{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:09:24Z","timestamp":1774307364490,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Key Research and Development Program of China: 2023YFA1011704","award":["2023YFA1011704"],"award-info":[{"award-number":["2023YFA1011704"]}]},{"name":"the National Key Research and Development Program of China: 2021YFB0300101","award":["2021YFB0300101"],"award-info":[{"award-number":["2021YFB0300101"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,12]]},"DOI":"10.1145\/3673038.3673042","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:29:01Z","timestamp":1723141741000},"page":"640-649","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["CAMLB-SpMV: An Efficient Cache-Aware Memory Load-Balancing SpMV on CPU"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9811-0234","authenticated-orcid":false,"given":"Jihu","family":"Guo","sequence":"first","affiliation":[{"name":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha 410073,China. National Key Laboratory of Parallel and Distributed Computing,National University of Defense Technology, Changsha 410073, China, National University of Defense Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1444-6778","authenticated-orcid":false,"given":"Rui","family":"Xia","sequence":"additional","affiliation":[{"name":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha 410073,China. National Key Laboratory of Parallel and Distributed Computing,National University of Defense Technology, Changsha 410073, China, National University of Defense Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3745-7541","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha 410073,China. National Key Laboratory of Parallel and Distributed Computing,National University of Defense Technology, Changsha 410073, China, National University of Defense Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1028-2035","authenticated-orcid":false,"given":"Xiaoxiong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha 410073,China. National Key Laboratory of Parallel and Distributed Computing,National University of Defense Technology, Changsha 410073, China, National University of Defense Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6706-2044","authenticated-orcid":false,"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha 410073,China. National Key Laboratory of Parallel and Distributed Computing,National University of Defense Technology, Changsha 410073, China, National University of Defense Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2012.118"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2020.102710"},{"key":"e_1_3_2_1_3_1","unstructured":"Advanced Micro\u00a0Devices (AMD). 2024. AOCL-Sparse. https:\/\/github.com\/amd\/aocl-sparse."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380930"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.69"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654078"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2016.64"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-58"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.10.036"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.151"},{"key":"e_1_3_2_1_11_1","volume-title":"The anatomy of a large-scale hypertextual web search engine. Computer networks and ISDN systems 30, 1-7","author":"Brin Sergey","year":"1998","unstructured":"Sergey Brin and Lawrence Page. 1998. The anatomy of a large-scale hypertextual web search engine. Computer networks and ISDN systems 30, 1-7 (1998), 107\u2013117."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1583991.1584053"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588195.3593002"},{"key":"e_1_3_2_1_14_1","volume-title":"An effective SPMV based on block strategy and hybrid compression on GPU. The Journal of Supercomputing","author":"Cui Huanyu","year":"2022","unstructured":"Huanyu Cui, Nianbin Wang, Yuhua Wang, Qilong Han, and Yuezhu Xu. 2022. An effective SPMV based on block strategy and hybrid compression on GPU. The Journal of Supercomputing (2022), 1\u201322."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2699470"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.OA-2016-0168"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.38"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3017994"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-008-0251-8"},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Algorithms and Architectures for Parallel Processing. Springer, 22\u201339","author":"Guo Jihu","year":"2023","unstructured":"Jihu Guo, Jie Liu, Qinglin Wang, and Xiaoxiong Zhu. 2023. Optimizing CSR-Based SpMV on a New MIMD Architecture Pezy-SC3s. In International Conference on Algorithms and Architectures for Parallel Processing. Springer, 22\u201339."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11075-016-0241-5"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.05.353"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586251"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462181"},{"key":"e_1_3_2_1_26_1","volume-title":"HASpMV: Heterogeneity-Aware Sparse Matrix-Vector Multiplication on Modern Asymmetric Multicore Processors. In 2023 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 209\u2013220","author":"Li Wenxuan","year":"2023","unstructured":"Wenxuan Li, Helin Cheng, Zhengyang Lu, Yuechen Lu, and Weifeng Liu. 2023. HASpMV: Heterogeneity-Aware Sparse Matrix-Vector Multiplication on Modern Asymmetric Multicore Processors. In 2023 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 209\u2013220."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-019-02835-4"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205313"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751209"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607051"},{"key":"e_1_3_2_1_31_1","volume-title":"Hyper-Threading Technology Architecture and Microarchitecture.Intel Technology Journal 6, 1","author":"Marr T","year":"2002","unstructured":"Deborah\u00a0T Marr, Frank Binns, David\u00a0L Hill, Glenn Hinton, David\u00a0A Koufaty, J\u00a0Alan Miller, and Michael Upton. 2002. Hyper-Threading Technology Architecture and Microarchitecture.Intel Technology Journal 6, 1 (2002)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3016078.2851190"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/639508.639512"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370327"},{"key":"e_1_3_2_1_35_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_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751244"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-06486-4"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3225230"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3168818"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2692916.2555255"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433815"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577506"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178495"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00104"}],"event":{"name":"ICPP '24: the 53rd International Conference on Parallel Processing","location":"Gotland Sweden","acronym":"ICPP '24"},"container-title":["Proceedings of the 53rd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673042","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:31:16Z","timestamp":1758648676000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":44,"alternative-id":["10.1145\/3673038.3673042","10.1145\/3673038"],"URL":"https:\/\/doi.org\/10.1145\/3673038.3673042","relation":{},"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"2024-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}