{"id":"https://openalex.org/W4395106472","doi":"https://doi.org/10.1145/3620666.3651378","title":"DTC-SpMM: Bridging the Gap in Accelerating General Sparse Matrix Multiplication with Tensor Cores","display_name":"DTC-SpMM: Bridging the Gap in Accelerating General Sparse Matrix Multiplication with Tensor Cores","publication_year":2024,"publication_date":"2024-04-24","ids":{"openalex":"https://openalex.org/W4395106472","doi":"https://doi.org/10.1145/3620666.3651378"},"language":"en","primary_location":{"id":"doi:10.1145/3620666.3651378","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620666.3651378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},"type":"conference-paper","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/A5054056254","display_name":"Ruibo Fan","orcid":"https://orcid.org/0009-0006-7492-2069"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ruibo Fan","raw_affiliation_strings":["Data Science and Analytics Thrust, HKUST(GZ), Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0006-7492-2069","affiliations":[{"raw_affiliation_string":"Data Science and Analytics Thrust, HKUST(GZ), Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076987000","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-4585-4152"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Department of Computer Science & Engineering, HKUST, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4585-4152","affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, HKUST, Hong Kong, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100730785","display_name":"Xiaowen Chu","orcid":"https://orcid.org/0000-0001-9745-4372"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaowen Chu","raw_affiliation_strings":["Data Science and Analytics Thrust, HKUST(GZ), Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-9745-4372","affiliations":[{"raw_affiliation_string":"Data Science and Analytics Thrust, HKUST(GZ), Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.991599977016449,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6718590259552002},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.535024881362915},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11092808842658997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6718590259552002},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.535024881362915},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11092808842658997},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3620666.3651378","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620666.3651378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-138752","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-138752","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G2191774043","display_name":null,"funder_award_id":"62272122","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1567553843","https://openalex.org/W2069479716","https://openalex.org/W2073364718","https://openalex.org/W2624431344","https://openalex.org/W2626696598","https://openalex.org/W2734941459","https://openalex.org/W2808128431","https://openalex.org/W2914631005","https://openalex.org/W2921480401","https://openalex.org/W2951338975","https://openalex.org/W2952099486","https://openalex.org/W2964337156","https://openalex.org/W2970971581","https://openalex.org/W2973134322","https://openalex.org/W2998957070","https://openalex.org/W2999347085","https://openalex.org/W3021975806","https://openalex.org/W3043303806","https://openalex.org/W3045744481","https://openalex.org/W3057934400","https://openalex.org/W3090369187","https://openalex.org/W3091170309","https://openalex.org/W3100839241","https://openalex.org/W3104001151","https://openalex.org/W3115410382","https://openalex.org/W3128982134","https://openalex.org/W3130421533","https://openalex.org/W3132185085","https://openalex.org/W3132695675","https://openalex.org/W3175498521","https://openalex.org/W3187908937","https://openalex.org/W3208099998","https://openalex.org/W4200216396","https://openalex.org/W4223482256","https://openalex.org/W4226401363","https://openalex.org/W4281561529","https://openalex.org/W4293024985","https://openalex.org/W4297834616","https://openalex.org/W4308090748","https://openalex.org/W4309672181","https://openalex.org/W4310563332","https://openalex.org/W4320063610","https://openalex.org/W4327911434","https://openalex.org/W4381832157","https://openalex.org/W4384705403","https://openalex.org/W4390188278","https://openalex.org/W6783267081"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Sparse":[0],"Matrix-Matrix":[1],"Multiplication":[2],"(SpMM)":[3],"is":[4],"a":[5,48,71,105],"building-block":[6],"operation":[7],"in":[8,17,115,120],"scientific":[9],"computing":[10],"and":[11,59,94],"machine":[12],"learning":[13],"applications.":[14],"Recent":[15],"advancements":[16],"hardware,":[18],"notably":[19],"Tensor":[20],"Cores":[21],"(TCs),":[22],"have":[23],"created":[24],"promising":[25],"opportunities":[26],"for":[27,55,78],"accelerating":[28,56,79],"SpMM.":[29],"However,":[30],"harnessing":[31],"these":[32,66],"hardware":[33],"accelerators":[34],"to":[35,140],"speed":[36],"up":[37,134,139],"general":[38,80],"SpMM":[39,58,81,116],"necessitates":[40],"considerable":[41],"effort.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,68],"undertake":[47],"comprehensive":[49],"analysis":[50],"of":[51,108],"the":[52],"state-of-the-art":[53],"techniques":[54],"TC-based":[57],"identify":[60],"crucial":[61],"performance":[62,113],"gaps.":[63],"Drawing":[64],"upon":[65],"insights,":[67],"propose":[69],"DTC-SpMM,":[70],"novel":[72],"approach":[73],"with":[74,104,122],"systematic":[75],"optimizations":[76],"tailored":[77],"on":[82,101],"TCs.":[83],"DTC-SpMM":[84,132],"encapsulates":[85],"diverse":[86,106],"aspects,":[87],"including":[88],"efficient":[89],"compression":[90],"formats,":[91],"reordering":[92],"methods,":[93],"runtime":[95],"pipeline":[96],"optimizations.":[97,125],"Our":[98],"extensive":[99],"experiments":[100],"modern":[102],"GPUs":[103],"range":[107],"benchmark":[109],"matrices":[110],"demonstrate":[111],"remarkable":[112],"improvements":[114],"acceleration":[117],"by":[118,138],"TCs":[119],"conjunction":[121],"our":[123],"proposed":[124],"The":[126],"case":[127],"study":[128],"also":[129],"shows":[130],"that":[131],"speeds":[133],"end-to-end":[135],"GNN":[136,144],"training":[137],"1.91\u00d7":[141],"against":[142],"popular":[143],"frameworks.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}