{"id":"https://openalex.org/W4413412033","doi":"https://doi.org/10.1145/3721145.3730425","title":"CoLa: Towards Communication-efficient Distributed Sparse Matrix-Matrix Multiplication on GPUs","display_name":"CoLa: Towards Communication-efficient Distributed Sparse Matrix-Matrix Multiplication on GPUs","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4413412033","doi":"https://doi.org/10.1145/3721145.3730425"},"language":"en","primary_location":{"id":"doi:10.1145/3721145.3730425","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721145.3730425","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3730425","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3730425","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070491781","display_name":"Lixing Zhang","orcid":"https://orcid.org/0009-0008-7377-9269"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lixing Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014615052","display_name":"Yingxia Shao","orcid":"https://orcid.org/0000-0002-8559-2628"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingxia Shao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088172355","display_name":"Shigang Li","orcid":"https://orcid.org/0000-0003-0022-7865"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shigang Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070491781"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.223782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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":0.9980999827384949,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9980000257492065,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.6912199854850769},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.661601185798645},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6481021046638489},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6002311706542969},{"id":"https://openalex.org/keywords/cola","display_name":"Cola (plant)","score":0.5489417314529419},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5169205665588379},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5137213468551636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13557258248329163},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.081432044506073},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07880878448486328},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.066098153591156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912199854850769},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.661601185798645},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6481021046638489},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6002311706542969},{"id":"https://openalex.org/C2781138811","wikidata":"https://www.wikidata.org/wiki/Q114264","display_name":"Cola (plant)","level":2,"score":0.5489417314529419},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5169205665588379},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5137213468551636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13557258248329163},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.081432044506073},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07880878448486328},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.066098153591156},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721145.3730425","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721145.3730425","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3730425","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:10.1145/3721145.3730425","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721145.3730425","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3730425","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/G1108969597","display_name":null,"funder_award_id":"62192784","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G130652162","display_name":null,"funder_award_id":"202304","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G421627741","display_name":null,"funder_award_id":"62272054","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6749463622","display_name":null,"funder_award_id":"20230484319","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8136954100","display_name":null,"funder_award_id":"2022ZD0116315","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","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/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413412033.pdf","grobid_xml":"https://content.openalex.org/works/W4413412033.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2007152167","https://openalex.org/W2029852131","https://openalex.org/W2035080386","https://openalex.org/W2048509145","https://openalex.org/W2056999868","https://openalex.org/W2095836023","https://openalex.org/W2119148081","https://openalex.org/W2483598939","https://openalex.org/W2484446135","https://openalex.org/W2734941459","https://openalex.org/W2788919350","https://openalex.org/W2914631005","https://openalex.org/W2926767350","https://openalex.org/W2964337156","https://openalex.org/W3101708369","https://openalex.org/W3130554079","https://openalex.org/W3159109662","https://openalex.org/W3169307980","https://openalex.org/W3198239267","https://openalex.org/W3208099998","https://openalex.org/W4282967794","https://openalex.org/W4285503871","https://openalex.org/W4293024985","https://openalex.org/W4321466355","https://openalex.org/W4384705403","https://openalex.org/W4394998401","https://openalex.org/W4396571432"],"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],"is":[4,19],"a":[5,48,120],"critical":[6],"operator":[7],"in":[8],"many":[9],"applications,":[10],"such":[11],"as":[12,82],"graph":[13],"neural":[14],"networks":[15],"(GNNs).However,":[16],"when":[17],"SpMM":[18,52,124],"scaled":[20],"to":[21,60,85,103],"multiple":[22],"GPUs,":[23],"existing":[24],"works":[25],"face":[26],"significant":[27],"challenges:":[28],"(1)":[29],"massive":[30,43],"redundant":[31,44],"communication":[32,49,62,76,87,109],"and":[33,91,107,143,148],"(2)":[34],"unawareness":[35,66],"of":[36,42,67,140],"heterogeneous":[37,68],"links.To":[38],"address":[39],"the":[40,65],"issue":[41],"communication,":[45,93],"we":[46,70,117],"introduce":[47],"redundancy-free":[50],"distributed":[51,123],"algorithm":[53],"that":[54,135],"efficiently":[55],"reutilizes":[56],"fetched":[57],"remote":[58,98],"data":[59,99],"reduce":[61,86],"volume.To":[63],"tackle":[64],"links,":[69],"propose":[71],"two":[72],"link-aware":[73],"optimization":[74],"techniques:":[75],"fusion,":[77],"which":[78,94],"leverages":[79],"local":[80],"GPUs":[81],"embedding":[83],"caches":[84],"over":[88,111,145],"slow":[89],"links;":[90],"requestcoalesced":[92],"coalesces":[95],"necessary":[96],"requested":[97],"into":[100],"bulk":[101],"transfers":[102],"maximize":[104],"bandwidth":[105],"utilization":[106],"minimize":[108],"volume":[110],"proxy-based":[112],"links.Based":[113],"on":[114,127],"these":[115],"techniques,":[116],"develop":[118],"CoLa,":[119],"highly":[121],"communication-efficient":[122],"framework.Extensive":[125],"evaluations":[126],"real-world":[128],"datasets":[129],"under":[130],"different":[131],"multi-GPU":[132],"settings":[133],"demonstrate":[134],"CoLa":[136],"achieves":[137],"geomean":[138],"speedups":[139],"8.56,":[141],"9.12,":[142],"57.97":[144],"CAGNET,":[146],"MGGCN,":[147],"MGG,":[149],"respectively.":[150],"CCS":[151],"Concepts":[152]},"counts_by_year":[],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}