{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:45:43Z","timestamp":1773708343024,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":57,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB3001801"],"award-info":[{"award-number":["2023YFB3001801"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322201"],"award-info":[{"award-number":["62322201"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072018"],"award-info":[{"award-number":["62072018"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2020"],"award-info":[{"award-number":["U23B2020"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2028"],"award-info":[{"award-number":["U22A2028"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,2]]},"DOI":"10.1145\/3627535.3638471","type":"proceedings-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T14:22:41Z","timestamp":1708438961000},"page":"229-242","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Tetris: Accelerating Sparse Convolution by Exploiting Memory Reuse on GPU"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1453-6642","authenticated-orcid":false,"given":"Xiaoyan","family":"Liu","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4635-7309","authenticated-orcid":false,"given":"Xuegui","family":"Zheng","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1101-7927","authenticated-orcid":false,"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7186-0556","authenticated-orcid":false,"given":"Zhongzhi","family":"Luan","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-1473","authenticated-orcid":false,"given":"Depei","family":"Qian","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,2,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523442"},{"key":"e_1_3_2_1_3_1","volume-title":"Escoin: Efficient sparse convolutional neural network inference on gpus. arXiv preprint arXiv:1802.10280","author":"Chen Xuhao","year":"2018","unstructured":"Xuhao Chen. 2018. Escoin: Efficient sparse convolutional neural network inference on gpus. arXiv preprint arXiv:1802.10280 (2018)."},{"key":"e_1_3_2_1_4_1","volume-title":"Runtime Composition of Iterations for Fusing Loop-carried Sparse Dependence. In SC23: International Conference for High Performance Computing, Networking, Storage and Analysis. ACM, 1--14","author":"Cheshmi Kazem","year":"2023","unstructured":"Kazem Cheshmi, Michelle Mills Strout, and Maryam Mehri Dehnavi. 2023. Runtime Composition of Iterations for Fusing Loop-carried Sparse Dependence. In SC23: International Conference for High Performance Computing, Networking, Storage and Analysis. ACM, 1--14."},{"key":"e_1_3_2_1_5_1","volume-title":"cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759","author":"Chetlur Sharan","year":"2014","unstructured":"Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)."},{"key":"e_1_3_2_1_6_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. 2019. Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"e_1_3_2_1_8_1","volume-title":"online. https:\/\/github.com\/neuralmagic\/sparsezoo Accessed","author":"Community Neural Magic","year":"2023","unstructured":"Neural Magic Community. 2023. SparseZoo. online. https:\/\/github.com\/neuralmagic\/sparsezoo Accessed July 25, 2023."},{"key":"e_1_3_2_1_9_1","unstructured":"Shane Cook. 2012. CUDA programming: a developer's guide to parallel computing with GPUs. Newnes."},{"key":"e_1_3_2_1_10_1","volume-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv preprint arXiv:1602.02830","author":"Courbariaux Matthieu","year":"2016","unstructured":"Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1. arXiv preprint arXiv:1602.02830 (2016)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_12_1","volume-title":"SC22: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, 1--15","author":"Du Zhen","year":"2022","unstructured":"Zhen Du, Jiajia Li, Yinshan Wang, Xueqi Li, Guangming Tan, and Ninghui Sun. 2022. Alphasparse: generating high performance spmv codes directly from sparse matrices. In SC22: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, 1--15."},{"key":"e_1_3_2_1_13_1","volume-title":"NeurIPS ML for Systems workshop","author":"Elthakeb Ahmed","year":"2019","unstructured":"Ahmed Elthakeb, Prannoy Pilligundla, FatemehSadat Mireshghallah, Amir Yazdanbakhsh, Sicuan Gao, and Hadi Esmaeilzadeh. 2019. Releq: an automatic reinforcement learning approach for deep quantization of neural networks. In NeurIPS ML for Systems workshop, 2018."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433723"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_17_1","volume-title":"Gpu kernels for block-sparse weights. arXiv preprint arXiv:1711.09224 3, 2","author":"Gray Scott","year":"2017","unstructured":"Scott Gray, Alec Radford, and Diederik P Kingma. 2017. Gpu kernels for block-sparse weights. arXiv preprint arXiv:1711.09224 3, 2 (2017), 2."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433722"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.23919\/ELINFOCOM.2019.8706476"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_22_1","first-page":"1","article-title":"Evaluation of the performance of GPU global memory coalescing","volume":"4","author":"Kim Dae-Hwan","year":"2017","unstructured":"Dae-Hwan Kim. 2017. Evaluation of the performance of GPU global memory coalescing. Evaluation 4, 4 (2017), 1--5.","journal-title":"Evaluation"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2017.7975270"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115709"},{"key":"e_1_3_2_1_25_1","volume-title":"Enabling sparse winograd convolution by native pruning. arXiv preprint arXiv:1702.08597","author":"Li Sheng","year":"2017","unstructured":"Sheng Li, Jongsoo Park, and Ping Tak Peter Tang. 2017. Enabling sparse winograd convolution by native pruning. arXiv preprint arXiv:1702.08597 (2017)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575706"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458744.3473352"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_1_30_1","volume-title":"Mohamed Hamed N Taha, and Nour Eldeen M Khalifa","author":"Loey Mohamed","year":"2021","unstructured":"Mohamed Loey, Gunasekaran Manogaran, Mohamed Hamed N Taha, and Nour Eldeen M Khalifa. 