving Concurrent GNN Training Tasks on GPU With Fine-Grained Kernel Fusion. IEEE Transactions on Parallel and Distributed Systems (TPDS) (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"Accelerating sparse matrix-matrix multiplication with GPU Tensor Cores. Computers & Electrical Engineering 88","author":"Zachariadis Orestis","year":"2020","unstructured":"Orestis Zachariadis, Nitin Satpute, Juan G\u00f3mez-Luna, and Joaqu\u00edn Olivares. 2020. Accelerating sparse matrix-matrix multiplication with GPU Tensor Cores. Computers & Electrical Engineering 88 (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\/3710848.3710858","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3710848.3710858","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:15:41Z","timestamp":1755875741000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3710848.3710858"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,28]]},"references-count":46,"alternative-id":["10.1145\/3710848.3710858","10.1145\/3710848"],"URL":"https:\/\/doi.org\/10.1145\/3710848.3710858","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"}}]}}