{"id":"https://openalex.org/W4409248587","doi":"https://doi.org/10.1109/hpca61900.2025.00109","title":"HSMU-SpGEMM: Achieving High Shared Memory Utilization for Parallel Sparse General Matrix-Matrix Multiplication on Modern GPUs","display_name":"HSMU-SpGEMM: Achieving High Shared Memory Utilization for Parallel Sparse General Matrix-Matrix Multiplication on Modern GPUs","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4409248587","doi":"https://doi.org/10.1109/hpca61900.2025.00109"},"language":"en","primary_location":{"id":"doi:10.1109/hpca61900.2025.00109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca61900.2025.00109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074710425","display_name":"Min Wu","orcid":"https://orcid.org/0000-0002-0668-8315"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Wu","raw_affiliation_strings":["Hunan University,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082012083","display_name":"Huizhang Luo","orcid":"https://orcid.org/0000-0003-2392-0267"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huizhang Luo","raw_affiliation_strings":["Hunan University,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045425987","display_name":"Fenfang Li","orcid":"https://orcid.org/0000-0002-6158-4498"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fenfang Li","raw_affiliation_strings":["Hunan University,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359686","display_name":"Yiran Zhang","orcid":"https://orcid.org/0000-0001-5897-2572"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiran Zhang","raw_affiliation_strings":["Arizona State University,Tempe,United States"],"affiliations":[{"raw_affiliation_string":"Arizona State University,Tempe,United States","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008574161","display_name":"Zhuo Tang","orcid":"https://orcid.org/0000-0001-9081-8153"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Tang","raw_affiliation_strings":["Hunan University,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["Hunan University,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077249620","display_name":"Jeff Zhang","orcid":"https://orcid.org/0000-0001-7411-8923"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Zhang","raw_affiliation_strings":["Arizona State University,Tempe,United States"],"affiliations":[{"raw_affiliation_string":"Arizona State University,Tempe,United States","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006345319","display_name":"Chubo Liu","orcid":"https://orcid.org/0000-0002-2372-6715"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chubo Liu","raw_affiliation_strings":["Hunan University,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,Changsha,China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5074710425"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":7.3583,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96372992,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1452","last_page":"1466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9932000041007996,"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":0.9932000041007996,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9592999815940857,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/parallel-computing","display_name":"Parallel computing","score":0.7231025099754333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6987364888191223},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6232995986938477},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5787674188613892},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5222340822219849},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5030872225761414},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.48437246680259705},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.12980365753173828},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09584182500839233},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09301832318305969},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0614410936832428}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7231025099754333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6987364888191223},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6232995986938477},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5787674188613892},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5222340822219849},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5030872225761414},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.48437246680259705},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.12980365753173828},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09584182500839233},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09301832318305969},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0614410936832428},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca61900.2025.00109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca61900.2025.00109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1515144947","https://openalex.org/W1973918431","https://openalex.org/W2021011079","https://openalex.org/W2035080386","https://openalex.org/W2089437293","https://openalex.org/W2095249664","https://openalex.org/W2132958419","https://openalex.org/W2410432900","https://openalex.org/W2410461480","https://openalex.org/W2618168961","https://openalex.org/W2751658790","https://openalex.org/W2765934619","https://openalex.org/W2781869913","https://openalex.org/W2913334236","https://openalex.org/W2914086833","https://openalex.org/W2962729196","https://openalex.org/W2990549974","https://openalex.org/W3000305333","https://openalex.org/W3016832937","https://openalex.org/W3043796721","https://openalex.org/W3155922894","https://openalex.org/W3187908937","https://openalex.org/W4220912491","https://openalex.org/W4236418138","https://openalex.org/W4283033672","https://openalex.org/W4309620166","https://openalex.org/W4318540786","https://openalex.org/W4385623280","https://openalex.org/W6765228345","https://openalex.org/W6859502420"],"related_works":["https://openalex.org/W1599154403","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"],"abstract_inverted_index":{"Sparse":[0],"general":[1],"matrix-matrix":[2],"multiplication":[3],"(SpGEMM)":[4],"is":[5,109],"a":[6,19,48],"core":[7],"primitive":[8],"for":[9],"numerous":[10],"scientific":[11],"applications.":[12],"Traditional":[13],"hash-based":[14,84],"approaches":[15],"fail":[16],"to":[17],"strike":[18],"balance":[20],"between":[21],"reducing":[22],"hash":[23],"collisions":[24],"and":[25,90],"efficiently":[26],"utilizing":[27],"fast":[28],"shared":[29,55,65],"memory,":[30],"which":[31],"significantly":[32],"undermines":[33],"the":[34,62],"performance":[35,103],"of":[36],"executing":[37],"SpGEMM":[38,85],"on":[39,58,93],"GPUs.":[40,60],"To":[41],"address":[42],"this":[43,45],"issue,":[44],"paper":[46],"introduces":[47],"novel":[49],"accumulator":[50],"design":[51],"that":[52],"achieves":[53],"high":[54,64],"memory":[56,66],"utilization":[57,67],"modern":[59],"For":[61],"proposed":[63],"algorithm,":[68],"i.e.,":[69],"HSMU-SpGEMM<sup":[70],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[71,107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[72],"we":[73],"further":[74],"optimize":[75],"different":[76],"symbolic":[77],"stages.":[78],"Our":[79],"evaluations":[80],"with":[81],"four":[82],"state-of-the-art":[83],"libraries":[86],"(Nsparse,":[87],"spECK,":[88],"OpSparse,":[89],"NVIDIA\u2019s":[91],"cuSPARSE)":[92],"three":[94],"NVIDIA":[95],"GPUs":[96],"(Ampere,":[97],"Ada":[98],"Lovelace,":[99],"Turing)":[100],"demonstrate":[101],"significant":[102],"benefits":[104],"from":[105],"HSMU-SpGEMM.<sup":[106],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>HSMU-SpGEMM":[108],"available":[110],"at":[111],"https://github.com/wuminqaq/HSMUSpGEMM":[112]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
