{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T20:33:48Z","timestamp":1783715628429,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272122"],"award-info":[{"award-number":["62272122"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong RIF","award":["R6021-20"],"award-info":[{"award-number":["R6021-20"]}]},{"name":"Hong Kong CRF","award":["C2004-21G"],"award-info":[{"award-number":["C2004-21G"]}]},{"name":"Hong Kong CRF","award":["C7004-22G"],"award-info":[{"award-number":["C7004-22G"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3620666.3651378","type":"proceedings-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T12:08:21Z","timestamp":1713960501000},"page":"253-267","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["DTC-SpMM: Bridging the Gap in Accelerating General Sparse Matrix Multiplication with Tensor Cores"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7492-2069","authenticated-orcid":false,"given":"Ruibo","family":"Fan","sequence":"first","affiliation":[{"name":"Data Science and Analytics Thrust, HKUST(GZ), Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4585-4152","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science & Engineering, HKUST, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9745-4372","authenticated-orcid":false,"given":"Xiaowen","family":"Chu","sequence":"additional","affiliation":[{"name":"Data Science and Analytics Thrust, HKUST(GZ), Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Computing graph neural networks: A survey from algorithms to accelerators. ACM Computing Surveys (CSUR), 54(9):1--38","author":"Abadal Sergi","year":"2021","unstructured":"Sergi Abadal, Akshay Jain, Robert Guirado, Jorge L\u00f3pez-Alonso, and Eduard Alarc\u00f3n. Computing graph neural networks: A survey from algorithms to accelerators. ACM Computing Surveys (CSUR), 54(9):1--38, 2021."},{"key":"e_1_3_2_1_2_1","volume-title":"AOCL: AMD optimizing CPU libraries","author":"AMD.","year":"2020","unstructured":"AMD. AOCL: AMD optimizing CPU libraries, 2020. Accessed on July 26, 2023."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569691"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476182"},{"key":"e_1_3_2_1_5_1","volume-title":"Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509","author":"Child Rewon","year":"2019","unstructured":"Rewon Child, Scott Gray, Alec Radford, and Ilya Sutskever. Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509, 2019."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530508"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363545"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00057"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781003033707-22"},{"key":"e_1_3_2_1_10_1","volume-title":"May","author":"Fey Matthias","year":"2019","unstructured":"Matthias Fey and Jan Eric Lenssen. Fast Graph Representation Learning with PyTorch Geometric, May 2019."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433723"},{"key":"e_1_3_2_1_12_1","volume-title":"Block-sparse gpu kernels","author":"Gray Scott","year":"2017","unstructured":"Scott Gray, Alec Radford, and Diederik P Kingma. Block-sparse gpu kernels, 2017."},{"key":"e_1_3_2_1_13_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems, 30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11075-005-1526-2"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286206"},{"key":"e_1_3_2_1_16_1","volume-title":"Eiman Ebrahimi, Jinjun Xiong, Rakesh Nagi, and Wen-mei W Hwu. Efficient inference on gpus for the sparse deep neural network graph challenge","author":"Hidayetoglu Mert","year":"2020","unstructured":"Mert Hidayetoglu, Carl Pearson, Vikram Sharma Mailthody, Eiman Ebrahimi, Jinjun Xiong, Rakesh Nagi, and Wen-mei W Hwu. Efficient inference on gpus for the sparse deep neural network graph challenge 2020. CoRR, 2020."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208062"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"e_1_3_2_1_19_1","volume-title":"https:\/\/github.com\/HPMLL\/DTC-SpMM_ASPLOS24.git","author":"HPMLL.","year":"2024","unstructured":"HPMLL. DTC-SpMM_ASPLOS24. https:\/\/github.com\/HPMLL\/DTC-SpMM_ASPLOS24.git, 2024."