{"id":"https://openalex.org/W4413411760","doi":"https://doi.org/10.1145/3721145.3725770","title":"HR-SpMM: Adaptive Row Partitioning and Hybrid Kernel Design for Sparse Matrix Multiplication","display_name":"HR-SpMM: Adaptive Row Partitioning and Hybrid Kernel Design for Sparse Matrix Multiplication","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4413411760","doi":"https://doi.org/10.1145/3721145.3725770"},"language":"en","primary_location":{"id":"doi:10.1145/3721145.3725770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721145.3725770","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3725770","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3725770","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100537256","display_name":"Qi Wang","orcid":"https://orcid.org/0009-0003-0204-6678"},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0003-0204-6678","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027916046","display_name":"Y.P. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaobin Wang","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0005-6602-9994","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109924629","display_name":"Yi Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Luo","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0002-2800-6976","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084210108","display_name":"Rong Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Luo","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0000-2307-7674","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100966435","display_name":"Pingping Tang","orcid":"https://orcid.org/0000-0002-5888-975X"},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingping Tang","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-5888-975X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan, China","institution_ids":["https://openalex.org/I1297991670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1297991670"],"apc_list":null,"apc_paid":null,"fwci":3.0189,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90661633,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6934731006622314},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6103346347808838},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.44949811697006226},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4327704906463623},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.42667779326438904},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3534323573112488},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24510902166366577},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.12500235438346863},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.06708827614784241},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06006309390068054},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.05767253041267395}],"concepts":[{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6934731006622314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6103346347808838},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.44949811697006226},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4327704906463623},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.42667779326438904},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3534323573112488},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24510902166366577},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.12500235438346863},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.06708827614784241},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06006309390068054},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.05767253041267395},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721145.3725770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721145.3725770","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3725770","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3721145.3725770","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721145.3725770","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3725770","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8094119792","display_name":"\u62d3\u5c55\u4f17\u6838\u6709\u6548\u5e76\u884c\u6e90\u7684\u5fae\u7ebf\u7a0b\u5f0f\u8f6f\u786c\u4ef6\u652f\u6301\u673a\u5236","funder_award_id":"61672438","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322559","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474"},{"id":"https://openalex.org/F4320323711","display_name":"Southwest University","ror":"https://ror.org/01kj4z117"},{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413411760.pdf","grobid_xml":"https://content.openalex.org/works/W4413411760.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1985312666","https://openalex.org/W2016563136","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2626696598","https://openalex.org/W2734941459","https://openalex.org/W2808128431","https://openalex.org/W2914631005","https://openalex.org/W2964357930","https://openalex.org/W3130660608","https://openalex.org/W3132695675","https://openalex.org/W3141650078","https://openalex.org/W4243261006","https://openalex.org/W4283377648","https://openalex.org/W4321448346","https://openalex.org/W4396601317","https://openalex.org/W4401540678","https://openalex.org/W4402192457","https://openalex.org/W4407785380"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W1925544630","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"Sparse":[0],"Matrix-Matrix":[1],"Multiplication":[2],"(SpMM)":[3],"plays":[4],"a":[5,35,68,124],"critical":[6],"role":[7],"in":[8,59],"high-performance":[9],"computing":[10],"and":[11,22,45,56,76,89,95],"applications":[12],"like":[13],"Graph":[14],"Neural":[15],"Networks":[16],"(GNNs).However,":[17],"due":[18],"to":[19,51,99,110],"the":[20,114],"sparsity":[21],"irregularity":[23],"of":[24,117],"real-world":[25],"data,":[26],"optimizing":[27],"SpMM":[28],"performance":[29],"on":[30,72],"modern":[31],"GPUs":[32],"has":[33],"remained":[34],"significant":[36],"challenge.Existing":[37],"methods":[38],"often":[39],"involve":[40],"trade-offs":[41],"between":[42],"load":[43],"balancing":[44],"hardware":[46,115],"utilization,":[47],"making":[48],"it":[49],"difficult":[50],"efficiently":[52],"handle":[53],"both":[54],"long":[55,87],"short":[57,90,121],"rows":[58,83,88,103,122],"sparse":[60,81],"matrices.To":[61],"address":[62],"these":[63],"issues,":[64],"we":[65],"propose":[66],"HR-SpMM,":[67],"lightweight":[69],"framework":[70],"based":[71],"adaptive":[73],"row":[74],"partitioning":[75],"hybrid":[77],"kernel":[78],"design.HR-SpMM":[79],"divides":[80],"matrix":[82],"into":[84,107],"two":[85],"categories:":[86],"rows,":[91],"leveraging":[92],"Tensor":[93,118],"Cores":[94],"CUDA":[96],"Cores,":[97,119],"respectively,":[98],"optimize":[100],"computational":[101],"efficiency.Long":[102],"are":[104],"further":[105],"partitioned":[106],"fixed-size":[108],"blocks":[109],"fully":[111],"align":[112],"with":[113],"characteristics":[116],"while":[120],"adopt":[123],"flexible":[125]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}