{"id":"https://openalex.org/W2979411997","doi":"https://doi.org/10.1109/ipdps47924.2020.00080","title":"A High-Throughput Solver for Marginalized Graph Kernels on GPU","display_name":"A High-Throughput Solver for Marginalized Graph Kernels on GPU","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W2979411997","doi":"https://doi.org/10.1109/ipdps47924.2020.00080","mag":"2979411997"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps47924.2020.00080","pdf_url":null,"source":{"id":"https://openalex.org/S4363607067","display_name":"2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.06310","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040471064","display_name":"Yu-Hang Tang","orcid":"https://orcid.org/0000-0001-7424-5439"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-Hang Tang","raw_affiliation_strings":["Computational Research Division, Lawrence Berkeley National Laboratory"],"affiliations":[{"raw_affiliation_string":"Computational Research Division, Lawrence Berkeley National Laboratory","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075496842","display_name":"O\u011fuz Selvitopi","orcid":"https://orcid.org/0000-0002-0203-0372"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oguz Selvitopi","raw_affiliation_strings":["Computational Research Division, Lawrence Berkeley National Laboratory"],"affiliations":[{"raw_affiliation_string":"Computational Research Division, Lawrence Berkeley National Laboratory","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019066795","display_name":"Doru Thom Popovici","orcid":"https://orcid.org/0000-0002-7271-8092"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doru Thom Popovici","raw_affiliation_strings":["Computational Research Division, Lawrence Berkeley National Laboratory"],"affiliations":[{"raw_affiliation_string":"Computational Research Division, Lawrence Berkeley National Laboratory","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035719914","display_name":"Ayd\u0131n Bulu\u00e7","orcid":"https://orcid.org/0000-0001-7253-9038"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aydin Buluc","raw_affiliation_strings":["Computational Research Division, Lawrence Berkeley National Laboratory"],"affiliations":[{"raw_affiliation_string":"Computational Research Division, Lawrence Berkeley National Laboratory","institution_ids":["https://openalex.org/I148283060"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":16,"citation_normalized_percentile":{"value":0.999854,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":91},"biblio":{"volume":null,"issue":null,"first_page":"728","last_page":"738"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Matching and Analysis Techniques","score":0.9989,"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"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Matching and Analysis Techniques","score":0.9989,"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"}},{"id":"https://openalex.org/T11273","display_name":"Graph Neural Network Models and Applications","score":0.9988,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Performance Optimization","score":0.9922,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7085069},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU Computing","score":0.614886},{"id":"https://openalex.org/keywords/signal-processing-on-graphs","display_name":"Signal Processing on Graphs","score":0.59011},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel Computing","score":0.545987},{"id":"https://openalex.org/keywords/heterogeneous-computing","display_name":"Heterogeneous Computing","score":0.540171},{"id":"https://openalex.org/keywords/graph-processing","display_name":"Graph Processing","score":0.537181},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.45464027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862245},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7085069},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.67890227},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.45464027},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.41846436},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39803165},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2007091},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps47924.2020.00080","pdf_url":null,"source":{"id":"https://openalex.org/S4363607067","display_name":"2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1910.06310","pdf_url":"https://arxiv.org/pdf/1910.06310","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1582329","pdf_url":"https://escholarship.org/content/qt06c0t6w6/qt06c0t6w6.pdf","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":["Office of Scientific and Technical Information"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/06c0t6w6","pdf_url":"https://escholarship.org/content/qt06c0t6w6/qt06c0t6w6.pdf?t=q3s89y","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":["California Digital