2021. Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection. Sustainable cities and society 65 (2021), 102600."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.241"},{"key":"e_1_3_2_1_33_1","volume-title":"European Conference on Parallel Processing. Springer, 444--455","author":"Martineau Matt","year":"2018","unstructured":"Matt Martineau, Patrick Atkinson, and Simon McIntosh-Smith. 2018. Benchmarking the nvidia v100 gpu and tensor cores. In European Conference on Parallel Processing. Springer, 444--455."},{"key":"e_1_3_2_1_34_1","volume-title":"NPC 2014, Ilan, Taiwan, September 18--20, 2014. Proceedings 11","author":"Mei Xinxin","year":"2014","unstructured":"Xinxin Mei, Kaiyong Zhao, Chengjian Liu, and Xiaowen Chu. 2014. Benchmarking the memory hierarchy of modern GPUs. In Network and Parallel Computing: 11th IFIP WG 10.3 International Conference, NPC 2014, Ilan, Taiwan, September 18--20, 2014. Proceedings 11. Springer, 144--156."},{"key":"e_1_3_2_1_35_1","volume-title":"GPU technology conference","author":"Micikevicius Paulius","unstructured":"Paulius Micikevicius. 2012. GPU performance analysis and optimization. In GPU technology conference, Vol. 3."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11515-8_10"},{"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. 2010. Cusparse library. In GPU Technology Conference."},{"key":"e_1_3_2_1_38_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_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.12"},{"key":"e_1_3_2_1_40_1","volume-title":"Hai Li, Yiran Chen, and Pradeep Dubey.","author":"Park Jongsoo","year":"2016","unstructured":"Jongsoo Park, Sheng Li, Wei Wen, Ping Tak Peter Tang, Hai Li, Yiran Chen, and Pradeep Dubey. 2016. Faster cnns with direct sparse convolutions and guided pruning. arXiv preprint arXiv:1608.01409 (2016)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED51717.2021.9424344"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037745"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2016.06.005"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/SASP.2010.5521144"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2857721"},{"key":"e_1_3_2_1_46_1","first-page":"302","article-title":"Torchsparse: Efficient point cloud inference engine","volume":"4","author":"Tang Haotian","year":"2022","unstructured":"Haotian Tang, Zhijian Liu, Xiuyu Li, Yujun Lin, and Song Han. 2022. Torchsparse: Efficient point cloud inference engine. Proceedings of Machine Learning and Systems 4 (2022), 302--315.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_47_1","unstructured":"NVIDIA Performance Toolkit. 2014. NVIDIA PerfKit. (2014)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2017.7995254"},{"key":"e_1_3_2_1_49_1","first-page":"040901","article-title":"Development of convolutional neural network and its application in image classification: a survey","volume":"58","author":"Wang Wei","year":"2019","unstructured":"Wei Wang, Yujing Yang, Xin Wang, Weizheng Wang, and Ji Li. 2019. Development of convolutional neural network and its application in image classification: a survey. Optical Engineering 58, 4 (2019), 040901--040901.","journal-title":"Optical Engineering"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087243"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of Machine Learning and Systems 5","author":"Won Jaeyeon","year":"2023","unstructured":"Jaeyeon Won, Changwan Hong, Charith Mendis, Joel Emer, and Saman Amarasinghe. 2023. Unified Convolution Framework: A compiler-based approach to support sparse convolutions. Proceedings of Machine Learning and Systems 5 (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575742"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080215"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"e_1_3_2_1_55_1","first-page":"1","article-title":"Apollo: Automatic partition-based operator fusion through layer by layer optimization","volume":"4","author":"Zhao Jie","year":"2022","unstructured":"Jie Zhao, Xiong Gao, Ruijie Xia, Zhaochuang Zhang, Deshi Chen, Lei Chen, Renwei Zhang, Zhen Geng, Bin Cheng, and Xuefeng Jin. 2022. Apollo: Automatic partition-based operator fusion through layer by layer optimization. Proceedings of Machine Learning and Systems 4 (2022), 1--19.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454106"},{"key":"e_1_3_2_1_57_1","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. 2022. {SparTA}:{Deep-Learning} Model Sparsity via {Tensor-with-Sparsity-Attribute}. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 213--232."},{"key":"e_1_3_2_1_58_1","volume-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878","author":"Zhu Michael","year":"2017","unstructured":"Michael Zhu and Suyog Gupta. 2017. To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878 (2017)."}],"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\/3627535.3638471","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627535.3638471","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\/3627535.3638471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,20]]},"references-count":57,"alternative-id":["10.1145\/3627535.3638471","10.1145\/3627535"],"URL":"https:\/\/doi.org\/10.1145\/3627535.3638471","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"}}]}}