{"id":"https://openalex.org/W4404047373","doi":"https://doi.org/10.1145/3703356","title":"Characterizing and Understanding HGNN Training on GPUs","display_name":"Characterizing and Understanding HGNN Training on GPUs","publication_year":2024,"publication_date":"2024-11-04","ids":{"openalex":"https://openalex.org/W4404047373","doi":"https://doi.org/10.1145/3703356"},"language":"en","primary_location":{"id":"doi:10.1145/3703356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703356","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3703356","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070317336","display_name":"Dengke Han","orcid":"https://orcid.org/0000-0003-0641-5779"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengke Han","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","University of the Chinese Academy of Sciences, Beijing China","State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0641-5779","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004624509","display_name":"Mingyu Yan","orcid":"https://orcid.org/0000-0002-6915-955X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Yan","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing China"],"raw_orcid":"https://orcid.org/0000-0002-6915-955X","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023098180","display_name":"Xiaochun Ye","orcid":"https://orcid.org/0000-0003-4598-1685"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Ye","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing China"],"raw_orcid":"https://orcid.org/0000-0003-4598-1685","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011407484","display_name":"Dongrui Fan","orcid":"https://orcid.org/0000-0001-5219-0908"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongrui Fan","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing China"],"raw_orcid":"https://orcid.org/0000-0001-5219-0908","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6516,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85642458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"22","issue":"1","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9954000115394592,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9925000071525574,"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":0.7818167805671692},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6134204268455505},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4008258581161499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38978785276412964},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32059359550476074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7818167805671692},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6134204268455505},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4008258581161499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38978785276412964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32059359550476074},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3703356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703356","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3703356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3703356","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1702756715","display_name":null,"funder_award_id":"2022YFB4501400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3475438616","display_name":null,"funder_award_id":"62202451","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2604314403","https://openalex.org/W2624431344","https://openalex.org/W2744097819","https://openalex.org/W2762390662","https://openalex.org/W2896429681","https://openalex.org/W2907492528","https://openalex.org/W2911286998","https://openalex.org/W2913208203","https://openalex.org/W2963919031","https://openalex.org/W3003952093","https://openalex.org/W3004208721","https://openalex.org/W3004507689","https://openalex.org/W3035529900","https://openalex.org/W3096566397","https://openalex.org/W3103513278","https://openalex.org/W3108202858","https://openalex.org/W3123919296","https://openalex.org/W3124491941","https://openalex.org/W3124523381","https://openalex.org/W3138871094","https://openalex.org/W3152893301","https://openalex.org/W3202811093","https://openalex.org/W3211257700","https://openalex.org/W3213412677","https://openalex.org/W4224254405","https://openalex.org/W4238297360","https://openalex.org/W4241140669","https://openalex.org/W4281691175","https://openalex.org/W4290877962","https://openalex.org/W4290944486","https://openalex.org/W4293246010","https://openalex.org/W4294068568","https://openalex.org/W4310421401","https://openalex.org/W4311314339","https://openalex.org/W4312106615","https://openalex.org/W4312650633","https://openalex.org/W4323030310","https://openalex.org/W4380875717","https://openalex.org/W4382202833","https://openalex.org/W4389476227","https://openalex.org/W4389495241","https://openalex.org/W4394661761","https://openalex.org/W4396506070","https://openalex.org/W4401862168","https://openalex.org/W6754929296","https://openalex.org/W6785482172"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Owing":[0],"to":[1,32,43,65,78],"their":[2,33,116],"remarkable":[3],"representation":[4],"capabilities":[5],"for":[6],"heterogeneous":[7],"graph":[8],"data,":[9],"Heterogeneous":[10],"Graph":[11],"Neural":[12],"Networks":[13],"(HGNNs)":[14],"have":[15],"been":[16],"widely":[17],"adopted":[18],"in":[19,119],"many":[20],"critical":[21],"real-world":[22],"domains":[23],"such":[24],"as":[25],"recommendation":[26],"systems":[27],"and":[28,52,67,72,90,101,115,124,131],"medical":[29],"analysis.":[30],"Prior":[31],"practical":[34],"application,":[35],"identifying":[36],"the":[37,57,69,75,107,112],"optimal":[38],"HGNN":[39,60,96,121],"model":[40],"parameters":[41],"tailored":[42],"specific":[44],"tasks":[45],"through":[46],"extensive":[47],"training":[48,76,97,122],"is":[49,63],"a":[50,87],"time-consuming":[51],"costly":[53],"process.":[54],"To":[55],"enhance":[56],"efficiency":[58],"of":[59,93],"training,":[61],"it":[62],"essential":[64],"characterize":[66],"analyze":[68],"execution":[70],"semantics":[71],"patterns":[73],"within":[74],"process":[77],"identify":[79],"performance":[80,113],"bottlenecks.":[81],"In":[82],"this":[83],"study,":[84],"we":[85,110],"conduct":[86],"comprehensive":[88],"quantification":[89],"in-depth":[91],"analysis":[92],"two":[94],"mainstream":[95],"scenarios,":[98],"including":[99],"single-GPU":[100],"multi-GPU":[102],"distributed":[103],"training.":[104],"Based":[105],"on":[106],"characterization":[108],"results,":[109],"reveal":[111],"bottlenecks":[114],"underlying":[117],"causes":[118],"different":[120],"scenarios":[123],"propose":[125],"optimization":[126],"guidelines":[127],"from":[128],"both":[129],"software":[130],"hardware":[132],"perspectives.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}