{"id":"https://openalex.org/W2588282852","doi":"https://doi.org/10.1145/3038228.3038237","title":"High-performance Cholesky factorization for GPU-only execution","display_name":"High-performance Cholesky factorization for GPU-only execution","publication_year":2017,"publication_date":"2017-02-04","ids":{"openalex":"https://openalex.org/W2588282852","doi":"https://doi.org/10.1145/3038228.3038237","mag":"2588282852"},"language":"en","primary_location":{"id":"doi:10.1145/3038228.3038237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3038228.3038237","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3038237&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the General Purpose GPUs","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3038237&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101964224","display_name":"Azzam Haidar","orcid":"https://orcid.org/0000-0002-3177-2084"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Azzam Haidar","raw_affiliation_strings":["University of Tennessee, U.S.A"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, U.S.A","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033346633","display_name":"Ahmad Abdelfatah","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad Abdelfatah","raw_affiliation_strings":["University of Tennessee, U.S.A"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, U.S.A","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["University of Tennessee, U.S.A"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, U.S.A","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, U.S.A., Oak Ridge National Laboratory, U.S.A., University of Manchester, UK"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, U.S.A., Oak Ridge National Laboratory, U.S.A., University of Manchester, UK","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I28407311","https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101964224"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":1.6181,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84141426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8963648080825806},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8471890687942505},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.6608842611312866},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5920215845108032},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5562813878059387},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.49881649017333984},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.47790178656578064},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4283468723297119},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08875399827957153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8963648080825806},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8471890687942505},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.6608842611312866},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5920215845108032},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5562813878059387},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.49881649017333984},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.47790178656578064},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4283468723297119},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08875399827957153},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3038228.3038237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3038228.3038237","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3038237&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the General Purpose GPUs","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3038228.3038237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3038228.3038237","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3038237&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the General Purpose GPUs","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1687433189","display_name":null,"funder_award_id":"1339822","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1836428231","display_name":null,"funder_award_id":"1339822","funder_id":"https://openalex.org/F4320309480","funder_display_name":"Nvidia"},{"id":"https://openalex.org/G7262430608","display_name":null,"funder_award_id":"ACI-1339822","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2588282852.pdf","grobid_xml":"https://content.openalex.org/works/W2588282852.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W57243869","https://openalex.org/W1004371317","https://openalex.org/W1028753842","https://openalex.org/W1480928214","https://openalex.org/W1539904802","https://openalex.org/W1585237817","https://openalex.org/W1968460630","https://openalex.org/W1997033059","https://openalex.org/W2002257715","https://openalex.org/W2006682733","https://openalex.org/W2016279572","https://openalex.org/W2025829250","https://openalex.org/W2026188397","https://openalex.org/W2049926709","https://openalex.org/W2122002474","https://openalex.org/W2138215414","https://openalex.org/W2162322364","https://openalex.org/W2170597842","https://openalex.org/W2170611190","https://openalex.org/W2493354458","https://openalex.org/W2505064766","https://openalex.org/W2509368344"],"related_works":["https://openalex.org/W1615383022","https://openalex.org/W1507301366","https://openalex.org/W2340180648","https://openalex.org/W2103667109","https://openalex.org/W2022666014","https://openalex.org/W2995515486","https://openalex.org/W2079303253","https://openalex.org/W2085237598","https://openalex.org/W2159870643","https://openalex.org/W2113124081"],"abstract_inverted_index":{"We":[0,126],"present":[1],"our":[2,62],"performance":[3],"analysis,":[4],"algorithm":[5,203],"designs,":[6],"and":[7,18,54,70,114,153],"the":[8,12,22,57,60,110,115,133,140,145,150,207,213],"optimizations":[9],"needed":[10],"for":[11,21,103],"development":[13],"of":[14,51],"high-performance":[15],"GPU-only":[16,107,141,208],"algorithms,":[17],"in":[19,86,168,212],"particular,":[20],"dense":[23],"Cholesky":[24],"factorization.":[25],"In":[26],"contrast":[27,87],"to":[28,88,94,119,165,197],"currently":[29,210],"promoted":[30],"designs":[31,63],"that":[32,91,128,139],"solve":[33],"parallelism":[34],"challenges":[35,117],"on":[36,97,129,171],"multicore":[37,182],"architectures":[38,67],"by":[39],"representing":[40],"algorithms":[41,90,148],"as":[42],"Directed":[43],"Acyclic":[44],"Graphs":[45],"(DAGs),":[46],"where":[47,193],"nodes":[48],"are":[49,56],"tasks":[50,74,96,152],"fine":[52,81],"granularity":[53,73],"edges":[55],"dependencies":[58],"between":[59],"tasks,":[61],"explicitly":[64],"target":[65],"manycore":[66],"like":[68,132],"GPUs":[69],"feature":[71],"coarse":[72],"(that":[75],"can":[76,155],"be":[77,157],"hierarchically":[78],"split":[79],"into":[80],"grain":[82],"data-parallel":[83],"subtasks).":[84],"Furthermore,":[85],"hybrid":[89,146],"schedule":[92],"difficult":[93],"parallelize":[95],"CPUs,":[98,183,192],"we":[99],"develop":[100],"highly-efficient":[101],"code":[102,142],"entirely":[104,158],"GPU":[105,161],"execution.":[106],"codes":[108],"remove":[109],"expensive":[111],"CPU-to-GPU":[112,124],"communications":[113,154],"tuning":[116],"related":[118],"slow":[120],"CPU":[121,151],"and/or":[122],"low":[123],"bandwidth.":[125],"show":[127],"latest":[130],"GPUs,":[131],"P100,":[134],"this":[135],"becomes":[136],"so":[137],"important":[138],"even":[143],"outperforms":[144,205],"MAGMA":[147],"when":[149],"not":[156],"overlapped":[159],"with":[160],"computations.":[162],"Weachieve":[163],"up":[164,196],"4,300":[166],"GFlop/s":[167],"double":[169],"precision":[170],"a":[172],"P100":[173],"GPU,":[174],"which":[175],"is":[176],"about":[177,198],"7-8x":[178],"faster":[179],"than":[180],"high-end":[181],"e.g.,":[184],"two":[185],"10-cores":[186],"Intel":[187],"Xeon":[188],"E5-2650":[189],"v3":[190],"Haswell":[191],"MKL":[194],"runs":[195],"500-600":[199],"Gflop/s.":[200],"The":[201],"new":[202],"also":[204],"significantly":[206],"implementation":[209],"available":[211],"NVIDIA":[214],"cuSOLVER":[215],"library.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}