},{"key":"e_1_3_2_1_20_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_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00075"},{"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\/3437801.3441585"},{"key":"e_1_3_2_1_24_1","volume-title":"Inter-kernel reuse-aware thread block scheduling. ACM Transactions on Architecture and Code Optimization (TACO), 17(3):1--27","author":"Huzaifa Muhammad","year":"2020","unstructured":"Muhammad Huzaifa, Johnathan Alsop, Abdulrahman Mahmoud, Giordano Salvador, Matthew D Sinclair, and Sarita V Adve. Inter-kernel reuse-aware thread block scheduling. ACM Transactions on Architecture and Code Optimization (TACO), 17(3):1--27, 2020."},{"key":"e_1_3_2_1_25_1","volume-title":"Dissecting the nvidia volta gpu architecture via microbenchmarking. arXiv preprint arXiv:1804.06826","author":"Jia Zhe","year":"2018","unstructured":"Zhe Jia, Marco Maggioni, Benjamin Staiger, and Daniele P Scarpazza. Dissecting the nvidia volta gpu architecture via microbenchmarking. arXiv preprint arXiv:1804.06826, 2018."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374546"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3016078.2851152"},{"key":"e_1_3_2_1_28_1","volume-title":"Metis: A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices","author":"Karypis George","year":"1997","unstructured":"George Karypis and Vipin Kumar. Metis: A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices. 1997."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916336"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599843"},{"key":"e_1_3_2_1_31_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. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01244"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC54578.2021.00006"},{"key":"e_1_3_2_1_34_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_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037709"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571934"},{"key":"e_1_3_2_1_37_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_38_1","volume-title":"NVIDIA volta gpu architecture whitepaper. https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf","author":"NVIDIA.","year":"2017","unstructured":"NVIDIA. NVIDIA volta gpu architecture whitepaper. https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf, 2017. Accessed on July 27, 2023."},{"key":"e_1_3_2_1_39_1","volume-title":"NVIDIA ampere GA102 GPU architecture whitepaper. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf","author":"NVIDIA.","year":"2020","unstructured":"NVIDIA. NVIDIA ampere GA102 GPU architecture whitepaper. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf, 2020. Accessed on July 27, 2023."},{"key":"e_1_3_2_1_40_1","volume-title":"NVIDIA ampere GA102 GPU architecture whitepaper. https:\/\/www.nvidia.com\/content\/PDF\/nvidia-ampere-ga-102-gpu-architecture-whitepaper-v2.pdf","author":"NVIDIA.","year":"2020","unstructured":"NVIDIA. NVIDIA ampere GA102 GPU architecture whitepaper. https:\/\/www.nvidia.com\/content\/PDF\/nvidia-ampere-ga-102-gpu-architecture-whitepaper-v2.pdf, 2020. Accessed on July 27, 2023."},{"key":"e_1_3_2_1_41_1","volume-title":"NVIDIA ada gpu architecture whitepaper. https:\/\/images.nvidia.com\/aem-dam\/Solutions\/geforce\/ada\/nvidia-ada-gpu-architecture.pdf","author":"NVIDIA.","year":"2023","unstructured":"NVIDIA. NVIDIA ada gpu architecture whitepaper. https:\/\/images.nvidia.com\/aem-dam\/Solutions\/geforce\/ada\/nvidia-ada-gpu-architecture.pdf, 2023. Accessed on July 27, 2023."},{"key":"e_1_3_2_1_42_1","volume-title":"NVIDIA CUDA C Programming Guide. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html","author":"NVIDIA.","year":"2023","unstructured":"NVIDIA. NVIDIA CUDA C Programming Guide. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html, 2023. Accessed on July 5, 2023."},{"key":"e_1_3_2_1_43_1","volume-title":"PTX ISA: CUDA Toolkit documentation","author":"NVIDIA.","year":"2023","unstructured":"NVIDIA. PTX ISA: CUDA Toolkit documentation, 2023. Accessed on July 27, 2023."},{"key":"e_1_3_2_1_44_1","unstructured":"NVIDIA. Accelerating matrix multiplication with block-sparse format and NVIDIA tensor cores. https:\/\/developer.nvidia.com\/blog\/accelerating-matrix-multiplication-with-block-sparse-format-and-nvidia-tensor-cores\/ Publication date not provided. Accessed on July 27 2023."},{"key":"e_1_3_2_1_45_1","volume-title":"et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.59"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108752"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3217824"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926300"},{"key":"e_1_3_2_1_50_1","volume-title":"Efficient transformers: A survey. ACM Comput. Surv., 55(6), dec","author":"Tay Yi","year":"2022","unstructured":"Yi Tay, Mostafa Dehghani, Dara Bahri, and Donald Metzler. Efficient transformers: A survey. ACM Comput. Surv., 55(6), dec 2022."