{"id":"https://openalex.org/W7092292283","doi":"https://doi.org/10.1145/3725843.3756077","title":"C3ache: Towards Hierarchical Cache-Centric Computing for Sparse Matrix Multiplication on GPGPUs","display_name":"C3ache: Towards Hierarchical Cache-Centric Computing for Sparse Matrix Multiplication on GPGPUs","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W7092292283","doi":"https://doi.org/10.1145/3725843.3756077"},"language":null,"primary_location":{"id":"doi:10.1145/3725843.3756077","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756077","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756077?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture","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/10.1145/3725843.3756077?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaojie Li","orcid":"https://orcid.org/0009-0009-3903-9686"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Li","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0009-3903-9686","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingyu Wang","orcid":"https://orcid.org/0000-0003-4006-8870"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Wang","raw_affiliation_strings":["Sun Yat-Sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0003-4006-8870","affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Baiqing Zhong","orcid":"https://orcid.org/0009-0001-7455-815X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baiqing Zhong","raw_affiliation_strings":["Sun Yat-Sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0001-7455-815X","affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haiqiu Huang","orcid":"https://orcid.org/0009-0008-6366-7386"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiqiu Huang","raw_affiliation_strings":["Sun Yat-Sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0008-6366-7386","affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guangjie Cao","orcid":"https://orcid.org/0009-0006-2387-4802"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangjie Cao","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0006-2387-4802","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhiyi Yu","orcid":"https://orcid.org/0000-0002-8802-0457"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Yu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-8802-0457","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45040747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1026","last_page":"1039"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6467000246047974,"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":0.6467000246047974,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.07190000265836716,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.06679999828338623,"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/matrix-multiplication","display_name":"Matrix multiplication","score":0.4471000134944916},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.43639999628067017},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4056999981403351},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.396699994802475},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.30000001192092896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6805999875068665},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4471000134944916},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.43639999628067017},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39079999923706055},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725843.3756077","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756077","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756077?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3725843.3756077","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756077","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756077?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3040571651","display_name":null,"funder_award_id":"62204271","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6871751676","display_name":null,"funder_award_id":"92373103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G691677441","display_name":null,"funder_award_id":"62334014","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7092292283.pdf","grobid_xml":"https://content.openalex.org/works/W7092292283.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1985263109","https://openalex.org/W1997542937","https://openalex.org/W2003168947","https://openalex.org/W2003458338","https://openalex.org/W2003840611","https://openalex.org/W2020545624","https://openalex.org/W2035080386","https://openalex.org/W2076508696","https://openalex.org/W2089939118","https://openalex.org/W2090593986","https://openalex.org/W2098602979","https://openalex.org/W2152290683","https://openalex.org/W2161042056","https://openalex.org/W2170382128","https://openalex.org/W2170546376","https://openalex.org/W2347043188","https://openalex.org/W2613569094","https://openalex.org/W2794952988","https://openalex.org/W2801000640","https://openalex.org/W2891911973","https://openalex.org/W2963989532","https://openalex.org/W2980186997","https://openalex.org/W3016832937","https://openalex.org/W3022326557","https://openalex.org/W3048581975","https://openalex.org/W3103168911","https://openalex.org/W3130554079","https://openalex.org/W3158831985","https://openalex.org/W3183406752","https://openalex.org/W3187908937","https://openalex.org/W3206171855","https://openalex.org/W4308090212","https://openalex.org/W4313839325","https://openalex.org/W4360831845","https://openalex.org/W4386764076","https://openalex.org/W4388283449","https://openalex.org/W4389491968","https://openalex.org/W4389500318","https://openalex.org/W4392309078","https://openalex.org/W4404955086"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"matrix":[1],"multiplications":[2],"(SPMMs)":[3],"are":[4,11],"fundamental":[5],"kernels":[6],"in":[7,42,59,81,188],"various":[8],"domains":[9],"and":[10,77,103,128,139,154,160,192,233],"highly":[12],"demanded":[13],"to":[14,27,38,123,144,198,227],"be":[15],"executed":[16],"on":[17,35,135],"general-purpose":[18],"graphics":[19],"processing":[20,187],"units":[21,58,191,196],"(GPGPUs).However,":[22],"it":[23],"is":[24,142,222],"a":[25,112,217],"challenge":[26],"efficiently":[28],"execute":[29],"SPMMs":[30],"across":[31,45],"varying":[32],"sparsity":[33,43,69],"regimes":[34],"GPGPUs":[36,53],"due":[37],"the":[39,49,71,85,131,136,146,163,171,178,200,207,213,230,234],"significant":[40],"variations":[41],"patterns":[44,102],"different":[46,157],"domains.Most":[47],"of":[48,87,181,204,209,237],"state-of-the-art":[50],"works":[51],"enhance":[52],"by":[54,98],"integrating":[55],"dedicated":[56],"accelerator":[57],"processor,":[60],"which":[61],"prioritize":[62],"computational":[63],"density":[64],"over":[65],"memory":[66,75,100,126,164,189,214,231],"subsystem":[67],"optimizations.As":[68],"increases,":[70],"overhead":[72,236],"from":[73],"expensive":[74],"accesses":[76],"redundant":[78],"input":[79],"fetches":[80],"sparse":[82,225],"matrices":[83],"constrains":[84],"effectiveness":[86],"processor-centric":[88],"optimization":[89],"schemes.Consequently,":[90],"these":[91,108],"optimizations":[92],"become":[93],"suboptimal":[94],"for":[95,224],"workloads":[96],"dominated":[97],"irregular":[99],"access":[101,165,215],"low":[104],"arithmetic":[105],"intensity.To":[106],"address":[107],"problems,":[109],"we":[110],"proposed":[111,143,223],"hierarchical":[113],"cachecentric":[114],"computing":[115],"architecture":[116],"with":[117,156,162,212],"hybrid":[118,132],"dataflow,":[119],"\ud835\udc36":[120,167,238,242],"3":[121,168,239,243],"\ud835\udc4e\ud835\udc50\u210e\ud835\udc52,":[122,244],"achieve":[124],"near-optimal":[125],"efficiency":[127],"data":[129,185,210],"reuse.First,":[130],"dataflow":[133,138,141],"based":[134],"outer-product":[137],"Gustavson's":[140],"decouple":[145],"SPMM":[147],"computation":[148,202],"into":[149,183],"two":[150,179,201],"distinct":[151],"phases":[152,203],"(multiplication":[153],"merging)":[155],"behavioral":[158],"characteristics":[159],"align":[161],"pattern.Furthermore,":[166],"\ud835\udc4e\ud835\udc50\u210e\ud835\udc52":[169],"restructures":[170],"cache":[172,182],"hierarchy":[173],"through":[174],"in-cache":[175],"computing,":[176],"transforming":[177],"levels":[180],"largescale":[184],"parallel":[186],"(PIM)":[190],"in-situ":[193],"merging":[194],"PIM":[195],"respectively":[197],"map":[199],"SPMMs.To":[205],"synchronize":[206],"granularity":[208],"fetching":[211],"pattern,":[216],"novel":[218],"memory-aware":[219],"compressed":[220],"format":[221],"encoding":[226],"further":[228],"reduce":[229],"transaction":[232],"decoding":[235],"\ud835\udc4e\ud835\udc50\u210e\ud835\udc52.To":[240],"realize":[241],"an":[245]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-18T00:00:00"}