Library"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.1910.06310","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1910.06310","pdf_url":"https://arxiv.org/pdf/1910.06310","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":["https://openalex.org/W2979411997"],"referenced_works_count":31,"referenced_works":["https://openalex.org/W125936143","https://openalex.org/W1560724230","https://openalex.org/W1835509607","https://openalex.org/W1973202568","https://openalex.org/W1981885118","https://openalex.org/W1987427622","https://openalex.org/W2002555321","https://openalex.org/W2047259596","https://openalex.org/W2056124433","https://openalex.org/W2095117703","https://openalex.org/W2095420020","https://openalex.org/W2099438806","https://openalex.org/W2101234009","https://openalex.org/W2104266030","https://openalex.org/W2112882545","https://openalex.org/W2114977680","https://openalex.org/W2130479394","https://openalex.org/W2161201865","https://openalex.org/W2165874743","https://openalex.org/W2183700426","https://openalex.org/W2414494135","https://openalex.org/W2732233446","https://openalex.org/W2760713876","https://openalex.org/W2767891136","https://openalex.org/W2796649226","https://openalex.org/W2805455759","https://openalex.org/W2897970024","https://openalex.org/W2911738047","https://openalex.org/W2979411997","https://openalex.org/W3103176605","https://openalex.org/W4255476700"],"related_works":["https://openalex.org/W947442053","https://openalex.org/W4287182096","https://openalex.org/W4249323025","https://openalex.org/W27867058","https://openalex.org/W2317245370","https://openalex.org/W2283866686","https://openalex.org/W2148915962","https://openalex.org/W2030310580","https://openalex.org/W198851386","https://openalex.org/W1980160788"],"abstract_inverted_index":{"We":[0,155,208],"present":[1],"the":[2,15,21,41,50,59,62,66,76,109,132,148,157,160,193,202,205,215,256],"design":[3],"and":[4,17,65,111,131,172,225,231,251],"optimization":[5],"of":[6,20,27,53,69,115,159,192,204,222,241,255],"a":[7,33,44,104,140,169,183],"linear":[8,79],"solver":[9,31,74,235,257],"on":[10,214,229],"General":[11],"Purpose":[12],"GPUs":[13],"for":[14,135,188,220],"efficient":[16],"high-throughput":[18],"evaluation":[19],"marginalized":[22],"graph":[23,216],"kernel":[24],"between":[25,61],"pairs":[26],"labeled":[28],"graphs.":[29,55],"The":[30,253],"implements":[32],"preconditioned":[34],"conjugate":[35],"gradient":[36],"(PCG)":[37],"method":[38],"to":[39,43,106,151,200,238],"compute":[40],"solution":[42],"generalized":[45],"Laplacian":[46],"equation":[47],"associated":[48],"with":[49,58],"tensor":[51,77,217],"product":[52,78,91,218],"two":[54],"To":[56],"cope":[57],"gap":[60],"instruction":[63],"throughput":[64],"memory":[67,86,134,150],"bandwidth":[68],"current":[70],"generation":[71],"GPUs,":[72],"our":[73],"forms":[75],"system":[80],"on-the-fly":[81,96],"without":[82],"storing":[83,164],"it":[84],"in":[85,93,103,129],"when":[87],"performing":[88],"matrix-vector":[89],"dot":[90],"operations":[92],"PCG.":[94],"Such":[95],"computation":[97],"is":[98],"accomplished":[99],"by":[100,118,163],"using":[101,168,178],"threads":[102],"warp":[105],"cooperatively":[107],"stream":[108],"adjacency":[110],"edge":[112],"label":[113],"matrices":[114],"individual":[116],"graphs":[117,161,194],"small":[119],"square":[120],"matrix":[121],"blocks":[122],"called":[123],"tiles,":[124],"which":[125],"are":[126],"then":[127],"staged":[128],"registers":[130],"shared":[133,149],"later":[136],"reuse.":[137,154],"Warps":[138],"across":[139],"thread":[141],"block":[142],"can":[143],"further":[144],"share":[145],"tiles":[146,167,199,221],"via":[147],"increase":[152],"data":[153],"exploit":[156],"sparsity":[158],"hierarchically":[162],"only":[165],"non-empty":[166],"coordinate":[170],"format":[171],"nonzero":[173,190],"elements":[174,191],"within":[175],"each":[176],"tile":[177],"bitmaps.":[179],"Besides,":[180],"we":[181],"propose":[182],"new":[184],"partition-based":[185],"reordering":[186],"algorithm":[187],"aggregating":[189],"into":[195],"fewer":[196],"but":[197],"denser":[198],"improve":[201],"efficiency":[203],"sparse":[206],"format.":[207],"carry":[209],"out":[210],"extensive":[211],"theoretical":[212],"analyses":[213],"primitives":[219],"various":[223],"density":[224],"evaluate":[226],"their":[227],"performance":[228],"synthetic":[230],"real-world":[232],"datasets.":[233],"Our":[234],"delivers":[236],"three":[237],"four":[239],"orders":[240],"magnitude":[242],"speedup":[243],"over":[244],"existing":[245],"CPU-based":[246],"solvers":[247],"such":[248],"as":[249],"GraKeL":[250],"GraphKernels.":[252],"capability":[254],"enables":[258],"kernel-based":[259],"learning":[260],"tasks":[261],"at":[262],"unprecedented":[263],"scales.":[264]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2979411997","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4}],"updated_date":"2024-11-30T13:03:53.398326","created_date":"2019-10-18"}
