{"id":"https://openalex.org/W7084046715","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00069","title":"Adaptive Sketching Based Construction of H2 Matrices on GPUs","display_name":"Adaptive Sketching Based Construction of H2 Matrices on GPUs","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W7084046715","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00069"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw66978.2025.00069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Wajih Halim Boukaram","orcid":null},"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":true,"raw_author_name":"Wajih Halim Boukaram","raw_affiliation_strings":["Lawrence Berkeley National Laboratory,Berkeley,CA,USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley,CA,USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Liu","orcid":null},"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":"Yang Liu","raw_affiliation_strings":["Lawrence Berkeley National Laboratory,Berkeley,CA,USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley,CA,USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pieter Ghysels","orcid":null},"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":"Pieter Ghysels","raw_affiliation_strings":["Lawrence Berkeley National Laboratory,Berkeley,CA,USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley,CA,USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaoye Sherry Li","orcid":null},"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":"Xiaoye Sherry Li","raw_affiliation_strings":["Lawrence Berkeley National Laboratory,Berkeley,CA,USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley,CA,USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49671764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"433","last_page":"442"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.08739999681711197,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.08739999681711197,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13370","display_name":"Diverse Scientific and Economic Studies","score":0.04360000044107437,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14427","display_name":"Environmental Monitoring and Data Management","score":0.03400000184774399,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.9467999935150146},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5803999900817871},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4787999987602234},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4438000023365021},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3702000081539154},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.3601999878883362}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9467999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234000205993652},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6220999956130981},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5803999900817871},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4787999987602234},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43160000443458557},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3521000146865845},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw66978.2025.00069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1028753842","https://openalex.org/W1480958225","https://openalex.org/W1839773802","https://openalex.org/W1983103429","https://openalex.org/W2010717035","https://openalex.org/W2018419001","https://openalex.org/W2040187556","https://openalex.org/W2083903752","https://openalex.org/W2105591391","https://openalex.org/W2141719776","https://openalex.org/W2156164638","https://openalex.org/W2169370352","https://openalex.org/W2188296733","https://openalex.org/W2523870537","https://openalex.org/W2541711885","https://openalex.org/W2731223652","https://openalex.org/W2753660654","https://openalex.org/W2947960294","https://openalex.org/W2950678188","https://openalex.org/W2962927345","https://openalex.org/W2963754333","https://openalex.org/W3042983441","https://openalex.org/W3112080169","https://openalex.org/W3194901892","https://openalex.org/W3201568135","https://openalex.org/W4318776389","https://openalex.org/W4321636779","https://openalex.org/W4392505042","https://openalex.org/W4399558744","https://openalex.org/W4400410171"],"related_works":[],"abstract_inverted_index":{"We":[0],"develop":[1],"a":[2,10,25,63,126],"novel":[3],"linear-complexity":[4],"bottom-up":[5,151],"sketching-based":[6,117,132,152],"algorithm":[7,22,118,135],"for":[8,58],"constructing":[9],"${\\mathcal{H}^2}$":[11,88,133,153],"matrix,":[12],"and":[13,29,44,74,87,104],"present":[14],"its":[15],"high":[16],"performance":[17],"GPU":[18,38,55,77,93,112,145],"implementation.":[19],"The":[20,34,65],"construction":[21,134,154],"requires":[23],"both":[24],"black-box":[26],"sketching":[27],"operator":[28],"an":[30,110,130],"entry":[31],"evaluation":[32],"function.":[33],"novelty":[35],"of":[36,46,71,114,147,150],"our":[37,91,101],"approach":[39],"centers":[40],"around":[41],"the":[42,47,69,76,115,120,137,143,148],"design":[43],"implementation":[45,94,113,146],"above":[48],"two":[49],"operations":[50],"in":[51,62],"batched":[52],"mode":[53],"on":[54],"with":[56],"accommodation":[57],"variable-size":[59],"data":[60],"structures":[61],"batch.":[64],"batch":[66],"algorithms":[67],"minimize":[68],"number":[70],"kernel":[72],"launches":[73],"maximize":[75],"throughput.":[78],"When":[79],"applied":[80],"to":[81,97,106],"covariance":[82],"matrices,":[83],"volume":[84],"IE":[85],"matrices":[86],"update":[89],"operations,":[90],"proposed":[92],"achieves":[95,125],"up":[96,105],"13\u00d7":[98],"speedup":[99,108,128],"over":[100,109,129],"CPU":[102],"implementation,":[103],"1000\u00d7":[107],"existing":[111,131],"top-down":[116],"from":[119,136],"H2Opus":[121],"library.":[122,139],"It":[123],"also":[124],"660\u00d7":[127],"ButterflyPACK":[138],"Our":[140],"work":[141],"represents":[142],"first":[144],"class":[149],"algorithms.":[155]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}