},{"key":"e_1_3_2_1_51_1","unstructured":"Vijay Thakkar Pradeep Ramani Cris Cecka Aniket Shivam Honghao Lu Ethan Yan Jack Kosaian Mark Hoemmen Haicheng Wu Andrew Kerr Matt Nicely Duane Merrill Dustyn Blasig Fengqi Qiao Piotr Majcher Paul Springer Markus Hohnerbach Jin Wang and Manish Gupta. CUTLASS January 2023."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsb.2010.01.021"},{"key":"e_1_3_2_1_53_1","volume-title":"ICLR workshop on representation learning on graphs and manifolds","author":"Wang Minjie Yu","year":"2019","unstructured":"Minjie Yu Wang. Deep graph library: Towards efficient and scalable deep learning on graphs. In ICLR workshop on representation learning on graphs and manifolds, 2019."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00088"},{"key":"e_1_3_2_1_55_1","first-page":"515","volume-title":"15th USENIX symposium on operating systems design and implementation (OSDI 21)","author":"Wang Yuke","year":"2021","unstructured":"Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, Yuan Xie, and Yufei Ding. GNNAdvisor: An adaptive and efficient runtime system for GNN acceleration on GPUs. In 15th USENIX symposium on operating systems design and implementation (OSDI 21), pages 515--531, 2021."},{"key":"e_1_3_2_1_56_1","first-page":"779","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Wang Yuke","year":"2023","unstructured":"Yuke Wang, Boyuan Feng, Zheng Wang, Tong Geng, Kevin Barker, Ang Li, and Yufei Ding. {MGG}: Accelerating graph neural networks with {Fine-Grained} {Intra-Kernel} {Communication-Computation} pipelining on {Multi-GPU} platforms. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23), pages 779--795, 2023."},{"key":"e_1_3_2_1_57_1","first-page":"149","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Wang Yuke","year":"2023","unstructured":"Yuke Wang, Boyuan Feng, Zheng Wang, Guyue Huang, and Yufei Ding. TC-GNN: Bridging sparse GNN computation and dense tensor cores on GPUs. In 2023 USENIX Annual Technical Conference (USENIX ATC 23), pages 149--164, 2023."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291125.3291146"},{"key":"e_1_3_2_1_59_1","volume-title":"Flash-llm: Enabling cost-effective and highly-efficient large generative model inference with unstructured sparsity. arXiv preprint arXiv:2309.10285","author":"Xia Haojun","year":"2023","unstructured":"Haojun Xia, Zhen Zheng, Yuchao Li, Donglin Zhuang, Zhongzhu Zhou, Xiafei Qiu, Yong Li, Wei Lin, and Shuaiwen Leon Song. Flash-llm: Enabling cost-effective and highly-efficient large generative model inference with unstructured sparsity. arXiv preprint arXiv:2309.10285, 2023."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00071"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374520"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96983-1_48"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582047"},{"key":"e_1_3_2_1_64_1","volume-title":"A novel genetic algorithm with hierarchical evaluation strategy for hyperparameter optimisation of graph neural networks. arXiv preprint arXiv:2101.09300","author":"Yuan Yingfang","year":"2021","unstructured":"Yingfang Yuan, Wenjun Wang, George M Coghill, and Wei Pang. A novel genetic algorithm with hierarchical evaluation strategy for hyperparameter optimisation of graph neural networks. arXiv preprint arXiv:2101.09300, 2021."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2020.106848"},{"key":"e_1_3_2_1_66_1","first-page":"213","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zheng Ningxin","year":"2022","unstructured":"Ningxin Zheng, Bin Lin, Quanlu Zhang, Lingxiao Ma, Yuqing Yang, Fan Yang, Yang Wang, Mao Yang, and Lidong Zhou. SparTA: Deep-Learning model sparsity via Tensor-with-Sparsity-Attribute. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22), pages 213--232, 2022."}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","location":"La Jolla CA USA","acronym":"ASPLOS '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651378","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:43Z","timestamp":1750291423000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":66,"alternative-id":["10.1145\/3620666.3651378","10.1145\/3620666"],"URL":"https:\/\/doi.org\/10.1145\/3620666.3651378","relation":{},"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2024-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}