{"id":"https://openalex.org/W2127906479","doi":"https://doi.org/10.1145/2688500.2688534","title":"Towards batched linear solvers on accelerated hardware platforms","display_name":"Towards batched linear solvers on accelerated hardware platforms","publication_year":2015,"publication_date":"2015-01-24","ids":{"openalex":"https://openalex.org/W2127906479","doi":"https://doi.org/10.1145/2688500.2688534","mag":"2127906479"},"language":"en","primary_location":{"id":"doi:10.1145/2688500.2688534","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2688500.2688534","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2688500.2688534","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2688500.2688534","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/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]},{"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"]}],"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":5.1677,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95809678,"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":"261","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9918000102043152,"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":0.9918000102043152,"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":0.9901000261306763,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9876000285148621,"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":0.8674964904785156},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8566602468490601},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7309329509735107},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.6045929193496704},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.5000221729278564},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.469096302986145},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.45431825518608093},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4473666846752167},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4464607834815979},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4396895468235016},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.42603519558906555},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.41523921489715576},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3286832571029663},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.22937366366386414},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.14850741624832153},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.131474107503891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8674964904785156},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8566602468490601},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7309329509735107},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.6045929193496704},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.5000221729278564},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.469096302986145},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.45431825518608093},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4473666846752167},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4464607834815979},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4396895468235016},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.42603519558906555},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.41523921489715576},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3286832571029663},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.22937366366386414},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.14850741624832153},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.131474107503891},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2688500.2688534","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2688500.2688534","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2688500.2688534","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2688500.2688534","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2688500.2688534","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2688500.2688534","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2127906479.pdf","grobid_xml":"https://content.openalex.org/works/W2127906479.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4224251700","https://openalex.org/W160834089","https://openalex.org/W2112488134","https://openalex.org/W2919544312","https://openalex.org/W2988894191","https://openalex.org/W2132919497","https://openalex.org/W2387567929","https://openalex.org/W2013417994","https://openalex.org/W2137144623","https://openalex.org/W3208993877"],"abstract_inverted_index":{"As":[0],"hardware":[1],"evolves,":[2],"an":[3],"increasingly":[4],"effective":[5],"approach":[6,95],"to":[7,14,17,38,43,82,88,119,170,173,182,202,218],"develop":[8],"energy":[9,47,179],"efficient,":[10],"high-performance":[11],"solvers,":[12],"is":[13,96,115,132],"design":[15],"them":[16],"work":[18,83],"on":[19,98,190,194,221],"many":[20,26],"small":[21,79],"and":[22,70,122,161,176],"independent":[23],"problems.":[24],"Indeed,":[25],"applications":[27],"already":[28],"need":[29],"this":[30,57,114],"functionality,":[31],"especially":[32],"for":[33,52,75,109,127,213],"GPUs,":[34,214],"which":[35],"are":[36,73],"known":[37],"be":[39],"currently":[40],"about":[41],"four":[42],"five":[44],"times":[45],"more":[46],"efficient":[48],"than":[49],"multicore":[50],"CPUs":[51],"every":[53],"floating-point":[54],"operation.":[55],"In":[56],"paper,":[58],"we":[59,215],"describe":[60],"the":[61,64,100,120,123,159,165,191,209,222],"development":[62,166],"of":[63,78,105,140,167],"main":[65],"one-sided":[66],"factorizations:":[67],"LU,":[68],"QR,":[69],"Cholesky;":[71],"that":[72,113],"needed":[74],"a":[76,103,135,145,149,195,203],"set":[77],"dense":[80],"matrices":[81],"in":[84,117,208],"parallel.":[85],"We":[86,151],"refer":[87],"such":[89],"algorithms":[90,101,126],"as":[91,102],"batched":[92,106,168,186,204],"factorizations.":[93,129],"Our":[94],"based":[97,189],"representing":[99],"sequence":[104],"BLAS":[107],"routines":[108],"GPU-contained":[110],"execution.":[111],"Note":[112],"similar":[116],"functionality":[118],"LAPACK":[121],"hybrid":[124],"MAGMA":[125],"large-matrix":[128],"But":[130],"it":[131],"different":[133],"from":[134],"straightforward":[136],"approach,":[137],"whereby":[138],"each":[139],"GPU's":[141],"symmetric":[142],"multiprocessors":[143],"factorizes":[144],"single":[146],"problem":[147],"at":[148],"time.":[150],"illustrate":[152],"how":[153],"our":[154,183],"performance":[155],"analysis":[156],"together":[157],"with":[158],"profiling":[160],"tracing":[162],"tools":[163],"guided":[164],"factorizations":[169],"achieve":[171],"up":[172,217],"2-fold":[174],"speedup":[175,220],"3-fold":[177],"better":[178],"efficiency":[180],"compared":[181],"highly":[184],"optimized":[185],"CPU":[187],"implementations":[188],"MKL":[192],"library":[193,212],"two-sockets,":[196],"Intel":[197],"Sandy":[198],"Bridge":[199],"server.":[200],"Compared":[201],"LU":[205],"factorization":[206],"featured":[207],"NVIDIA's":[210],"CUBLAS":[211],"achieves":[216],"2.5-fold":[219],"K40":[223],"GPU.":[224]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}