{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:12:37Z","timestamp":1766268757067,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":38,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Key Research and Development Program of China","award":["2021YFB0300101","2023YFA1011704"],"award-info":[{"award-number":["2021YFB0300101","2023YFA1011704"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,12]]},"DOI":"10.1145\/3673038.3673054","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:29:01Z","timestamp":1723141741000},"page":"1166-1175","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SaSpGEMM: Sorting-Avoiding Sparse General Matrix-Matrix Multiplication on Multi-Core Processors"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5746-164X","authenticated-orcid":false,"given":"Chuhe","family":"Hong","sequence":"first","affiliation":[{"name":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8286-6566","authenticated-orcid":false,"given":"Qinglin","family":"Wang","sequence":"additional","affiliation":[{"name":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2875-0770","authenticated-orcid":false,"given":"Runzhang","family":"Mao","sequence":"additional","affiliation":[{"name":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5419-9560","authenticated-orcid":false,"given":"Yuechao","family":"Liang","sequence":"additional","affiliation":[{"name":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, 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, China and National Key Laboratory of Parallel and Distributed Computing, 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, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"e_1_3_2_1_1_1","series-title":"SIAM Journal on Matrix Analysis and Applications,SIAM Journal on Matrix Analysis and Applications (Nov","volume-title":"Exploiting Multiple Levels of Parallelism in Sparse Matrix-Matrix Multiplication","author":"Azad Ariful","year":"2016","unstructured":"Ariful Azad, Grey Ballard, Aydin Buluc, James Demmel, Laura Grigori, Oded Schwartz, and Sivan Toledo. 2016. Exploiting Multiple Levels of Parallelism in Sparse Matrix-Matrix Multiplication. SIAM Journal on Matrix Analysis and Applications,SIAM Journal on Matrix Analysis and Applications (Nov 2016)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx1313"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1137\/110838844"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916223"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605611"},{"key":"e_1_3_2_1_6_1","volume-title":"A fast radix sort. The computer journal 35, 6","author":"Davis J.","year":"1992","unstructured":"Ian\u00a0J. Davis. 1992. A fast radix sort. The computer journal 35, 6 (1992), 636\u2013642."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916550"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00071"},{"key":"e_1_3_2_1_10_1","volume-title":"Optimization of SpGEMM with Risc-V vector instructions. arXiv preprint arXiv:2303.02471","author":"F\u00e8vre Valentin\u00a0Le","year":"2023","unstructured":"Valentin\u00a0Le F\u00e8vre and Marc Casas. 2023. Optimization of SpGEMM with Risc-V vector instructions. arXiv preprint arXiv:2303.02471 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"A Systematic Survey of General Sparse Matrix-Matrix Multiplication. arXiv: Distributed, Parallel, and Cluster Computing,arXiv: Distributed, Parallel, and Cluster Computing (Feb","author":"Gao Jianhua","year":"2020","unstructured":"Jianhua Gao, Weixing Ji, Zhaonian Tan, and Yueyan Zhao. 2020. A Systematic Survey of General Sparse Matrix-Matrix Multiplication. arXiv: Distributed, Parallel, and Cluster Computing,arXiv: Distributed, Parallel, and Cluster Computing (Feb 2020)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/1354247"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1137\/0613024"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"John\u00a0R. Gilbert Steve Reinhardt and Viral\u00a0B. Shah. 2007. High-Performance Graph Algorithms from Parallel Sparse Matrices. 260\u2013269. https:\/\/doi.org\/10.1007\/978-3-540-75755-9_32","DOI":"10.1007\/978-3-540-75755-9_32"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3350755.3400216"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/355791.355796"},{"key":"e_1_3_2_1_17_1","volume-title":"The computer journal 5, 1","author":"Hoare AR","year":"1962","unstructured":"Charles\u00a0AR Hoare. 1962. Quicksort. The computer journal 5, 1 (1962), 10\u201316."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208062"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Guyue Huang Guohao Dai Yu Wang and Huazhong Yang. 2020. GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks. In SC20: International Conference for High Performance Computing Networking Storage and Analysis. https:\/\/doi.org\/10.1109\/sc41405.2020.00076","DOI":"10.1109\/sc41405.2020.00076"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.15"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588195.3593000"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2308221"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205313"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ipdps.2014.47"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.47"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2019.102545"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/icpp.2017.19"},{"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","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374521"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358330"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57675-2_16"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295701"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.114894"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2907537"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3168818"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2692916.2555255"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96983-1_48"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2366731"}],"event":{"name":"ICPP '24: the 53rd International Conference on Parallel Processing","acronym":"ICPP '24","location":"Gotland Sweden"},"container-title":["Proceedings of the 53rd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673054","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:31:00Z","timestamp":1758648660000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673054"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":38,"alternative-id":["10.1145\/3673038.3673054","10.1145\/3673038"],"URL":"https:\/\/doi.org\/10.1145\/3673038.3673054","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"}}]}}