{"id":"https://openalex.org/W1991324025","doi":"https://doi.org/10.1145/2716282.2716288","title":"Optimization for performance and energy for batched matrix computations on GPUs","display_name":"Optimization for performance and energy for batched matrix computations on GPUs","publication_year":2015,"publication_date":"2015-02-03","ids":{"openalex":"https://openalex.org/W1991324025","doi":"https://doi.org/10.1145/2716282.2716288","mag":"1991324025"},"language":"en","primary_location":{"id":"doi:10.1145/2716282.2716288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2716282.2716288","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2716288&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using 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=2716288&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, USA"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039642335","display_name":"Tingxing Dong","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":"Tingxing Dong","raw_affiliation_strings":["University of Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"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":"Piotr Luszczek","raw_affiliation_strings":["University of Tennessee, USA"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, USA","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, USA"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, USA","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, USA / Oak Ridge National Laboratory, USA / University of Manchester, UK"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, USA / Oak Ridge National Laboratory, USA / 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":5,"corresponding_author_ids":["https://openalex.org/A5101964224"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":2.9677,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.9082038,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9965000152587891,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8605513572692871},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8281970024108887},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7752264738082886},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.595342755317688},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.5348763465881348},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.49954938888549805},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4899512827396393},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4867999255657196},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4817785918712616},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4793161153793335},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.4368411600589752},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.41122376918792725},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32955437898635864},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.24600160121917725},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.12018665671348572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8605513572692871},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8281970024108887},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7752264738082886},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.595342755317688},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.5348763465881348},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.49954938888549805},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4899512827396393},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4867999255657196},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4817785918712616},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4793161153793335},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.4368411600589752},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.41122376918792725},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32955437898635864},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.24600160121917725},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.12018665671348572},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2716282.2716288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2716282.2716288","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2716288&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2716282.2716288","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2716282.2716288","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2716288&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"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"},{"id":"https://openalex.org/G8753669605","display_name":null,"funder_award_id":"N14-11-00190","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1991324025.pdf","grobid_xml":"https://content.openalex.org/works/W1991324025.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W48467709","https://openalex.org/W1004371317","https://openalex.org/W1539904802","https://openalex.org/W1737435842","https://openalex.org/W1985691044","https://openalex.org/W2016279572","https://openalex.org/W2028425870","https://openalex.org/W2070525241","https://openalex.org/W2099021415","https://openalex.org/W2129170915","https://openalex.org/W2130289795","https://openalex.org/W2148551624","https://openalex.org/W2169150754","https://openalex.org/W2187691968","https://openalex.org/W2405076432","https://openalex.org/W2548744442","https://openalex.org/W4365806354"],"related_works":["https://openalex.org/W4224251700","https://openalex.org/W2919544312","https://openalex.org/W2387567929","https://openalex.org/W2013417994","https://openalex.org/W3103849684","https://openalex.org/W2052455844","https://openalex.org/W2087974793","https://openalex.org/W640960419","https://openalex.org/W2127054029","https://openalex.org/W2084136662"],"abstract_inverted_index":{"As":[0],"modern":[1],"hardware":[2],"keeps":[3],"evolving,":[4],"an":[5],"increasingly":[6],"effective":[7],"approach":[8,97],"to":[9,17,20,40,45,87,129,162,192,195,204,226,241],"develop":[10],"energy":[11,49,137,201],"efficient":[12,50],"and":[13,74,82,176,181,187,198],"high-performance":[14],"solvers":[15],"is":[16,98,128],"design":[18],"them":[19],"work":[21,64],"on":[22,79,100,212,244],"many":[23],"small":[24,69],"size":[25],"independent":[26],"problems.":[27],"Many":[28],"applications":[29],"already":[30],"need":[31],"this":[32,88],"functionality,":[33],"especially":[34],"for":[35,65,111,236],"GPUs,":[36,237],"which":[37],"are":[38],"known":[39],"be":[41],"currently":[42],"about":[43],"four":[44],"five":[46],"times":[47],"more":[48],"than":[51],"multicore":[52,118],"CPUs.":[53],"We":[54,85,170],"describe":[55],"the":[56,59,80,102,124,133,143,146,160,177,185,213,233,245],"development":[57,186],"of":[58,68,90,107,116,145,179,189,220],"main":[60],"one-sided":[61],"factorizations":[62,191],"that":[63],"a":[66,93,105,155,164,168,227],"set":[67],"dense":[70],"matrices":[71],"in":[72,123,232],"parallel,":[73],"we":[75,151,238],"illustrate":[76,171],"our":[77,173,205],"techniques":[78],"LU":[81,229],"Cholesky":[83],"factorizations.":[84],"refer":[86],"mode":[89],"operation":[91],"as":[92,104,122,139,141],"batched":[94,108,190,208,228],"factorization.":[95],"Our":[96],"based":[99,211],"representing":[101],"algorithms":[103],"sequence":[106],"BLAS":[109],"routines":[110],"GPU-only":[112],"execution.":[113],"The":[114],"goal":[115],"avoiding":[117],"CPU":[119,209],"use,":[120],"e.g.,":[121],"hybrid":[125],"CPU-GPU":[126],"algorithms,":[127],"exclusively":[130],"benefit":[131],"from":[132,142],"GPU's":[134],"significantly":[135],"higher":[136],"efficiency,":[138],"well":[140],"removal":[144],"costly":[147],"CPU-to-GPU":[148],"communications.":[149],"Furthermore,":[150],"do":[152],"not":[153],"use":[154,178],"single":[156,165],"symmetric":[157],"multiprocessor":[158],"(on":[159],"GPU)":[161],"factorize":[163],"problem":[166],"at":[167],"time.":[169],"how":[172],"performance":[174],"analysis":[175],"profiling":[180],"tracing":[182],"tools":[183],"guided":[184],"optimization":[188],"achieve":[193],"up":[194,240],"2-fold":[196],"speedup":[197,243],"$3$-fold":[199],"better":[200],"efficiency":[202],"compared":[203],"highly":[206],"optimized":[207],"implementations":[210],"MKL":[214],"library":[215,235],"(when":[216],"using":[217],"two":[218],"sockets":[219],"Intel":[221],"Sandy":[222],"Bridge":[223],"CPUs).":[224],"Compared":[225],"factorization":[230],"featured":[231],"CUBLAS":[234],"achieved":[239],"2.5":[242],"K40":[246],"GPU.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}